WO2016070823A1

WO2016070823A1 - Instruction processing method and device

Info

Publication number: WO2016070823A1
Application number: PCT/CN2015/093858
Authority: WO
Inventors: 赵家伟
Original assignee: 中兴通讯股份有限公司
Priority date: 2014-11-05
Filing date: 2015-11-05
Publication date: 2016-05-12
Also published as: CN105630456A

Abstract

An instruction processing method and device. The method comprises: monitoring a condition for triggering to execute an instruction (S102); and in a case in which the condition meets a preset rule, controlling execution of the instruction, wherein the preset rule is at least obtained by learning a corresponding condition when the instruction is executed once or multiple times (S104). The method resolves a problem in related technologies that an operation mode of an intelligent housing system cannot be flexibly controlled, so that the operation mode of the intelligent housing system can be flexibly controlled, an operation is simplified, and user experience is improved.

Description

Instruction processing method and device

Technical field

The present invention relates to the field of communications, and in particular to an instruction processing method and apparatus.

Background technique

With the maturity of the Internet of Things technology, smart home products are gradually welcomed by the market. Generally, a smart home system includes a smart gateway device and a peripheral controlled terminal, and a platform device deployed on the network side. As the backbone of the smart home network, the intelligent gateway device manages and controls peripheral controlled terminals such as cameras, security sensors, white goods, etc. through wireless protocols such as Zigbee and WIreless-Fidelity (WLAN). At the same time, the intelligent gateway accesses the external network platform through the Internet interface, and uniformly manages the home user information and control command forwarding through the network platform, thereby realizing the remote control of the smart home system based on the mobile terminal, for example, controlling the home appliance lighting system through the smart phone. The switch, the security system is disarmed, and the home security alarm is obtained.

At present, the operation mode of the smart home system is mainly passively accepting the manual control of the user, or controlling according to the personalized pre-configured data of the user. For example, in the manual control mode, after the user returns home, the security system is manually disarmed through the remote controller or the smart phone; after the user leaves the home, the security system is manually armed through the smart phone. User personalized pre-configuration mode, set the time schedule for the air-conditioning cycle to be turned on, or pre-configure the relationship between the infrared detector and the camera perspective. As the smart home system becomes more and more complex, the disadvantages of the two methods are that the user's learning cost and operation complexity are increased. Second, the pre-configuration method may not meet the user's flexibility requirements and lose the use value in actual use. .

In view of the related art, it is impossible to flexibly control the operation mode of the smart home system, and an effective solution has not been proposed.

Summary of the invention

The present invention provides an instruction processing method and apparatus to at least solve the problem that the related art cannot flexibly control the operation mode of the smart home system.

According to an aspect of an embodiment of the present invention, there is provided an instruction processing method comprising: monitoring a condition for triggering execution of an instruction; and controlling execution of the instruction if the condition meets a predetermined rule, wherein the predetermined rule At least the learning of the corresponding condition when the instruction is executed one or more times is obtained.

Optionally, if the condition meets the predetermined rule, controlling the execution of the instruction includes: when the condition meets the predetermined rule, modifying the predetermined rule; and receiving the prompt for the modification Responding to: controlling execution of the instruction according to the response, wherein the instruction is executed in a case where the predetermined rule is not revised according to the response confirmation; in a case where the predetermined rule is revised according to the response confirmation And executing the instruction if the condition meets the revised predetermined rule.

Optionally, the response is used to indicate at least one of: the instruction is not executed for the case that the condition meets the predetermined rule for the time; the predetermined rule is cancelled; after the instruction is executed, no longer And modifying the predetermined rule; after the executing the instruction, the condition prompts the modification when the condition meets the predetermined rule or the revised predetermined rule.

Optionally, performing the modification prompt on the predetermined rule includes: determining, according to a pre-configured option, whether the modification prompt is performed on the predetermined rule, and if the determination result is yes, performing the modification prompt; If the determination result is no, controlling the execution of the instruction includes: executing the instruction.

Optionally, the predetermined rule is stored locally or from other network elements.

Optionally, the predetermined rule includes at least one of: time, account information, user location information, environment information, status information of a device that executes the instruction, or an instruction that has been sent to the device, where the account information Used to identify the device.

Optionally, the monitoring of the condition for triggering the execution instruction comprises: monitoring the condition for triggering the execution instruction according to a preset policy; or, after receiving the operation instruction, monitoring the condition for triggering the execution instruction.

Optionally, before the condition of triggering the execution of the instruction is monitored, the method further includes: sending the corresponding condition when the instruction is executed one or more times to another network element, where the other network element is once Or learning the corresponding condition when the instruction is executed multiple times to obtain the network element of the predetermined rule; or learning the corresponding condition when the instruction is executed one or more times locally to obtain the predetermined rule.

Optionally, learning the corresponding condition when the instruction is executed one or more times to obtain the predetermined rule comprises: obtaining the predetermined by combining or inducting the same or similarity in the condition corresponding to the instruction multiple times. rule.

According to another aspect of the embodiments of the present invention, there is provided another instruction processing method, including: receiving a condition corresponding to one or more executions of an instruction; learning the condition to obtain a predetermined rule, wherein the predetermined rule The subject for instructing to receive the predetermined rule controls execution of the instruction if the condition meets the predetermined rule; transmitting the predetermined rule.

Optionally, learning the condition to obtain the predetermined rule comprises: obtaining the predetermined rule by combining or inducting the same or similarities in the conditions corresponding to the instruction multiple times.

According to an aspect of an embodiment of the present invention, an instruction processing apparatus includes: a monitoring module configured to monitor a condition for triggering an execution instruction; and a control module configured to control the condition if the condition meets a predetermined rule Execution of an instruction, wherein the predetermined rule is obtained by learning at least a condition corresponding to one or more executions of the instruction.

Optionally, the control module includes: a prompting unit, configured to: when the condition meets the predetermined rule, Determining a predetermined rule to perform a modification prompt; the receiving unit is configured to receive a response to the modification prompt; the first execution unit is configured to control execution of the instruction according to the response, wherein the non-revision is confirmed according to the response In the case of the predetermined rule, the instruction is executed; the second execution unit is configured to, in the case of confirming the predetermined rule according to the response confirmation, in a case where the condition meets the revised predetermined rule, Execute the instructions.

Optionally, the prompting unit is further configured to determine, according to the pre-configured option, whether to perform the modification prompt on the predetermined rule, and if the determination result is yes, perform the modification prompt; In the event of no, controlling the execution of the instructions includes executing the instructions.

Optionally, the monitoring module is further configured to monitor the condition that triggers the execution instruction according to a preset policy; or, after receiving the operation instruction, monitor the condition that triggers the execution instruction.

Optionally, the device further includes: a sending module, configured to send a corresponding condition when the instruction is executed one or more times to another network element, where the other network element is configured to perform the one or more times The network element of the predetermined rule is learned by the condition corresponding to the instruction; the learning module is configured to learn the condition corresponding to the one or more executions of the instruction locally to obtain the predetermined rule.

Optionally, the learning module is further configured to obtain the predetermined rule by merging or summarizing the same or similarities in the conditions corresponding to the execution of the instruction multiple times.

According to another aspect of the embodiments of the present invention, there is still another instruction processing apparatus, including: a receiving module configured to receive a condition corresponding to one or more executions of an instruction; and a learning module configured to learn the condition Obtaining a predetermined rule, wherein the predetermined rule is used to indicate that the subject receiving the predetermined rule controls execution of the instruction if the condition meets the predetermined rule; and the sending module is configured to send the predetermined rule.

Through the embodiment of the present invention, the condition for triggering the execution of the instruction is monitored; and when the condition meets the predetermined rule, the control is performed. The execution of the instruction, wherein the predetermined rule is obtained by learning at least the condition corresponding to one or more executions of the above instruction. The invention solves the problem that the related mode cannot flexibly control the operation mode of the smart home system, thereby realizing the flexible control of the operation mode of the smart home system, simplifying the operation and improving the user experience.

DRAWINGS

The drawings described herein are intended to provide a further understanding of the invention, and are intended to be a part of the invention. In the drawing:

1 is a flow chart of an instruction processing method according to an embodiment of the present invention;

2 is a block diagram showing the structure of an instruction processing apparatus according to an embodiment of the present invention;

3 is a block diagram 1 of a structure of an instruction processing apparatus according to an embodiment of the present invention;

4 is a block diagram 2 of a structure of an instruction processing apparatus according to an embodiment of the present invention;

FIG. 5 is a flowchart 1 of an instruction processing method according to an embodiment of the present invention; FIG.

