[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2022233065A1 - 反馈方法及电子设备 - Google Patents

反馈方法及电子设备 Download PDF

Info

Publication number
WO2022233065A1
WO2022233065A1 PCT/CN2021/092240 CN2021092240W WO2022233065A1 WO 2022233065 A1 WO2022233065 A1 WO 2022233065A1 CN 2021092240 W CN2021092240 W CN 2021092240W WO 2022233065 A1 WO2022233065 A1 WO 2022233065A1
Authority
WO
WIPO (PCT)
Prior art keywords
reference information
user instruction
information
vehicle
feedback
Prior art date
Application number
PCT/CN2021/092240
Other languages
English (en)
French (fr)
Inventor
王正玑
潘爵雨
张�浩
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN202180001586.1A priority Critical patent/CN113366466A/zh
Priority to PCT/CN2021/092240 priority patent/WO2022233065A1/zh
Publication of WO2022233065A1 publication Critical patent/WO2022233065A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3343—Query execution using phonetics

Definitions

  • the present application relates to the field of communications, and in particular, to a feedback method and electronic device.
  • the terminal device can usually obtain feedback information corresponding to the user instruction according to the user instruction. For example, if a user instruction is input by voice, the terminal device can generate feedback information matching the speech rate based on the speech rate. For another example, the terminal device may also generate feedback information matching the response identifier corresponding to the user instruction according to the response identifier corresponding to the user instruction.
  • the content of the feedback information is all corresponding to user instructions. For example, if the user sends a user instruction of "navigate to the car wash" to the vehicle, the vehicle can feed back the navigation information of the car wash to the user.
  • the vehicle it is difficult to meet the actual needs of users by executing the operations corresponding to user instructions in actual scenarios. For example, the car does not need to be washed in rainy days, but the feedback information of car washing is given, so that the user's time and resources are wasted and the user's experience is degraded.
  • the embodiments of the present application provide a feedback method and an electronic device, which can solve the problem that the operation corresponding to executing the user instruction cannot meet the actual needs of the user, and can improve the accuracy of the feedback information, thereby improving the user experience.
  • a feedback method includes: obtaining user instructions. Get reference information associated with a user command.
  • the reference information is information that affects whether to execute the user instruction.
  • Feedback information is generated based on reference information associated with the user instruction.
  • user instructions can be analyzed in combination with reference information to generate feedback information indicating that the user instruction is recommended to be executed, or feedback information to indicate that the user instruction is not recommended to be executed or a fault alarm is generated.
  • the operation suggestion corresponding to the user instruction can be obtained in combination with the actual scene, and then the corresponding operation can be performed according to the feedback information.
  • the execution of the operation corresponding to the user instruction can be stopped in time to save time and cost; on the other hand, when the operation corresponding to the user instruction corresponds to the actual scene, the user can continue Execute the operation corresponding to the user instruction. In this way, the problem that the actual needs of the user cannot be satisfied due to the execution of the corresponding operation according to the user's instruction can be solved, the accuracy of the feedback information can be improved, and the user experience can be improved.
  • generating the feedback information according to the reference information associated with the user instruction may include: acquiring an evaluation result of the reference information associated with the user instruction.
  • Feedback information is generated based on reference information and evaluation results associated with user instructions. In this way, feedback information can be generated in combination with each reference information associated with the user instruction, thereby further improving the accuracy of the feedback information.
  • obtaining the evaluation result of the reference information associated with the user instruction may include: obtaining the evaluation result according to the evaluation function.
  • the input parameters of the evaluation function include user instructions and reference information associated with the user instructions.
  • generating the feedback information based on the reference information associated with the user instruction and the evaluation result may include: if the evaluation result satisfies the first condition, generating the first feedback information according to the reference information associated with the user instruction.
  • the first feedback information is used to indicate that it is recommended not to execute the user instruction or to give a fault alarm.
  • the reference information satisfies the first condition, it can be considered that the operation corresponding to executing the user instruction is difficult to meet the actual needs of the user, and then the first feedback information indicating that the user instruction is not executed or a fault alarm is generated, so as to improve the accuracy of the feedback information, and Save time and cost.
  • generating feedback information based on the reference information associated with the user instruction and the evaluation result may include: if the evaluation result satisfies the second condition, generating second feedback information according to the reference information associated with the user instruction.
  • the second feedback information is used to indicate that it is recommended not to execute the user instruction or a fault alarm.
  • the second condition includes: the value of the existing evaluation result is within the first range, or the value of the weighted summation result of all the evaluation results is within the second range.
  • the reference information satisfies the second condition, it can be considered that the operation corresponding to executing the user instruction is difficult to meet the actual needs of the user, and then the second feedback information indicating that the user instruction is not executed or a fault alarm is generated, so as to improve the accuracy of the feedback information, and Save time and cost.
  • generating the second feedback information according to the reference information associated with the user instruction may include: generating the second feedback information according to the target reference information.
  • the target reference information may be: reference information associated with the user instruction corresponding to the result satisfying the third condition.
  • the second feedback information can be generated according to the reference information that has a greater impact on the user's instruction, so that the accuracy of the feedback information can be further improved.
  • acquiring the reference information associated with the user instruction may include: acquiring the reference information. Calculate the degree of association between user instructions and reference information. Get reference information associated with a user command.
  • the reference information associated with the user instruction is: the reference information of which the degree of association is greater than or equal to the threshold of the degree of association.
  • the correlation may be cosine similarity, Jaccard similarity, or Pearson similarity.
  • the reference information may include vehicle information
  • the vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, fuel level, air conditioning mode, air conditioning Condenser status, A/C temperature sensor status, humidity sensor status, or A/C compressor status.
  • the reference information may include non-vehicle information, and the non-vehicle information may include one or more of the following: weather, temperature, humidity, distance, concentration of respirable particulate matter, service price, or promotional activity information.
  • acquiring the evaluation result of the reference information associated with the user instruction may include: acquiring the evaluation result of the reference information associated with the user instruction according to the priority of the reference information associated with the user instruction.
  • the evaluation result is obtained according to the priority, and when the evaluation result of the reference information with a high priority is within the first range, it is possible to avoid calculating the evaluation results of other reference information, so as to reduce the amount of calculation and further improve the feedback efficiency.
  • the feedback method described in the first aspect may further include: outputting feedback information.
  • the user can determine the next operation according to the feedback information, thereby further improving the user experience.
  • outputting the feedback information may include: outputting the feedback information by means of voice or image.
  • the reference information can come from the cloud. In this way, the reference information can be updated in real time, thereby further improving the accuracy of the feedback information.
  • the reference information can be stored locally. In this way, the same device that uses the reference information and stores the reference information can obtain the reference information faster, thereby improving the efficiency. In addition, when the vehicle obtains the reference information related to the device on the vehicle, it can avoid sending the reference information to other devices outside the vehicle, which can reduce the risk of personal data leakage, thereby improving the security of the reference information.
  • the user instructions may include: instruction categories and/or keywords.
  • the user command is a voice command.
  • the user can input user instructions through voice, avoiding manual input of instructions, thereby improving driving safety.
  • acquiring the user instruction may include: acquiring the user instruction through a touch screen. In this way, more accurate user instructions can be obtained, and the accuracy of the feedback information can be further improved.
  • an electronic device may include: an acquisition module and a generation module.
  • the acquisition module can be used to acquire user instructions.
  • the acquiring module can also be used to acquire the reference information associated with the user instruction.
  • the reference information is information that affects whether to execute the user instruction.
  • the generating module may be configured to generate feedback information according to the reference information associated with the user instruction.
  • the generating module can also be used to obtain the evaluation result of the reference information associated with the user instruction through the obtaining module.
  • the generating module can also be used to generate feedback information based on the reference information and evaluation results associated with the user instruction.
  • the generating module can also be used to obtain the evaluation result according to the evaluation function through the obtaining module.
  • the input parameters of the evaluation function may include user instructions and reference information associated with the user instructions.
  • the generating module may be further configured to generate the first feedback information according to the reference information associated with the user instruction when the evaluation result satisfies the first condition.
  • the first feedback information is used to indicate that it is recommended not to execute the user instruction or to give a fault alarm.
  • the reference information associated with the user instruction may be multiple, and the evaluation results may also be multiple, and the reference information associated with the user instruction and the evaluation results are in one-to-one correspondence.
  • the generating module may be further configured to generate the second feedback information according to the reference information associated with the user instruction when the evaluation result satisfies the second condition.
  • the second feedback information is used to indicate that it is recommended not to execute the user instruction or a fault alarm.
  • the second condition may include: the value of the existing evaluation result is within the first range, or the value of the weighted summation result of all the evaluation results is within the second range.
  • the generating module may also be configured to generate the second feedback information according to the target reference information.
  • the target reference information may be: reference information associated with the user instruction corresponding to the evaluation result satisfying the third condition.
  • the obtaining module can also be used to obtain reference information.
  • the acquiring module can also be used to calculate the degree of association between the user instruction and the reference information.
  • the acquiring module can also be used to acquire the reference information associated with the user instruction.
  • the reference information associated with the user instruction may be reference information with an association degree greater than or equal to a threshold of the association degree.
  • the degree of association may be cosine similarity.
  • the reference information may include vehicle information, which may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, fuel level, air conditioning mode, air conditioning condensation air conditioner status, air conditioner temperature sensor status, humidity sensor status, or air conditioner compressor status.
  • vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, fuel level, air conditioning mode, air conditioning condensation air conditioner status, air conditioner temperature sensor status, humidity sensor status, or air conditioner compressor status.
  • the reference information may include non-vehicle information, and the non-vehicle information may include one or more of the following: weather, temperature, humidity, distance, concentration of respirable particulate matter, service price, or promotional activity information.
  • the acquiring module may be further configured to acquire the evaluation result of the reference information associated with the user instruction according to the priority of the reference information associated with the user instruction.
  • the user instruction may be a voice instruction.
  • a third aspect provides an electronic device capable of performing the method of any one of the first aspects.
  • a vehicle comprising the electronic device of any one of the second aspect or the third aspect.
  • a fifth aspect provides a vehicle capable of performing the method of any one of the first aspects.
  • an electronic device comprising: a processor and a memory; the memory is used for storing computer instructions, and when the processor executes the instructions, the electronic device executes the feedback method according to any one of the first aspects
  • an electronic device including: a processor and an interface circuit.
  • the interface circuit is used to receive the code instruction and transmit it to the processor.
  • a processor for executing code instructions to perform the feedback method of any one of the first aspects.
  • an electronic device in an eighth aspect, includes a processor and a transceiver, the transceiver is used for information interaction between the electronic device and other electronic devices, and the processor executes program instructions to execute any one of the first aspects. feedback method.
  • a ninth aspect provides a processor configured to execute the method of any one of the first aspects.
  • a tenth aspect provides a server.
  • the server is configured to execute the feedback method described in the first aspect.
  • a computer-readable storage medium includes a computer program or instruction, and when the computer program or instruction is run on a computer, executes the feedback method of any one of the first aspect.
  • a twelfth aspect provides a computer program product, comprising a computer program or instructions that, when run on a computer, cause the computer to perform the feedback method of any one of the first aspects.
  • FIG. 1 is a schematic diagram 1 of the architecture of a feedback system provided by an embodiment of the present application.
  • FIG. 2 is a second schematic diagram of the architecture of a feedback system provided by an embodiment of the present application.
  • FIG. 3 is a schematic flowchart 1 of a feedback method according to an embodiment of the present application.
  • FIG. 4 is a second schematic flowchart of a feedback method provided by an embodiment of the present application.
  • FIG. 5 is a schematic diagram 1 of a data flow of a feedback method provided by an embodiment of the present application.
  • FIG. 6 is a second schematic diagram of the data flow of the feedback method provided by the embodiment of the present application.
  • FIG. 7 is a schematic structural diagram 1 of an electronic device provided by an embodiment of the present application.
  • FIG. 8 is a second schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the terminal device has two feedback methods for outputting feedback information according to an instruction, and the specific implementation manners of the terminal device outputting feedback in the prior art are respectively described below.
  • the terminal device can output the corresponding query result according to the speech rate when the user sends out the query voice.
  • the terminal device may acquire the query voice input by the user, recognize the query voice, and determine the corresponding query command. Then, the terminal device sends a query instruction to a network device, such as a server. Next, the terminal device receives the query result fed back by the network device according to the query instruction. Afterwards, the terminal device can determine the corresponding speech rate according to the query speech input by the user, and feed back the speech rate and the query result. Finally, the terminal device can generate voice feedback information corresponding to the voice speaking rate according to the query result and the voice speaking rate based on multiple preset feedback templates. For example, the user sends out the query voice "How is the temperature today".
  • the terminal device can identify the urgency of the user to obtain information through the speech rate.
  • the faster the speech rate the higher the urgency of the user, so that simpler voice feedback information can be output.
  • the terminal device only pays attention to the feedback method of the speech rate, ignoring the actual needs of the users in the actual scene, and does not analyze the impact of the actual scene on the operation corresponding to the execution of the query voice, which is prone to actual situations.
  • the result of executing the operation cannot meet the actual needs of the user, resulting in limited improvement of the user experience by the output query result.
  • the terminal device may have a built-in rule base, and output a feedback result corresponding to the response type identifier according to the response type identifier input by the voice.
  • Each voice control instruction corresponds to a response type identifier
  • the terminal device performs corresponding operations according to the voice control instruction, and outputs response feedback corresponding to the response type identifier in the voice control instruction.
  • the response feedback corresponds to the response type identifier in a one-to-one manner. For example, in the scenario where the temperature is adjusted by the air conditioner, if the response type identifier of the voice control command "Air conditioner is set to 25 degrees" is the response type identifier A, the temperature can be adjusted to 25 degrees, and the voice response "The air conditioner has been set to 25 degrees” is returned. degree”, that is, output voice response feedback.
  • the temperature of the air conditioner can be adjusted to 25 degrees, and the lighting module can be controlled to execute the corresponding lighting response command, that is, output the lighting response feedback.
  • the terminal device may output the response feedback corresponding to the response type identifier based on the rule base in which the response type identifier corresponds to the response feedback one-to-one.
  • the terminal device also ignored the user's emotions in the actual scene, did not analyze the impact of the actual scene on the execution of the operation, and was prone to the situation that the result of the actual execution of the operation could not meet the actual needs of the user, As a result, the output response feedback has limited improvement in user experience.
  • the embodiment of the present application provides a feedback method, which can generate feedback information by combining actual reference information and user instructions, so as to avoid the occurrence of execution results that cannot meet the actual needs of users caused by executing corresponding operations according to the instructions. situation, improve the user experience.
  • MFCC Mel-scale frequency cepstral coefficients
  • TF-IDF Term frequency-inverse document frequency
  • Cosine similarity also known as cosine similarity
  • the similarity of two vectors can be evaluated by calculating the cosine value of the angle between them.
  • two texts to be compared can be converted into corresponding vectors, so as to determine the similarity between the two texts by using cosine similarity.
  • the value range of the cosine similarity can be between [-1, 1]. At this time, the closer the value of the cosine similarity is to 1, the higher the similarity between the two texts, and the higher the value of the cosine similarity. Close to -1, the lower the similarity between the two texts.
  • the cosine similarity may also be a normalized value.
  • the value range of the cosine similarity can also be between [0, 1]. At this time, the closer the value of the cosine similarity is to 1, the higher the similarity between the two texts, the higher the cosine similarity. The closer the value of is to 0, the lower the similarity between the two texts.
  • the technical solutions of the embodiments of the present application can be applied to mobile phones, wearable devices, augmented reality (AR)/virtual reality (VR) devices, tablet computers, notebook computers, and ultra-mobile personal computers (ultra-mobile personal computers).
  • computer, UMPC netbook
  • personal digital assistant personal digital assistant, PDA
  • the electronic device of the present application may also be an on-board module, on-board module, on-board component, on-board chip or on-board unit built into the vehicle as one or more components or units.
  • on-board chip or on-board unit can implement the feedback method provided in this application, of course, in the following embodiments, no limitation is imposed on the specific form of the electronic device.
  • FIG. 1 is a schematic diagram 1 of the architecture of the feedback system provided by the embodiment of the present application.
  • the feedback system may include electronics.
  • the electronic device may include an input/output unit and a processing unit, and there may be one or more input/output units and one or more processing units.
  • the above input and output unit may be used to execute S301 in FIG. 3 described below, and the above processing unit may be used to execute S302 to S303 in FIG. 3 described below. It should be noted that, S301 in the following FIG. 3 may also be executed by the processing unit.
  • the input and output unit may be used to acquire information input by the user, convert the information input by the user into text information, and send the text information to the processing unit.
  • the processing unit may acquire the user instruction according to the text information, and determine the corresponding feedback information.
  • the processing unit may perform corresponding operations according to the feedback information, and may also output the feedback information through the input/output unit.
  • the wired mode may include transmission modes such as cables, optical fibers, and network cables, and the wireless mode may include wireless connections based on one or more wireless communication protocols. Implementation is not limited.
  • the input/output unit may be connected to the transceiver unit, and the input/output unit may also be a unit with a transceiver function.
  • the input/output unit may receive user instructions sent from network equipment and/or other terminal equipment, and may also send user instructions to network equipment. And/or another terminal device sends feedback information.
  • the feedback system may further include a network device in communication with the processing unit, and the network device may transmit vehicle information and/or non-vehicle information to the processing unit.
  • the above-mentioned processing unit is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the electronic device, and executes various functions of the electronic device by running or executing the application stored in the memory and calling the data stored in the memory. and processing data.
  • the processing unit may include one or more processing modules; for example, the processing unit may be a communication information processing system running on a Kirin 960 chip manufactured by Huawei Technologies Co., Ltd. or a processor.
  • the above input and output units may be input/output units such as artificial intelligence (artificial intelligence, AI) speakers with interactive functions, touch screens, etc., based on the interaction between the user and the input and output units, to collect the instructions issued by the user, or to receive feedback information. Then output the corresponding feedback information.
  • AI artificial intelligence
  • the AI speaker can collect the voice information sent by the user, and can output feedback information by voice.
  • the above-mentioned network device may be a device with a wireless transceiver function or a chip or a chip system that may be provided in the device.
  • the network devices include but are not limited to: access points (APs) in wireless fidelity (WiFi) systems, such as home gateways, routers, servers, switches, bridges, etc., wireless relay nodes, wireless Backhaul node, transmission point (transmission and reception point, TRP or transmission point, TP), etc., can be network nodes that constitute gNB or transmission point, such as baseband unit (BBU), or distributed unit (distributed unit, DU) , A roadside unit (RSU) with base station function, etc.
  • BBU baseband unit
  • DU distributed unit
  • RSU roadside unit
  • FIG. 2 is a second schematic diagram of the architecture of the feedback system provided by the embodiment of the present application.
  • the feedback system includes electronics.
  • the electronic equipment may include AI speakers and processing units.
  • the function of the input and output unit shown in FIG. 1 can be realized by the AI speaker shown in FIG. 2
  • the function of the processing unit shown in FIG. 1 can be realized by the processing unit shown in FIG. 2 .
  • the AI speaker can collect the voice information sent by the user, identify the actual needs of the user through deep learning technology, and convert the voice information into text information for use by other modules in the in-vehicle system.
  • the above processing unit may determine corresponding feedback information according to the text information.
  • the AI speaker can also output feedback information through the speaker.
  • the AI speaker may include a voice recognition module and a first drive module.
  • the processing unit may include: a data acquisition module, an impact factor extraction module, an impact factor evaluation module, a feedback information generation module, and a second drive module.
  • the above-mentioned speech recognition module can use the MFCC feature extraction technology and the cyclic neural network technology to convert the speech information into text information.
  • the first drive module of the above-mentioned AI speaker can be connected with the second drive module of the processing unit to realize data transmission between the AI speaker and the processing unit.
  • the AI speaker sends text information to the processing unit, and the processing unit sends feedback to the AI speaker information.
  • the above data acquisition module can be used to acquire reference information of electronic equipment or other equipment, such as vehicle information or non-vehicle information.
  • the feedback system may further include a vehicle electronic control unit (ECU) connected to the data acquisition module, and the data acquisition module may obtain from the vehicle ECU according to the relevant information of the engine, wheels and brake sensors, etc.
  • the driving status data of the vehicle such as speed, steering wheel angle, etc.
  • the data acquisition module and the vehicle ECU can transmit the driving state data of the vehicle through a vehicle signal line, such as a bus.
  • the embodiments of the present application do not limit the specific implementation of the information transmission between the data collection module and the vehicle ECU.
  • the feedback system may further include a server in communication with the data collection module, and the server may return corresponding reference information to the data collection module according to the reference information transmitted by the data collection module.
  • the data acquisition module can receive the reference information from the server through the network card driver.
  • a server may also be used to implement the function of the processing unit.
  • the above impact factor extraction module can use feature extraction and machine learning methods to classify text information, and can also use TF-IDF algorithm to extract keywords in text information.
  • the impact factor extraction module can also calculate the cosine similarity with the reference information in the impact factor library based on the obtained instruction categories and keywords, and extract the reference information in which the cosine similarity exceeds the similarity threshold.
  • the above-mentioned impact factor evaluation module can obtain the corresponding reference information, such as vehicle information and non-vehicle information, from the data acquisition module according to the reference information whose similarity exceeds the similarity threshold, so as to evaluate whether the operation corresponding to the user instruction is consistent with the actual scene. Correspondence, that is, judging whether the operation corresponding to the user instruction in the actual scene is necessary or can be executed.
  • the above-mentioned feedback information generation module may generate corresponding feedback information according to the evaluation result of the impact factor evaluation module, and the feedback information may be used to indicate that the user instruction is recommended to be executed or the user instruction is not recommended to be executed.
  • the processing unit can send feedback information to the AI speaker, so that the AI speaker can use the speaker to output the feedback information.
  • the above-mentioned AI speaker can also be connected with a transceiver to implement a transceiver function.
  • the AI speaker can send the feedback information to other devices through the transceiver, so that other devices can perform operations corresponding to the feedback information.
  • the above processing unit may also send feedback information to the vehicle ECU through a vehicle bus or a signal line, thereby controlling the vehicle ECU to perform operations corresponding to the feedback information.
  • FIGS. 1 and 2 are simplified schematic diagrams for easy understanding only, and the feedback system may also include other electronic devices and/or other network devices, which are not shown in FIGS. 1 and 2 .
  • FIG. 3 is a schematic flowchart 1 of a feedback method provided by an embodiment of the present application.
  • This feedback method can be applied to the feedback system shown in FIG. 1 and FIG. 2 , and the electronic device in the feedback system is used as an example for the vehicle to be described below.
  • the feedback method includes S301-S303.
  • the user instructions may be information indicating one or more operations that need to be performed.
  • the user instruction may be related information for instructing the air conditioner to be turned on.
  • the user instruction may include a keyword and an instruction category, and the instruction category may be an operation category corresponding to the user instruction, such as an operation instruction, a travel instruction, a query instruction, and the like.
  • the keyword may be the operation and/or the operation object corresponding to the user instruction.
  • text information may be processed based on feature extraction and classification techniques to obtain keywords and instruction categories of user instructions.
  • the instruction category may be "operation category”
  • the keywords may include "turn on” and "air conditioner”.
  • the instruction category may be "travel”
  • the keywords may include "navigation” and "car wash”.
  • the above-mentioned user instructions may be voice instructions. That is, user instructions can be acquired through voice.
  • obtaining the user instruction may include step 1 and step 2.
  • Step 1 acquire voice information.
  • the voice information can be obtained through a sound pickup device, such as a microphone (microphone, MIC) or the AI speaker with sound pickup function shown in FIG. 2 above.
  • a sound pickup device such as a microphone (microphone, MIC) or the AI speaker with sound pickup function shown in FIG. 2 above.
  • Step 2 obtaining user instructions according to the voice information.
  • voice information can be converted into text information.
  • feature extraction technology and neural network technology such as MFCC feature extraction technology and recurrent neural network technology, can be used to convert speech information into text information.
  • the instruction category and/or keywords are acquired according to the text information, so as to obtain the user instruction.
  • feature extraction techniques and machine learning methods can be used to process textual information to determine corresponding instruction categories.
  • the most important one or more keywords can be extracted from multiple keywords by using the TF-IDF algorithm, so as to determine the keywords corresponding to the voice information, and then obtain user instructions according to the instruction category and the extracted keywords.
  • the user can input user instructions through voice, avoiding manual input of instructions, thereby improving driving safety.
  • user instructions can also be obtained through the touch screen.
  • the touch operation information input by the user can be collected through the touch screen, and the touch operation information can be converted into text information by using the feature extraction technology and the neural network technology. Then, the instruction category and/or keywords are acquired according to the text information, so as to obtain the user instruction.
  • the user instruction may also be determined according to touch operation information, or determined according to key operation information, or may be obtained from other devices.
  • the embodiments of the present application do not limit the specific implementation manner of acquiring the user instruction.
  • S302 Obtain reference information associated with the user instruction (also referred to as associated reference information).
  • the reference information may be information affecting various possible operations.
  • the reference information may include vehicle information and/or non-vehicle information.
  • the vehicle information may be information that affects the execution of user instructions and is related to in-vehicle equipment, such as a vehicle engine and an in-vehicle air conditioner.
  • the above-mentioned vehicle information may include information of equipment on the vehicle and/or information of other equipment outside the vehicle.
  • the electronic device may be a processor on a vehicle, and if the instruction type in the user instruction is a travel instruction, the vehicle information may be the status information of a vehicle electronic control unit (ECU) related to travel.
  • ECU vehicle electronic control unit
  • the vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, fuel level, air conditioning mode, air conditioning condenser status, air conditioning temperature sensor status , or the air conditioner compressor status.
  • the user instruction has the same meaning as the operation corresponding to the user instruction. Executing the user instruction may be implemented by executing an operation corresponding to the user instruction.
  • the associated reference information may be information in the reference information that affects the execution of the user's instruction.
  • the cross-reference information may be vehicle information and/or non-vehicle information that affects the execution of the current user instruction.
  • the associated reference information may be vehicle information including one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, fuel quantity , or the state of the vehicle's driveline.
  • the vehicle cooling system can be used to dissipate the heat absorbed by the heated components to ensure that the engine works at a suitable temperature.
  • a vehicle cooling system may include a fin assembly or the like.
  • the vehicle cooling system may further include: a cooling water jacket, a water pump, a fan, a water tank, a thermostat, and the like.
  • the vehicle ignition system is used to generate a spark between the electrodes of the spark plug on time to ignite the mixture.
  • a vehicle ignition system may include: a power source (eg, a battery, a generator), an ignition switch, an ignition coil, additional resistors, a distributor, and the like.
  • the vehicle starting system is used to make the engine transition from a stationary state to a working state.
  • a vehicle starting system may include a battery, a starter, a starter switch, a relay, and the like.
  • the vehicle transmission system is the power system used to generate the driving force of the vehicle.
  • a vehicle driveline may include: transmissions, clutches, cardan gears, final drives, differentials, axle shafts, and the like.
  • the vehicle information may be state information related to the air conditioner.
  • the vehicle information may also include one or more of the following: condenser status, temperature sensor status, or air conditioner compressor status.
  • the vehicle information may also include one or more of the following: the state of the crank link mechanism of the vehicle, the state of the valve train of the vehicle, the state of the vehicle supply System status, vehicle lubrication system status, vehicle braking system status, vehicle driveline status, vehicle travel system status, or vehicle steering system status.
  • the vehicle information may further include one or more of the following: the state of the air conditioner evaporator, or the state of the air conditioner expansion valve.
  • each item of vehicle information may include the status of one or more components.
  • a vehicle driveline may include the status of components such as clutches and/or transmissions.
  • non-vehicle information may be information related to the scene (environment) that affects the execution of user instructions, such as weather, temperature, distance, service price, humidity, concentration of inhalable particulate matter, and promotional activities when executing user instructions. information, etc.
  • obtaining the associated reference information may include steps 3 to 5.
  • Step 3 obtain reference information.
