CN114999472A - Air conditioner control method and device and air conditioner - Google Patents
Air conditioner control method and device and air conditioner Download PDFInfo
- Publication number
- CN114999472A CN114999472A CN202210456438.5A CN202210456438A CN114999472A CN 114999472 A CN114999472 A CN 114999472A CN 202210456438 A CN202210456438 A CN 202210456438A CN 114999472 A CN114999472 A CN 114999472A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- user
- information
- voice
- voiceprint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 89
- 230000004044 response Effects 0.000 claims description 30
- 238000004891 communication Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000004378 air conditioning Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 9
- 206010063385 Intellectualisation Diseases 0.000 abstract description 5
- 238000000605 extraction Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 230000033228 biological regulation Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 210000000721 basilar membrane Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003928 nasal cavity Anatomy 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 210000002105 tongue Anatomy 0.000 description 1
- 210000000515 tooth Anatomy 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
- F24F11/58—Remote control using Internet communication
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/20—Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
- G10L17/24—Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Signal Processing (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides an air conditioner control method, an air conditioner control device and an air conditioner, wherein the method comprises the following steps: receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner; acquiring voiceprint information of a user according to the awakening voice; acquiring a first confidence coefficient that a user belongs to a target group according to voiceprint information; and if the first confidence coefficient is determined to be larger than or equal to a first threshold value, controlling the air conditioner to be switched to a first operation mode suitable for the target crowd. According to the air conditioner control method and device and the air conditioner, the voiceprint matching can be carried out according to the awakening voice of the user so as to determine the age identity of the user, the temperature and humidity control operation of the air conditioner can be automatically carried out so as to switch to the operation mode suitable for the age identity, the humanization, the intellectualization and the interaction of the air conditioner are effectively improved, convenience can be particularly provided for special people, and the most suitable feeling and experience are provided for the special people.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to an air conditioner control method and device and an air conditioner.
Background
In the current air conditioner market, the interaction process of the voice air conditioner is mostly mechanical question and answer, and although humanized answer free from mechanical answer exists, the intelligent degree is far from meeting the use requirement of a user in the current period.
For example: aiming at the old people, the use habits, the environmental temperature, the humidity and the like of the air conditioner of the old people are different. Based on this, need urgently need when the user opens the air conditioner, can discern the identity information of user's age, use habit, and then can be automatic for it adjusts the air conditioner to suitable mode to improve user's comfort level.
In the prior art, a registered voiceprint recognition method is adopted, namely, a user inputs corresponding voice to a system according to a section of provided characters by the user using an air conditioner at an app end, and then the voice is bound or memorized through a background. When the user performs identity authentication, the user must accurately input the segment of characters to realize effective authentication, and the realization difficulty is very high for some special people, such as the old or children.
Disclosure of Invention
The invention provides an air conditioner control method, an air conditioner control device and an air conditioner, which are used for solving the defects that a registered voiceprint recognition method adopted by the prior art needs a user to accurately input pre-input characters, so that the man-machine interaction is complex and the air conditioner is not suitable for special people.
In a first aspect, the present invention provides an air conditioner control method, including:
receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner;
acquiring voiceprint information of the user according to the awakening voice;
acquiring a first confidence coefficient that the user belongs to a target group according to the voiceprint information;
and if the first confidence coefficient is determined to be larger than or equal to a first threshold value, controlling the air conditioner to be switched to a first operation mode suitable for the target crowd.
According to the air conditioner control method provided by the invention, after the first confidence that the user is attributed to the target group is obtained, the method further comprises the following steps:
if the first confidence coefficient is determined to be smaller than a first threshold value but larger than a second threshold value, outputting a first prompt;
if the first answer voice of the user aiming at the first prompt is not received within a first preset time length, controlling the air conditioner to operate in an original operation mode;
the first prompt is used for inquiring whether the user starts the first operation mode; the original operation mode is based on an operation mode of the air conditioner at the end of the last operation period.