6 is a structural block diagram 3 of an instruction processing apparatus according to an embodiment of the present invention;

7 is a flow chart of a smart home control method according to an embodiment of the present invention;

8 is a flowchart of a learning control instruction learning method in a smart home control method according to an embodiment of the present invention;

9 is a schematic diagram of a smart gateway related unit according to an embodiment of the present invention;

FIG. 10 is a schematic diagram of a network platform related unit according to an embodiment of the present invention; FIG.

11 is a schematic diagram of a smart home network according to an embodiment of the present invention;

Figure 12 is an interaction timing diagram in accordance with an embodiment of the present invention.

detailed description

The invention will be described in detail below with reference to the drawings in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.

An instruction processing method is provided in this embodiment. FIG. 1 is a flowchart of an instruction processing method according to an embodiment of the present invention. As shown in FIG. 1, the flow includes the following steps:

Step S102, monitoring conditions for triggering execution of the instruction;

Step S104, in the case that the condition meets the predetermined rule, the execution of the instruction is obtained, wherein the predetermined rule is obtained by learning at least the condition corresponding to the execution of the instruction one or more times.

Through the above steps, at least one or more times when the instruction is executed, the corresponding condition is learned to obtain a predetermined rule. When it is determined that the condition for triggering the execution instruction meets the predetermined rule, the execution of the control instruction is performed by passively accepting the manual control of the user or performing the control according to the user's personalized pre-configured data, and the above steps may be automatically performed. The learning reservation rule reduces the manual participation of the user, thereby solving the problem that the related technology cannot flexibly control the operation mode of the smart home system, thereby realizing the flexible control of the operation mode of the smart home system, simplifying the operation and improving the user. Experience.

The predetermined rules learned above may have some problems with the user's request. In an optional embodiment, when the condition meets the predetermined rule, the predetermined rule is modified, by which the user can modify the predetermined rule; then, receiving a response to the modification prompt; and according to the response control instruction Execution, wherein the instruction is executed in the case where the predetermined rule is not revised according to the response confirmation; in the case where the predetermined rule is revised according to the response confirmation, the instruction is executed if the condition meets the revised predetermined rule. For example, when the monitored condition satisfies the trigger condition of the execution instruction, the user is prompted whether to modify the trigger condition for executing the instruction, and when the user indicates that the trigger condition for executing the instruction is not modified, the instruction is directly executed, and the user instructs the modification to execute the instruction. When the trigger condition of the instruction is received, the user's revision of the trigger condition for executing the instruction is received, and the condition is monitored here, and the condition is executed when the condition monitored again meets the trigger condition for executing the revised instruction.

The above response to the revised prompt may have multiple manifestations, that is, the response may also reflect other functions that the user wishes to perform. In an alternative embodiment, the response may be used to indicate at least one of the following: If the condition meets the predetermined rule, the instruction is not executed; the predetermined rule is cancelled; after the instruction is executed, the predetermined rule is no longer modified; after the instruction is executed, the monitored condition meets the predetermined rule or revised each time Suggestions for modification when scheduling rules. Thus, the user can flexibly control the execution of the instructions by different settings of the response to the revision prompt.

The generation of the predetermined rule may be obtained by learning the corresponding condition when the instruction is executed multiple times. Therefore, the generated predetermined rule is relatively stable, and the user can trust the predetermined rule. In another case, the user may also choose not to trust the predetermined rule, but need to view the rules to facilitate the modification. In view of these two user requirements, in an alternative embodiment, a configurable option can be added to allow the user to select whether or not to modify the predetermined rules generated by the learning. For example, it is determined whether to modify the predetermined rule according to the pre-configured option. If the determination result is yes, the modification prompt is performed; if the determination result is negative, the execution of the control instruction includes: directly executing the instruction. With this added configuration option, the user's choices can be made more flexible and the user experience can be improved.

The foregoing embodiment or the optional implementation manner may be performed in a gateway device or on a smart device connected to the gateway. In the case of being executed on the gateway, the learned predetermined rule saved in the gateway may be different. Smart device. If executed on the smart device, the learned predetermined rules saved in the smart device may be only for themselves, or may be for other smart devices or gateways. Considering the storage space of the gateway and the smart device, these learned rules can also be saved on other network elements and obtained from other network elements when needed. The gateway and smart device in this paragraph are merely examples, and the above embodiments or alternative embodiments may be executed on any device.

For the learning of predetermined rules, the processing power of the gateway or smart device can be considered, and it can be performed on these devices if its processing capability allows. Alternatively, you can learn on other network elements to reduce the burden on the gateway or smart device. That is, the above-mentioned predetermined rule is stored locally or from other network elements, and in the case where the predetermined rule is stored locally, the corresponding condition is learned locally when the instruction is executed one or more times to obtain the predetermined rule; Rules originated In the case of other network elements, the corresponding condition is sent to other network elements when the instruction is executed one or more times, wherein the other network element is a network that learns the conditions corresponding to one or more executions of the instruction to obtain a predetermined rule. yuan. The execution of the predetermined rules on which device can be performed can take into account the network conditions and/or device processing conditions before making a selection. In another optional embodiment, if at least two devices are learning the predetermined rules, the at least two devices can exchange the predetermined rules learned by each.

The predetermined rule may include a plurality of information, which may be set according to different needs. In another optional embodiment, the predetermined rule may include at least one of the following: time, account information, user location information, environment information, Status information of the device that executed the instruction or an instruction that has been sent to the device, wherein the account information is used to identify the device, if a predetermined rule for multiple smart devices is saved on one device (eg, a gateway), This account information is needed to distinguish which device the rule is for. If a device's predetermined rules are only for itself, then the account information is not needed.

The monitoring trigger execution instruction involved in the foregoing step S102 may be active monitoring or passive monitoring. In an optional embodiment, the condition for triggering the execution instruction is monitored according to a preset policy; or, after receiving the operation instruction, monitoring The condition that triggers the execution of the instruction.

The generation of the predetermined rules can also be accomplished in a number of ways. In an alternative embodiment, the predetermined rules are obtained by merging or summarizing the same or similarities in the conditions corresponding to the multiple execution instructions. For example, consider using some existing fuzzy algorithms to merge or generalize.

In the embodiment, an instruction processing device is further provided, which is used to implement the above-mentioned embodiments and optional embodiments, and has not been described again. As used below, the term "module" may implement a combination of software and/or hardware of a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.

2 is a structural block diagram of an instruction processing apparatus according to an embodiment of the present invention. As shown in FIG. 2, the apparatus includes: a monitoring module 22 configured to monitor a condition for triggering an execution instruction; and a control module 24 configured to meet the predetermined condition In the case of a rule, the execution of the instruction is controlled, wherein the predetermined rule is obtained by learning at least one or more conditions corresponding to the execution of the instruction.

3 is a block diagram of a structure of an instruction processing apparatus according to an embodiment of the present invention. As shown in FIG. 3, the control module 24 includes: a prompting unit 242, configured to modify a predetermined rule when the condition meets the predetermined rule; The receiving unit 244 is configured to receive a response to the modification prompt; the first execution unit 246 is configured to control execution of the instruction according to the response, wherein the instruction is executed if it is confirmed according to the response that the predetermined rule is not revised; The second execution unit 248 is arranged to execute the instruction in the case where the condition conforms to the revised predetermined rule in the case of confirming the revision of the predetermined rule according to the response.

In an optional embodiment, the response is for indicating at least one of: for the case that the condition meets the predetermined rule, the instruction is not executed; the predetermined rule is cancelled; after the instruction is executed, the predetermined rule is no longer A modification prompt is made; after the instruction is executed, the modification prompt is performed each time the condition meets the predetermined rule or the revised predetermined rule.

In an optional embodiment, the prompting unit 242 is further configured to determine whether to perform the modification prompt on the predetermined rule according to the pre-configured option, and if the determination result is yes, perform the modification prompt; if the determination result is no In the case of controlling the execution of the instruction, the execution of the instruction is performed.

In an alternative embodiment, the predetermined rules are stored locally or from other network elements.

In an optional embodiment, the predetermined rule includes at least one of: time, account information, user location information, environment information, status information of a device that executes the instruction, or an instruction that has been sent to the device, wherein the account information Used to identify the device.