  • the reference information can come from the cloud.
  • the input/output unit may include a transceiver module, and the input/output unit may receive reference information from the cloud through the transceiver module.
  • the reference information can be updated in real time, thereby further improving the accuracy of the feedback information.
  • the reference information can also be stored locally.
  • the feedback information may be stored in the vehicle's memory.
  • the same device that uses the reference information and stores the reference information can obtain the reference information faster, thereby improving the efficiency.
  • the vehicle when the vehicle obtains the reference information related to the device on the vehicle, it can avoid sending the reference information to other devices outside the vehicle, which can reduce the risk of personal data leakage, thereby improving the security of the reference information.
  • the reference information may also be stored in other devices that can communicate with the electronic device, such as a cloud server.
  • the types of reference information may be obtained by preprocessing historical vehicle information and historical non-vehicle information by using a classification technology. Specifically, historical vehicle information and historical non-vehicle information can be acquired in advance, and then multi-level classification is used to process historical vehicle information and historical non-vehicle information until the leaf nodes of the classification are difficult to subdivide, and the historical vehicle information and historical non-vehicle information can be determined.
  • the category of the reference information may be obtained according to the local processing of historical vehicle information and historical non-vehicle information, or may be obtained from a network device or other terminal devices.
  • the embodiments of the present application do not limit the specific implementation manner in which the processing unit obtains the reference information.
  • the category of reference information may be a factor related to the user's instruction
  • the reference information corresponding to a category of reference information is the above vehicle information or non-vehicle information
  • a reference information may correspond to one or more vehicle information, or One or more non-vehicle information correspondences.
  • the reference information that is, the corresponding vehicle information and/or non-vehicle information
  • the category of the reference information is "the working mode of the air conditioner”
  • the vehicle information of "the working mode of the air conditioner is the cooling mode” may be correspondingly acquired.
  • the processing unit may correspondingly obtain the non-vehicle information of "weather is rainy”.
  • the above method may be used to first analyze the user instructions, determine the type of reference information to be acquired, and then acquire the associated reference information correspondingly; or acquire all the reference information, and then retrieve all the reference information according to the user instruction.
  • the reference information determine the cross-reference information.
  • the embodiments of the present application do not limit specific implementations of vehicle information and non-vehicle information.
  • Step 4 Calculate the degree of association between the user instruction and the reference information.
  • the degree of association may be the size of the correlation between the user instruction and the reference information, and the size of the correlation may be determined according to the degree of influence of the reference information on the operation corresponding to the user instruction. For example, if the user command is a travel command, the state of the vehicle startup system has a greater impact on the "travel" operation, while the air conditioner condenser state has a smaller impact on the "travel” operation. Therefore, the difference between the state of the vehicle startup system and the user command The degree of correlation is greater than the degree of correlation between the state of the air conditioner condenser and the user command.
  • the above-mentioned degree of association may be represented by the degree of similarity between the user instruction and the reference information.
  • the association may be cosine similarity, Jaccard similarity, or Pearson similarity.
  • cosine similarity can be used to characterize the degree of similarity between two vectors.
  • both the user instruction and the reference information to be compared may be converted into corresponding vectors, and then the cosine similarity between the two vectors, that is, the similarity between the user instruction and the reference information, may be calculated.
  • cos( ⁇ ) w ⁇ i /
  • cos( ⁇ ) is the cosine similarity
  • w is the keyword
  • ⁇ i is the ith reference information
  • is the norm of the keyword w
  • is the norm of the ith reference information.
  • the reference information related to the user instruction can be accurately determined based on the cosine similarity, thereby further improving the accuracy of the feedback information.
  • the value range of the cosine similarity can be between [-1, 1].
  • the cosine similarity can also be a value after normalization. That is to say, the value range of the cosine similarity can also be between [0, 1]. The closer the value of the cosine similarity is to 1, the higher the similarity between the user instruction and the reference information, the higher the cosine similarity. The closer the value is to 0, the lower the similarity between the user instruction and the reference information.
  • Step 5 obtain the associated reference information.
  • the associated reference information may be reference information whose similarity with the user instruction is greater than a similarity threshold among all the reference information.
  • the associated reference information may be determined according to the degree of association between the user instruction and the reference information.
  • the specific implementation of the related reference information will be described below by taking the specific implementation of the similarity indicating the correlation as an example.
  • the similarity may be used to indicate the degree of correlation between the user instruction and the reference information, that is, the degree of influence of the reference information on the operation corresponding to the user instruction. The higher the similarity, the higher the degree of correlation between the user instruction and the reference information. On the contrary, the lower the similarity, the lower the correlation between the user instruction and the reference information.
  • reference information 1 is the working state of the vehicle ECU
  • reference information 2 is the working mode of the air conditioner
  • the user instruction includes the keyword "turn on the air conditioner”
  • the user instruction and reference information 2 The similarity is higher than the similarity between the user information and the reference information 1, that is, the degree of correlation between the user information and the reference information 2 is higher.
  • the similarity threshold may be one or multiple, and when the similarity threshold is multiple, the similarity thresholds corresponding to different reference information may be the same or different.
  • obtaining the associated reference information may include: obtaining the priority of each reference information, and obtaining the associated reference information according to the priority and the association degree.
  • the priority of the associated reference information is higher than the priority threshold.
  • the priority of the reference information may be used to indicate the degree of importance of the reference information or the degree of influence of the reference information on the operation corresponding to the user instruction.
  • Priority can be expressed numerically.
  • the priority is higher than the priority threshold, which may be higher than the priority corresponding to the priority threshold.
  • a larger value represents a higher priority
  • a smaller value represents a lower priority
  • the priority is higher than the priority threshold, which may be the priority value greater than the priority threshold.
  • a smaller value indicates a higher priority
  • a lower value indicates a lower priority
  • the priority is higher than the priority threshold
  • the value of the priority may be smaller than the priority threshold.
  • the reference information includes reference information 1-reference information 5, and the priority is positively correlated with the priority value. If the similarity between reference information 1, reference information 3, and reference information 5 and the user instruction is greater than the similarity threshold, the priority values corresponding to reference information 1 to reference information 5 are respectively 5 to 1, and the priority threshold value is "3". Then the reference information associated with the user instruction includes: reference information 1 .
  • the reference information associated with the user instruction can be accurately selected from a plurality of reference information by means of correlation degree comparison, thereby improving the accuracy of the feedback information.
  • the feedback information may indicate that it is recommended not to execute the user instruction or fault alarm information, or the feedback information may indicate that the user instruction is suggested to be executed.
  • step S303 generating feedback information according to the reference information may include steps 6 and 7.
  • Step 6 Obtain the evaluation result of the associated reference information.
  • the evaluation result can be obtained according to the evaluation function.
  • the input parameters of the evaluation function include user instructions and cross-reference information.
  • the evaluation result can be obtained according to the user's instruction and the associated reference information.
  • the associated reference information may be one or more.
  • multiple cross-reference information corresponds to one evaluation result.
  • the user instruction and the related reference information can be used as input parameters of the evaluation function, and then the evaluation result can be obtained.
  • the evaluation result can also be obtained through the evaluation conditions.
  • Each cross-reference information has its own corresponding evaluation conditions.
  • the related reference information includes the related reference information 1 and the related reference information 5, and the related reference information 1 and the related reference information 5 correspond to the evaluation condition 1 to the evaluation condition 5 in turn.
  • the respective evaluation results corresponding to the related reference information 2 to the related reference information 5 can be obtained.
  • the evaluation results are described below with examples. For example, if the user instruction includes the keyword “turn on the air conditioner” and the reference information includes “the working mode of the air conditioner”, the evaluation condition of "the working mode of the air conditioner should be turned off when performing the operation of turning on the air conditioner” can be obtained. Evaluate the user instruction and the associated reference information according to the evaluation conditions, and obtain the corresponding evaluation result.
  • evaluation condition in the embodiment of the present application may also be the above-mentioned evaluation function.
  • the evaluation conditions may include one or more conditions.
  • the evaluation conditions corresponding to different vehicle information and non-vehicle information may be the same or different.
  • the product of the evaluation result corresponding to each associated reference information and the weight corresponding to each associated reference information may be determined as the evaluation result.
  • linked reference information includes linked reference information 1 to linked reference information 3
  • linked reference information 1 to linked reference information 3 respectively correspond to evaluation results 1-assessment result 3
  • linked reference information 1 to linked reference information 3 respectively correspond to weights are respectively weight 1 to weight 3
  • the product of evaluation result 1 and weight 1 is an evaluation result
  • the product of evaluation result 2 and weight 2 is an evaluation result
  • the product of evaluation result 3 and weight 3 is an evaluation result.
  • the evaluation result can be obtained according to the importance of the reference information, thereby improving the accuracy of the evaluation result and further improving the accuracy of the feedback information.
  • the evaluation result in the embodiment of the present application may also be any evaluation result with reference to related information.
  • the evaluation result can be a numerical value or a state corresponding to the reference information, such as normal or abnormal.
  • obtaining the evaluation result of the reference information associated with the user instruction may include: obtaining the evaluation result of the associated reference information according to the priority of the associated reference information.
  • the correlated reference information includes correlated reference information 1 - correlated reference information 5
  • the priority values of correlated reference information 1 - correlated reference information 5 are: 5-1.
  • the priority value is positively correlated with the priority, then the evaluation results can be obtained in descending order of the priority of the associated reference information.
  • the evaluation result is obtained according to the priority, and when the evaluation result of the reference information with high priority is located in a certain numerical range, such as the first range, the evaluation result of other reference information can be avoided to be calculated, so as to reduce the amount of calculation, thereby further Improve feedback efficiency.
  • Step 7 based on the related reference information and the evaluation result, generate feedback information.
  • the operation corresponding to the user command is "turn on the air conditioner"
  • the scene "the outdoor temperature and the indoor temperature are both 20°C” even if the operation of turning on the air conditioner is performed, it is difficult to meet the actual needs of users who use the air conditioner to make the surroundings cooler. , and a large amount of power resources will be wasted, so the evaluation result indicating "the operation corresponding to the user's instruction can not be executed” can be obtained, and it can be determined that the feedback information can be "the temperature is suitable, no need to turn on the air conditioner", that is to say, the feedback Information indication: Do not execute user instructions.
  • the air conditioner may also operate according to the set temperature.
  • the outdoor temperature and the indoor temperature are both 20°C
  • the feedback information of the air conditioner is "the temperature is suitable, there is no need to turn on the air conditioner”
  • the indoor temperature is set to 16°C
  • the air conditioner can still be turned on and Control the air conditioner to run in cooling mode.
  • the vehicle information is "failure of the condenser tube in the air conditioner”
  • the vehicle information in the actual scene has a great influence on the operation corresponding to the user command, which may easily cause the operation corresponding to the user command to fail to be executed.
  • Operation cannot be performed it can be determined that the feedback information can be “the air conditioner is faulty and cannot be turned on”, that is, the feedback information indicates that the user instruction does not need to be executed.
  • step 7 is specifically described in numerical representation in combination with the evaluation results below.
  • step 7 generating feedback information based on the related reference information and the evaluation result may include: if the evaluation result satisfies the first condition, generating the first feedback information according to the related reference information.
  • the first feedback information is used to indicate that it is recommended not to execute the user instruction or to give a fault alarm.
  • the first condition may be: the value of the evaluation result is less than 0. It can be understood that the first condition may also be that the evaluation result of the associated reference information is within other numerical ranges.
  • the generated feedback information may also indicate that it is recommended to execute the user instruction. For example, if the value of the evaluation result is greater than 0, the generated feedback information may indicate that it is recommended to execute the user instruction.
  • the reference information satisfies the first condition, it can be considered that it is difficult to execute the user instruction to meet the actual needs of the user, and then the first feedback information indicating that the user instruction is not executed or a fault alarm is generated, which improves the accuracy of the feedback information and saves time. and cost.
  • the above step 7, generating feedback information based on the related reference information and the evaluation result may include: if the evaluation result satisfies the second condition, generating the second Feedback.
  • the second feedback information is used to indicate that it is recommended not to execute the user instruction or a fault alarm.
  • the second condition includes: the value of the existing evaluation result is within the first range, or the value of the weighted summation result of all the evaluation results is within the second range.
  • the first range is a range less than 0, there is an evaluation result with a value less than 0, and the second feedback information is generated.
  • the contents of the first feedback information and the second feedback information may be the same or different.
  • the reference information satisfies the second condition, it can be considered that the execution of the user instruction is difficult to meet the actual needs of the user, and the second feedback information for indicating that the user instruction is not to be executed or a fault alarm is generated, which improves the accuracy of the feedback information, and can Save time and cost.
  • generating the feedback information based on the associated reference information and the evaluation result may include: generating the second feedback information according to the target reference information.
  • the target reference information is: related reference information corresponding to the evaluation result satisfying the third condition.
  • the evaluation result satisfying the third condition may be an evaluation result whose value is within the second range.
  • the second feedback information may be generated according to the associated reference information corresponding to the evaluation result with the smallest value.
  • the related reference information includes related reference information 1 - related reference information 5 . If the evaluation result of the linked reference information 2 is the smallest and less than 0, the target reference information is the linked reference information 2, and the second feedback information corresponds to the linked reference information 2.
  • generating feedback information based on the reference information and the evaluation result may include: if the evaluation result satisfies the fourth condition, generating third feedback information according to the associated reference information corresponding to the evaluation result with the largest value .
  • the fourth condition includes: the value of each evaluation result is within the third range.
  • the third feedback information is used to indicate that it is recommended to execute the user instruction.
  • the first range as a range greater than 0 as an example
  • the related reference information includes related reference information 1 - related reference information 5 .
  • the values of the evaluation results corresponding to the related reference information 1 to the related reference information 5 are all greater than 0, and the evaluation result corresponding to the related reference information 3 is the largest, and the third feedback information is generated according to the evaluation result corresponding to the related reference information 3 .
  • the feedback information may not be generated.
  • the fifth condition may be: the value of each evaluation result is within the fourth range.
  • the fifth condition may be: the value of each evaluation result is the same.
  • the fifth condition is: the value of each evaluation result is 0. It should be noted that, when the fifth condition is satisfied, feedback information suggesting executing the user instruction, such as third feedback information, may also be generated.
  • the first condition to the fifth evaluation condition are different from each other.
  • a value of an evaluation result may indicate a feedback type corresponding to the linked reference information
  • the feedback type corresponding to the linked reference information may include: no feedback information, feedback information indicating that it is recommended to execute a user instruction (such as third feedback information) .
  • Feedback information (such as the first feedback information and the second feedback information) indicating that it is recommended not to execute the user instruction or the fault alarm.
  • the generated feedback information corresponds to all associated reference information.
  • the evaluation result For example, if the evaluation result is 0, it indicates: no feedback information; if the evaluation result is greater than 0, it indicates: it is recommended to execute the user instruction; if the evaluation result is less than 0, it indicates: it is recommended not to execute the user instruction or a fault alarm. It should be noted that the evaluation result may also be other numerical values, and the numerical value of the evaluation result is not specifically limited in the embodiments of the present application.
  • the third feedback information is generated. If there is an evaluation result indication corresponding to the associated reference information: it is recommended not to execute the user instruction or a fault alarm, then the first feedback information or the second feedback information is generated. If the evaluation results of all the cross-reference information indicate that there is no feedback information, the feedback information may not be generated.
  • third feedback information may also be generated.
  • the feedback information may also be determined according to the priority of each associated reference information.
  • the priority of the associated reference information is used to indicate the importance of the associated reference information.
  • the priority can be represented by a numerical value.
  • the contextual reference information corresponding to the user instruction includes: contextual reference information 1 - contextual reference information 3, and the evaluation results corresponding to contextual reference information 1 - contextual reference information 3 indicate in sequence: it is recommended to execute the user command, it is recommended not to execute the user command, or a fault alarm , it is recommended to execute the user instruction, the priority values 5, 7, and 3 corresponding to the related reference information 1-related reference information 3 in turn, and the priority is positively correlated with the priority value, then the feedback information is generated according to the evaluation result corresponding to the related reference information 2, Such as the second feedback information.
  • Manner 1 Generate the second feedback information according to the vehicle information and the evaluation result.
  • Vehicle information includes one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, air conditioner condenser status, air conditioner temperature sensor status, or air conditioner compressor status.
  • the evaluation condition may include the second condition.
  • generating feedback information based on the contextual reference information and the evaluation result may include: if the second condition is satisfied, generating the second feedback information according to the contextual reference information.
  • the second feedback information may be used to indicate that it is recommended not to execute the user instruction or a fault alarm
  • the second condition may include one or more of the following conditions:
  • Condition 3 the vehicle starting system is in an abnormal working state.
  • Condition 4 the vehicle transmission system is in an abnormal working state. or,
  • the temperature sensor of the air conditioner is in an abnormal working state. or,
  • Condition 7 the air conditioner compressor is in an abnormal working state.
  • the abnormal working state may be a state in which a structural component or assembly is faulty.
  • the vehicle cooling system in an abnormal working state, which may be that a component of the vehicle cooling system is faulty.
  • the water tank is faulty.
  • the vehicle ignition system is in an abnormal working state. It could be that a component of the vehicle ignition system is faulty.
  • the ignition coil is faulty.
  • the vehicle starting system is in an abnormal working state, it may be that the components of the vehicle starting system are faulty.
  • the starter switch is faulty.
  • the vehicle transmission system is in an abnormal working state, which may be a failure of a component of the vehicle transmission system.
  • the transmission is faulty, or the clutch is faulty.
  • Condition 5 the condenser of the air conditioner is in an abnormal working state, which may be due to the failure of the components of the condenser.
  • Condition 6 the temperature sensor of the air conditioner is in an abnormal working state, which may be a failure of the temperature sensor or a component related to the temperature sensor.
  • Condition 7 the air-conditioning compressor is in an abnormal working state, which may be a malfunction of the air-conditioning compressor.
  • the second condition may be related reference information, a condition that is satisfied when the user instruction can be executed or is necessary to be executed.
  • the second condition is satisfied, which may be that each condition included in the second condition is satisfied.
  • the second condition includes Condition 1, which is satisfied if it is determined that the vehicle cooling system is in an abnormal operating state.
  • the second condition includes condition 1 and condition 2. If it is determined that the vehicle cooling system is in an abnormal working state and the vehicle ignition system is in an abnormal working state, the second condition is satisfied.
  • Each condition in the second condition may correspond to an evaluation result. The evaluation results can be used to indicate that it is recommended not to execute user instructions or to warn of failures.
  • the second feedback information may correspond to one or more associated reference information.
  • the operations corresponding to different related reference information may be the same or different.
  • the related reference information includes vehicle information as an example for description. For example, if there are multiple pieces of vehicle information, if all the vehicle information satisfies the second condition, one corresponding second feedback information may be generated according to the evaluation results of all the vehicle information. For another example, when there are multiple pieces of vehicle information, the second feedback information is obtained according to an evaluation result of one of the multiple pieces of vehicle information. That is, the second feedback information corresponds to one piece of vehicle information.
  • the second feedback information is generated according to the non-vehicle information and the evaluation result.
  • the evaluation condition may include a second condition
  • the non-vehicle information may include one or more of the following: weather, temperature, service price corresponding to the operation, humidity, or concentration of inhalable particulate matter.
  • generating the feedback information based on the associated reference information and the evaluation result may include: if the second condition is satisfied, generating the second feedback information according to the reference information.
  • the second feedback information is used to indicate: it is recommended not to execute the user instruction or the fault alarm; the second condition may include one or more of the following conditions:
  • the weather belongs to the first weather set. or,
  • the temperature is within the first temperature range. or,
  • the service price is within the first price range. or,
  • the humidity is within the first humidity interval. or,
  • the concentration of the inhalable particulate matter is within the first concentration interval.
  • the first weather set may be a set of weathers corresponding to scenarios in which the user instruction does not need to be executed or cannot be executed.
  • the first temperature interval may be a temperature interval corresponding to a scenario in which the user instruction does not need to be executed or cannot be executed.
  • the first price range is a service price range corresponding to a scenario where the user instruction does not need to be executed or cannot be executed.
  • the non-vehicle information includes the weather
  • the weather belongs to the first weather set, it can be determined that the second feedback information corresponding to "weather" may be unnecessary or difficult to execute in the scenario corresponding to the weather.
  • the non-vehicle information includes temperature
  • the temperature is within the first temperature range, it can be determined that in the scenario corresponding to the temperature, it is unnecessary or difficult to execute the user instruction, and "temperature" corresponds to the second feedback information.
  • the non-vehicle information includes the service price
  • the service price is within the first price range, it can be determined that in the scenario corresponding to the service price, it is not necessary or difficult to execute the user instruction, and the "service price" corresponds to the second price.
  • Feedback For the implementation of the second feedback information in the second mode, reference may be made to the implementation mode of the second feedback information in the first mode, which will not be repeated here.
  • the second feedback information is generated according to the vehicle information and the non-vehicle information.
  • the vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, air conditioner condenser status, air conditioner temperature sensor status, air conditioner compressor status,
  • the non-vehicle information may also include one or more of the following: weather, temperature, service price corresponding to the operation, humidity, or the concentration of inhalable particulate matter.
  • the second condition may include both the condition corresponding to the vehicle information and the corresponding non-vehicle information. conditions of. For example, the second condition includes one or more of conditions 1 to 7, and also includes one or more of conditions 8 to 12.
  • the evaluation condition may include the second condition
  • the vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, or vehicle transmission system status state.
  • Non-vehicle information may include one or more of the following: weather, temperature, or service prices for operations.
  • Step 7, generating feedback information based on the associated reference information and the evaluation result may include: if the second condition is satisfied, generating second feedback information according to the associated reference information.
  • the second condition may include one or more of the following conditions:
  • the vehicle cooling system is in an abnormal working state. or,
  • Condition 14 the vehicle ignition system is in an abnormal working state. or,
  • the vehicle transmission system is in an abnormal working state.
  • Condition 17 the weather belongs to the first weather set. or,
  • the temperature is within the first temperature range. or,
  • Condition 19 the service price is within the first price range.
  • condition 13 to condition 19 may correspond to the implementation manners of reference condition 1 to condition 4 and condition 8 to condition 10 in sequence, which will not be repeated here.
  • the second condition further includes: the fuel level is within the first fuel level threshold, and/or the air conditioning mode is an abnormal working mode, and/or the distance is within the first distance threshold, and/or there is a promotion.
  • the third feedback information is generated according to the vehicle information and the evaluation result.
  • the evaluation conditions may include a fourth condition, and the vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle powertrain status, air conditioning condenser status, air conditioning temperature sensor status, air conditioning Compressor status.
  • the above step 7, generating feedback information based on the associated reference information and the evaluation result may include: generating third feedback information if the fourth condition is satisfied.
  • the third feedback information may be used to indicate that it is recommended to execute the user instruction.
  • the fourth condition may include one or more of the following conditions:
  • the vehicle cooling system is in a normal working state. or,
  • the ignition system of the vehicle is in a normal working state. or,
  • the vehicle starting system is in a normal working state. or,
  • the vehicle transmission system is in a normal working state. or,
  • the air conditioner condenser is in a normal working state. or,
  • the temperature sensor of the air conditioner is in a normal working state. or,
  • the air conditioner compressor is in a normal working state.
  • the normal operating state may be a state in which the structural device or component is free of failure.
  • the vehicle cooling system is in normal working condition, may be that the components of the vehicle cooling system are not faulty.
  • Condition 21 the vehicle ignition system is in a normal working state, which may mean that the components of the vehicle ignition system are not faulty.
  • Condition 22 the vehicle starting system is in a normal working state, which may mean that the components of the vehicle starting system are not faulty.
  • Condition 23 the vehicle drive system is in a normal working state, which may mean that the components of the vehicle drive system are not faulty.
  • the air conditioner condenser is in a normal working state, which may mean that the components of the air conditioner condenser are not faulty.
  • Condition 25 the temperature sensor of the air conditioner is in a normal working state, and it may be that the components of the temperature sensor of the air conditioner are not faulty.
  • Condition 26 the air-conditioning compressor is in a normal working state, but the air-conditioning compressor is in a normal working state. It should be noted that the working state of an assembly (any item of vehicle information) can be determined according to the working state of one or more components included in the assembly.
  • the fourth condition may be a condition that the cross-reference information satisfies when the user instruction can be executed or is necessary to be executed.
  • the fourth condition is satisfied, and each condition included in the fourth condition may be satisfied.
  • the fourth condition includes condition 20, which is satisfied if the vehicle cooling system is determined to be in a normal operating state.
  • the fourth condition includes condition 20 and condition 21. If it is determined that the vehicle cooling system is in a normal working state and the vehicle ignition system is in a normal working state, the fourth condition is satisfied.
  • the third feedback information corresponding to the user instruction may correspond to one or more associated reference information.
  • the related reference information includes vehicle information as an example for description.
  • the third feedback information may be obtained according to the evaluation result of each piece of vehicle information among the multiple pieces of vehicle information. That is, the third feedback information corresponds to a plurality of pieces of vehicle information.
  • a corresponding third feedback information may be generated.
  • the vehicle information corresponding to the user instruction A includes the state of the vehicle cooling system and the state of the vehicle starting system. The system state determines the third feedback information corresponding to the user instruction A.
  • the third feedback information may be obtained according to an evaluation result of one piece of vehicle information among the multiple pieces of vehicle information. That is, the third feedback information corresponds to one piece of vehicle information.
  • the third feedback information may be generated according to the priority of the associated reference information.
  • the higher the priority of the reference information the higher the correlation degree between the related reference information and the user instruction, and the lower the priority, the lower the correlation degree between the related reference information and the user instruction.
  • the related reference information 1 corresponds to the evaluation result X
  • the related reference information 2 corresponds to the evaluation result Y
  • the evaluation result X indicates "the condenser is in normal working state and can be opened”
  • the evaluation result Y indicates "temperature If the priority of the related reference information 1 is higher than the priority of the related reference information 2, it indicates that the correlation degree of the related reference information 1 and the "turn on the air conditioner” is higher than that of the related reference information 2 and the "turn on the air conditioner". If the correlation degree is higher, the third feedback information is "the condenser is working normally and the air conditioner can be turned on”.
  • the related reference information with the highest priority may be acquired first, then an evaluation result is generated according to the related reference information with the highest priority, and then the third feedback information is acquired according to the evaluation result.
  • an evaluation result corresponding to each linked reference information may be generated first, and then the third feedback information is obtained according to the evaluation result corresponding to the linked reference information with the highest priority.
  • the third feedback information may correspond to one associated reference information, or may correspond to multiple associated reference information.
  • the following description is given by taking the related reference information as including vehicle information as an example.
  • the related reference information when there are multiple pieces of vehicle information, when each piece of vehicle information satisfies the corresponding condition in the fourth condition, an evaluation result corresponding to each piece of vehicle information may be generated, and the third feedback information may correspond to multiple pieces of vehicle information.
  • the corresponding evaluation result 1 can be obtained
  • the state of the vehicle transmission system satisfies the above condition 23
  • the corresponding evaluation result 2 can be obtained, and the third feedback information can be obtained according to the evaluation result 1 and the evaluation result. Result 2 was obtained. It should be noted that operations corresponding to different evaluation results may be the same or different.