According to the air conditioner control method provided by the invention, if a first response voice of the user for the first prompt is received within a first preset time length;
acquiring a first response semantic of the first response voice;
if the user intention is determined to be the opening of the first operation mode according to the first response semantics, controlling the air conditioner to be switched to the first operation mode;
and if the user intention is determined not to start the first operation mode according to the first response semantics, controlling the air conditioner to operate the original operation mode.
According to the air conditioner control method provided by the invention, if the first confidence coefficient is determined to be less than or equal to the second threshold value, the air conditioner is controlled to operate in the original operation mode.
According to the air conditioner control method provided by the invention, acquiring the voiceprint information of the user according to the awakening voice comprises the following steps:
under the condition of non-strong noise, extracting the Mel frequency cepstrum coefficient characteristic of the awakening voice in the short-time frequency spectrum to be used as the voiceprint information;
and under the condition of strong noise, extracting at least one of the power normalization cepstrum coefficient characteristic, the Gamma atom frequency cepstrum coefficient characteristic and the time-frequency Gabor filtering characteristic of the awakening voice as the voiceprint information.
According to the air conditioner control method provided by the invention, according to the voiceprint information, the first confidence that the user is belonged to the target crowd is obtained, and the method comprises the following steps:
comparing the voiceprint information with all voiceprint sample information in a voiceprint model library;
screening out target voiceprint sample information with the highest similarity to the voiceprint information in the voiceprint model library;
and taking the crowd corresponding to the target voiceprint sample information as a target crowd to which the user belongs, and taking the similarity as a first confidence coefficient of the target crowd to which the user belongs.
The air conditioner control method provided by the invention further comprises the following steps: after obtaining the voiceprint information of the user, the method further comprises the following steps:
according to the voiceprint information, obtaining the confidence coefficient that the user is identified as any family member, and setting the highest confidence coefficient as a second confidence coefficient;
if the second confidence is determined to be larger than or equal to a third threshold, acquiring the identity information of the family member corresponding to the second confidence, and starting a function of replying a nickname; the identity information comprises nickname information;
if the second confidence is smaller than a third threshold value, outputting a second prompt; the second prompt is used for prompting the user to input a nickname;
if a second response voice of the user for the second prompt is received within a second preset time length;
and extracting nickname information from second response semantics corresponding to the second response voice, and storing the nickname information into a cloud platform family information base.
According to the air conditioner control method provided by the invention, the obtaining of the confidence level that the user is identified as any family member according to the voiceprint information comprises the following steps:
comparing the voiceprint information with voiceprint sample information of each family member in the cloud platform family information base;
and setting the comparison result as the confidence level that the user is identified as each family member.
According to the air conditioner control method provided by the invention, after the air conditioner is controlled to be switched to the first operation mode suitable for the target crowd, the method further comprises the following steps:
receiving a control instruction input by the user to respond to the control instruction to control the air conditioner to be switched from the first operation mode to a second operation mode;
and uploading the second operation mode, the identity information of the user, the environment temperature and humidity information and the current date information to the cloud platform family information base together.
According to the air conditioner control method provided by the invention, after receiving the wake-up voice input by the user, the method further comprises the following steps:
according to the awakening voice, determining the direction information of the user before the air conditioner;
and adjusting the direction of the swing blade of the air conditioner based on the direction information, so that the wind direction of the circulating wind blown out from the air outlet of the air conditioner deviates from the direction of the user.
In a second aspect, the present invention also provides an air conditioning control apparatus, including:
the voice acquisition unit receives a wake-up voice input by a user so as to respond to the wake-up voice to start the air conditioner;
a voiceprint extraction unit, configured to obtain voiceprint information of the user according to the wake-up voice;
the user identification unit is used for acquiring a first confidence coefficient that the user belongs to a target group according to the voiceprint information;
and the operation control unit is used for controlling the air conditioner to be switched to a first operation mode suitable for the target crowd under the condition that the first confidence coefficient is determined to be greater than or equal to a first threshold value.