In an alternative embodiment, the monitoring module 22 is further configured to monitor the condition that triggers the execution of the instruction in accordance with a predetermined policy; or, after receiving the operational instruction, monitor the condition that triggered the execution of the instruction.

4 is a block diagram of a structure of an instruction processing apparatus according to an embodiment of the present invention. As shown in FIG. 4, the apparatus further includes: a sending module 26 configured to send a corresponding condition when one or more times of executing the instruction to another network. a unit, wherein the other network element is a network element that learns the condition corresponding to one or more executions of the instruction to obtain the predetermined rule; and the learning module 28 is configured to perform a condition corresponding to the local execution of the instruction one or more times. Learn to get the predetermined rules.

In an alternative embodiment, the learning module 28 is further arranged to derive a predetermined rule by merging or summarizing the same or similarities in the conditions corresponding to the execution of the instruction multiple times.

An instruction processing method is also provided in this embodiment. FIG. 5 is a flowchart 1 of an instruction processing method according to an embodiment of the present invention. As shown in FIG. 5, the flow includes the following steps:

Step S502, receiving a condition corresponding to one or more executions of the instruction;

Step S504, learning the condition to obtain a predetermined rule, where the predetermined rule is used to indicate that the subject receiving the predetermined rule controls execution of the instruction if the condition meets the predetermined rule;

Step S506, sending a predetermined rule.

Through the above steps, the subject instructing to receive the predetermined rule controls the execution of the instruction if the condition meets the predetermined rule, and then the subject receiving the predetermined rule can flexibly control the instruction, and the execution of the instruction is mainly passive compared to the related art. Accepting the user's manual control, or controlling according to the user's personalized pre-configured data, the above steps solve the problem that the related technology cannot flexibly control the operation mode of the smart home system, thereby realizing the flexible control of the operation mode of the smart home system. , simplifying the operation and improving the user experience.

The predetermined rule may include a plurality of information, and in another alternative embodiment, the predetermined rule includes at least one of: time, account information, user location information, environmental information, status information of a device that executes the instruction, or has been directed to the device The sent command, wherein the account information is used to identify the device.

The generation of the predetermined rule may also be implemented in a plurality of manners. In an optional embodiment, learning the condition to obtain the predetermined rule includes: obtaining, by combining or inducting the same or similarities in the conditions corresponding to the execution of the instruction multiple times. Schedule rules.

6 is a structural block diagram 3 of an instruction processing apparatus according to an embodiment of the present invention. As shown in FIG. 6, the apparatus includes: a receiving module 62 configured to receive a condition corresponding to one or more executions of an instruction; and a learning module 64, setting The predetermined rule is obtained by learning the condition, wherein the predetermined rule is used to indicate that the subject receiving the predetermined rule controls the execution of the instruction if the condition meets the predetermined rule; and the sending module 66 is configured to send the predetermined rule.

In an alternative embodiment, the learning module 62 is further configured to derive the predetermined rule by merging or summarizing the same or similarities in the conditions corresponding to the execution of the instruction multiple times.

The following alternative embodiment is an illustration of a smart home system.

The optional embodiment provides a smart home system control method, which implements a control method combining automatic learning of the system and active intervention by the user. In this optional embodiment, the intelligent gateway collects and analyzes the user's usage habits and operation instructions to form a learning control instruction knowledge base; the intelligent gateway uses the learning control instruction knowledge base to predict the planned execution according to the current environmental context information during operation. The instruction sends a learning control instruction correction request to the user, and the intelligent gateway acquires and analyzes the learning control instruction correction response, and completes the control of the planned execution instruction and the optimization of the learning control instruction knowledge base according to the analysis result.

7 is a flow chart of a smart home control method according to an embodiment of the present invention, and FIG. 7 provides a smart home control method, which is applied to a smart home system, where the system includes at least a smart gateway device and a learning control instruction knowledge base, and the above learning control The instruction knowledge base includes at least one learning control instruction, where the learning control instruction includes a learning control instruction triggering condition, a corresponding planned execution instruction, and a modified parameter option set, wherein the learning control instruction triggering condition includes at least one attribute and a corresponding attribute value, as shown in the figure. As shown in 7, the method includes the following steps:

Step S702, the intelligent gateway monitors environment context information.

Step S704, the intelligent gateway determines whether the environment context information matches the learning control instruction triggering condition, and when yes, step S706 is performed; otherwise, step S702 is performed;

Step S706: The smart gateway sends a learning control instruction correction request to the user through the human-machine interface.

Step S708, the intelligent gateway acquires and analyzes the learning control instruction correction response, and optimizes the learning control instruction or the control plan execution instruction according to the analysis result.

The modified parameter option set includes but is not limited to: sending a learning control instruction correction request: YES/NO (NO: no transmission, YES: transmission); when the transmission learning control instruction correction request is YES, the above modified parameter option set The method further includes: accepting the learning control instruction execution and canceling the subsequent correction request or accepting the learning control instruction execution (and subsequently sending the correction request each time) or prohibiting the execution of the learning control instruction or canceling the learning control instruction or the optimization learning control instruction triggering condition , including the attribute and attribute value corresponding to the triggering condition of the learning control instruction;

Optionally, in step S702, the environment context information includes at least an attribute included in a learning control instruction triggering condition;

Optionally, before the step S706 is performed, the smart gateway may directly execute the plan execution instruction in the learning control instruction by determining that the sending the learning control instruction correction request option is NO;

Optionally, the manual interface in step S706 includes, but is not limited to, a display screen of a PC, a smart phone, or an electrical device;

Optionally, the foregoing learning control instruction correction request in step S706 includes the foregoing modified parameter option set;

Optionally, in step S708, the result option included in the learning control instruction correction response and the parameter option in the learning control instruction correction request correspond to each other. Optionally, the learning control instruction correction response includes, but is not limited to, accepting the learning control instruction execution and canceling the subsequent modification request or accepting the learning control instruction execution (and subsequently sending the correction request each time) or prohibiting the execution of the learning control instruction or Deactivating the learning control instruction or optimizing the learning control instruction triggering condition, including the attribute and the attribute value corresponding to the triggering condition of the learning control instruction;

Optionally, in step S708, the control of the plan execution instruction refers to that the smart gateway extracts a plan execution instruction from the matched learning control instruction according to the environment context information, and controls the system to execute the plan execution instruction; the optimized learning control instruction is The intelligent gateway corrects the result option included in the response according to the learning control instruction, modifies the attribute and the attribute value included in the triggering condition of the learning control instruction corresponding to the learning control instruction, and updates the learning control instruction knowledge base;

Optionally, the learning control instruction knowledge base is downloaded from the network platform by the smart gateway, and stored in a local system of the smart gateway, where the version of the knowledge base is maintained by the network platform;

Optionally, the learning control instruction triggering condition may be defined by a quintuple <T, U, L, E, P>, including five attributes and corresponding attribute values, wherein the attribute T represents time, and the attribute U represents user account information. The attribute L represents user location information, the attribute E represents home environment information (temperature, humidity, illuminance, noise, etc.), and the attribute P indicates that operation instruction information or system internal state information has occurred; the trigger condition quintuple has at least attribute values One is not null (Null).

Optionally, the above-mentioned plan execution instruction is defined by a tuple <S>, where S represents a plan execution instruction, including at least one executable instruction information;

The above learning control instruction includes a learning control instruction trigger condition and a planned execution instruction, which are defined by a binary group <I, S>, wherein I represents the above learning control instruction trigger condition quintuple information <T, U, L, E, P >, S represents the above plan execution instruction;

Optionally, the method for tracking the environment context information by the smart gateway includes active acquisition and passive acquisition, and the active acquisition refers to the intelligent gateway actively acquiring the environment from the internal system operation of the intelligent gateway, the external controlled device or the network platform according to the system setting policy. Context information; passive acquisition refers to passively receiving user's operation instructions and passively receiving information data reported by an externally controlled device;

The above-mentioned plan execution instruction is pre-configured in the system, and according to the pre-configured plan execution instruction, the system automatically learns the user behavior habits, acquires the learning control instruction trigger condition matching the above-mentioned plan execution instruction, thereby determining the learning control instruction set and learning. Control instruction knowledge base;

Optionally, FIG. 8 is a flowchart of a learning control instruction learning method in a smart home control method according to an embodiment of the present invention. The learning control instruction learning step is as shown in FIG.