  • Manner 5 Generate third feedback information according to the non-vehicle information and the evaluation result, the evaluation condition may include the fourth condition, and the non-vehicle information may include one or more of the following: weather, temperature, service price corresponding to the operation, humidity, or availability. The concentration of inhaled particulate matter.
  • the above step 7, generating feedback information based on the associated reference information and the evaluation result, may include: generating third feedback information if the first condition is satisfied.
  • the third feedback information is used to indicate that it is recommended to execute the user instruction.
  • the fourth condition includes one or more of the following conditions:
  • Condition 27 the weather belongs to the second weather set.
  • the temperature is within the second temperature range. or,
  • the humidity is within the second humidity interval. or,
  • the concentration of the inhalable particulate matter is within the second concentration interval.
  • Condition 27 and Condition 28 are described below, respectively.
  • the second weather set may be a set of weathers corresponding to scenarios in which the user instruction can be executed or necessary to be executed.
  • the second temperature interval may be a temperature interval corresponding to a scenario in which the user instruction can be executed or it is necessary to execute the user instruction.
  • the second service interval may be a price that may be spent when the user instruction can be executed or necessary to execute.
  • the second humidity interval may be a set of humidity corresponding to scenarios in which the user instruction can be executed or it is necessary to execute the user instruction.
  • the second concentration interval may be a set of concentrations of inhalable particulate matter corresponding to scenarios where the user instruction can be executed or it is necessary to execute the user instruction. For example, if the user instruction is "navigate to a car wash", the corresponding service price may be the price of one car wash.
  • the non-vehicle information includes the weather
  • the weather belongs to the second weather set
  • the user instruction can be executed or necessary to be executed in the scenario corresponding to the weather
  • "weather” corresponds to the evaluation result that recommends executing the user instruction.
  • the non-vehicle information includes temperature
  • the user command can be executed or it is necessary to execute the user command
  • "temperature" corresponds to the evaluation result that recommends executing the user command.
  • the non-vehicle information includes the service price
  • the service price is within the second price range
  • the scenario corresponding to the service price it is possible or necessary to execute the user instruction, and the "service price" corresponds to the suggestion to execute the user instruction. evaluation results.
  • the implementation of the third feedback information in the fifth mode may correspond to the implementation of the third feedback information in the reference mode four, which will not be repeated here.
  • vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, A/C condenser status, A/C temperature sensor status, A/C compressor status, non-vehicle status
  • vehicle information may also include one or more of the following: weather, temperature, service price corresponding to operation, humidity, or concentration of inhalable particulate matter
  • the fourth condition may include both conditions corresponding to vehicle information and conditions corresponding to non-vehicle information .
  • the fourth condition includes one or more of conditions 20 to 26, and also includes one or more of conditions 27 to 31.
  • the evaluation conditions may include a fourth condition
  • the vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, or vehicle transmission system status state.
  • Non-vehicle information may include one or more of the following: weather, temperature, or service prices.
  • the above step 7, generating feedback information based on the associated reference information and the evaluation result, may include: if the fourth condition is satisfied, generating third feedback information according to the associated reference information.
  • the third feedback information is used to indicate that it is recommended to execute the user instruction.
  • the fourth condition includes one or more of the following conditions:
  • Condition 32 the vehicle cooling system is in a normal working state. or,
  • Condition 33 the vehicle ignition system is in a normal working state. or,
  • Condition 34 the vehicle starting system is in a normal working state. or,
  • Condition 35 the vehicle transmission system is in a normal working state. or,
  • Condition 36 the weather belongs to the second weather set. or,
  • Condition 37 the temperature is within the second temperature range. or,
  • Condition 38 the service price is within the second price range.
  • the implementation manners of condition 32 to condition 38 may correspond to the implementation manners of reference condition 20 to condition 23 and condition 27 to condition 29, and details are not described herein again.
  • the implementation of the third feedback information in the sixth mode reference may be made to the implementation modes of the third feedback information in the fourth and fifth modes, and details are not repeated here.
  • the evaluation result 3 is "the device is working normally, the air conditioner can be turned on", and the corresponding operation may be to turn on the air conditioner.
  • the evaluation result 4 is "the temperature in the car is lower than 15 degrees, and the heating mode of the air conditioner can be turned on”, and the corresponding operation can be to adjust the working mode of the air conditioner to the heating mode.
  • the evaluation result 5 is "Today is sunny, the air conditioner can be turned on", and the corresponding operation can be to turn on the air conditioner.
  • the operations corresponding to evaluation result 3 and evaluation result 4 are different, and the operations corresponding to evaluation result 3 and evaluation result 5 are the same.
  • only the second condition may be used to generate the second feedback information, or only the fourth condition may be used to generate the third feedback information, or the second condition and the fourth condition may be combined to generate the Feedback information corresponding to user commands.
  • the feedback information is generated by combining the above conditions 10 and 29, when the non-vehicle information includes the service price
  • the evaluation result corresponding to the condition 10 indicates that it is recommended not to execute the user instruction.
  • the evaluation result corresponding to condition 29 indicates that it is recommended to execute the user instruction.
  • the intersection of the first price range and the second price range is empty, that is, the first price range and the second price range are mutually exclusive. The embodiments of the present application do not limit the specific implementation manner of the evaluation conditions.
  • evaluation results corresponding to different conditions may be different or the same.
  • one evaluation result may be selected from multiple evaluation results for generating feedback information.
  • the fourth condition further includes: the fuel level is within the second fuel level threshold, and/or the air conditioning mode is a normal working mode, and/or the distance is within the second distance threshold, and/or there is no promotion.
  • the fifth condition is different from the second condition and the fourth condition.
  • no feedback information may be generated.
  • the following is an example in conjunction with a specific scenario.
  • the fifth condition includes: when the temperature is in the third temperature range, if the user command is "turn on the air conditioner", the first temperature range is the range below 23°C, the second temperature range is the range above 27°C, and the third temperature range is the range below 27°C.
  • the temperature range is from 23°C to 27°C (including 23°C and 27°C). If the temperature is between 23°C and 27°C, it can be determined that the temperature is suitable. There is no need to turn on the air conditioner and no feedback information is generated.
  • the second price range is below price A, indicating that the car wash price is relatively cheap
  • the first price range is above price B, indicating that the car wash price is expensive
  • the third price range is the price.
  • a - price B where A ⁇ B. If the service price, such as the car wash price, is between price A and price B, it can be determined that the car wash price is normal and no feedback information is generated.
  • the second feedback information can also be generated.
  • the vehicle information may also include a device that executes user instructions, such as the status of other components or components on the vehicle.
  • the content of the vehicle information may be determined according to a specific scenario, which is not specifically limited in this embodiment of the present application. If the vehicle information further includes other information, the second condition or the fourth condition may further include a condition corresponding to the other information.
  • the fourth condition may also include one or more of these vehicle information
  • the second condition may further include that one or more items of the vehicle information are in an abnormal working state.
  • the non-vehicle information is not limited to the types listed in the embodiments of the present application. The type of non-vehicle information may be determined according to an actual application scenario, which is not specifically limited in this embodiment of the present application. The above-mentioned second condition and fourth condition may be determined according to vehicle information or non-vehicle information.
  • feedback information can be generated in combination with each reference information associated with the user instruction, thereby further improving the accuracy of the feedback information.
  • the feedback method shown in FIG. 3 may further include: outputting feedback information.
  • outputting the feedback information may include: outputting the feedback information by means of voice or image.
  • outputting feedback information may also be sending feedback information to other devices.
  • the user can determine the next operation according to the feedback information, thereby further improving the user experience.
  • the device on the corresponding vehicle can also be controlled to execute the user instruction according to the generated feedback information.
  • the following takes the electronic device including the processing unit and the input/output unit as an example, and the operation after the feedback information is generated is described in combination with the solution 1- solution 3 as an example.
  • the processing unit may control the electronic device to execute the operation corresponding to the user instruction according to the feedback information.
  • the processing unit is the processing unit in the automatic driving ECU
  • the feedback information is "the weather is suitable, it is recommended to navigate to the car wash”
  • the processing unit in the automatic driving ECU can be based on The feedback information controls the car to follow the navigation path of the car wash.
  • the input and output unit can output the feedback information, so that after the user obtains the feedback information, he can control the corresponding device to perform the operation corresponding to the user's instruction according to the feedback information.
  • the processing unit of the mobile phone can output the feedback information through an input and output unit, such as a touch screen, a speaker, etc. .
  • the user can then, based on the feedback information, not drive the vehicle to the car wash on rainy days.
  • the processing unit can control the electronic device to perform corresponding operations according to the feedback information, and can also output the feedback information through the input and output unit, so that the user can obtain the feedback information.
  • the electronic device can also execute the user instruction without outputting the feedback information through the input and output unit.
  • the processing unit can send feedback information to the input and output unit, and then the input and output unit sends the feedback information to the terminal device, so that the terminal device can perform corresponding operations according to the feedback information.
  • the execution device is an air conditioner
  • the electronic device is an on-board display
  • the feedback information is "indoor temperature is high, it is recommended to turn on the air conditioner”
  • the electronic device can send the feedback information to the air conditioner through the input and output unit, so that the air conditioner can be turned on according to the feedback information Cooling mode.
  • the embodiments of the present application do not limit the specific implementation manner in which the processing unit outputs the feedback information.
  • the feedback indication information corresponding to all the linked reference information is 0, it means that the linked reference information has nothing to do with the actual needs of the user, and in this case, the feedback information may not be output.
  • step S301 may be implemented by an input and output unit.
  • Step S301 may also be implemented jointly by the input and output unit and the processing unit.
  • the above step 1 may be implemented by an input/output unit
  • the above step 2 may be implemented by a processing unit.
  • Steps S302 to S303 may be implemented by a processing unit.
  • the function of the processing unit may also be implemented by a server or other device or device with computing functions, which is not specifically limited in this embodiment of the present application.
  • the vehicle information may also be device information of other devices, and the non-vehicle information may also be environment information related to other devices.
  • user instructions can be analyzed in combination with reference information to obtain feedback information indicating: recommending execution, or feedback information indicating: recommending not executing user instructions or fault alarms.
  • the operation suggestion corresponding to the user's instruction can be obtained in combination with the actual scene, and then the corresponding operation can be performed according to the feedback information.
  • the execution of the operation corresponding to the user instruction can be stopped in time to save the user's time and resources.
  • the operation corresponding to the user instruction may continue to be executed. In this way, the problem that the actual needs of the user cannot be met caused by performing the corresponding operation according to the user instruction can be solved, the accuracy of the feedback information can be improved, and the user experience can be improved.
  • the following takes the electronic device shown in FIG. 2 as an example to describe in detail the specific implementation of the feedback method provided in the embodiment of the present application in the vehicle-mounted module.
  • FIG. 4 is a second schematic flowchart of a feedback method according to an embodiment of the present application.
  • This feedback method can be applied to the in-vehicle system shown in FIG. 2 , and specifically implements the feedback method shown in FIG. 3 .
  • the input and output unit shown in FIG. 1 may be the AI speaker shown in FIG. 2
  • the processing unit shown in FIG. 1 may be the processing unit shown in FIG. 2 .
  • the feedback method may include the following S401-S409:
  • the AI speaker collects the voice information input by the user.
  • the AI speaker can collect the voice information input by the user through the built-in microphone.
  • scenario 1 the user sends a voice message of "turn on the air conditioner", and the AI speaker can collect the voice message of "turn on the air conditioner” through the built-in microphone.
  • scenario 2 the user sends a voice message of "navigate to the car wash”, and the AI speaker can collect the voice message of "navigate to the car wash” through the built-in microphone.
  • the AI speaker converts the voice information into text information.
  • the text information may be the text of "turn on the air conditioner”.
  • the text information may be the text of "navigate to the car wash”.
  • the AI speaker can convert speech information into text based on MFCC feature extraction and recurrent neural network technology to obtain text information.
  • the AI speaker sends text information to the processing unit. Accordingly, the processing unit can receive text information from the AI speaker.
  • the AI speaker can send text information to the second driving module of the processing unit through the first driving module.
  • the first driver module and the second driver module may be a universal asynchronous receiver/transmitter (UART) driver interface.
  • the processing unit determines the corresponding user instruction according to the text information.
  • FIG. 5 is a schematic diagram 1 of a data flow of a feedback method according to an embodiment of the present application.
  • the user instruction may include the instruction category “operation type” of the operation type instruction and the keywords of “turn on” and “air conditioner”.
  • FIG. 6 is a second schematic diagram of a data flow of a feedback method provided by an embodiment of the present application.
  • the user instruction may include the instruction category “travel category” of the travel category instruction, and keywords of “navigation” and “car wash”.
  • the processing unit classifies the text information by using feature extraction and machine learning methods, and determines that the instruction category corresponding to the voice information is an operation instruction.
  • the processing unit can also use the TF-IDF algorithm to extract keywords in the text information.
  • the processing unit selects the associated reference information according to the cosine similarity between the user instruction and the plurality of reference information respectively.
  • the associated reference information is reference information whose cosine similarity is greater than the similarity threshold.
  • reference may be made to the relevant content in the above S302, which will not be repeated here.
  • the relevant reference information may include vehicle information such as air conditioner status and air conditioner working mode, and the relevant reference information may also include non-vehicle information such as weather, temperature, humidity, and PM2.5 concentration.
  • the cross-reference information may include travel-related vehicle information, such as the ECU status of the driving system or the fuel level.
  • the ECU status of the driving system may include one or more of the following vehicle information: engine-related ECU status, cooling system ECU status, vehicle ignition system ECU status, vehicle starting system ECU status, vehicle transmission system ECU status, and other vehicle information.
  • the similarity threshold may be 0.5.
  • the vehicle information may include the status of the condenser, temperature sensor, and air conditioner compressor at the current moment, and may also include vehicle information such as the current working mode of the air conditioner and the supported working modes.
  • the non-vehicle information may include non-vehicle information such as interior temperature, exterior temperature, humidity, and fine particulate matter (PM2.5).
  • the vehicle information may include vehicle information such as the engine ECU status, cooling system ECU status, ignition system ECU status, starting system ECU status, and transmission system status of the driving system at the current moment.
  • vehicle information shown in FIG. 6 may include the state of the engine, the state of the transmission, and the state of the clutch.
  • the non-vehicle information may include non-vehicle information such as local weather in the next 24 hours, discounts (service prices) of the target car wash, and the distance between the current location and the car wash.
  • the processing unit obtains the evaluation result according to the user instruction and the reference information.
  • the processing unit may determine the corresponding evaluation condition according to the user instruction and the associated reference information. Then, the evaluation results are obtained according to the evaluation conditions.
  • the feedback information is determined according to the evaluation result, vehicle information and non-vehicle information.
  • the feedback information may indicate: feedback information suggesting not to execute the user instruction or fault alarm, such as the first feedback information or the second feedback information.
  • the feedback information may also indicate: feedback information suggesting to execute the user instruction, such as third feedback information.
  • Evaluation condition 2 is used to generate feedback information corresponding to the air conditioning mode according to the non-vehicle information. If the temperature inside and outside the car is lower than 15 degrees Celsius, the third feedback message of "The temperature is low, it is recommended to adjust the working mode of the air conditioner to the warm air mode" is determined. If the temperature inside and outside the car is higher than 32 degrees Celsius, then determine the third feedback information of "The temperature is high, it is recommended to adjust the working mode of the air conditioner to the cooling mode”. If the concentration of PM2.5 reaches the pollution threshold, it is determined that "the air pollution is serious, and it is recommended to adjust the working mode of the air conditioner to the ventilation mode".
  • Condition 3 is evaluated, and feedback information corresponding to temperature is generated. If the temperature inside and outside the car is 20 degrees Celsius, the second feedback message of "The temperature is suitable, it is not recommended to turn on the air conditioner" is determined. If the temperature outside the vehicle reaches 32 degrees Celsius, the third feedback message of "The temperature outside the vehicle is high, it is recommended to adjust the temperature of the air conditioner to 25 degrees Celsius” is determined. If the default settings of the temperature inside the car and the temperature of the air conditioner are both 25 degrees Celsius, the third feedback message of "The temperature in the car and the temperature of the air conditioner are both 25 degrees Celsius, and the air conditioner can be turned on” can be determined.
  • the second feedback information of “the equipment is running abnormally, it is recommended to repair and then navigate” is determined. Conversely, if the engine ECU status, cooling system ECU status, ignition system ECU status, and starting system ECU status are all in normal working status, determine the third feedback message of "the equipment is running normally, it is recommended to navigate to wash the car".
  • Evaluate Condition 5 which is used to generate feedback information based on the weather. If the local weather in the next 24 hours is suitable, the third feedback information of "the weather is suitable and suitable for navigating to the car wash" can be determined. If there is heavy rain in the next 24 hours, the second feedback information of "it may rain in the future, not suitable for car washing” can be determined. If there may be a tropical storm climate in the next 24 hours, the second feedback information of "there may be a storm in the future, travel is not recommended" can be determined.
  • Evaluation condition 6 used to generate feedback information based on the service price. If the target car wash shop has discounted car wash activities, the third feedback information of "there are discount activities, car wash is recommended" can be determined. If the car wash price of the target car wash shop increases, the second feedback information of "the car wash price increases, and the car wash is suspended” can be determined. If there is no change in the car wash price of the target car wash shop, the third feedback message of "no change in the car wash price, the car can be washed" can be obtained.
  • the processing unit may evaluate in priority order based on the priority corresponding to the associated reference information, that is, the priority corresponding to the evaluation condition, so as to obtain feedback information with different priorities.
  • the processing unit sends feedback information to the AI speaker. Accordingly, the AI speaker receives feedback information from the processing unit.
  • the processing unit may send one of the multiple pieces of feedback information to the AI speaker. If there is second feedback information in the plurality of feedback information, the processing unit may send the second feedback information with the highest priority to the AI speaker. If the multiple pieces of feedback information are all third feedback information, the processing unit may send the third feedback information with the highest priority to the AI speaker.
  • the specific implementation manner of sending the feedback information reference may be made to the above-mentioned related content of S303, which will not be repeated here.
  • the processing unit sends the second feedback information to the AI speaker. If the multiple feedback information is the third feedback information, and the third feedback information with the highest priority is "The temperature is low, it is recommended to adjust the working mode of the air conditioner to the warm air mode", then the processing unit can send the third feedback information to the AI speaker. Feedback.
  • the AI speaker outputs a voice corresponding to the feedback information.
  • the AI speaker can convert the feedback information into speech, and then send out the speech through the speaker.
  • the AI speaker when the AI speaker receives the above-mentioned second feedback information, it can send out the feedback voice "the temperature of the condenser is too high, it is recommended to turn on the air conditioner after maintenance" through the speaker.
  • the AI speaker receives the above-mentioned third feedback information, it can send out the feedback voice "the temperature is low, it is recommended to adjust the working mode of the air conditioner to the warm air mode” through the speaker.
  • the AI speaker when the AI speaker receives the above-mentioned second feedback information, it can send out the feedback voice of "the device is running abnormally, it is recommended to repair it before navigating" through the speaker.
  • the AI speaker receives the above-mentioned third feedback information, it can send out the feedback voice of "there are preferential activities, it is recommended to wash the car" through the speaker.
  • the processing unit may also send third feedback information to the air conditioner through the vehicle bus, so as to control the air conditioner to perform an operation corresponding to the third feedback information.
  • the processing unit may also send third feedback information to the vehicle navigation system ECU through the vehicle bus, so as to control the vehicle navigation system ECU to perform an operation corresponding to the third feedback information.
  • the user can refer to the feedback voice sent by the AI speaker, perform the corresponding operation, or re-instruct the AI speaker, thereby avoiding the situation that the actual execution result cannot meet the user's actual needs, saving the user's time and resources, and improving the user experience.
  • the feedback method provided by the embodiments of the present application has been described in detail above with reference to FIGS. 3 to 6 .
  • the electronic device for implementing the feedback method provided by the embodiments of the present application will be described in detail below with reference to FIGS. 7-8 .
  • FIG. 7 is a schematic structural diagram 1 of an electronic device provided by an embodiment of the present application.
  • the electronic device 700 includes: an acquisition module 701 and a generation module 702 .
  • FIG. 7 only shows the main components of the electronic device.
  • the obtaining module 701 may be used to obtain user instructions.
  • the obtaining module 701 can also be used to obtain reference information associated with the user instruction.
  • the reference information is information that affects whether to execute the user instruction.
  • the generating module 701 may be configured to generate feedback information according to the reference information associated with the user instruction.
  • the generating module 701 may also be configured to obtain the evaluation result of the reference information associated with the user instruction through the obtaining module 701 .
  • the generating module 701 may also be configured to generate feedback information based on the reference information associated with the user instruction and the evaluation result.
  • the generating module 701 may also be configured to obtain the evaluation result according to the evaluation function through the obtaining module 701 .
  • the input parameters of the evaluation function include user instructions and reference information associated with the user instructions.
  • the generating module 701 may be further configured to generate the first feedback information according to the reference information when the evaluation result satisfies the first condition.
  • the first feedback information is used to indicate: information suggesting not to execute the user instruction or a fault alarm.
  • the generating module 701 may be further configured to generate the second feedback information according to the reference information associated with the user instruction when the evaluation result satisfies the second condition.
  • the second feedback information is used to indicate that it is recommended not to execute the user instruction or a fault alarm.
  • the second condition may include: the value of the existing evaluation result is within the first range, or the value of the weighted summation result of all the evaluation results is within the second range.
  • the generating module 701 may also be configured to generate the second feedback information according to the target reference information.
  • the target reference information may be reference information corresponding to the evaluation result satisfying the third condition.
  • the obtaining module 701 can also be used to obtain reference information.
  • the obtaining module 701 may also be used to calculate the degree of association between the user instruction and the reference information.
  • the obtaining module 701 can also be used to obtain reference information associated with the user instruction.
  • the reference information associated with the user instruction may be reference information with an association degree greater than or equal to a threshold of the association degree.
  • the degree of association may be cosine similarity.
  • the reference information may include vehicle information
  • the vehicle information may include one or more of the following: vehicle cooling system status, vehicle ignition system status, vehicle starting system status, vehicle driveline status, fuel level, air conditioning mode, air conditioning Condenser status, A/C temperature sensor status, humidity sensor status, or A/C compressor status.
  • the reference information may include non-vehicle information, and the non-vehicle information may include one or more of the following: weather, temperature, humidity, distance, concentration of respirable particulate matter, service price, or promotional activity information.
  • the obtaining module 701 may be further configured to obtain the evaluation result of the reference information associated with the user instruction according to the priority of the reference information associated with the user instruction.
  • the user instruction may be a voice instruction.
  • the acquiring module 701 and the generating module 702 may also be integrated into one module, such as a processing module.
  • the processing module may be used to implement the processing function of the electronic device 700 .
  • the electronic device 700 may further include a storage module (not shown in FIG. 7 ), where the storage module stores programs or instructions.
  • the processing module executes the program or instruction
  • the electronic device 700 can execute the feedback method as shown in FIG. 3 or FIG. 4 .
  • the electronic device 700 may further include a transceiver module (not shown in FIG. 7 ).
  • the transceiver module is used to implement the transceiver function of the electronic device 700 .
  • the transceiver module may include a receiving module and a sending module. The receiving module and the sending module are respectively used to implement the receiving function and the sending function of the electronic device 700 .
  • the acquisition module 701 may include a transceiver module.
  • the acquiring module 701 and the generating module 702 involved in the electronic device 700 may be implemented by a processor or a processor-related circuit component, and may be a processor or a processing unit; the transceiver module may be implemented by a transceiver or a transceiver-related circuit component, Can be a transceiver or a transceiver unit.
  • the electronic device 700 may be a terminal device, a chip (system) or other components or components that can be provided in the terminal device, or a device including the terminal device, which is not limited in this application.
  • FIG. 8 is a second schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the electronic device may be a terminal device or a chip (system) or other components or assemblies that can be provided in the terminal device.
  • the electronic device 800 may include a processor 801 .
  • the electronic device 800 may further include a memory 802 and/or a transceiver 803 .
  • the processor 801 is coupled with the memory 802 and the transceiver 803, such as can be connected through a communication bus.
  • each component of the electronic device 800 will be specifically introduced:
  • the processor 801 is the control center of the electronic device 800, and may be a processor or a general term for multiple processing elements.
  • the processor 801 is one or more central processing units (CPUs), may also be a specific integrated circuit (application specific integrated circuit, ASIC), or is configured to implement one or more of the embodiments of the present application
  • An integrated circuit such as: one or more microprocessors (digital signal processor, DSP), or, one or more field programmable gate array (field programmable gate array, FPGA).
  • the processor 801 may execute various functions of the electronic device 800 by running or executing software programs stored in the memory 802 and calling data stored in the memory 802 .
  • the processor 801 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 8 .
  • the electronic device 800 may also include multiple processors, such as the processor 801 and the processor 804 shown in FIG. 2 .
  • processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU).
  • a processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).
  • the memory 802 is used for storing the software program for executing the solution of the present application, and the execution is controlled by the processor 801.
  • the processor 801. For the specific implementation, reference may be made to the above method embodiments, which will not be repeated here.
  • memory 802 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, random access memory (RAM), or a random access memory (RAM) or other type of static storage device that can store information and instructions.
  • ROM read-only memory
  • RAM random access memory
  • RAM random access memory
  • RAM random access memory
  • RAM random access memory
  • Other types of dynamic storage devices for instructions which may also be electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), or other optical disks storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or capable of carrying or storing desired program code in the form of instructions or data structures and any other medium that can be accessed by a computer, but is not limited thereto.
  • the memory 802 may be integrated with the processor 801, or may exist independently, and be coupled to the processor 801 through an interface circuit (not shown in FIG. 8)
  • the transceiver 803 is used for communication with other electronic devices.
  • the electronic device 800 is a terminal device, and the transceiver 803 may be used to communicate with a network device or communicate with another terminal device.
  • the transceiver 803 may include a receiver and a transmitter (not shown separately in FIG. 8). Among them, the receiver is used to realize the receiving function, and the transmitter is used to realize the sending function.
  • the transceiver 803 may be integrated with the processor 801, or may exist independently, and be coupled to the processor 801 through an interface circuit (not shown in FIG. 8) of the electronic device 800, which is not made in this embodiment of the present application Specific restrictions.
  • the structure of the electronic device 800 shown in FIG. 8 does not constitute a limitation to the electronic device, and an actual electronic device may include more or less components than those shown in the figure, or combine some components, or Different component arrangements.
  • the electronic device in FIG. 7 may be a network device or a terminal device—any electronic device in FIG. 6 may be a network device, such as a server, or a terminal device, such as a vehicle-mounted terminal.
  • the embodiments of the present application provide a feedback system.
  • the feedback system includes electronics.
  • the feedback system may also include a network device.
  • processors in the embodiments of the present application may be a central processing unit (central processing unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (digital signal processors, DSP), dedicated integrated Circuit (application specific integrated circuit, ASIC), off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the memory in the embodiments of the present application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • DDR SDRAM double data rate synchronous dynamic random access memory
  • enhanced SDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous connection dynamic random access memory Fetch memory
  • direct memory bus random access memory direct rambus RAM, DR RAM
  • the above embodiments may be implemented in whole or in part by software, hardware (eg, circuits), firmware, or any other combination.
  • the above-described embodiments may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated.
  • the computer may be a general purpose computer, special purpose computer, computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server or data center Transmission to another website site, computer, server or data center by wire (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that contains one or more sets of available media.
  • the usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media.
  • the semiconductor medium may be a solid state drive.
  • At least one means one or more, and “plurality” means two or more.
  • At least one item(s) below” or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s).
  • at least one item (a) of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c may be single or multiple .
  • the size of the sequence numbers of the above-mentioned processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present application. implementation constitutes any limitation.
  • the disclosed systems, electronic devices and methods may be implemented in other manners.
  • the embodiments of the electronic device described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be Incorporation may either be integrated into another system, or some features may be omitted, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Acoustics & Sound (AREA)
  • Artificial Intelligence (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • User Interface Of Digital Computer (AREA)
  • Navigation (AREA)