In a third aspect, the present invention provides an air conditioner comprising: the air conditioner comprises an air conditioner body, wherein a processor, a voice acquisition device and a wireless communication device are arranged in the air conditioner body, and the voice acquisition device and the wireless communication device are arranged on the air conditioner body;
the air conditioner control method further comprises a memory and a program or an instruction which is stored on the memory and can be run on the processor, and the program or the instruction is executed by the processor to execute the air conditioner control method according to any one of the first aspect.
In a fourth aspect, the present invention provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the air conditioner control method according to any one of the above-mentioned methods.
In a fifth aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the air conditioning control method as described in any of the above.
According to the air conditioner control method and device and the air conditioner, the voiceprint matching can be carried out according to the awakening voice of the user so as to determine the age identity of the user, the temperature and humidity control operation of the air conditioner can be automatically carried out so as to switch to the operation mode suitable for the age identity, the humanization, the intellectualization and the interaction of the air conditioner are effectively improved, the convenience can be particularly provided for special people, and the most suitable experience and experience are provided for the special people.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of an air conditioning control method according to the present invention;
FIG. 2 is a second schematic flow chart of the air conditioning control method according to the present invention;
FIG. 3 is a schematic flow chart of obtaining voiceprint information according to the present invention;
FIG. 4 is a schematic flow chart of the function of initiating reply with nickname provided by the present invention;
FIG. 5 is a schematic structural diagram of an air conditioning control device provided by the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that in the description of the embodiments of the present invention, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The terms "first," "second," and the like in this application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one.
The following describes an air conditioner control method and device provided by an embodiment of the invention with reference to fig. 1 to 6.
Fig. 1 is a schematic flow chart of an air conditioner control method provided by the present invention, as shown in fig. 1, including but not limited to the following steps:
step 101: and receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner.
Wherein, the user can be any family member; the air conditioner may be one of a wall-mounted air conditioner, a cabinet air conditioner, a ceiling air conditioner, and the like; the wake-up voice may be a voice that the user sends out an air conditioner with an on intention for controlling the air conditioner to be turned on, for example: "turn on the air conditioner", "please turn on the air conditioner", etc., and the present invention is not particularly limited thereto.
Optionally, a voice collecting device is disposed on the air conditioner, and includes a microphone array, an Analog-to-Digital Converter (ADC) chip, and a control chip (e.g., an XMOS chip). The microphone array comprises a plurality of microphones, and the ADC chip is connected with the microphones and used for converting analog signals output by the microphone array into digital signals to be output; the XMOS chip is connected with the ADC chip and used for receiving the digital signal output by the ADC chip.
And after receiving the awakening voice collected by the voice collecting device, the internal processor of the air conditioner obtains the starting intention of the user according to the semantic judgment result converted from the awakening voice, so as to control the air conditioner to be started.
Step 102: and acquiring the voiceprint information of the user according to the awakening voice.
The voiceprint information refers to a kind of sound wave spectrum carrying speech information and capable of being displayed by an electroacoustic instrument. The generation of speech is a complex physiological and physical process between the human body's speech center and the pronunciation organs. The vocal organs used by the users while speaking, including tongue, teeth, larynx, lung, nasal cavity, vary widely from person to person in terms of size and morphology, so the acoustic spectra of any two users differ.
Although, the speech acoustic characteristics of each user are both relatively stable and variable, they are not absolute and invariant. The variation can come from physiology, pathology, psychology, simulation, camouflage and is also related to environmental interference. However, since the pronunciation organs of each user are different, it is still possible to distinguish the voices of different users or determine whether the voices are the same person.
In view of the above, as an alternative embodiment, the present invention converts the wake-up speech into a log domain spectrum after acquiring the wake-up speech; based on log domain frequency spectrum, using pre-trained voiceprint information extraction model to extract voiceprint information of each frame of awakening voice.
It should be noted that, when the voiceprint information extraction is implemented, the voiceprint information extraction is implemented based on a recognition method unrelated to the text, and the voice content of the user is not specified.
Step 103: and acquiring a first confidence degree that the user belongs to a target crowd according to the voiceprint information.
The target population may be different populations classified according to age groups, for example, children with ages less than a first preset age (e.g. 7 years) are classified as one population, and children with ages more than a second preset age (e.g. 60 years) are classified as another population.