Step S802, the smart gateway continuously acquires all environment context information related to the learning control instruction, and saves the information to the system;

Step S804, when the smart gateway detects that the pre-configured plan execution instruction occurs, according to the characteristics of the system setting and the plan execution instruction, the environment context information during the period when the plan execution instruction occurs or occurs before is generated from the system;

Step S806, the smart gateway uploads the planned execution instruction and related environment context information to the network platform;

Step S808, the network platform analyzes the environment context information, and determines that the learning control instruction trigger condition quintuple information corresponding to the plan execution instruction is combined into a candidate learning control instruction, and is stored in the candidate learning control instruction table;

Step S810, the network platform collects the candidate learning control instructions for a period of time, and analyzes each candidate learning control instruction table. When the frequency and number of occurrences of the candidate learning control instruction of a certain characteristic or a certain characteristic satisfy a certain ratio and a threshold, Then, the candidate learning control instruction is determined as a training control instruction that is successfully trained, and is combined and stored in the learning control instruction knowledge base.

Optionally, the above intelligent control method adopts a fuzzy theory analysis and control method;

Optionally, the uplink port of the smart gateway is connected to the network platform, and the connection manner includes but is not limited to Ethernet, WiFi, Passive Optical Network (PON), and third generation mobile communication system (3G). / fourth generation mobile communication system (4G);

The smart gateway is connected to one or more controlled devices by means of wired communication or wireless communication, and the intelligent gateway acquires relevant information data from the controlled device or receives control instructions of the user to implement control of the controlled device; The wired communication mode between the gateway and the controlled terminal includes but is not limited to five types of network cables, coaxial cables, power lines, telephone lines, etc.; the wireless communication methods of the above intelligent gateway and the controlled terminal include but are not limited to Zigbee, wifi, Bluetooth low power consumption. (Bluetooth low energy, referred to as BLE), radio frequency (Radio Frequency, referred to as RF);

Optionally, the controlled device includes, but is not limited to, an Internet Protocol (IP) camera, a security detector terminal, a home medical terminal, a home appliance automation and energy control terminal, a smart home appliance, etc. .

An intelligent gateway applied in a smart home system, wherein the smart gateway is connected to one or more controlled devices by wired communication or wireless communication, and the intelligent gateway obtains relevant information from the controlled device and feeds back to the user or the receiving user. The control command is implemented to control the controlled device. The smart gateway is connected to the network platform by wired communication or wireless communication. FIG. 9 is a schematic diagram of the relevant unit of the intelligent gateway according to the embodiment of the present invention, and the processing unit included in the intelligent gateway As shown in Figure 9, it includes:

The storage unit 901 is configured to: save environment context information acquired by the smart gateway; and set to save the learning control instruction knowledge base;

The data collection unit 902: the intelligent gateway continuously acquires the environment context information related to the learning control instruction and saves it to the system; when the smart gateway detects that the pre-configured plan execution instruction occurs, according to the characteristics of the system setting and the planned execution instruction, Obtaining environmental context information from the system when the planned execution instruction occurs or a period of time before the occurrence; the intelligent gateway uploads the planned execution instruction and related environment context information to the network platform;

The intelligent control unit 903: the intelligent gateway queries the learning control instruction knowledge base, and compares the matching degree between the attribute and the attribute value and the environmental context information of the learning control instruction triggering condition included in the knowledge base; when a learning control instruction triggers the condition When the environment context information is matched, the intelligent gateway sends a learning control instruction correction request to the user through the human-machine interface, and the correction request includes a correction parameter option set; the intelligent gateway corrects the response according to the learning control instruction, and completes the control of the planned execution instruction. And the optimization of the learning control instruction knowledge base described above.

Optionally, in the intelligent control unit, the optimization of the learning control instruction knowledge base refers to: the intelligent gateway corrects the result option included in the response according to the learning control instruction, and modifies the attribute included in the triggering condition of the learning control instruction corresponding to the learning control instruction. Attribute value and update the learning control instruction knowledge base;

The communication unit 904: transmitting the environment context information and the corresponding plan execution instruction to the network platform according to the execution result of the data collection unit; receiving the control message of the intelligent control unit, and controlling the peripheral controlled terminal and the network platform;

Optionally, the communication manner between the uplink and the controlled interface of the smart gateway includes but is not limited to five types of network cables, a coaxial cable, a power line, a telephone line, a Zigbee, a wifi, a BLE, an RF, and the like;

Optionally, the uplink port of the smart gateway is connected to the network platform, and the connection manner includes but is not limited to Ethernet, WiFi, PON, and mobile 3G/4G;

A network platform is applied in a smart home system, and the network platform is connected to an intelligent gateway to implement management of management and management commands of the intelligent gateway and the user. FIG. 10 is a schematic diagram of a related unit of the network platform according to an embodiment of the present invention. A schematic diagram of a processing unit is shown in FIG. 10, including:

The storage unit 1001 is configured to: save a plan execution instruction uploaded by the smart gateway and related environment context information; set to save a candidate learning control instruction table; and set to save the learning control instruction knowledge base;

The learning unit 1002: the network platform analyzes the environment context information, and determines the learning control instruction trigger condition quintuple information corresponding to the plan execution instruction, and combines them into a candidate learning control instruction, and stores them in the candidate learning control instruction table; The network platform collects the candidate learning control instruction for a period of time, and analyzes the candidate learning control instruction table. When the probability or the number of occurrences of a candidate learning control instruction is greater than a certain ratio or threshold, determining the candidate learning control instruction as training Successful learning control instructions are stored in the learning control instruction knowledge base. Complete the update of the knowledge base according to the knowledge base adjustment request transmitted by the intelligent gateway;

The communication unit 1003: sends a learning control instruction knowledge base to the smart gateway according to the processing result of the learning unit; and is configured to receive the plan execution instruction and related environment context information uploaded by the smart gateway; and receive the knowledge base update sent by the smart gateway device.

The optional embodiment is illustrated by a typical smart home system. The system includes a smart home network platform (hereinafter referred to as a network platform) deployed in the network, an intelligent gateway deployed in the owner's home, and a plurality of door and window magnetic detectors and infrared detection. , intelligent switch panel, smart socket, infrared forwarding controller (can control the on/off of white goods such as water heaters and air conditioners) Wait. The intelligent gateway accesses the home wireless router through the wired mode and accesses the network platform through the resident network; the sensors such as the door and window magnetic, infrared detector, and infrared forwarding controller are wirelessly connected to the intelligent gateway through the RF433Mhz; the owner carries the dedicated RF433Mhz The wireless remote control device can communicate with the intelligent gateway through the wireless remote controller, and can complete the arming and disarming of the smart home security system at home, or the owner remotely controls the opening of the home air conditioner through the smart phone-specific application (Application, referred to as APP). / Turn off, or control the lighting in your home through the smart switch panel. FIG. 11 is a schematic diagram of a smart home network according to an embodiment of the present invention, with reference to a smart home system network diagram 11.

The following is an example of turning on the air conditioner.

In an alternative embodiment, consider the normal use scenario of the owner: when the weather is hot (for example, above 33 degrees), the owner usually starts to open the air conditioning system in the home in advance through the smartphone-specific APP at 6 o'clock in the afternoon. It is guaranteed that when you arrive home at 6:30, your home can stay at around 24 degrees in the air conditioner.

The detailed implementation process is as follows:

In this alternative embodiment, the system pre-configuration plan execution instruction S1 = "turn on the air conditioner", so that the system performs the learning process in a targeted and efficient manner.