Abstract

本申请提供一种反馈方法及电子设备，能够解决执行指令对应的操作所导致的执行结果不能满足用户实际需求的问题，从而能够针对用户发出指令对应的需求确定对应的反馈信息，节省用户的时间和资源，提升用户体验。可应用于终端设备中。该方法包括: 获取用户指令; 获取与用户指令关联的参考信息; 根据与所述用户指令关联的参考信息，生成反馈信息。

Description

反馈方法及电子设备 技术领域
本申请涉及通信领域，尤其涉及一种反馈方法及电子设备。
背景技术
随着终端设备的发展，用户与终端设备之间的交互越来越多。终端设备通常可以根据用户指令，获取用户指令对应的反馈信息。例如，通过语音方式输入用户指令，则终端设备可以基于语速，生成与语速匹配的反馈信息。又如，终端设备还可以根据用户指令对应的应答标识，生成与用户指令对应的应答标识匹配的反馈信息。
上述获取反馈信息的方案中，反馈信息的内容均是与用户指令对应的。如用户向车辆发出“导航到洗车店”的用户指令，车辆可以向用户反馈洗车店的导航信息。然而，在实际场景中执行用户指令对应的操作，难以满足用户的实际需求，如雨天不需要洗车，但是给出了洗车的反馈信息，以致于浪费用户的时间和资源，导致用户的体验降低。
发明内容
本申请实施例提供一种反馈方法及电子设备，能够解决执行用户指令对应的操作不能满足用户实际需求的问题，能够提高反馈信息的准确性，从而提升用户体验。
为达到上述目的，本申请采用如下技术方案：
第一方面，提供一种反馈方法。该反馈方法包括：获取用户指令。获取与用户指令关联的参考信息。其中，参考信息为影响是否执行用户指令的信息。根据与用户指令关联的参考信息生成反馈信息。
基于第一方面所述的反馈方法，可以结合参考信息分析用户指令，生成用于指示：建议执行用户指令的反馈信息，或者生成用于指示：建议不执行用户指令或故障告警的反馈信息。如此，可以结合实际场景获得与用户指令对应的操作建议，进而可以根据反馈信息执行对应的操作。一方面，在用户指令对应的操作与实际场景不对应时，可以及时地停止执行用户指令对应的操作，节省时间和成本；另一方面，在用户指令对应的操作与实际场景对应时，可以继续执行用户指令对应的操作。由此，可以解决根据用户指令执行对应的操作所导致的不能满足用户的实际需求的问题，能够提高反馈信息的准确性，从而提升用户体验。
一种可能的设计方案中，根据与用户指令关联的参考信息生成反馈信息，可以包括：获取与用户指令关联的参考信息的评估结果。基于与用户指令关联的参考信息和评估结果，生成反馈信息。如此，可以结合各个与用户指令关联的参考信息，生成反馈信息，从而进一步提高反馈信息的准确性。
一种可能的设计方案中，获取与用户指令关联的参考信息的评估结果可以包括：根据评估函数获得评估结果。其中，评估函数的输入参数包括用户指令和与用户指令 关联的参考信息。
可选地，基于与用户指令关联的参考信息和评估结果，生成反馈信息，可以包括：若评估结果满足第一条件，则根据与用户指令关联的参考信息生成第一反馈信息。其中，第一反馈信息用于指示：建议不执行用户指令或故障告警。如此，在参考信息满足第一条件时，可以认为执行用户指令对应的操作难以满足用户实际需求，进而生成指示建议不执行用户指令或故障告警的第一反馈信息，提高反馈信息的准确性，且可以节省时间和成本。
可选地，与用户指令关联的参考信息可以为多个，评估结果也可以为多个，与用户指令关联的参考信息与评估结果一一对应。
进一步地，基于与用户指令关联的参考信息和评估结果，生成反馈信息，可以包括：若评估结果满足第二条件，则根据与用户指令关联的参考信息生成第二反馈信息。其中，第二反馈信息用于指示：建议不执行用户指令或故障告警。第二条件包括：存在评估结果的值在第一范围内，或所有评估结果的加权求和结果的值在第二范围内。如此，在参考信息满足第二条件时，可以认为执行用户指令对应的操作难以满足用户实际需求，进而生成指示建议不执行用户指令或故障告警的第二反馈信息，提高反馈信息的准确性，且可以节省时间和成本。
或者，进一步地，根据与用户指令关联的参考信息生成第二反馈信息，可以包括：根据目标参考信息生成第二反馈信息。其中，目标参考信息可以为：满足第三条件的结果对应的与用户指令关联的参考信息。如此，可以根据对用户指令影响更大的参考信息生成第二反馈信息，从而能够进一步提高反馈信息的准确性。
一种可能的设计方案中，获取与用户指令关联的参考信息，可以包括：获取参考信息。计算用户指令与参考信息之间的关联度。获取与用户指令关联的参考信息。其中，与用户指令关联的参考信息为：关联度大于或等于关联度阈值的参考信息。如此，通过关联度比较的方式，可以从多个参考信息中准确地选择出与用户指令关联的参考信息，从而提高反馈信息的准确性。
可选地，关联度可以为余弦相似度、杰卡德相似度、或皮尔森相似度。
可选地，参考信息可以包括车辆信息，车辆信息可以包括如下的一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、油量、空调模式、空调冷凝器状态、空调温度传感器状态、湿度传感器状态、或空调压缩机状态。
或者，可选地，参考信息可以包括非车辆信息，非车辆信息可以包括如下一项或多项：天气、温度、湿度、距离、可吸入颗粒物的浓度、服务价格、或促销活动信息。
可选地，获取与用户指令关联的参考信息的评估结果，可以包括：根据与用户指令关联的参考信息的优先级，获取与用户指令关联的参考信息的评估结果。如此，根据优先级获取评估结果，在优先级高的参考信息的评估结果位于第一范围内时，可以避免计算其他参考信息的评估结果，以减少计算量，从而进一步提高反馈效率。
一种可能的设计方案中，第一方面所述的反馈方法还可以包括：输出反馈信息。如此，用户可以根据反馈信息确定下一步操作，从而进一步提升用户体验。
可选地，输出反馈信息，可以包括：通过语音或图像的方式，输出反馈信息。
一种可能的设计方案中，参考信息可以来自云端。如此，可以实时地更新参考信息，进一步提高反馈信息的准确性。
一种可能的设计方案中，参考信息可以存储在本地中。如此，使用参考信息和存储参考信息的为同一个设备，可以更快地得到参考信息，进而提高效率。此外，在车辆获取与车辆上设备相关的参考信息时，可以避免向车辆外的其他设备发送参考信息，能够降低个人数据泄漏的风险，从而提高参考信息的安全性。
一种可能的设计方案中，用户指令可以包括：指令类别和/或关键字。
一种可能的设计方案中，用户指令为语音指令。如此，用户可以通过语音输入用户指令，避免手动输入指令，从而能够提高行车安全性。
一种可能的设计方案中，获取用户指令，可以包括：通过触摸屏获取用户指令。如此，可以获得更准确的用户指令，进一步提高反馈信息的准确性。
第二方面，提供一种电子设备，该电子设备可以包括：获取模块和生成模块。获取模块，可以用于获取用户指令。获取模块，还可以用于获取与用户指令关联的参考信息。其中，参考信息为影响是否执行用户指令的信息。生成模块，可以用于根据与用户指令关联的参考信息生成反馈信息。
一种可能的设计方案中，生成模块，还可以用于通过获取模块获取与用户指令关联的参考信息的评估结果。生成模块，还可以用于基于与用户指令关联的参考信息和评估结果，生成反馈信息。
可选地，生成模块，还可以用于通过获取模块，根据评估函数获得评估结果。其中，评估函数的输入参数可以包括用户指令和与用户指令关联的参考信息。
可选地，生成模块，还可以用于在评估结果满足第一条件时，根据与用户指令关联的参考信息生成第一反馈信息。其中，第一反馈信息用于指示：建议不执行用户指令或故障告警。
进一步地，与用户指令关联的参考信息可以为多个，评估结果也可以为多个，与用户指令关联的参考信息与评估结果一一对应。
或者，进一步地，生成模块，还可以用于在评估结果满足第二条件时，根据与用户指令关联的参考信息生成第二反馈信息。其中，第二反馈信息用于指示：建议不执行用户指令或故障告警。第二条件可以包括：存在评估结果的值在第一范围内，或所有评估结果的加权求和结果的值在第二范围内。
一种可能的设计方案中，生成模块，还可以用于根据目标参考信息生成第二反馈信息。其中，目标参考信息可以为：满足第三条件的评估结果对应的与用户指令关联的参考信息。
可选地，获取模块，还可以用于获取参考信息。获取模块，还可以用于计算用户指令与参考信息之间的关联度。获取模块，还可以用于获取与用户指令关联的参考信息。其中，与用户指令关联的参考信息可以为关联度大于或等于关联度阈值的参考信息。
可选地，关联度可以为余弦相似度。
可选地，参考信息可以包括车辆信息，车辆信息可以包括如下一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、油量、 空调模式、空调冷凝器状态、空调温度传感器状态、湿度传感器状态、或空调压缩机状态。
或者，可选地，参考信息可以包括非车辆信息，非车辆信息可以包括如下一项或多项：天气、温度、湿度、距离、可吸入颗粒物的浓度、服务价格、或促销活动信息。
可选地，获取模块，还可以用于根据与用户指令关联的参考信息的优先级，获取与用户指令关联的参考信息的评估结果。
一种可能的设计方案中，用户指令可以为语音指令。
此外，第二方面所述的电子设备的技术效果可以参考第一方面所述的反馈方法的技术效果，此处不再赘述。
第三方面，提供一种电子设备，电子设备能够执行第一方面中任一项的方法。
此外，第三方面所述的电子设备的技术效果可以参考第一方面所述的反馈方法的技术效果，此处不再赘述。
第四方面，提供一种车辆，车辆包括如第二方面或第三方面中任一项的电子设备。
第五方面，提供一种车辆，车辆能够执行第一方面中任一项的方法。
此外，第四方面和第五方面中任一方面所述的车辆的技术效果可以参考第一方面所述的反馈方法的技术效果，此处不再赘述。
第六方面，提供一种电子设备，包括：处理器和存储器；存储器用于存储计算机指令，当处理器执行该指令时，以使电子设备执行第一方面中任一项的反馈方法
第七方面，提供一种电子设备，包括：处理器和接口电路。其中，接口电路，用于接收代码指令并传输至处理器。处理器，用于运行代码指令以执行第一方面中任一项的反馈方法。
第八方面，提供一种电子设备，电子设备包括处理器和收发器，收发器用于电子设备和其他电子设备之间进行信息交互，处理器执行程序指令，用以执行第一方面中任一项的反馈方法。
此外，第六方面至第八方面中任一方面所述的电子设备的技术效果可以参考第一方面所述的反馈方法的技术效果，此处不再赘述。
第九方面，提供一种处理器，处理器用于执行第一方面中任一项的方法。
第十方面，提供一种服务器。其中，服务器用于执行第一方面所述的反馈方法。
第十一方面，提供一种计算机可读存储介质，计算机可读存储介质包括计算机程序或指令，当计算机程序或指令在计算机上运行时，执行第一方面中任一项的反馈方法。
第十二方面，提供一种计算机程序产品，包括计算机程序或指令，当该计算机程序或指令在计算机上运行时，使得该计算机执行第一方面中任一项的反馈方法。
附图说明
图1为本申请实施例提供的反馈系统的架构示意图一；
图2为本申请实施例提供的反馈系统的架构示意图二；
图3为本申请实施例提供的反馈方法的流程示意图一；
图4为本申请实施例提供的反馈方法的流程示意图二；
图5为本申请实施例提供的反馈方法的数据流向示意图一；
图6为本申请实施例提供的反馈方法的数据流向示意图二；
图7为本申请实施例提供的电子设备的架构示意图一；
图8为本申请实施例提供的电子设备的架构示意图二。
具体实施方式
下面对现有的技术方案进行简要描述。
目前，终端设备有两种根据指令输出反馈信息的反馈方法，下面分别描述现有技术中终端设备输出反馈的具体实现方式。
反馈方法1，终端设备可以根据用户发出查询语音时的语速，输出对应的查询结果。
具体地，终端设备可以获取用户输入的查询语音并识别上述查询语音，确定对应的查询指令。然后，终端设备向网络设备，如服务器发送查询指令。接着，终端设备接收来自网络设备根据查询指令反馈的查询结果。之后，终端设备可以根据用户输入的查询语音，确定对应的语音语速，并反馈语音语速和查询结果。最后，终端设备可以基于预设的多种反馈模板，根据查询结果和语音语速，生成与语音语速对应的语音反馈信息。例如，用户发出“今天温度如何”的查询语音，如果语音语速较快，则生成简单的语音反馈信息，如“今天温度为29℃”，如果语音语速较慢，则生成详细的语音反馈信息，如“今天温度为29℃，降水概率为23％，湿度为77％，风速为18公里/时”。
在上述反馈方法1中，终端设备可以通过语速来识别用户获取信息的急切程度，语速越快，用户的急切程度越高，从而可以输出更简单的语音反馈信息。然而，申请人发现：反馈方法1中，终端设备只关注语音语速的反馈方式，忽略了实际场景中的用户的实际需求，没有分析实际场景对执行查询语音对应的操作的影响，容易出现实际执行操作的结果不能满足用户的实际需求的情况，从而导致输出的查询结果对用户体验的提升有限。
反馈方法2，终端设备可以内置规则库，根据语音输入的应答类型标识，输出与应答类型标识对应的反馈结果。
每个语音控制指令对应一种应答类型标识，终端设备根据语音控制指令执行相应的操作，并输出与语音控制指令中应答类型标识对应的应答反馈。其中，应答反馈与应答类型标识一一对应。举例来说，在通过空调调节温度的场景中，若语音控制指令“空调设置25度”的应答类型标识为应答类型标识A，则可以调节温度为25度，并反馈语音应答“空调已经设置25度”，即输出语音应答反馈。若语音控制指令“空调设置25度”的应答类型标识为应答类型标识B，则可以调节空调温度为25度，并控制灯光模块执行相应的灯光应答指令，即输出灯光应答反馈。
在上述反馈方法2中，终端设备可以基于应答类型标识与应答反馈一一对应的规则库，输出与应答类型标识对应的应答反馈。然而，申请人发现：反馈方法2中，终端设备也忽略了实际场景中用户的情绪，没有分析实际场景对执行操作的影响，也容易出现实际执行操作的结果与不能满足用户实际需求的情况，从而导致输出的应答反馈对用户体验的提升有限。
为了提高反馈信息的准确性，本申请实施例提供一种反馈方法，能够结合实际参 考信息与用户指令生成反馈信息，从而避免出现根据指令执行对应的操作所导致的执行结果不能满足用户实际需求的情况，提升用户体验。
首先介绍本申请实施例所涉及的技术术语。
1、梅尔倒谱系数(mel-scale frequency cepstral coefficients，MFCC)：是一种在语音识别领域中广泛使用的语音特征，可以用于表征语音信号的能量在不同频率范围的分布。
2、词频-逆文本频率指数(term frequency–inverse document frequency，TF-IDF)算法：是一种用于信息检索与数据挖掘的常用加权技术，用于评估一个字词对于一个文件集或一个语料库中的其中一份文件的重要程度，例如，一个字词的重要性随着该字词在文件中出现的次数成正比增加，但同时会随着该字词在语料库中出现的频率成反比下降。
3、余弦相似度(cosine similarity)：又称为余弦相似性，可以通过计算两个向量的夹角余弦值来评估他们的相似度。本申请实施例可以将需要比较的两个文本转换为对应的向量，从而利用余弦相似性确定两者的相似度。余弦相似度的取值范围可以在[-1,1]之间，此时，余弦相似度的取值越趋近于1，代表两个文本的相似度越高，余弦相似度的取值越趋近于-1，代表两个文本的相似度越低。需要说明的是，余弦相似度还可以是经过归一化后的数值。也就是说，余弦相似度的取值范围还可以在[0,1]之间，此时，余弦相似度的取值越趋近于1，代表两个文本的相似度越高，余弦相似度的取值越趋近于0，代表两个文本的相似度越低。
下面将结合附图，对本申请中的技术方案进行描述。
本申请实施例的技术方案可应用于手机、可穿戴设备、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、平板电脑、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、个人数字助理(personal digital assistant，PDA)等任意终端设备上。本申请的电子设备还可以是作为一个或多个部件或者单元而内置于车辆的车载模块、车载模组、车载部件、车载芯片或者车载单元，车辆通过内置的车载模块、车载模组、车载部件、车载芯片或者车载单元可以实施本申请提供的反馈方法，当然，在以下实施例中，对该电子设备的具体形式不作任何限制。
为便于理解本申请实施例，首先以图1中示出的反馈系统为例详细说明适用于本申请实施例的反馈系统。示例性地，图1为本申请实施例提供的反馈系统的架构示意图一。
如图1所示，该反馈系统可以包括电子设备。其中，电子设备可以包括输入输出单元和处理单元，输入输出单元可以有一个或多个，处理单元可以有一个或多个。上述输入输出单元可以用于执行下述图3中的S301，上述处理单元可以用于执行下述图3中的S302-S303。需要说明的是，下述图3中的S301还可以由处理单元执行。
一种可能的设计方案中，输入输出单元可以用于获取用户输入的信息，并将用户输入的信息转换为文本信息，向处理单元发送该文本信息。处理单元可以根据文本信息获取用户指令，并确定对应的反馈信息。并且，处理单元可以根据反馈信息执行对应的操作，也可以通过输入输出单元输出该反馈信息，具体实现方式可以参考下述图 3所示出的方法实施例，此处不再赘述。
可以说明的是，输入输出单元和处理单元之间可以通过有线或无线的方式传输信息，如文本信息。其中，有线方式可以包括：电缆、光纤、网线等传输方式，无线方式可以包括基于一种或多种无线通信协议的无线连接，本申请实施例对输入输出单元和处理单元之间传输信息的具体实现不做限定。
可选地，输入输出单元可以与收发单元连接，输入输出单元也可以为具有收发功能的单元，该输入输出单元可以接收来自网络设备和/或其他终端设备发送的用户指令，还可以向网络设备和/或另一终端设备发送反馈信息。
可选地，反馈系统还可以包括与处理单元通信的网络设备，网络设备可以向处理单元发送车辆信息和/或非车辆信息。
上述处理单元是电子设备的控制中心，利用各种接口和线路连接电子设备的各个部分，通过运行或执行存储在存储器内的应用，以及调用存储在存储器内的数据，执行电子设备的各种功能和处理数据。在一些实施例中，处理单元可包括一个或多个处理模块；举例来说，处理单元可以是运行在华为技术有限公司制造的麒麟960芯片或者是处理器上的通信信息处理系统。
上述输入输出单元可以为具有交互功能的人工智能(artificial intelligence，AI)音箱、触摸屏等输入/输出单元，可以基于用户与输入输出单元的交互，采集用户发出的指令，也可以在收到反馈信息后输出对应的反馈信息。以AI音箱为例，AI音箱可以采集用户发出的语音信息，并且可以通过语音的方式输出反馈信息。
上述网络设备可以为具有无线收发功能的设备或可设置于该设备的芯片或芯片系统。该网络设备包括但不限于：无线保真(wireless fidelity，WiFi)系统中的接入点(access point，AP)，如家庭网关、路由器、服务器、交换机、网桥等，无线中继节点、无线回传节点、传输点(transmission and reception point，TRP或者transmission point，TP)等，可以为构成gNB或传输点的网络节点，如基带单元(BBU)，或，分布式单元(distributed unit，DU)、具有基站功能的路边单元(road side unit，RSU)等。
下面结合一个示例，具体说明图1中所示出的反馈系统在内置于车辆的车载系统中的具体实现。
示例性地，图2为本申请实施例提供的反馈系统的架构示意图二。如图2所示，该反馈系统包括电子设备。其中，电子设备可以包括AI音箱和处理单元。
示例性地，图1中所示出的输入输出单元的功能可以由图2所示出的AI音箱实现，图1中所示出的处理单元的功能可以由图2所示出的处理单元实现。AI音箱可以采集用户发出的语音信息，并通过深度学习技术识别用户实际需求，将该语音信息转换为文本信息，以便车载系统中的其他模块使用。上述处理单元可以根据文本信息确定对应的反馈信息。并且，AI音箱还可以通过扬声器输出反馈信息。
其中，AI音箱可以包括语音识别模块和第一驱动模块。处理单元可以包括：数据采集模块、影响因子提取模块、影响因子评估模块、反馈信息生成模块和第二驱动模块。
具体地，上述语音识别模块可以利用MFCC特征提取技术和循环神经网络技术， 将语音信息转换为文本信息。
其中，上述AI音箱的第一驱动模块可以与处理单元的第二驱动模块连接，实现AI音箱和处理单元之间的数据传输，如AI音箱向处理单元发送文本信息，处理单元向AI音箱发送反馈信息。
上述数据采集模块可以用于获取电子设备或其他设备的参考信息，如车辆信息或非车辆信息。
可选地，反馈系统还可以包括与数据采集模块连接的车辆电子控制单元(electronic control unit，ECU)，数据采集模块可以从车辆ECU中，根据发动机、车轮和制动传感器等的相关信息，获取车辆的行驶状态数据，如速度、方向盘转角等。可以说明的是，数据采集模块与车辆ECU可以通过车辆信号线，如总线传输车辆的行驶状态数据。本申请实施例不限定数据采集模块与车辆ECU传输信息的具体实现方式。
可选地，反馈系统还可以包括与数据采集模块通信的服务器，服务器可以根据数据采集模块传递的参考信息，向数据采集模块返回对应的参考信息。相应地，数据采集模块可以通过网卡驱动接收来自服务器的参考信息。
可以理解，本申请实施例中，还可以采用服务器实现处理单元的功能。
上述影响因子提取模块可以使用特征提取和机器学习方法对文本信息分类，还可以使用TF-IDF算法提取文本信息中的关键字。影响因子提取模块还可以基于得到的指令类别和关键字，计算与影响因子库中的参考信息之间的余弦相似度，提取其中余弦相似度超过相似度阈值的参考信息。
上述影响因子评估模块可以根据相似度超过相似度阈值的参考信息，从数据采集模块中获取对应的参考信息，如车辆信息和非车辆信息，以此来评估该用户指令对应的操作是否与实际场景对应，即判断实际场景中用户指令对应的操作是否有必要执行或者能否执行。
上述反馈信息生成模块可以根据影响因子评估模块的评估结果，生成对应的反馈信息，反馈信息可以用于指示：建议执行用户指令或建议不执行用户指令。处理单元可以向AI音箱发送反馈信息，以便AI音箱利用扬声器输出反馈信息。
可选地，上述AI音箱还可以与收发器连接，实现收发功能。AI音箱可以通过收发器向其他设备发送该反馈信息，以便其他设备执行反馈信息对应的操作。上述处理单元还可以通过车辆总线或信号线向车辆ECU发送反馈信息，从而控制车辆ECU执行反馈信息对应的操作。
应当指出的是，本申请实施例中的方案还可以应用于其他反馈系统中，相应的名称也可以用其他反馈系统中对应功能的名称进行替代。
应理解，图1和图2仅为便于理解而示例的简化示意图，该反馈系统中还可以包括其他电子设备，和/或，其他网络设备，图1和图2中未予以画出。
下面将结合图3和图4对本申请实施例提供的反馈方法进行具体阐述。
示例性地，图3为本申请实施例提供的反馈方法的流程示意图一。该反馈方法可以适用于图1和图2中所示出的反馈系统，下面以反馈系统中的电子设备为车辆举例说明。
如图3所示，该反馈方法包括S301-S303。
S301，获取用户指令。
示例性地，用户指令可以为指示需要执行的一种或多种操作的信息。例如，若用户需要打开空调，则用户指令可以是用于指示空调开启的相关信息。用户指令可以包括关键字和指令类别，指令类别可以为该用户指令对应的操作的类别，如操作类指令、出行类指令、查询类指令等。关键字可以是用户指令对应的操作和/或操作对象。
本申请实施例中，可以基于特征提取和分类技术处理文本信息，获取用户指令的关键字和指令类别。例如，用户指示“打开空调”，则指令类别可以为“操作类”，关键字可以包括“打开”和“空调”。又例如，用户指示“导航去洗车店”，则指令类别可以为“出行类”，关键字可以包括“导航”和“洗车店”。
在一些可能的设计方案中，上述用户指令可以为语音指令。也就是说，用户指令可以通过语音的获取。此时，上述步骤S301，获取用户指令可以包括步骤1和步骤2。
步骤1，获取语音信息。
示例性地，可以通过拾音设备，如麦克风(microphone，MIC)、上述图2中所示出的具有拾音功能的AI音箱获取语音信息。
步骤2，根据语音信息获取用户指令。
示例性地，可以将语音信息转换为文本信息。例如，可以利用特征提取技术和神经网络技术，如MFCC特征提取技术和循环神经网络技术，将语音信息转换为文本信息。
然后，根据文本信息获取指令类别和/或关键字，从而得到用户指令。例如，可以利用特征提取技术和机器学习方法处理文本信息，确定对应的指令类别。并且，还可以利用TF-IDF算法从多个关键字中提取最重要的一个或多个关键字，从而确定语音信息对应的关键字，进而根据指令类别和提取的关键字得到用户指令。
如此，用户可以通过语音输入用户指令，避免手动输入指令，从而能够提高行车安全性。
在一些可能的设计方案中，还可以通过触摸屏获取用户指令。
示例性地，可以通过触摸屏采集用户输入的触摸操作信息，利用特征提取技术和神经网络技术，将触摸操作信息转换为文本信息。然后，根据文本信息获取指令类别和/或关键字，从而得到用户指令。
如此，可以获得更准确的用户指令，进一步提高反馈信息的准确性。
需要说明的是，用户指令还可以是根据触摸操作信息确定的，或者，根据按键的操作信息确定的，还可以是从其他设备获取的。本申请实施例不限定获取用户指令的具体实现方式。
S302，获取与用户指令关联的参考信息(也可以简称为关联参考信息)。
示例性地，参考信息可以为影响各种可能操作的信息。参考信息可以包车辆信息和/或非车辆信息。车辆信息可以为影响执行用户指令的，且与车载设备，如车辆发动机、车载空调相关的信息。相应地，上述车辆信息可以包括车辆上设备的信息，和/或车辆外其他设备的信息。例如，电子设备可以为车辆上的处理器，若用户指令中的指令类别为出行类指令，则车辆信息可以为与出行相关的车辆电子控制单元(electronic control unit，ECU)的状态信息。示例性地，车辆信息可以包括如下一项或多项：车辆 冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、油量、空调模式、空调冷凝器状态、空调温度传感器状态、或空调压缩机状态。
需要说明的是，用户指令与用户指令对应的操作所的含义相同。执行用户指令可以通过执行用户指令对应的操作实现。
关联参考信息可以为参考信息中影响执行用户指令的信息。示例性地，关联参考信息可以为影响执行当前用户指令的车辆信息和/或非车辆信息。例如，若用户指令中关键字为“导航去洗车店”，则关联参考信息可以为包括如下一项或多项的车辆信息：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、油量、或车辆传动系统的状态。
其中，车辆冷却系统可以用于散发受热部件吸收的热量，以确保发动机在适宜的温度状态下工作。例如，车辆冷却系统可以包括散热片组件等。又如，车辆冷却系统还可以包括：冷却水套、水泵、风扇、水箱和节温器等。车辆点火系统用于按时在火花塞电极间产生电火花以点燃混合气体。例如，车辆点火系统可以包括：电源(如蓄电池、发电机)、点火开关、点火线圈、附加电阻、分电器等。车辆起动系统用于使发动机由静止状态过渡到工作状态。例如，车辆起动系统可以包括：蓄电池、起动机、起动开关、继电器等。车辆传动系统是用于使汽车产生驱动力的动力系统。例如，车辆传动系统可以包括：变速器、离合器、万向传动装置、主减速器、差速器和半轴等。
若用户指令中的关键字为“打开空调”，则车辆信息可以为空调相关的状态信息。例如，车辆信息还可以包括如下一项或多项：冷凝器状态、温度传感器状态、或空调压缩机状态。
可以理解的是，本申请实施例中，若用户指令的指令类别为出行类指令，则车辆信息还可以包括如下一项或多项：车辆曲柄连杆机构状态、车辆配气机构状态、车辆供给系统状态、车辆润滑系统状态、车辆制动系统状态、车辆传动系统状态、车辆行驶系统状态、或车辆转向系统状态。若用户指令的指令类别为操作类指令，则车辆信息还可以包括如下一项或多项：空调蒸发器状态、或空调膨胀阀状态。其中，车辆信息的每一项，可以包括一个或多个部件的状态。例如，车辆传动系统可以包括离合器和/或变速器等部件的状态。
同理，上述非车辆信息可以为影响执行用户指令的，且与场景(环境)有关的信息，如执行用户指令时的天气、温度、距离、服务价格、湿度、可吸入颗粒物的浓度、促销活动信息等。
一种可能的设计方案中，上述步骤S302，获取关联参考信息，可以包括：步骤3至步骤5。
步骤3，获取参考信息。
可选地，参考信息可以来自云端。例如，对于图1中所示出的电子设备而言，输入输出单元可以包括收发模块，输入输出单元可以通过收发模块，接收来自云端的参考信息。如此，可以实时地更新参考信息，进一步提高反馈信息的准确性。
或者，可选地，参考信息也可以是存储在本地。例如，反馈信息可以存储在车辆的存储器中。
如此，使用参考信息和存储参考信息的为同一个设备，可以更快地得到参考信息， 进而提高效率。此外，在车辆获取与车辆上设备相关的参考信息时，可以避免向车辆外的其他设备发送参考信息，能够降低个人数据泄漏的风险，从而提高参考信息的安全性。