In the optional embodiment, the intelligent gateway and the network platform first collect the behavior data of the owner through a long period of operation (default 30 days), and perform data analysis, and finally obtain the learning control instruction related to the plan execution instruction. Implementation steps include:

Step S11: The above-mentioned intelligent gateway periodically acquires all the environment context information related to the learning control instruction, and saves it to the system. In this embodiment, the environment context information related to S1 “turning on the air conditioner” includes at least “turning on the air conditioner through the remote controller” Time, the temperature at home when the air conditioner is turned on"; after the intelligent gateway obtains the above environmental context information, it is saved in the intelligent gateway through the storage unit;

Step S12: When the smart gateway detects that a predefined plan execution instruction occurs, according to the characteristics of the system setting and the planned execution instruction, the environment context information of the system execution instruction is generated or occurs for a period of time before the occurrence of the planned execution instruction; In the example, when the smart gateway detects that the S1 "turn on the air conditioner" occurs, the environment context information is extracted from the "time when the air conditioner is turned on by the remote controller and the temperature at the home when the air conditioner is turned on". In this embodiment, five groups are listed, and the data is "18:00, 33", "18:06, 34", "18:09, 32", "17:56, 35", "23:03,34";

Step S13: The smart gateway uploads the plan execution instruction and the related environment context information to the network platform. In this embodiment, the smart gateway acquires an environment context that is pre-configured for 30 days in a long period of time. Upload information to the web platform;

Step S14: The network platform analyzes the environment context information, and determines that the learning control instruction trigger condition quintuple information corresponding to the plan execution instruction is combined into a candidate learning control instruction, and is stored in the candidate learning control instruction table; In this alternative embodiment, the candidate learning control instruction is expressed as follows:

Table 1-1: Schematic diagram of candidate learning control instructions

序号Serial number	候选学习控制指令Candidate learning control instruction
11	“18：00、33”\|S1“开启空调”"18:00, 33" \| S1 "turn on the air conditioner"
22	“18：06、34”\|S1“开启空调”"18:06, 34"\|S1 "turn on the air conditioner"
33	“18：09、32”\|S1“开启空调”"18:09, 32"\|S1 "turn on the air conditioner"
44	“17：56、35”\|S1“开启空调”"17:56, 35"\|S1 "turn on the air conditioner"
55	“23：03、34”\|S1“开启空调”"23:03, 34"\|S1 "turn on the air conditioner"

Step S15: The network platform collects the candidate learning control instructions for a period of time, and analyzes each candidate learning control instruction table, when the probability, the number of times, or the interval characteristics of a candidate learning control instruction meets a certain ratio, threshold, or interval. And determining, the candidate learning control instruction is a training control instruction that is successfully trained, and is combined and stored in the learning control instruction knowledge base.

In the optional embodiment, the method of fuzzy theory analysis is adopted, and the network platform analyzes and merges into a learning control instruction:

Table 1-2: Learning Control Instructions in the Alternative Embodiment

In the optional embodiment, the knowledge base including the above learning control instruction is uniformly stored in the network platform. During the running process of the system, the maintenance update of the knowledge base is completed by the network platform. To improve the efficiency of the learning control, the intelligent gateway is based on the network. The update notification of the platform automatically downloads the latest knowledge base bound to the above intelligent gateway from the network platform;

In this alternative embodiment, assume an application scenario for the owner: in summer, the weather is hot and the temperature is 33 degrees. The owner's wireless remote control ID is “yk010101”. FIG. 12 is an interaction sequence diagram according to an embodiment of the present invention. The implementation details of the foregoing intelligent control method are as shown in FIG. 12, and include:

Step S1202: The smart gateway monitors the home environment context information. In the optional embodiment s, the environment context information related to the attribute included in the learning control instruction trigger condition includes “the current time of the system, the owner wireless remote control ID number, and the current temperature of the home”. Etc; the intelligent gateway periodically detects the above information;

Step S1204: The smart gateway determines whether the environment context information matches the trigger condition of the learning control instruction. When matching, Step S1206 is performed; otherwise, step S1202 is performed; in the optional embodiment, the corresponding attribute value in the learning control instruction triggering condition includes: T=“18:00”, U=“yk010101”, E=“32-34” . In this embodiment, the environment context information is the temperature 33 degrees, the owner's remote controller ID and the system current time, satisfying the learning control command triggering condition corresponding to the S3 "turn on the air conditioner" execution instruction, so the result is a match, step S1206 is performed;

Step S1206: The smart gateway sends a learning control instruction correction request to the user through the human machine interface;

In the optional embodiment, the artificial interface is a smart phone; the owner has installed the APP software of the smart home system on the smart phone, and the smart phone communicates with the intelligent gateway through the 3G mode; optionally, the man-machine is completed. Before the interaction, the owner uses the registered account to log in to the APP software, completes the binding of the smart gateway and the account, and successfully adds peripheral sensors, including the carry-on remote control (ID=yk010101), the smart phone APP and the smart gateway have been successfully registered to the network. After the step S1204 is completed, the smart gateway detects the selection of the transmission learning control instruction correction request in the correction parameter option set, and determines that it is YES, so the learning control instruction correction request message is sent to the smart phone APP through the customized Internet protocol;

The learning control instruction correction request includes a correction parameter option set; wherein the correction parameter option set includes: sending a learning control instruction correction request: YES (NO: no transmission, YES: transmission); when sending the learning control instruction correction request is YES The modified parameter option set further includes: accepting the learning control instruction execution and canceling the subsequent modification request or accepting the learning control instruction execution (and subsequently sending the correction request each time) or prohibiting the current learning control instruction from executing or canceling the learning control instruction or (and) optimizing the learning control instruction triggering condition, including the attribute and the attribute value corresponding to the triggering condition of the learning control instruction, wherein the attribute and the attribute value include <T=“18:00”, U=“yk010101”, L=“ Empty (null), E = "32-34", P = "null">, where the T, U, E parameters allow the user to view and modify;

Step S1208: The intelligent gateway acquires and analyzes the learning control instruction correction response, and optimizes the learning control instruction or the control plan execution instruction according to the analysis result. In this embodiment, the result option included in the learning control instruction correction response and the parameter option in the learning control instruction correction request correspond to each other, and when the user smartphone APP receives the learning control instruction correction request, the mobile phone APP displays the mobile phone screen. The parameter selection in the control command correction request is provided for the user to make a selection or adjustment. In this embodiment, the result of the user selection is: the optimization learning control instruction triggering condition=YES, and the user feedback obtained by the intelligent gateway is E=” 32-38”, that is, the upper limit of the trigger condition for the user to adjust the ambient temperature to 38 degrees, in order to better adapt to the sudden high temperature weather, other options are not selected;

Step S1210: After receiving the response message, the smart gateway modifies the learning control instruction triggering condition to be <T=“18:00”, U=“yk010101”, L=“null”, E=“32-38”, P = "null">, subsequent planned execution instruction control will be implemented according to the new learning control instruction trigger condition. The current plan execution instruction also satisfies the new learning control instruction trigger condition, so the system executes the plan execution instruction.

In the foregoing optional embodiment, for the above-mentioned typical smart home system, the method for tracking and detecting the environment context information by the smart gateway includes active acquisition and passive acquisition, and the active acquisition refers to the intelligent gateway running from the internal system of the intelligent gateway according to the system setting policy. The externally controlled device or the network platform actively obtains the environment context information; the passive acquisition refers to passively receiving the user's operation instruction and passively receiving the information data reported by the externally controlled device, and the acquired environmental context information includes but is not limited to time information and users. Account information, user location information, temperature, humidity, illuminance, noise, room in the home environment The internal air indicator and the user control appliance switch message, the security cloth disarming message, the alarm release message, the camera video control message, the motion detection message actively reported by the camera, the triggered alarm message of the active magnetic report of the door magnetic field, and the triggering alarm triggered by the infrared detector actively reporting The message, the smoke detector actively reports the triggering alarm message, etc.;

In the optional embodiment, the intelligent control method uses a fuzzy theory analysis and control method;

In the optional embodiment, the uplink port of the smart gateway is connected to the network platform, and the connection manner includes but is not limited to Ethernet, WiFi, PON, and mobile 3G/4G;

The smart gateway is connected to one or more controlled devices by means of wired communication or wireless communication, and the intelligent gateway acquires relevant information data from the controlled device or receives control instructions of the user to implement control of the controlled device; The wired communication mode between the gateway and the controlled terminal includes but is not limited to five types of network cables, coaxial cables, power lines, telephone lines, etc.; the wireless communication methods of the smart gateway and the controlled terminal include but are not limited to Zigbee, wifi, BLE, RF;

In the optional embodiment, the controlled device includes a smart panel, a smart socket or an infrared remote control transponder, a temperature sensor, and the like.

An intelligent gateway used in a smart home system. In this embodiment, the intelligent gateway is connected to one or more controlled devices by means of wired communication or wireless communication, and the intelligent gateway obtains relevant information feedback from the controlled device. The user or the user receives the control command to control the controlled device. The smart gateway uplink is connected to the network platform by wired communication or wireless communication. The smart gateway features include:

The storage unit is configured to save the environment context information acquired by the intelligent gateway; and is configured to save the learning control instruction knowledge base; in the optional embodiment, the intelligent gateway tracks and detects the environmental context information related to the S1 “turning on the air conditioner”, and data (only List the data submitted in this embodiment) as "18:00, 33", "18:06, 34", "18:09, 32", "17:56, 35", "23:03,34"; After the learning control instruction knowledge base is successfully trained, the storage unit will permanently store the knowledge base in a flash table (flash) through a data table or a configuration form. For example, in the present embodiment, the knowledge base includes a learning control instruction.

The data collection unit (corresponding to the above-mentioned monitoring module 22): the intelligent gateway continuously acquires the environment context information related to the learning control instruction and saves it to the system; when the intelligent gateway detects that the pre-configured plan execution instruction occurs, according to the system setting and planning Executing the characteristics of the instruction, obtaining environment context information from the system when the planned execution instruction occurs or a period of time before the occurrence; the intelligent gateway uploads the planned execution instruction and related environment context information to the network platform;

An intelligent control unit (corresponding to the above-mentioned control module 24): the intelligent gateway queries the learning control instruction knowledge base, and compares the matching degree between the attribute and the attribute value of the learning control instruction triggering condition included in the knowledge base and the environment context information; When the triggering condition of the learning control instruction matches the environmental context information, the intelligent gateway sends a learning control instruction correction request to the user through the human-machine interface, where the correction request includes a modified parameter option set; the intelligent gateway corrects the response according to the learning control instruction. The control of the above-mentioned plan execution instruction and the optimization of the above-mentioned learning control instruction knowledge base are completed. The optimization of the learning control instruction knowledge base in the intelligent control unit refers to that the intelligent gateway modifies the result option included in the response control command according to the learning control instruction, and modifies the genus included in the triggering condition of the learning control instruction corresponding to the learning control instruction. And the attribute value, and update the learning control instruction knowledge base; in this embodiment, the control unit execution manner, refer to steps S1204, S1206, S1208 in this embodiment;

The communication unit: sends the environment context information and the corresponding plan execution instruction to the network platform according to the execution result of the data collection unit; receives the control message of the intelligent control unit, and controls the peripheral controlled terminal and the network platform;

The communication manner between the uplink and the controlled interface of the smart gateway includes but is not limited to five types of network cables, coaxial cables, power lines, telephone lines, Zigbee, wifi, BLE, RF, and the like;

The uplink port of the smart gateway is connected to the network platform, and the connection manner includes but is not limited to Ethernet, WiFi, PON, and mobile 3G/4G;

A network platform is applied in a smart home system. In the optional embodiment, the network platform is connected to the intelligent gateway to implement management and management command transmission of the intelligent gateway and the user. The main features include:

a storage unit (the receiving module 62 implements the function of the storage unit): configured to save a plan execution instruction uploaded by the smart gateway and related environment context information; set to save a candidate learning control instruction table; and set to save the learning control instruction knowledge base ;

a learning unit (corresponding to the learning module 64): the network platform analyzes the environment context information, and determines a learning control instruction trigger condition quintuple information corresponding to the plan execution instruction, and combines them into a candidate learning control instruction, and stores the In the candidate learning control instruction list; the network platform collects the candidate learning control instructions for a period of time, and analyzes the candidate learning control instruction table, and determines when the probability or the number of occurrences of a candidate learning control instruction is greater than a certain ratio or threshold. The candidate learning control instruction is a training control instruction that is successfully trained, and is stored in the learning control instruction knowledge base.

The communication unit (corresponding to the learning module 66) sends a learning control instruction knowledge base to the smart gateway, and is configured to receive the plan execution instruction and related environment context information uploaded by the smart gateway.

The following is an example of the shutdown of the security system.

In another optional embodiment, considering the owner's use scenario: the owner is in a home activity state from 18:30 to 22:00 in the evening, and the security system generally works in the disarmed mode. When the owner starts to sleep at 22:00, usually use the wireless remote control to switch the system working mode to sleep mode, that is, the boundary sensor such as door and window magnetic and infrared detectors is in the armed state, the system automatically turns off the lights in the home to protect the owner during the night break. Property security.

In this optional embodiment, the plan execution instruction S2=“sleep mode” is pre-configured;

In the optional embodiment, the intelligent gateway and the network platform first collect the behavior habit data of the owner through a period of operation, and perform data analysis, and finally obtain the learning control instructions related to the three plan execution instructions, and the implementation steps include:

Step S21: The above-mentioned intelligent gateway periodically acquires all the environment context information related to the learning control instruction, and saves it to the system. In this embodiment, the environment context information related to the S2 “sleep mode” includes at least the “time of the sleep mode trigger, The wireless remote controller identifier (Identity, abbreviated as ID) number; the smart gateway obtains the above environment context information, and saves it in the smart gateway through the storage unit;

Step S22: When the smart gateway detects that a predefined plan execution instruction occurs, according to the characteristics of the system setting and the plan execution instruction, the environment context information of the system execution instruction is generated or occurs for a period of time before the occurrence of the planned execution instruction; In the example, when the smart gateway detects that the S2 "sleep mode" occurs, the "sleep mode trigger time and the wireless remote controller ID number" are extracted from the environment context information. In this embodiment, five groups are listed, and the data is "22: 10, yk010101", "22:01, yk010101", "23:50, yk010101", "22:04, yk010101", "22:00, yk010101";

Step S23: The smart gateway uploads the planned execution instruction and the related environment context information to the network platform. In this embodiment, the smart gateway acquires a long period of time (this time can be pre-configured for 30 days or longer). The environment context information is uploaded to the network platform;

Step S24: The network platform analyzes the environment context information, and determines that the learning control instruction trigger condition quintuple information corresponding to the plan execution instruction is combined into a candidate learning control instruction, and is stored in the candidate learning control instruction table; In this embodiment, the candidate learning control instruction is expressed as follows:

Table 2-1: Schematic Table of Candidate Learning Control Instructions

序号Serial number	候选学习控制指令Candidate learning control instruction
66	“22：10、yk010101”\|S2“睡眠模式”"22:10, yk010101"\|S2 "Sleep Mode"
77	“22：01、yk010101”\|S2“睡眠模式”"22:01, yk010101"\|S2 "Sleep Mode"
88	“23：50、yk010101”\|S2“睡眠模式”"23:50, yk010101"\|S2 "Sleep Mode"
99	“22：04、yk010101”\|S2“睡眠模式”"22:04, yk010101"\|S2 "Sleep Mode"
1010	“22：00、yk010101”\|S2“睡眠模式”"22:00, yk010101"\|S2 "Sleep Mode"

Step S25: The network platform collects the candidate learning control instructions for a period of time, and analyzes each candidate learning control instruction table, when the probability, the number of times, or the interval characteristics of a candidate learning control instruction meets a certain ratio, threshold, or interval. And determining, the candidate learning control instruction is a training control instruction that is successfully trained, and is combined and stored in the learning control instruction knowledge base.

In the optional embodiment, the method of fuzzy theory analysis is adopted, and after the network platform analyzes, the induction is merged into one learning control instruction:

Table 2-2: Learning Control Instructions in this Embodiment

In this alternative embodiment, assume that one of the owner's usage scenarios is as follows: In summer, the weather is hot and the temperature is 33 degrees, and the owner goes to bed at 22:06 in the evening. The owner's wireless remote control ID is “yk010101”. Under the premise that the intelligent gateway has acquired the knowledge base of the learning control instruction, the implementation details of the above intelligent control method are as follows:

Step S211: The smart gateway monitors the home environment context information. In this embodiment, the environment context information related to the attribute included in the learning control instruction triggering condition includes “the current time of the system, the owner wireless remote controller ID number”; the intelligent gateway is from the above hypothetical scenario. The obtained environmental context information includes "system current time";

Step S212: The smart gateway determines whether the environment context information matches the learning control instruction triggering condition, and if yes, step S213 is performed; otherwise, step S211 is performed; in this embodiment, the corresponding attribute value in the learning control instruction triggering condition includes: = "yk010101" and T = "22:10". In this embodiment, the environment context information is the owner's remote controller ID and the system time T (the current time when the gateway collects the environment context information), and satisfies the learning control instruction triggering condition corresponding to the S2 “sleep mode” plan execution instruction, so the present embodiment The situation is a match, so step S213 is performed, otherwise step S211 is performed;