可以理解，本申请实施例中，参考信息还可以存储在可与电子设备通信的其他设备，如云服务器上。
本申请实施例参考信息的类别可以有一种或多种，参考信息的类别可以是利用分类技术，预先处理历史车辆信息和历史非车辆信息得到的。具体地，可以预先获取历史车辆信息和历史非车辆信息，再利用多层次分类的方式处理历史车辆信息和历史非车辆信息，直到分类的叶节点难以细分后，确定历史车辆信息和历史非车辆信息对应的参考信息的类别。参考信息的类别，可以是根据本地处理历史车辆信息和历史非车辆信息得到的，还可以是来自网络设备或其他终端设备的。本申请实施例不限定处理单元获取参考信息的具体实现方式。
示例性地，参考信息的类别可以为与用户指令相关的因素，一个参考信息的类别对应的参考信息为上述车辆信息或非车辆信息，一个参考信息可以与一个或多个车辆信息对应，或与一个或多个非车辆信息对应。具体地，可以根据参考信息的类别获取参考信息，即对应的车辆信息和/或非车辆信息。例如，参考信息的类别为“空调的工作模式”，则可以对应获取“空调的工作模式为制冷模式”的车辆信息。再例如，参考信息的类别为“天气”，则处理单元可以对应获取“天气为雨天”的非车辆信息。
需要说明的是，本申请实施例中，可以采用上述方式先分析用户指令，确定需要获取的参考信息的类别，再对应获取关联参考信息；也可以获取所有的参考信息，再根据用户指令从所有的参考信息中，确定关联参考信息。本申请实施例不限定车辆信息和非车辆信息的具体实现方式。
步骤4，计算用户指令与参考信息之间的关联度。
示例性地，关联度可以是用户指令与参考信息之间的相关性大小，该相关性大小可以根据参考信息对用户指令对应的操作的影响程度确定。例如，用户指令为出行类指令，则车辆启动系统状态对“出行”操作的影响较大，而空调冷凝器状态对“出行”操作的影响较小，因此，车辆启动系统状态与用户指令之间的关联度比空调冷凝器状态与用户指令之间的关联度大。
可选地，上述关联度可以采用用户指令与参考信息之间的相似度表示。例如，关联度可以为余弦相似度、杰卡德相似度、或皮尔森相似度。
示例性地，余弦相似度可以用于表征两个向量之间的相似程度。本申请实施例中，可以将需要比较的用户指令和参考信息都转换为对应的向量，再计算两个向量之间的余弦相似度，即用户指令和参考信息的相似度。例如，cos(θ)＝w·α i/||w|| ||α i||，其中，cos(θ)为余弦相似度，w为关键字，α i为第i个参考信息，||w||为关键字w的范数，||α i||为第i个参考信息的范数。如此，可以基于余弦相似度，准确地确定与用户指令相关的参考信息，进一步提高反馈信息的准确性。
其中，余弦相似度的取值范围可以在[-1,1]之间，此时，余弦相似度的取值越趋近于1，代表用户指令和参考信息的相似度越高，余弦相似度的取值越趋近于-1，代表用户指令和参考信息的相似度越低。需要说明的是，余弦相似度还可以是经过归一化后 的取值。也就是说，余弦相似度的取值范围还可以在[0,1]之间，余弦相似度的取值越趋近于1，代表用户指令和参考信息的相似度越高，余弦相似度的取值越趋近于0，代表用户指令和参考信息的相似度越低。
需要说明的是，还可以利用其他方式获取用户指令与参考信息的相似度，如欧几里得距离(eucledian distance)、杰卡德相似系数(jaccard similarity coefficient)、皮尔森相关系数(pearson correlation coefficient)等相似度计算方式。本申请实施例不限定相似度的具体实现方式。
步骤5，获取关联参考信息。
可选地，关联参考信息可以为所有参考信息中，与用户指令的相似度大于相似度阈值的参考信息。
可以理解的是，本申请实施例中，可以根据用户指令与参考信息的关联度，确定关联参考信息。下面以相似度表示关联度的具体实现方式为例，说明关联参考信息的具体实现方式。示例性地，相似度可以用于表示用户指令与参考信息的相关程度，也就是参考信息对用户指令对应的操作的影响程度，相似度越高，表明用户指令与该参考信息的相关程度越高，反之，相似度越低，表明用户指令与该参考信息的相关程度越低。
例如，对于参考信息1和参考信息2，参考信息1为车辆ECU的工作状态，参考信息2为空调的工作模式，用户指令中包括“打开空调”的关键字，则用户指令与参考信息2的相似度，高于用户信息与参考信息1的相似度，即用户信息与参考信息2的相关程度更高。
可以理解的是，相似度阈值可以为一个，也可以为多个，当相似度阈值为多个时，不同参考信息对应的相似度阈值可以相同，也可以不同。
或者，可选地，上述步骤5，获取关联参考信息，可以包括，获取每个参考信息的优先级，根据优先级和关联度获取关联参考信息。
其中，关联参考信息的优先级高于优先级阈值。
示例性地，参考信息的优先级可以用于表示参考信息的重要程度或者参考信息对用户指令对应的操作的影响程度。参考信息越重要，参考信息的优先级越大，参考信息重要性越低，参考信息的优先级越低。参考信息对用户指令对应的操作的影响越大，参考信息的优先级越大，参考信息对用户指令对应的操作的影响越小，参考信息的优先级越低。优先级可以通过数值表示。优先级高于优先级阈值，可以是优先级比优先级阈值对应的优先级高。例如，数值越大，代表优先级越高，数值越小，代表优先级越低，则优先级高于优先级阈值，可以是优先级的数值大于优先级阈值。或者，数值越小代表优先级越高，数值越低，代表优先级越低，则优先级高于优先级阈值，可以是优先级的数值小于优先级阈值。以下以关联度为相似度举例说明。
例如，参考信息包括参考信息1-参考信息5，且优先级与优先级数值正相关。若参考信息1、参考信息3和参考信息5与用户指令的相似度大于相似度阈值，参考信息1-参考信息5各自对应的优先级数值依次为5至1，优先级阈值为“3”，则与用户指令关联的参考信息包括：参考信息1。
如此，通过关联度比较的方式，可以从多个参考信息中准确地选择出与用户指令 关联的参考信息，从而提高反馈信息的准确性。
S303，根据关联参考信息生成反馈信息。
示例性地，反馈信息可以指示：建议不执行用户指令的信息或故障告警信息，或者，反馈信息可以指示：建议执行用户指令。
上述步骤S303，根据参考信息生成反馈信息可以包括步骤6和步骤7。
步骤6，获取关联参考信息的评估结果。
可选地，可以根据评估函数获得评估结果。评估函数的输入参数包括用户指令和关联参考信息。换言之，可以根据用户指令，以及关联参考信息，获取评估结果。
其中，关联参考信息可以为一个或多个。示例性地，关联参考信息为多个，评估结果也为多个，关联参考信息与评估结果可以一一对应。或者，多个关联参考信息对应一个评估结果。具体地，可以将用户指令和关联参考信息作为评估函数的输入参数，进而获得评估结果。
可选地，申请实施例中，也可以通过评估条件获得评估结果。每个关联参考信息有各自对应的评估条件。例如，关联参考信息包括关联参考信息1和关联参考信息5，关联参考信息1和关联参考信息5依次对应评估条件1至评估条件5，则可以根据关联参考信息1对应的评估条件1，获得关联参考信息1对应的评估结果。类似地，可以获得关联参考信息2至关联参考信息5各自对应的评估结果。
为便于理解，以下结合实例说明评估结果。例如，用户指令包括“打开空调”的关键字，参考信息包括“空调的工作模式”，则可以得到“空调的工作模式在执行打开空调的操作时应当为关闭状态”的评估条件。根据评估条件评估用户指令和关联参考信息，可以得到对应的评估结果。
可以理解，本申请实施例中的评估条件，也可以是上述评估函数。
评估条件可以包括一个或多个条件，在评估条件包括多个条件时，不同的车辆信息和非车辆信息对应的评估条件可以相同，也可以不同。
本申请实施例中，可以将每个关联参考信息各自对应的评估结果，与每个与关联参考信息各自对应的权重的乘积，确定为评估结果。
例如，若关联参考信息包括关联参考信息1至关联参考信息3，关联参考信息1至关联参考信息3各自对应评估结果1-评估结果3，关联参考信息1至参关联参考信息3各自对应的权重分别为权重1至权重3，则评估结果1与权重1的乘积为一个评估结果，评估结果2与权重2的乘积为一个评估结果，评估结果3与权重3的乘积为一个评估结果。
如此，可以根据参考信息的重要性获取评估结果，从而能够提高评估结果的准确性，进一步提高反馈信息的准确性。
需要说明的是，本申请实施例中的评估结果，还可以是任一个参考关联信息的评估结果。评估结果，可以是数值，还可以是参考信息所对应的状态，如正常或异常。
本申请实施例中，上述步骤6，获取与用户指令关联的参考信息的评估结果，可以包括：根据关联参考信息的优先级，获取关联参考信息的评估结果。
示例性地，关联参考信息包括关联参考信息1-关联参考信息5，关联参考信息1-关联参考信息5的优先级数值依次为：5-1。其中，优先级数值与优先级正相关，则 可以按照关联参考信息的优先级从高到低的顺序获取评估结果。
如此，根据优先级获取评估结果，在优先级高的参考信息的评估结果位于某些数值范围内，如第一范围内时，可以避免计算其他参考信息的评估结果，以减少计算量，从而进一步提高反馈效率。
步骤7，基于关联参考信息和评估结果，生成反馈信息。
示例性地，可以基于车辆信息和非车辆信息对用户指令对应的操作的影响，评估用户指令的执行结果是否能够满足用户实际需求，以此判断实际场景中用户指令是否有必要执行或者能否执行，从而确定对应的反馈信息。
例如，假设用户指令对应的操作为“打开空调”，若场景中“室外温度和室内温度均为20℃”，则即使执行打开空调的操作，也难以满足通过空调让周围更凉爽的用户实际需求，且还会浪费大量的电力资源，由此可以得到指示“用户指令对应的操作可以不用执行”的评估结果，则可以确定反馈信息可以为“温度适宜，无需打开空调”，也就是说，反馈信息指示：不用执行用户指令。
可以理解的是，本申请实施例中，空调也可以按照设定的温度运行。例如，在一种可能的场景中，“室外温度和室内温度均为20℃”，空调反馈信息为“温度适宜，无需打开空调”，若设置的室内温度为16℃，则仍然可以打开空调并控制空调在制冷模式运行。若存在车辆信息中为“空调中的冷凝管发生故障”，则实际场景中车辆信息对用户指令对应的操作影响较大，容易导致用户指令对应的操作无法执行，可以得到指示“用户指令对应的操作无法执行”的评估结果，则可以确定反馈信息可以为“空调故障，无法打开”，也就是说，反馈信息指示：不用执行用户指令。
以下结合评估结果以数值表示具体说明上述步骤7。
可选地，若关联参考信息为一个，则上述步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若评估结果满足第一条件，则根据关联参考信息生成第一反馈信息。
其中，第一反馈信息用于指示：建议不执行用户指令或故障告警。
示例性地，第一条件可以是：评估结果的值小于0。可以理解，第一条件还可以是关联参考信息的评估结果位于其他数值范围内。
需要说明的是，若关联参考信息为一个，生成的反馈信息也可以指示：建议执行用户指令。例如，评估结果的值大于0，则生成的反馈信息可以指示：建议执行用户指令。
如此，在参考信息满足第一条件时，可以认为执行用户指令难以满足用户实际需求，进而生成指示建议不执行用户指令或故障告警的第一反馈信息，提高反馈信息的准确性，且可以节省时间和成本。
或者，可选地，若关联参考信息有多个，则上述步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若评估结果满足第二条件，则根据关联参考信息生成第二反馈信息。
其中，第二反馈信息用于指示：建议不执行用户指令或故障告警。第二条件包括：存在评估结果的值在第一范围内，或所有评估结果的加权求和结果的值在第二范围内。
示例性地，若第一范围为小于0的范围，则存在评估结果的值小于0，生成第二 反馈信息。
需要说明的是，本申请实施例中，第一反馈信息和第二反馈信息的内容可以相同，也可以不同。
如此，在参考信息满足第二条件时，可以认为执行用户指令难以满足用户实际需求，进而生成用于指示建议不执行用户指令或故障告警的第二反馈信息，提高反馈信息的准确性，且可以节省时间和成本。
进一步地，基于关联参考信息和评估结果，生成反馈信息，可以包括：根据目标参考信息生成第二反馈信息。
其中，目标参考信息为：满足第三条件的评估结果对应的关联参考信息。
示例性地，满足第三条件的评估结果可以为：值位于第二范围内的评估结果。
示例性地，可以根据值最小的评估结果对应的关联参考信息，生成第二反馈信息。
以第二范围为小于0的范围为例，若关联参考信息包括关联参考信息1-关联参考信息5。关联参考信息2的评估结果最小，且小于0，则目标参考信息为关联参考信息2，第二反馈信息与关联参考信息2对应。
如此，在参考信息满足第二条件时，可以认为执行用户指令难以满足用户实际需求，进而生成指示：建议不执行用户指令的第二反馈信息，提高反馈信息的准确性，且可以节省时间和成本。
或者，可选地，上述步骤7，基于参考信息和评估结果，生成反馈信息，可以包括：若评估结果满足第四条件，则根据值最大的评估结果对应的关联参考信息，生成第三反馈信息。
其中，第四条件包括：每个评估结果的值均位于第三范围内。
示例性地，第三反馈信息用于指示：建议执行用户指令。以第一范围为大于0的范围为例，若关联参考信息包括关联参考信息1-关联参考信息5。关联参考信息1-关联参考信息5各自对应的评估结果的值都大于0，且关联参考信息3对应的评估结果最大，则根据关联参考信息3对应的评估结果生成第三反馈信息。
如此，在上述第四条件被满足时，可以认为执行用户指令能够满足用户实际需求，从而生成建议执行用户指令的第三反馈信息。例如，洗车的应用场景中，若天气适合洗车，则给出建议执行用户指令的第三反馈信息，从而能够避免洗车后又被弄脏的问题，进而节省时间和成本。
若第五条件被满足，则可以不生成反馈信息。其中，第五条件可以是：每个评估结果的值均位于第四范围内。或者，第五条件可以是：每个评估结果的值均为同一个。例如，第五条件为：每个评估结果的值均为0。需要说明的是，第五条件被满足时，还可以生成建议执行用户指令的反馈信息，如第三反馈信息。
本申请实施例中，第一条件至第五评估条件各不相同。
本申请实施例中，一个评估结果的值可以指示关联参考信息对应的反馈类型，关联参考信息对应的反馈类型可以包括：无反馈信息、指示建议执行用户指令的反馈信息(如第三反馈信息)、指示建议不执行用户指令或故障告警的反馈信息(如第一反馈信息和第二反馈信息)。此时，生成的反馈信息与所有关联参考信息对应。以下举例详细说明。
例如，评估结果为0指示：无反馈信息；评估结果大于0指示：建议执行用户指令；评估结果小于0指示：建议不执行用户指令或故障告警。需要说明的是评估结果还可以是其他数值，本申请实施例中对评估结果的数值不作具体限定。
若每个关联参考信息对应的评估结果均指示：建议执行用户指令，则生成第三反馈信息。若存在关联参考信息对应的评估结果指示：建议不执行用户指令或故障告警，则生成第一反馈信息或第二反馈信息。若所有关联参考信息的评估结果均指示无反馈信息，则可以不生成反馈信息。
可以理解的是，以上例子仅用于举例，并不具体限定生成反馈信息的方式。例如，在一些可能的实施方式中，若存在关联参考信息对应的评估结果指示：建议执行用户指令和存在的评估结果指示无反馈信息，则也可以生成第三反馈信息。
示例性地，本申请实施例中，还可以根据各个关联参考信息的优先级确定反馈信息。其中，关联参考信息的优先级用于指示关联参考信息的重要程度。如，优先级可以用数值表示。例如，用户指令对应的关联参考信息包括：关联参考信息1-关联参考信息3，关联参考信息1-关联参考信息3对应的评估结果依次指示：建议执行用户指令、建议不执行用户指令或故障告警、建议执行用户指令，关联参考信息1-关联参考信息3依次对应的优先级数值5、7、3，优先级与优先级数值正相关，则根据关联参考信息2对应的评估结果生成反馈信息，如第二反馈信息。
下面以不同的车辆信息和非车辆信息对应的评估条件不同为例，详细说明评估结果包括参考信息对应的状态时步骤7，基于关联参考信息和评估结果，生成反馈信息的具体实现方式。
以下结合方式一-方式六详细说明。
方式一，根据车辆信息和评估结果生成第二反馈信息。车辆信息包括如下一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、空调冷凝器状态、空调温度传感器状态、或空调压缩机状态。评估条件可以包括第二条件。相应地，上述步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若第二条件被满足，则根据关联参考信息生成第二反馈信息。
其中，第二反馈信息可以用于指示：建议不执行用户指令或故障告警，第二条件可以包括如下一种或多种条件：
条件1，车辆冷却系统为异常工作状态。或者，
条件2，车辆点火系统为异常工作状态。或者，
条件3，车辆起动系统为异常工作状态。或者，
条件4，车辆传动系统为异常工作状态。或者，
条件5，空调冷凝器为异常工作状态。或者，
条件6，空调温度传感器为异常工作状态。或者，
条件7，空调压缩机为异常工作状态。
示例性地，异常工作状态可以为结构部件或组件存在故障的状态。其中，条件1，车辆冷却系统为异常工作状态，可以是车辆冷却系统的组件存在故障。例如，水箱存在故障。条件2，车辆点火系统为异常工作状态。可以是车辆点火系统的组件存在故障。例如，点火线圈存在故障。条件3，车辆起动系统为异常工作状态，可以是车辆起 动系统的组件存在故障。例如，起动开关存在故障。条件4，车辆传动系统为异常工作状态，可以是车辆传动系统的组件存在故障。例如，变速器存在故障，或者离合器存在故障。条件5，空调冷凝器为异常工作状态，可以是冷凝器的组件存在故障。条件6，空调温度传感器为异常工作状态，可以是温度传感器或者温度传感器相关的组件存在故障。条件7，空调压缩机为异常工作状态，可以是空调压缩机存在故障。
示例性地，第二条件可以为关联参考信息，在用户指令可以执行或者有必要执行时满足的条件。第二条件被满足，可以是第二条件所包括的每个条件均被满足。例如，第二条件包括条件1，若确定车辆冷却系统为异常工作状态，则第二条件被满足。又如，第二条件包括条件1和条件2，若确定车辆冷却系统为异常工作状态、且车辆点火系统为异常工作状态，则第二条件被满足。第二条件中的每一个条件，可以对应一个评估结果。评估结果可以用于指示：建议不执行用户指令或故障告警。
可以理解的是，第二反馈信息可以对应一个或多个关联参考信息。其中，不同的关联参考信息对应的操作可以相同，也可以不同。以下以关联参考信息包括车辆信息为例说明。例如，车辆信息为多个，若所有的车辆信息均满足第二条件时，则可以根据所有车辆信息的评估结果生成一个对应的第二反馈信息。又如，车辆信息为多个时，第二反馈信息根据多个车辆信息中的一个的评估结果获得。也就是说，第二反馈信息与一个车辆信息对应。
方式二，根据非车辆信息和评估结果生成第二反馈信息。评估条件可以包括第二条件，非车辆信息可以包括如下一种或多种：天气、温度、操作对应的业服务价格、湿度、或可吸入颗粒物的浓度。上述步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若第二条件被满足，则根据参考信息生成第二反馈信息。其中，第二反馈信息用于指示：建议不执行用户指令或故障告警；第二条件可以包括如下一种或多种条件：
条件8，天气属于第一天气集合。或者，
条件9，温度在第一温度区间内。或者，
条件10，服务价格位于第一价格区间内。或者，
条件11，湿度在第一湿度区间内。或者，
条件12，可吸入颗粒物的浓度在第一浓度区间内。
示例性地，第一天气集合可以为不需要执行或无法执行用户指令的场景对应的天气的集合。第一温度区间可以为不需要执行或无法执行用户指令的场景对应的温度区间。第一价格区间为不需要执行或无法执行用户指令的场景对应的服务价格区间。
例如，当非车辆信息包括天气时，若天气属于第一天气集合，则可以确定在该天气对应的场景下，可以不用执行或者难以执行用户指令，“天气”对应的第二反馈信息。
又如，当非车辆信息包括温度时，若温度在第一温度区间内，则可以确定在该温度对应的场景下，可以不用执行或者难以执行用户指令，“温度”对应第二反馈信息。
再如，当非车辆信息包括服务价格时，若服务价格在第一价格区间内，则可以确定在该服务价格对应的场景下，可以不用执行或者难以执行用户指令，“服务价格”对应第二反馈信息。方式二中第二反馈信息的实现，可以参考方式一中第二反馈信息 的实现方式，此处不再赘述。
方式三，根据车辆信息和非车辆信息生成第二反馈信息。示例性地，车辆信息可以包括如下一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、空调冷凝器状态、空调温度传感器状态、空调压缩机状态，非车辆信息也可以包括如下一项或多项：天气、温度、操作对应的服务价格、湿度、或可吸入颗粒物的浓度，第二条件可以既包括车辆信息对应的条件，又包括非车辆信息对应的条件。例如，第二条件包括条件1至条件7中的一项或多项，同时还包括条件8至条件12中的一项或多项。
以下结合“导航去洗车店”的具体应用场景详细说明。
“导航去洗车店”这一应用场景下，评估条件可以包括第二条件，车辆信息可以包括如下一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、或车辆传动系统状态。非车辆信息可以包括如下一项或多项：天气、温度、或操作对应的服务价格。步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若第二条件被满足，则根据关联参考信息生成第二反馈信息。第二条件可以包括如下一种或多种条件：
条件13，车辆冷却系统为异常工作状态。或者，
条件14，车辆点火系统为异常工作状态。或者，
条件15，车辆起动系统为异常工作状态。或者，
条件16，车辆传动系统为异常工作状态。或者，
条件17，天气属于第一天气集合。或者，
条件18，温度在第一温度区间内。或者，
条件19，服务价格位于第一价格区间内。
需要说明的是，条件13至条件19的具体实现方式，可以依次对应参考条件1至条件4和条件8至条件10的实现方式，在此不再赘述。
如此，在上述第二条件被满足时，可以认为实际场景中执行用户指令难以满足用户实际需求，从而给出建议不执行用户指令的第二反馈信息。例如，洗车的应用场景中，若天气不适合洗车，则给出建议不执行用户指令的第二反馈信息，从而能够避免洗车后又被弄脏的问题，进而节省时间和成本。
方式三中第二反馈信息的实现，可以参考方式一或方式二中第二反馈信息的实现方式，此处不再赘述。
需瑶说明的是，上述第二条件所包括的具体条件，仅用于举例，在实际实施中，还可以包括其他条件。例如，第二条件还包括：油量在第一油量阈值內，和/或，空调模式为异常工作模式，和/或，距离在第一距离阈值內，和/或，存在促销活动。
如此，方式一至方式三中任一方式，可在参考信息满足第二条件时，确定执行用户指令难以满足用户实际需求，进而生成用于指示建议不执行或故障告警的第二反馈信息，提高反馈信息的准确性。
方式四，根据车辆信息和评估结果生成第三反馈信息。评估条件可以包括第四条件，车辆信息可以包括如下一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、空调冷凝器状态、空调温度传感器状态、空调 压缩机状态。相应地，上述步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若第四条件被满足，则生成第三反馈信息。
其中，第三反馈信息可以用于指示：建议执行用户指令。第四条件可以包括如下一种或多种条件：
条件20，车辆冷却系统为正常工作状态。或者，
条件21，车辆点火系统为正常工作状态。或者，
条件22，车辆起动系统为正常工作状态。或者，
条件23，车辆传动系统为正常工作状态。或者，
条件24，空调冷凝器为正常工作状态。或者，
条件25，空调温度传感器为正常工作状态。或者，
条件26，空调压缩机为正常工作状态。
示例性地，正常工作状态可以为结构器件或组件无故障的状态。例如，条件20，车辆冷却系统为正常工作状态，可以是车辆冷却系统的组件无故障。条件21，车辆点火系统为正常工作状态，可以是车辆点火系统的组件无故障。条件22，车辆起动系统为正常工作状态，可以是车辆起动系统的组件无故障。条件23，车辆传动系统为正常工作状态，可以是车辆传动系统的组件无故障。条件24，空调冷凝器为正常工作状态，可以是空调冷凝器的组件无故障。条件25，空调温度传感器为正常工作状态，可以是空调温度传感器的组件无故障。条件26，空调压缩机为正常工作状态，可是空调压缩机为正常工作状态。需要说明的是，一个组件的工作状态(车辆信息的任一项)可以根据该组件所包含的一个或多个部件的工作状态确定。
示例性地，第四条件可以为关联参考信息在用户指令可以执行或者有必要执行时满足的条件。第四条件被满足，可以是第四条件所包括的每个条件均被满足。例如，第四条件包括条件20，若确定车辆冷却系统为正常工作状态，则第四条件被满足。又如，第四条件包括条件20和条件21，若确定车辆冷却系统为正常工作状态、且车辆点火系统为正常工作状态，则第四条件被满足。
需要说明的是，与用户指令对应的第三反馈信息可以与一个或多个关联参考信息对应。以下以关联参考信息包括车辆信息为例说明。例如，车辆信息有多个，则第三反馈信息可以根据多个车辆信息中，每个车辆信息的评估结果获得。也就是说，第三反馈信息与多个车辆信息对应。示例性地，所有车辆信息均满足第四条件时，可以生成一个对应的第三反馈信息。例如，与用户指令A对应的车辆信息包括车辆冷却系统状态、车辆起动系统状态，若车辆冷却系统状态、车辆起动系统状态对应满足上述条件20和条件22，则可以根据车辆冷却系统状态、车辆起动系统状态确定与用户指令A对应的第三反馈信息。又如，车辆信息有多个，则第三反馈信息可以根据多个车辆信息中一个车辆信息的评估结果获得。也就是说，第三反馈信息与一个车辆信息对应。
可选地，可以根据关联参考信息的优先级生成第三反馈信息。示例性地，参考信息的优先级越高，表示关联参考信息与用户指令的相关程度越高，反之优先级越低，表示关联参考信息与用户指令的相关程度越低。例如用户指令为“打开空调制热”，关联参考信息1对应评估结果X，关联参考信息2对应评估结果Y，评估结果X指示“冷凝器工作状态正常，可以打开”，评估结果Y指示“温度偏低，可以打开空调”， 若关联参考信息1对应的优先级高于关联参考信息2的优先级，则表明关联参考信息1与“打开空调”的相关程度，比关联参考信息2与“打开空调”的相关程度更高，则第三反馈信息为“冷凝器工作状态正常，可以打开空调”。
具体地，可以先获取优先级最高的关联参考信息，然后根据优先级最高的关联参考信息生成评估结果，然后根据该评估结果获取第三反馈信息。可以理解的是，本申请实施例中，还可以先生成每个关联参考信息各自对应的评估结果，然后根据优先级最高的关联参考信息对应的评估结果获取第三反馈信息。
类似地，第三反馈信息可以与一个关联参考信息对应，也可以与多个关联参考信息对应。以下以关联参考信息为包括车辆信息为例说明。例如，车辆信息为多个时，在每个车辆信息满足第四条件中对应的条件时，可以生成每个车辆信息各自对应的评估结果，第三反馈信息可以与多个车辆信息对应。例如，若车辆起动系统状态满足上述条件22，则可以获得对应的评估结果1，车辆传动系统状态满足上述条件23，则可以获得对应的评估结果2，第三反馈信息可以根据评估结果1和评估结果2获得。需要说明的是，不同的评估结果对应的操作可以相同，也可以不同。
方式五，根据非车辆信息和评估结果生成第三反馈信息，评估条件可以包括第四条件，非车辆信息可以包括如下一种或多种：天气、温度、操作对应的服务价格、湿度、或可吸入颗粒物的浓度。
上述步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若第一条件被满足，则生成第三反馈信息。第三反馈信息用于指示：建议执行用户指令。其中，第四条件包括如下一种或多种条件：
条件27，天气属于第二天气集合。
条件28，温度在第二温度区间内。或者，
条件29，服务价格在第二价格区间内。或者，
条件30，湿度在第二湿度区间内。或者，
条件31，可吸入颗粒物的浓度在第二浓度区间内。
以下条件27和条件28分别进行说明。
示例性地，第二天气集合可以为可以执行或者有必要执行用户指令的场景对应的天气的集合。第二温度区间可以为可以执行或者有必要执行用户指令的场景对应的温度区间。第二服务区间可以为可以执行或者有必要执行用户指令时，可能需要花费的价格。第二湿度区间可以为可以执行或者有必要执行用户指令的场景对应的湿度的集合。第二浓度区间可以为可以执行或者有必要执行用户指令的场景对应的可吸入颗粒物的浓度的集合。例如，用户指令为“导航去洗车店”，相应的服务价格可以为一次洗车花费的价格。