Step S213: The smart gateway sends a learning control instruction correction request to the user through the human-machine interface. In this embodiment, the manual interface is a smart phone; the smart phone installs the APP software corresponding to the embodiment, and implements the smart gateway through WIFI or 3G. The smart gateway sends a learning control instruction correction request message to the smart phone APP through a private protocol, where the learning control instruction correction request includes a modified parameter option set; wherein the modified parameter option set includes: sending a learning control instruction correction request: YES (NO) : not sent, YES: send); when the send learning control instruction correction request is YES, the modified parameter option set further includes: accepting the learning control instruction execution and canceling the subsequent correction request or accepting the learning control instruction execution (and subsequent each time) Sending the correction request) or prohibiting the current learning control instruction from executing or canceling the learning control instruction or (and) optimizing the learning control instruction triggering condition, including the attribute and the attribute value corresponding to the triggering condition of the learning control instruction; in this embodiment, Attributes and attribute values include <T=“22:10”, U = "yk010101", L = "null", E = "null", P = "null" >;

Step S214: The intelligent gateway acquires and analyzes the learning control instruction correction response, and optimizes the learning control instruction or the control plan execution instruction according to the analysis result. In this embodiment, the result option included in the learning control command correction response and the parameter option in the learning control instruction correction request respectively correspond to each other, and the embodiment includes: prohibiting the execution of the learning control instruction from being executed = YES, and other options are not In this embodiment, the smart gateway prohibits the execution of the "sleep mode" instruction. The reason for the prohibition may be that the owner needs to rest later, but the current prohibition does not affect the execution of the subsequent sleep mode learning control instruction.

Embodiments of the intelligent gateway and network platform refer to the above-described alternative embodiments.

The following takes the opening of the security system as an example.

The usage scenario involved in another optional embodiment: the owner carries the wireless remote controller with the wireless remote control, and the remote controller supports two-way communication, that is, receiving the wireless cycle survival detection message sent by the intelligent gateway within the coverage of the wireless radio, and replying The intelligent gateway, through this two-way detection mechanism, can determine the location of the owner at home or about to arrive home. When the owner gets off work (assuming the owner arrives at home at 18:30 pm), through the “disarming” function of the wireless remote control, the system is first disarmed, and then the entrance door is opened and the home is entered. Disarming first The reason for opening the entrance door is to prevent false alarms of the door magnetic detector that triggers the entrance door in the "disarming home" mode. Usually, the system also implements a delayed alarm mechanism in the off-home mode, that is, the owner triggers After the gate detector of the entrance door, the upcoming alarm can be cancelled within the delay time set by the system (usually 20 seconds).

In this scenario, the owner's daily behavior habits are regularly followed. When using the smart home system, the command actions in conjunction with their behavioral habits are also deterministic. This embodiment can well explain the content of the present invention, and the detailed implementation process is as follows:

In this optional embodiment, the pre-configured plan execution instruction includes S3=“system disarming”, so that the establishment of the learning control instruction knowledge base has a goal to follow;

In the optional embodiment, the intelligent gateway and the network platform first collect the behavior habit data of the owner through a period of operation, and perform data analysis, and finally obtain the learning control instruction of the S3, and the implementation steps include:

Step S31: The above-mentioned intelligent gateway periodically acquires all the environment context information related to the learning control instruction, and saves it to the system. In this embodiment, the environment context information related to S1 “system disarming” includes at least “the wireless remote controller of the service is The time detected by the intelligent gateway, the ID number of the wireless remote controller, and the time when the system is disarmed and triggered; after the intelligent gateway obtains the above environmental context information, it is saved in the intelligent gateway through the storage unit;

Step S32: When the smart gateway detects that a predefined plan execution instruction occurs, according to the characteristics of the system setting and the planned execution instruction, the environment context information of the system execution instruction when the planned execution instruction occurs or occurs before the occurrence occurs; In the example, when the intelligent gateway is detected that S1 “system disarming” occurs, the time when the owner's wireless remote controller is detected by the intelligent gateway, the ID number of the wireless remote controller, and the time when the system is disarmed is extracted from the environment context information. "This embodiment lists 5 groups, the data is "18:28, yk010101, 18:31", "18:30, yk010101, 18:33", "18:24, yk010101, 18:38", "18: 25, yk010101, 18:28", "10:26, yk010101, 8:00";

Step S33: The smart gateway uploads the plan execution instruction and related environment context information to the network platform. In this embodiment, the smart gateway acquires a long period of time (this time can be pre-configured for 30 days or longer). The environment context information is uploaded to the network platform;

Step S34: The network platform analyzes the environment context information, and determines a learning control instruction trigger condition quintuple information corresponding to the plan execution instruction, and combines them into a candidate learning control instruction, and stores the information in a candidate learning control instruction table; In this alternative embodiment, the candidate learning control instruction is expressed as follows:

Table 3-1: Schematic diagram of candidate learning control instructions in Embodiment 3

序号Serial number	候选学习控制指令Candidate learning control instruction
11	“18：28、yk010101、18：31”\|S1“系统撤防”"18:28, yk010101, 18:31"\|S1 "System Disarming"
22	“18：30、yk010101、18：33”\|S1“系统撤防”"18:30, yk010101, 18:33"\|S1 "System Disarming"
33	“18：24、yk010101、18：38”\|S1“系统撤防”"18:24, yk010101, 18:38"\|S1 "System Disarming"
44	“18：25、yk010101、18：28”\|S1“系统撤防”"18:25, yk010101, 18:28"\|S1 "System Disarmed"
55	“10：26、yk010101、08：00”\|S1“系统撤防”"10:26, yk010101, 08:00"\|S1 "System Disarming"

Step S35: The network platform collects candidate learning control instructions for a period of time, and analyzes each candidate learning control instruction. A table, when a probability, a number of times, or an interval characteristic of a candidate learning control instruction satisfies a certain ratio, a threshold, or an interval, determining that the candidate learning control instruction is a training control instruction that is successfully trained, and combining and storing in learning Control command knowledge base.

Table 3-2: Learning Control Instructions in Embodiment 3

In this alternative embodiment, assume that one of the owner's usage scenarios is as follows: In summer, the weather is hot and the temperature is 33 degrees. After the owner gets off work, he arrives at home on time at 18:29 minutes, and the intelligent gateway detects the owner's wireless remote controller at 18:27. The implementation details of the above intelligent control method are as follows:

Step S301: The intelligent gateway monitors the environment context information. In this embodiment, the environment context information related to the attribute included in the learning control instruction triggering condition includes: “the current time of the system, the time when the wireless remote controller of the owner is detected by the intelligent gateway, and the wireless remote control of the owner. The device ID number"; the environment context information obtained by the intelligent gateway from the above hypothetical scenario includes "the current time of the system, the time when the owner wireless remote controller is detected is 18:27";

Step S302: The smart gateway determines whether the environment context information matches the learning control instruction triggering condition. When the matching is performed, step S303 is performed; otherwise, step S301 is performed; in this embodiment, the corresponding attribute value in the learning control instruction triggering condition includes: P = "18:24~18:30"|Time when the owner's wireless remote controller is detected by the intelligent gateway, U=“yk010101”, and system time T (current time when the gateway collects environmental context information). In this embodiment, the environment context information is the remote controller ID of the owner, and the time 18:27 detected by the intelligent remote controller of the owner is satisfied by the learning control instruction triggering condition corresponding to the S1 “system disarming” plan execution instruction, so The implementation is a match, so step S303 is performed, otherwise step S301 is performed;

Step S303: The smart gateway sends a learning control instruction correction request to the user through the human-machine interface. In this embodiment, the manual interface is a smart phone; the smart phone installs the APP software corresponding to the embodiment, and implements the smart gateway through WIFI or 3G. The smart gateway sends a learning control instruction correction request message to the smart phone APP through a private protocol, where the learning control instruction correction request includes a modified parameter option set; wherein the modified parameter option set includes: sending a learning control instruction correction request: YES (NO) : not sent, YES: send); when the send learning control instruction correction request is YES, the modified parameter option set further includes: accepting the learning control instruction execution and canceling the subsequent correction request or accepting the learning control instruction execution (and subsequent each time) Send a correction request) or prohibit the execution of this learning control instruction or cancel the learning The control instruction or (and) the optimization learning control instruction triggering condition includes the attribute and the attribute value corresponding to the triggering condition of the learning control instruction; in this embodiment, the attribute and the attribute value included include <T=“P”|system disarming triggering Time, U=“yk010101”, L=“null”, E=“null”, P=“18:24～18:30”|Time when the owner's wireless remote controller is detected by the intelligent gateway>;

Step S304: The intelligent gateway acquires and analyzes the learning control instruction correction response, and optimizes the learning control instruction or the control plan execution instruction according to the analysis result. In this embodiment, the result option included in the learning control instruction correction response and the parameter option in the learning control instruction correction request respectively correspond to each other, and the embodiment includes: accepting the learning control instruction execution and canceling the subsequent correction request=YES, other None of the options are selected; in this embodiment, the intelligent gateway control system executes the S1 system disarming instruction and does not adjust the learning control instruction trigger condition.

Embodiments of the intelligent gateway and network platform refer to the above embodiments.

In summary, the optional embodiment reduces the complexity of the smart home system control, improves the efficiency and accuracy of the system intelligent learning control, thereby significantly improving the user experience and comfort.

Industrial Applicability: As can be seen from the above description, the present invention learns at least the condition corresponding to one or more executions of the instruction to obtain a predetermined rule. When the condition that triggers the execution of the instruction meets the predetermined rule, the execution of the control instruction is compared with The execution of the instructions in the related art is mainly passively accepting the manual control of the user, or controlling according to the personalized pre-configured data of the user. The above steps can automatically learn the predetermined rules to reduce the manual participation of the user, thereby solving the problem that the related technology cannot be used for the smart home. The operation mode of the system is flexibly controlled, thereby implementing flexible control of the operation mode of the smart home system, simplifying operation and improving the user experience.

In another embodiment, software is also provided for performing the technical solutions described in the above embodiments and alternative embodiments.

In another embodiment, a storage medium is further provided, wherein the software includes the above-mentioned software, including but not limited to: an optical disk, a floppy disk, a hard disk, an erasable memory, and the like.

It will be apparent to those skilled in the art that the various modules or steps of the present invention described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein. The steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module. Thus, the invention is not limited to any specific combination of hardware and software.

The above description is only an alternative embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes can be made to the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the present invention.

Claims

An instruction processing method includes:

Monitoring the conditions that trigger the execution of the instruction;

The execution of the instruction is controlled in a case where the condition meets a predetermined rule, wherein the predetermined rule is obtained by learning at least a condition corresponding to one or more executions of the instruction.
The method of claim 1 wherein, in the event that the condition meets a predetermined rule, controlling execution of the instruction comprises:

Modifying the predetermined rule when the condition meets the predetermined rule;

Receiving a response to the modification prompt;

Controlling execution of the instruction according to the response, wherein the instruction is executed if the predetermined rule is not revised according to the response confirmation; in the case of revising the predetermined rule according to the response confirmation, The instruction is executed if the condition meets the revised predetermined rule.
The method of claim 2 wherein the response is for indicating at least one of:

The instruction is not executed for the case where the condition described above meets the predetermined rule;

Cancel the predetermined rule;

After the execution of the instruction, the modification prompt is not performed on the predetermined rule;

After the execution of the instruction, the modification prompt is performed each time the condition meets the predetermined rule or the revised predetermined rule.
The method of claim 2, wherein

The prompting the modification to the predetermined rule includes: determining, according to a pre-configured option, whether the modification prompt is performed on the predetermined rule, and if the determination result is yes, performing the modification prompt;

In the case where the determination result is negative, controlling the execution of the instruction includes: executing the instruction.
The method of any of claims 1 to 4, wherein the predetermined rules are stored locally or from other network elements.
The method according to any one of claims 1 to 4, wherein the predetermined rule comprises at least one of the following:

Time, account information, user location information, environmental information, status information of devices that have executed the instructions, or instructions that have been sent to the device, wherein the account information is used to identify the device.
The method according to any one of claims 1 to 4, wherein the monitoring of the condition for triggering execution of the instruction comprises:

Monitoring the conditions that trigger the execution of the instruction according to a preset policy; or,

After receiving the operation command, the condition triggering the execution of the instruction is monitored.
The method according to any one of claims 1 to 4, wherein before the condition of triggering execution of the instruction is monitored, the method further comprises:

Sending the corresponding condition when the instruction is executed one or more times to other network elements, wherein the other network element is a network element that learns the condition corresponding to one or more executions of the instruction to obtain the predetermined rule ;or,

The predetermined rule is obtained by locally learning the condition corresponding to one or more executions of the instruction.
The method according to claim 8, wherein learning the corresponding condition when the instruction is executed one or more times to obtain the predetermined rule comprises:

The predetermined rule is obtained by merging or summarizing the same or similarities in the conditions corresponding to the execution of the instructions multiple times.
An instruction processing method includes:

The condition corresponding to receiving one or more executions of the instruction;

Learning the condition to obtain a predetermined rule, wherein the predetermined rule is used to indicate that the subject receiving the predetermined rule controls execution of the instruction if the condition meets the predetermined rule;

Sending the predetermined rule.
The method of claim 10, wherein the predetermined rule comprises at least one of:

Time, account information, user location information, environmental information, status information of devices that have executed the instructions, or instructions that have been sent to the device, wherein the account information is used to identify the device.
The method of claim 10, wherein learning the condition to obtain the predetermined rule comprises:

The predetermined rule is obtained by merging or summarizing the same or similarities in the conditions corresponding to the execution of the instructions multiple times.
An instruction processing device includes:

a monitoring module configured to monitor conditions for triggering execution of the instruction;

And a control module configured to control execution of the instruction if the condition meets a predetermined rule, wherein the predetermined rule is obtained by learning at least a condition corresponding to one or more executions of the instruction.
The apparatus of claim 13 wherein said control module comprises:

a prompting unit, configured to modify the predetermined rule when the condition meets the predetermined rule;

a receiving unit, configured to receive a response to the modification prompt;

a first execution unit configured to control execution of the instruction in response to the response, wherein Assuming that the predetermined rule is not revised, the instruction is executed;

And a second execution unit configured to execute the instruction if the condition meets the revised predetermined rule in a case where the predetermined rule is revised according to the response confirmation.
The apparatus of claim 14, wherein the response is for indicating at least one of:

The instruction is not executed for the case where the condition described above meets the predetermined rule;

Cancel the predetermined rule;

After the execution of the instruction, the modification prompt is not performed on the predetermined rule;

After the execution of the instruction, the modification prompt is performed each time the condition meets the predetermined rule or the revised predetermined rule.
The apparatus according to claim 14, wherein the prompting unit is further configured to determine whether to perform the modification prompt on the predetermined rule according to a pre-configured option, and if the determination result is yes, perform the modification prompt And in the case that the determination result is negative, controlling execution of the instruction includes: executing the instruction.
Apparatus according to any one of claims 13 to 16, wherein the predetermined rules are stored locally or from other network elements.
The apparatus according to any one of claims 13 to 16, wherein the predetermined rule comprises at least one of the following:

Time, account information, user location information, environmental information, status information of devices that have executed the instructions, or instructions that have been sent to the device, wherein the account information is used to identify the device.
The apparatus according to any one of claims 13 to 16, wherein the monitoring module is further configured to monitor the condition of triggering the execution instruction according to a preset policy; or, after receiving the operation instruction, monitoring the trigger execution instruction The conditions described.
The device according to any one of claims 13 to 16, wherein the device further comprises:

a sending module, configured to send the corresponding condition when the instruction is executed one or more times to another network element, where the other network element learns the condition corresponding to one or more executions of the instruction The network element of the predetermined rule;

The learning module is configured to learn the corresponding condition when the instruction is executed one or more times locally to obtain the predetermined rule.
The apparatus of claim 20, wherein the learning module is further configured to obtain the predetermined rule by merging or summarizing the same or similarities in the conditions corresponding to the execution of the instructions multiple times.
An instruction processing device includes:

a receiving module, configured to receive a condition corresponding to one or more executions of the instruction;

a learning module, configured to learn the condition to obtain a predetermined rule, wherein the predetermined rule is used to indicate that the subject receiving the predetermined rule controls execution of the instruction if the condition meets the predetermined rule;

A sending module is configured to send the predetermined rule.
The apparatus of claim 22, wherein the predetermined rule comprises at least one of:

Time, account information, user location information, environmental information, status information of devices that have executed the instructions, or instructions that have been sent to the device, wherein the account information is used to identify the device.
The apparatus of claim 22, wherein the learning module is further configured to obtain the predetermined rule by merging or summarizing the same or similarities in the conditions corresponding to the execution of the instructions multiple times.