例如，当非车辆信息包括天气时，若天气属于第二天气集合，则在该天气对应的场景下，可以执行或者有必要执行用户指令，“天气”对应建议执行用户指令的评估结果。又如，当非车辆信息包括温度时，若温度在第二温度区间内，则在该温度对应的场景下，可以执行或者有必要执行用户指令，“温度”对应建议执行用户指令的评估结果。再如，当非车辆信息包括服务价格时，若服务价格在第二价格区间内，则在该服务价格对应的场景下，可以执行或者有必要执行用户指令，“服务价格”对应建 议执行用户指令的评估结果。
方式五中第三反馈信息的实现，可以对应参考方式四中第三反馈信息的实现方式，此处不再赘述。
方式六：结合车辆信息和非车辆信息生成第三反馈信息。例如，车辆信息可以包括如下一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、空调冷凝器状态、空调温度传感器状态、空调压缩机状态，非车辆信息也可以包括如下一项或多项：天气、温度、操作对应的服务价格、湿度、或可吸入颗粒物的浓度，第四条件可以既包括车辆信息对应的条件，又包括非车辆信息对应的条件。例如，第四条件包括条件20至条件26中的一项或多项，同时还包括条件27至条件31中的一项或多项。
以下结合“导航去洗车店”的应用场景具体说明。
“导航去洗车店”这一应用场景下，评估条件可以包括第四条件，车辆信息可以包括如下一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、或车辆传动系统状态。非车辆信息可以包括如下一项或多项：天气、温度、或服务价格。上述步骤7，基于关联参考信息和评估结果，生成反馈信息，可以包括：若第四条件被满足，则根据关联参考信息生成第三反馈信息。
其中，第三反馈信息用于指示：建议执行用户指令。第四条件包括如下一种或多种条件：
条件32，车辆冷却系统为正常工作状态。或者，
条件33，车辆点火系统为正常工作状态。或者，
条件34，车辆起动系统为正常工作状态。或者，
条件35，车辆传动系统为正常工作状态。或者，
条件36，天气属于第二天气集合。或者，
条件37，温度在第二温度区间内。或者，
条件38，服务价格位于第二价格区间内。
本申请实施例中，条件32至条件38的实现方式，可以对应参考条件20至条件23和条件27-条件29的实现方式，在此不再赘述。方式六中第三反馈信息的实现，可以参考方式四和方式五中第三反馈信息的实现方式，此处不再赘述。
可以理解的是，不同的评估结果对应的操作可以相同，也可以不同。例如，评估结果3为“设备正常工作，可以打开空调”，对应的操作可以是打开空调。评估结果4为“车内温度低于15度，可以打开空调的暖风模式”，对应的操作可以是调整空调的工作模式为暖风模式。评估结果5为“今天为晴天，可以打开空调”，对应的操作可以是打开空调。评估结果3和评估结果4对应的操作不同，评估结果3和评估结果5对应的操作相同。
如此，方式四至方式六中，在参考信息满足第四条件时，可以认为执行用户指令能够满足用户实际需求，进而生成指示执行的第三反馈信息，提高反馈信息的准确性。
还可以说明的是，本申请实施例中，可以只利用第二条件生成第二反馈信息，也可以只利用第四条件生成第三反馈信息，还可以结合第二条件和第四条件，生成与用户指令对应的反馈信息。
例如，若结合上述条件10和条件29生成反馈信息，则当非车辆信息包括服务价格时，若服务价格在第二价格区间内，则条件10对应的评估结果指示：建议不执行用户指令。相应地，若服务价格在第二价格区间内，则条件29对应的评估结果指示：建议执行用户指令。其中，第一价格区间和第二价格区间的交集为空，即第一价格区间和第二价格区间互斥。本申请实施例不限定评估条件的具体实现方式。
可以理解的是，不同条件对应的评估结果可以不同，也可以为相同。在不同条件对应的评估结果不同时，可以从多个评估结果中，选择一个评估结果用于生成反馈信息。
需要说明的是，上述第四条件所包括的具体条件，仅用于举例，在实际实施中，还可以包括其他条件。例如，第四条件还包括：油量在第二油量阈值內，和/或，空调模式为正常工作模式，和/或，距离在第二距离阈值內，和/或，不存在促销活动。
其中，第五条件与第二条件和第四条件不同。
在一种可能的设计方案中，若第五条件被满足，则可以不生成反馈信息。以下结合具体场景举例说明。
例如，当第五条件包括：温度在第三温度区间时，若用户指令为“打开空调”，第一温度区间为低于23℃的范围，第二温度区间为超过27℃的范围，第三温度区间为23℃至27℃(包括23℃和27℃)的范围，若温度在23℃至27℃，则可以确定温度比较合适，不用打开空调，不生成反馈信息。
又如，若用户指令为“导航去洗车店”，第二价格区间为价格A以下，说明洗车价格较便宜，第一价格区间为价格B以上，说明洗车价格偏贵，第三价格区间为价格A-价格B，其中，A<B。若服务价格，如洗车价格在价格A-价格B之间，则可以确定洗车价格正常，不生成反馈信息。
可以理解，若第五条件被满足，还可以生成第二反馈信息。
本申请实施例中，车辆信息还可以包括执行用户指令的设备，如车辆上其他部件或组件的状态。关于车辆信息的内容，可以根据具体场景确定，本申请实施例对此不作具体限定。若车辆信息还包括其他信息，则第二条件或第四条件还可以包括与其他信息对应的条件。例如，若车辆信息还包括如下一项或多项：车辆曲柄连杆机构状态、车辆配气机构状态、车辆供给系统状态、车辆润滑系统状态、车辆制动系统状态、车辆传动系统状态、车辆行驶系统状态、车辆转向系统状态、冷凝器状态、温度传感器状态、或空调压缩机状态、空调蒸发器状态、或空调膨胀阀状态，则第四条件还可以包括这些车辆信息中的一项或多项为正常工作状态，第二条件还可以包括这些车辆信息中的一项或多项为异常工作状态。此外，非车辆信息并不限于本申请实施例中所列举的类型。非车辆信息的类型，可以根据实际的应用场景确定，本申请实施例对此不作具体限定。上述第二条件和第四条件，可以根据车辆信息或非车辆信息确定。
如此，可以结合各个与用户指令关联的参考信息，生成反馈信息，从而进一步提高反馈信息的准确性。
一种可能的设计方案中，图3所示的反馈方法还可以包括：输出反馈信息。
示例性地，输出反馈信息可以包括：通过语音或图像的方式，输出反馈信息。
可以理解，本申请实施例中，输出反馈信息，也可以是向其他设备发送反馈信息。
如此，用户可以根据反馈信息确定下一步操作，从而进一步提升用户体验。
一种可能的设计方案中，还可以根据生成的反馈信息，控制对应的车辆上的设备执行用户指令。
下面以电子设备包括处理单元和输入输出单元为例，结合方案1-方案3举例说明生成反馈信息后的操作。
方案1，当电子设备执行用户指令时，处理单元可以根据反馈信息控制电子设备执行用户指令对应的操作。举例来说，假设电子设备为车辆中的自动驾驶ECU，处理单元为自动驾驶ECU中的处理单元，反馈信息为“天气适宜，建议导航去洗车店”，则自动驾驶ECU中的处理单元可以根据该反馈信息控制汽车按照洗车店的导航路径行驶。
方案2，输入输出单元可以输出该反馈信息，以便用户在得到该反馈信息后，可以根据该反馈信息控制对应的设备执行用户指令对应的操作。举例来说，假设电子设备为用户携带的手机，反馈信息为“今天为雨天，不建议导航去洗车店”，则手机的处理单元可以通过输入输出单元，例如触摸屏、扬声器等，输出该反馈信息。用户则可以根据该反馈信息，不在下雨天驾驶车辆去洗车店。
可以理解的是，当电子设备用于执行用户指令时，处理单元可以根据反馈信息控制电子设备执行对应的操作，并且也可以通过输入输出单元输出反馈信息，使用户得到该反馈信息。
并且，在方案2中，若反馈信息为第三反馈信息，说明反馈信息对应的操作与实际场景对应，则电子设备也可以执行该用户指令，而可以不通过输入输出单元输出反馈信息。
方案3，当执行设备为其他设备时，处理单元可以向输入输出单元发送反馈信息，再由输入输出单元向该终端设备发送反馈信息，以便该终端设备根据该反馈信息执行对应的操作。例如，假设执行设备为空调，电子设备为车载显示器，反馈信息为“室内温度较高，建议打开空调”，则电子设备可以通过输入输出单元向空调发送该反馈信息，以便空调根据该反馈信息开启制冷模式。本申请实施例不限定处理单元输出反馈信息的具体实现方式。
需要说明的是，本申请实施例中，若所有关联参考信息对应的反馈指示信息均为0，说明关联参考信息与用户实际需求无关，此时，可以不输出反馈信息。
可以理解的是，本申请实施例中，步骤S301可以由输入输出单元实现。步骤S301还可以由输入输出单元和处理单元共同实现。例如，上述步骤1可以由输入输出单元实现，上述步骤2可以由处理单元实现。步骤S302-步骤S303，可以由处理单元实现。其中，处理单元的功能还可以由服务器或者其他具有计算功能的设备或器件实现，本申请实施例对此不作具体限定。
需要说明的是，本申请实施例中，若电子设备为车辆之外的其他设备，则车辆信息也可以为其他设备的设备信息，非车辆信息也可以是与其他设备相关的环境信息。
基于图3所示出的反馈方法，可以结合参考信息分析用户指令，获取用于指示：建议执行的反馈信息，或者用于指示：建议不执行用户指令或故障告警的反馈信息。如此，可以结合实际场景获得与用户指令对应的操作建议，进而可以根据反馈信息执 行对应的操作。一方面，在用户指令对应的操作与实际场景不对应时，可以及时地停止执行用户指令对应的操作，节省用户的时间和资源。另一方面，在用户指令对应的操作与实际场景对应时，可以继续执行用户指令对应的操作。由此，可以解决根据用户指令执行对应的操作所导致的不能满足用户实际需求的问题，能够提高反馈信息的准确性，提升用户体验。
下面以图2中所示出的电子设备为例，详细说明本申请实施例提供的反馈方法在车载模块中的具体实现。
示例性地，图4为本申请实施例提供的反馈方法的流程示意图二。该反馈方法可以适用于图2中所示出的车载系统中，具体实现图3中所示出的反馈方法。
其中，图1中所示出的输入输出单元可以为图2中所示出的AI音箱，图1中所示出的处理单元可以为图2中所示出的处理单元。
如图4所示，该反馈方法可以包括下述S401-S409：
S401，AI音箱采集用户输入的语音信息。
示例性地，AI音箱可以通过内置的麦克风采集用户输入的语音信息。
例如，场景1中，用户发出“打开空调”的语音信息，则AI音箱可以通过内置的麦克风，采集“打开空调”的语音信息。场景2中，用户发出“导航去洗车店”的语音信息，则AI音箱可以通过内置的麦克风，采集“导航去洗车店”的语音信息。
S402，AI音箱将语音信息转换为文本信息。
在上述场景1中，文本信息可以为“打开空调”的文本。在上述场景2中，文本信息可以为“导航去洗车店”的文本。
具体地，AI音箱可以基于MFCC特征提取和循环神经网络技术，将语音信息转换为文本，得到文本信息。
S403，AI音箱向处理单元发送文本信息。相应地，处理单元可以接收来自AI音箱的文本信息。
具体地，AI音箱可以通过第一驱动模块，向处理单元的第二驱动模块发送文本信息。第一驱动模块和第二驱动模块可以为通用异步收发传输器(universal asynchronous receiver/transmitter，UART)驱动接口。
S404，处理单元根据文本信息，确定对应的用户指令。
图5为本申请实施例提供的反馈方法的数据流向示意图一。如图5所示，在上述场景1中，用户指令可以包括操作类指令的指令类别“操作类”以及“打开”和“空调”的关键字。图6为本申请实施例提供的反馈方法的数据流向示意图二。如图6所示，在上述场景2中，用户指令可以包括出行类指令的指令类别“出行类”以及“导航”和“洗车店”的关键字。
具体地，处理单元利用特征提取和机器学习方法，对文本信息进行分类，确定语音信息对应的指令类别为操作类指令。处理单元还可以利用TF-IDF算法提取文本信息中的关键字。
S405，处理单元根据用户指令分别与多个参考信息的余弦相似度，选择关联参考信息。
其中，关联参考信息为余弦相似度大于相似度阈值的参考信息。处理单元选择关 联参考信息的具体实现方式，可以参考上述S302中的相关内容，此处不再赘述。
仍然参考图5所示，在上述场景1中，关联参考信息可以包括空调状态、空调工作模式等车辆信息，关联参考信息还可以包括天气、温度、湿度和PM2.5的浓度等非车辆信息。
仍然参考图6所示，在上述场景2中。关联参考信息可以包括与出行相关的车辆信息，如驾驶系统的ECU状态或油量。驾驶系统的ECU状态可以包括如下一种或多种：发动机相关的ECU状态、冷却系统ECU状态、车辆点火系统ECU状态、车辆起动系统ECU状态、车辆传动系统ECU状态等车辆信息，关联参考信息还可以包括天气、价格和距离等非车辆信息。
可选地，相似度阈值可以为0.5。
在上述场景1中，车辆信息可以包括当前时刻下冷凝器、温度传感器和空调压缩机的状态，还可以包括空调的当前工作模式以及支持的工作模式等车辆信息。非车辆信息可以包括车内温度、车外温度、湿度和细颗粒物(particulate matter，PM2.5)等非车辆信息。
在上述场景2中，车辆信息可以包括当前时刻下驾驶系统的发动机ECU状态、冷却系统ECU状态、点火系统ECU状态、起动系统ECU状态和传动系统的状态等车辆信息。例如，图6所示的车辆信息可以包括发动机的状态、变速器的状态和离合器的状态。非车辆信息可以包括未来24小时的本地天气、目标洗车店的打折优惠情况(服务价格)、当前位置与洗车店的距离等非车辆信息。
S406，处理单元根据用户指令和参考信息获取评估结果。
具体地，处理单元可以根据用户指令和关联参考信息，确定对应的评估条件。进而根据评估条件获取评估结果。
关于评估结果的实现，可以参见上述步骤S303，在此不再赘述。
S407，根据评估结果生成反馈信息。
示例性地，根据评估结果、车辆信息和非车辆信息，确定反馈信息。其中，反馈信息可以指示：建议不执行用户指令或故障告警的反馈信息，如第一反馈信息或第二反馈信息。反馈信息还可以指示：建议执行用户指令的反馈信息，如第三反馈信息。
继续参考图5所示，在上述场景1中，评估条件、评估结果与反馈信息的对应关系如下所示：
评估条件1，用于根据冷凝器、温度传感器和空调压缩机的状态生成反馈信息。若冷凝器、温度传感器和空调压缩机的状态为异常工作状态，空调状态为异常工作状态，则确定“设备运行异常，建议维修后打开空调”的第二反馈信息。可以理解的是，若冷凝器、温度传感器和空调压缩机的状态为正常工作状态，确定“设备运行正常，建议打开空调”的第三反馈信息。
评估条件2，用于根据非车辆信息生成空调模式对应的反馈信息。若车内外温度均低于15摄氏度，则确定“温度较低，建议调整空调的工作模式为暖风模式”的第三反馈信息。若车内外温度都高于32摄氏度，则确定“温度较高，建议调整空调的工作模式为制冷模式”的第三反馈信息。若PM2.5的浓度达到污染阈值，则确定“空气污染较严重，建议调整空调的工作模式为通风模式”。
评估条件3，生成温度对应的反馈信息。若车内外温度均为20摄氏度，则确定“温度适宜，不建议打开空调”的第二反馈信息。若车外温度达到32摄氏度，则确定“车外温度较高，建议调整空调的温度为25摄氏度”的第三反馈信息。若车内温度与空调温度的默认设置均为25摄氏度，则可以确定“车内温度与空调温度均为25摄氏度，可以打开空调”的第三反馈信息。
在上述场景2中，评估条件与反馈信息的对应关系如下所示：
评估条件4，用于根据驾驶系统的状态生成反馈信息。若驾驶系统的状态，如发动机ECU状态、冷却系统ECU状态、点火系统ECU状态、起动系统ECU状态、或传动系统ECU状态中存在异常工作状态，或者油量为异常状态，则确定“设备运行异常，建议维修后再导航”的第二反馈信息。继续参考图6所示，若发动机ECU状态、传动系统的变速器ECU状态、传动系统的离合器ECU状态中存在异常工作状态，则确定“设备运行异常，建议维修后再导航”的第二反馈信息。反之，若发动机ECU状态、冷却系统ECU状态、点火系统ECU状态和起动系统ECU状态均为正常工作状态，确定“设备运行正常，建议导航去洗车”的第三反馈信息。
评估条件5，用于根据天气生成反馈信息。若未来24小时的本地天气适宜，则可以确定“天气适宜，适合导航去洗车店”的第三反馈信息。若未来24小时内有暴雨，则可以确定“未来可能下雨，不适合洗车”的第二反馈信息。若未来24小内可能会出现热带风暴气候，则可以确定“未来可能有风暴，不建议出行”的第二反馈信息。
评估条件6，用于根据服务价格生成反馈信息。若目标洗车店有优惠打折的洗车活动，则可以确定“有优惠活动，建议洗车”的第三反馈信息。若目标洗车店的洗车价格上涨，则可以确定“洗车价格上涨，暂缓洗车”的第二反馈信息。若目标洗车店的洗车价格无变化，则可以“洗车价格无变化，可以洗车”的第三反馈信息。
需要说明的是，处理单元可以基于关联参考信息对应的优先级，即与评估条件对应的优先级，按照优先级顺序评估，从而可以得到具有不同优先级的反馈信息。
S408，处理单元向AI音箱发送反馈信息。相应地，AI音箱接收来自处理单元的反馈信息。
具体地，在反馈信息为多个时，处理单元可以向AI音箱发送多个反馈信息中的一个。若多个反馈信息中存在第二反馈信息，则处理单元可以向AI音箱发送优先级最高的第二反馈信息。若多个反馈信息均为第三反馈信息，则处理单元可以向AI音箱发送优先级最高的第三反馈信息。发送反馈信息的具体实现方式，可以参考上述S303的相关内容，此处不再赘述。
以上述场景1为例进行说明，多个反馈信息中仅存在“冷凝器温度过高，建议维修后再打开空调”的第二反馈信息，则处理单元向AI音箱发送该第二反馈信息。若多个反馈信息均为第三反馈信息，且优先级最大的第三反馈信息为“温度较低，建议调整空调的工作模式为暖风模式”，则处理单元可以向AI音箱发送该第三反馈信息。
以上述场景2为例进行说明，多个反馈信息中存在“未来可能有风暴，不建议出行”的第二反馈信息以及“设备运行异常，建议维修后再导航”的第二反馈信息，且“设备运行异常，建议维修后再导航”的第二反馈信息的优先级，高于“未来可能有风暴，不建议出行”的第二反馈信息，则处理单元可以向AI音箱发送“设备运行异常， 建议维修后再导航”的第二反馈信息。
S409，AI音箱输出与反馈信息对应的语音。
具体地，AI音箱可以将反馈信息转换为语音，再通过扬声器发出语音。例如，在上述场景1中，AI音箱在收到上述第二反馈信息时，可以通过扬声器发出“冷凝器温度过高，建议维修后再打开空调”的反馈语音。AI音箱在收到上述第三反馈信息时，可以通过扬声器发出“温度较低，建议调整空调的工作模式为暖风模式”的反馈语音。
再例如，在上述场景2中，AI音箱在收到上述第二反馈信息时，可以通过扬声器发出“设备运行异常，建议维修后再导航”的反馈语音。AI音箱在收到上述第三反馈信息时，可以通过扬声器发出“有优惠活动，建议洗车”的反馈语音。
可选地，在上述场景1中，处理单元还可以通过车辆总线向空调发送第三反馈信息，以控制空调执行该第三反馈信息对应的操作。在上述场景2中，处理单元还可以通过车辆总线向车辆导航系统ECU发送第三反馈信息，以控制车辆导航系统ECU执行第三反馈信息对应的操作。
如此，用户可以参考AI音箱发出的反馈语音，执行对应的操作，或重新向AI音响发出指示，从而可以避免实际执行结果不能满足用户实际需求的情况，节省用户的时间和资源，提升用户体验。
以上结合图3-图6详细说明了本申请实施例提供的反馈方法。以下结合图7-图8详细说明用于执行本申请实施例提供的反馈方法的电子设备。
示例性地，图7为本申请实施例提供的电子设备的结构示意图一。如图7所示，电子设备700包括：获取模块701和生成模块702。为了便于说明，图7仅示出了该电子设备的主要部件。
其中，获取模块701，可以用于获取用户指令。获取模块701，还可以用于获取与用户指令关联的参考信息。其中，参考信息为影响是否执行用户指令的信息。生成模块701，可以用于根据与用户指令关联的参考信息生成反馈信息。
一种可能的设计方案中，生成模块701，还可以用于通过获取模块701获取与用户指令关联的参考信息的评估结果。生成模块701，还可以用于基于与用户指令关联的参考信息和评估结果，生成反馈信息。
可选地，生成模块701，还可以用于通过获取模块701，根据评估函数获得评估结果。其中，评估函数的输入参数包括用户指令和与用户指令关联的参考信息。
可选地，生成模块701，还可以用于在评估结果满足第一条件时，根据参考信息生成第一反馈信息。其中，第一反馈信息用于指示：建议不执行用户指令的信息或故障告警。
进一步地，与用户指令关联的参考信息为可以多个，评估结果也可以为多个，与用户指令关联的参考信息与评估结果一一对应。
或者，进一步地，生成模块701，还可以用于在评估结果满足第二条件时，根据与用户指令关联的参考信息生成第二反馈信息。其中，第二反馈信息用于指示建议不执行用户指令或故障告警。第二条件可以包括：存在评估结果的值在第一范围内，或所有评估结果的加权求和结果的值在第二范围内。
一种可能的设计方案中，生成模块701，还可以用于根据目标参考信息生成第二 反馈信息。其中，目标参考信息可以为满足第三条件的评估结果对应的参考信息。
可选地，获取模块701，还可以用于获取参考信息。获取模块701，还可以用于计算用户指令与参考信息之间的关联度。获取模块701，还可以用于获取与用户指令关联的参考信息。其中，与用户指令关联的参考信息可以为关联度大于或等于关联度阈值的参考信息。
可选地，关联度可以为余弦相似度。
可选地，参考信息可以包括车辆信息，车辆信息可以包括如下的一项或多项：车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、油量、空调模式、空调冷凝器状态、空调温度传感器状态、湿度传感器状态、或空调压缩机状态。
或者，可选地，参考信息可以包括非车辆信息，非车辆信息可以包括如下一项或多项：天气、温度、湿度、距离、可吸入颗粒物的浓度、服务价格、或促销活动信息。
可选地，获取模块701，还可以用于根据与用户指令关联的参考信息的优先级，获取与用户指令关联的参考信息的评估结果。
一种可能的设计方案中，用户指令可以为语音指令。
可选地，获取模块701和生成模块702也可以集成为一个模块，如处理模块。其中，处理模块可以用于实现电子设备700的处理功能。
可选地，电子设备700还可以包括存储模块(图7中未示出)，该存储模块存储有程序或指令。当处理模块执行该程序或指令时，使得电子设备700可以执行如图3或图4所示的反馈方法。
可选地，电子设备700还可以包括收发模块(图7中未示出)。其中，收发模块用于实现电子设备700的收发功能。进一步地，收发模块可以包括接收模块和发送模块。其中，接收模块和发送模块分别用于实现电子设备700的接收功能和发送功能。
或者，可选地，获取模块701可以包括收发模块。
应理解，电子设备700中涉及的获取模块701和生成模块702可以由处理器或处理器相关电路组件实现，可以为处理器或处理单元；收发模块可以由收发器或收发器相关电路组件实现，可以为收发器或收发单元。
需要说明的是，电子设备700可以是终端设备，也可以是可设置于终端设备中的芯片(系统)或其他部件或组件，还可以是包含终端设备的装置，本申请对此不做限定。
此外，电子设备700的技术效果可以参考图3或图4所示出的反馈方法的技术效果，此处不再赘述。
示例性地，图8为本申请实施例提供的电子设备的架构示意图二。该电子设备可以是终端设备也可以是可设置于终端设备的芯片(系统)或其他部件或组件。如图8所示，电子设备800可以包括处理器801。可选地，电子设备800还可以包括存储器802和/或收发器803。其中，处理器801与存储器802和收发器803耦合，如可以通过通信总线连接。
下面结合图8对电子设备800的各个构成部件进行具体的介绍：
其中，处理器801是电子设备800的控制中心，可以是一个处理器，也可以是多 个处理元件的统称。例如，处理器801是一个或多个中央处理器(central processing unit，CPU)，也可以是特定集成电路(application specific integrated circuit，ASIC)，或者是被配置成实施本申请实施例的一个或多个集成电路，例如：一个或多个微处理器(digital signal processor，DSP)，或，一个或者多个现场可编程门阵列(field programmable gate array，FPGA)。
可选地，处理器801可以通过运行或执行存储在存储器802内的软件程序，以及调用存储在存储器802内的数据，执行电子设备800的各种功能。
在具体的实现中，作为一种实施例，处理器801可以包括一个或多个CPU，例如图8中所示出的CPU0和CPU1。
在具体实现中，作为一种实施例，电子设备800也可以包括多个处理器，例如图2中所示的处理器801和处理器804。这些处理器中的每一个可以是一个单核处理器(single-CPU)，也可以是一个多核处理器(multi-CPU)。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(例如计算机程序指令)的处理核。
其中，存储器802用于存储执行本申请方案的软件程序，并由处理器801来控制执行，具体实现方式可以参考上述方法实施例，此处不再赘述。
可选地，存储器802可以是只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)或者可存储信息和指令的其他类型的动态存储设备，也可以是电可擦可编程只读存储器(electrically erasable programmable read-only memory，EEPROM)、只读光盘(compact disc read-only memory，CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。存储器802可以和处理器801集成在一起，也可以独立存在，并通过电子设备800的接口电路(图8中未示出)与处理器801耦合，本申请实施例对此不作具体限定。
收发器803，用于与其他电子设备之间的通信。例如，电子设备800为终端设备，收发器803可以用于与网络设备通信，或者与另一个终端设备通信。
可选地，收发器803可以包括接收器和发送器(图8中未单独示出)。其中，接收器用于实现接收功能，发送器用于实现发送功能。
可选地，收发器803可以和处理器801集成在一起，也可以独立存在，并通过电子设备800的接口电路(图8中未示出)与处理器801耦合，本申请实施例对此不作具体限定。
需要说明的是，图8中示出的电子设备800的结构并不构成对该电子设备的限定，实际的电子设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
此外，电子设备800的技术效果可以参考上述方法实施例所述的反馈方法的技术效果，此处不再赘述。
需要说明的是，本申请实施例中，图7的电子设备可以是网络设备或终端设备-图6中任一的电子设备可以是网络设备，如服务器，或者终端设备，如车载终端。
本申请实施例提供一种反馈系统。该反馈系统包括电子设备。
可选地，该反馈系统还可以包括网络设备。
应理解，在本申请实施例中的处理器可以是中央处理单元(central processing unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
还应理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的随机存取存储器(random access memory，RAM)可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。
上述实施例，可以全部或部分地通过软件、硬件(如电路)、固件或其他任意组合来实现。当使用软件实现时，上述实施例可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令或计算机程序。在计算机上加载或执行所述计算机指令或计算机程序时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集合的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质。半导体介质可以是固态硬盘。
应理解，本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况，其中A,B可以是单数或者复数。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系，但也可能表示的是一种“和/或”的关系，具体可参考前后文进行理解。
本申请中，“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个) 的任意组合。例如，a,b,或c中的至少一项(个)，可以表示：a,b,c,a-b,a-c,b-c,或a-b-c，其中a,b,c可以是单个，也可以是多个。
应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、电子设备和方法，可以通过其它的方式实现。例如，以上所描述的电子设备的实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (34)

  1. 一种反馈方法，其特征在于，所述方法包括：
    获取用户指令；
    获取与所述用户指令关联的参考信息，其中，所述参考信息为影响是否执行所述用户指令的信息；
    根据所述与所述用户指令关联的参考信息生成反馈信息。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述与所述用户指令关联的参考信息生成反馈信息，包括：
    获取所述与所述用户指令关联的参考信息的评估结果；
    基于所述与所述用户指令关联的参考信息和所述评估结果，生成所述反馈信息。
  3. 根据权利要求2所述的方法，其特征在于，所述获取所述与所述用户指令关联的参考信息的评估结果，包括：
    根据评估函数获得所述评估结果，其中，所述评估函数的输入参数包括所述用户指令和所述与所述用户指令关联的参考信息。
  4. 根据权利要求2或3所述的方法，其特征在于，所述基于所述与所述用户指令关联的参考信息和所述评估结果，生成所述反馈信息，包括：
    若所述评估结果满足第一条件，则根据所述与所述用户指令关联的参考信息生成第一反馈信息，其中，所述第一反馈信息用于指示：建议不执行所述用户指令或故障告警。
  5. 根据权利要求2或3所述的方法，其特征在于，所述与所述用户指令关联的参考信息为多个，所述评估结果为多个，所述与所述用户指令关联的参考信息与所述评估结果一一对应。
  6. 根据权利要求5所述的方法，其特征在于，所述基于所述与所述用户指令关联的参考信息和所述评估结果，生成所述反馈信息，包括：
    若所述评估结果满足第二条件，则根据所述与所述用户指令关联的参考信息生成第二反馈信息，其中，所述第二反馈信息用于指示：建议不执行所述用户指令或故障告警；所述第二条件包括：存在所述评估结果的值在第一范围内，或所有所述评估结果的加权求和结果的值在第二范围内。
  7. 根据权利要求6所述的方法，其特征在于，所述根据所述与所述用户指令关联的参考信息生成第二反馈信息，包括：
    根据目标参考信息生成所述第二反馈信息，其中，所述目标参考信息为：满足第三条件的所述评估结果对应的所述与所述用户指令关联的参考信息。
  8. 根据权利要求1-7中任一项所述的方法，其特征在于，所述获取所述与所述用户指令关联的参考信息，包括：
    获取所述参考信息；
    计算所述用户指令与所述参考信息之间的关联度；
    获取所述与所述用户指令关联的参考信息，其中，所述与所述用户指令关联的参考信息为：所述关联度大于或等于关联度阈值的所述参考信息。
  9. 根据权利要求8所述的方法，其特征在于，所述关联度为余弦相似度。
  10. 根据权利要求1-9中任一项所述的方法，其特征在于，所述参考信息包括车辆信息，所述车辆信息包括如下一项或多项：
    车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、油量、空调模式、空调冷凝器状态、空调温度传感器状态、湿度传感器状态、或空调压缩机状态。
  11. 根据权利要求1-9中任一项所述的方法，其特征在于，所述参考信息包括非车辆信息，所述非车辆信息包括如下一项或多项：
    天气、温度、湿度、距离、可吸入颗粒物的浓度、服务价格、或促销活动信息。
  12. 根据权利要求2-11中任一项所述的方法，其特征在于，所述获取所述与所述用户指令关联的参考信息的评估结果，包括：
    根据所述与所述用户指令关联的参考信息的优先级，获取所述与所述用户指令关联的参考信息的评估结果。
  13. 根据权利要求1至12中任一项所述的方法，其特征在于，所述用户指令为语音指令。
  14. 一种电子设备，其特征在于，所述电子设备包括：获取模块和生成模块；
    所述获取模块，用于获取用户指令；
    所述获取模块，还用于获取与所述用户指令关联的参考信息，其中，所述参考信息为影响是否执行所述用户指令的信息；
    所述生成模块，用于根据所述与所述用户指令关联的参考信息生成反馈信息。
  15. 根据权利要求14所述的设备，其特征在于，
    所述生成模块，还用于通过所述获取模块获取所述与所述用户指令关联的参考信息的评估结果；
    所述生成模块，还用于基于所述与所述用户指令关联的参考信息和所述评估结果，生成所述反馈信息。
  16. 根据权利要求15所述的设备，其特征在于，
    所述生成模块，还用于通过所述获取模块，根据评估函数获得所述评估结果，其中，所述评估函数的输入参数包括所述用户指令和所述与所述用户指令关联的参考信息。
  17. 根据权利要求15或16所述的设备，其特征在于，
    所述生成模块，还用于在所述评估结果满足第一条件时，根据所述与所述用户指令关联的参考信息生成第一反馈信息，其中，所述第一反馈信息用于指示：建议不执行所述用户指令或故障告警。
  18. 根据权利要求15或16所述的设备，其特征在于，所述与所述用户指令关联的参考信息为多个，所述评估结果为多个，所述与所述用户指令关联的参考信息与所述评估结果一一对应。
  19. 根据权利要求18所述的设备，其特征在于，
    所述生成模块，还用于在所述评估结果满足第二条件时，根据所述与所述用户指令关联的参考信息生成第二反馈信息，其中，所述第二反馈信息用于指示：建议不执行所述用户指令或故障告警；所述第二条件包括：存在所述评估结果的值在第一范围 内，或所有所述评估结果的加权求和结果的值在第二范围内。
  20. 根据权利要求19所述的设备，其特征在于，
    所述生成模块，还用于根据目标参考信息生成所述第二反馈信息，其中，所述目标参考信息为：满足第三条件的所述评估结果对应的所述与所述用户指令关联的参考信息。
  21. 根据权利要求14-20中任一项所述的设备，其特征在于，
    所述获取模块，还用于获取所述参考信息；
    所述获取模块，还用于计算所述用户指令与所述参考信息之间的关联度；
    所述获取模块，还用于获取所述与所述用户指令关联的参考信息，其中，所述与所述用户指令关联的参考信息为：所述关联度大于或等于关联度阈值的所述参考信息。
  22. 根据权利要求21所述的设备，其特征在于，所述关联度为余弦相似度。
  23. 根据权利要求14-21中任一项所述的设备，其特征在于，所述参考信息包括车辆信息，所述车辆信息包括如下一项或多项：
    车辆冷却系统状态、车辆点火系统状态、车辆起动系统状态、车辆传动系统状态、油量、空调模式、空调冷凝器状态、空调温度传感器状态、湿度传感器状态、或空调压缩机状态。
  24. 根据权利要求14-21中任一项所述的设备，其特征在于，所述参考信息包括非车辆信息，所述非车辆信息包括如下一项或多项：
    天气、温度、湿度、距离、可吸入颗粒物的浓度、服务价格、或促销活动信息。
  25. 根据权利要求15-21中任一项所述的设备，其特征在于，
    所述获取模块，还用于根据所述与所述用户指令关联的参考信息的优先级，获取所述与所述用户指令关联的参考信息的评估结果。
  26. 根据权利要求14至25中任一项所述的设备，其特征在于，所述用户指令为语音指令。
  27. 一种电子设备，其特征在于，所述电子设备能够执行如权利要求1-14中任一项所述的方法。
  28. 一种车辆，其特征在于，所述车辆包括如权利要求14-26中任一项所述的电子设备。
  29. 一种车辆，其特征在于，所述车辆能够执行如权利要求1-13中任一项所述的方法。
  30. 一种电子设备，其特征在于，包括：处理器和存储器；所述存储器用于存储计算机指令，当所述处理器执行该指令时，所述电子设备执行如权利要求1-13中任一项所述的反馈方法。
  31. 一种电子设备，其特征在于，包括：处理器和接口电路；其中，
    所述接口电路，用于接收代码指令并传输至所述处理器；
    所述处理器，用于运行所述代码指令以执行如权利要求1-13中任一项所述的反馈方法。
  32. 一种电子设备，其特征在于，所述电子设备包括处理器和收发器，所述收发器用于所述电子设备和其他电子设备之间进行信息交互，所述处理器执行程序指令，用 以执行如权利要求1-13中任一项所述的反馈方法。
  33. 一种处理器，其特征在于，所述处理器用于执行如权利要求1-13中任一项所述的方法。
  34. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质包括计算机程序或指令，当所述计算机程序或指令在计算机上运行时，执行如权利要求1-13中任一项所述的方法。
PCT/CN2021/092240 2021-05-07 2021-05-07 反馈方法及电子设备 WO2022233065A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202180001586.1A CN113366466A (zh) 2021-05-07 2021-05-07 反馈方法及电子设备
PCT/CN2021/092240 WO2022233065A1 (zh) 2021-05-07 2021-05-07 反馈方法及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/092240 WO2022233065A1 (zh) 2021-05-07 2021-05-07 反馈方法及电子设备

Publications (1)

Publication Number Publication Date
WO2022233065A1 true WO2022233065A1 (zh) 2022-11-10

Family

ID=77523065

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/092240 WO2022233065A1 (zh) 2021-05-07 2021-05-07 反馈方法及电子设备

Country Status (2)

Country Link
CN (1) CN113366466A (zh)
WO (1) WO2022233065A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024207416A1 (en) * 2023-04-07 2024-10-10 Qualcomm Incorporated Inference data similarity feedback for machine learning model performance monitoring in beam prediction

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105857011A (zh) * 2016-04-14 2016-08-17 北京长安汽车工程技术研究有限责任公司 一种汽车空调控制方法、控制器及汽车空调控制系统
CN112026479A (zh) * 2020-08-31 2020-12-04 重庆长安汽车股份有限公司 一种汽车空调系统和汽车空调系统的控制方法
WO2021000506A1 (zh) * 2019-06-30 2021-01-07 广东美的制冷设备有限公司 空调器及其控制方法、控制终端、服务器和存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107728783B (zh) * 2017-09-25 2021-05-18 联想(北京)有限公司 人工智能处理方法及其系统
CN109253734A (zh) * 2018-11-22 2019-01-22 深圳市元征科技股份有限公司 一种导航路线的生成方法、系统及相关组件
CN112102036A (zh) * 2020-09-16 2020-12-18 京东数字科技控股股份有限公司 信息推荐方法、装置及存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105857011A (zh) * 2016-04-14 2016-08-17 北京长安汽车工程技术研究有限责任公司 一种汽车空调控制方法、控制器及汽车空调控制系统
WO2021000506A1 (zh) * 2019-06-30 2021-01-07 广东美的制冷设备有限公司 空调器及其控制方法、控制终端、服务器和存储介质
CN112026479A (zh) * 2020-08-31 2020-12-04 重庆长安汽车股份有限公司 一种汽车空调系统和汽车空调系统的控制方法

Also Published As

Publication number Publication date
CN113366466A (zh) 2021-09-07

Similar Documents

Publication Publication Date Title
CN110753934B (zh) 主动选择和标记图像以进行语义分割的系统和方法
JP6668497B2 (ja) テレマティクスシステム及びその対応する方法
EP3084676B1 (en) Secure vehicular data management with enhanced privacy
US10460394B2 (en) Autonomous or partially autonomous motor vehicles with automated risk-controlled systems and corresponding method thereof
US8924241B2 (en) System and method to determine an insurance policy benefit associated with an asset
US11468036B2 (en) Facilitating determination of reliability of crowd sourced information
JP6559792B2 (ja) オーダーペアリングのシステム及び方法
CN116342655A (zh) 用于在线实时多对象跟踪的装置和方法
WO2021212496A1 (zh) 一种电池检测的方法和装置
CN104321620A (zh) 基于用户简档信息通过改变的地图路线进行行为修改
US20230410577A1 (en) Systems and methods for system generated damage analysis
WO2020072501A1 (en) Roadside assistance system
US20230013317A1 (en) Hub for automated recovery after a critical event in shared mobility services
US11868222B2 (en) System and method for integration testing
CN109353345A (zh) 车辆控制方法、装置、设备、介质和车辆
EP3622384B1 (en) Actionable event determination based on vehicle diagnostic data
WO2022233065A1 (zh) 反馈方法及电子设备
Madhav et al. IMPROVE: Intelligent machine learning based portable, reliable and optimal verification system for future vehicles
US20220067848A1 (en) Dynamic transport energy control
Muthiya et al. Application of internet of things (IoT) in the automotive industry
Fahmi et al. Integrated Car Telemetry System Based On Internet Of Things: Application And Challenges
US20220305941A1 (en) Scheduling pre-departure charging of electric vehicles
WO2021217477A1 (zh) 异常消息的识别方法和装置
US12068608B2 (en) Determining energy sources to a location
Gulati et al. Insurance Automotive Application Using Edge Computing

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21939711

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21939711

Country of ref document: EP

Kind code of ref document: A1