For convenience of description, in the following embodiments, the target group is taken as an example for explaining, that is, the air conditioner control method provided by the present invention is a control method serving the target group, which is the elderly, and is not to be considered as a specific limitation to the protection scope of the present invention.
Optionally, after obtaining voiceprint information corresponding to the wake-up voice of the user, uploading the voiceprint information to a cloud server through a wireless network, performing age group identification on the voiceprint information in the cloud server, so as to determine a confidence level (referred to as a first confidence level, where the unit is a percentage) that the user is an old person as a target group according to the voiceprint information, and returning the first confidence level to the air conditioner internal processor.
Step 104: and if the first confidence coefficient is determined to be larger than or equal to a first threshold value, controlling the air conditioner to be switched to a first operation mode suitable for the target crowd.
In the case that the target group is the elderly, the first operation mode is an operation mode suitable for the elderly. For the old, the original temperature, wind direction, wind speed and the like of the air conditioner are adjusted in a targeted manner, and full-automatic indoor temperature, wind amount and wind direction adjustment is achieved, so that the use experience of the old on the air conditioner is met. For convenience of description, the first operation mode suitable for the elderly may be referred to as "elder care mode" in the following embodiments.
The setting of the lifetime care mode can be pre-designed and stored in the storage unit of the internal processor of the air conditioner according to the questionnaire survey, the user return visit, the collection of the use habits of the user and the like. Thus, once the air conditioner internal processor determines that the first confidence level is greater than or equal to the first threshold value, the elder care mode is automatically invoked and controlled to be executed.
Correspondingly, in the case that the target group is a child, the first operation mode refers to an operation mode suitable for children, and details are not described here.
If the first threshold is set to be 80 (the unit is percentage), the air conditioner internal processor can make a decision according to the comparison result of the first confidence and the first threshold, namely, under the condition that the first confidence is greater than 80, the user who inputs the awakening voice is determined to be the old man, and at the moment, the air conditioner is controlled to be switched to the running mode suitable for the old man.
According to the air conditioner control method, after voiceprint matching is carried out according to the awakening voice of the user to determine the age identity of the user, temperature and humidity control operation of the air conditioner can be automatically carried out to switch to the operation mode suitable for the age identity, humanization, intellectualization and interaction of the air conditioner are effectively improved, convenience can be particularly provided for special people, and the most suitable experience and experience are provided for the special people.
Based on the content of the foregoing embodiment, as an optional embodiment, after obtaining the first confidence that the user is attributed to the target group, the method further includes:
if the first confidence coefficient is determined to be smaller than a first threshold value but larger than a second threshold value, outputting a first prompt;
if the first answer voice of the user aiming at the first prompt is not received within a first preset time length, controlling the air conditioner to operate in an original operation mode;
the first prompt is used for inquiring whether the user starts the first operation mode; the original operation mode is based on an operation mode of the air conditioner at the end of the last operation period.
Fig. 2 is a second flowchart of the air conditioner control method according to the present invention, and taking fig. 2 as an example, the first threshold is 80, and the second threshold is 70, and after the user starts the air conditioner by inputting the wake-up voice, in a case where the processor in the air conditioner determines that the user starts the voiceprint detection function of the elderly by turning on the voiceprint switch of the elderly, the collected wake-up voice is converted into a corresponding digital signal, and the corresponding digital signal is sent to the cloud server. The cloud server feeds back the first confidence coefficient that the user is the old man to an air conditioner internal processor.
Wherein, the user opens old man's voiceprint switch can be that the user realizes through clicking the corresponding virtual button on the relevant APP of air conditioner, also can set up corresponding virtual button on the air conditioner panel to supply the user to trigger.
Optionally, the air conditioner internal processor may memorize this user selection after the elderly voiceprint switch is triggered, without requiring the user to trigger each time the air conditioner is turned on, unless the user actively turns it off.
Further, the processor in the air conditioner respectively compares the first confidence with a first threshold and a second threshold, if the first confidence is larger than or equal to the first threshold, the user is determined to be the old, and the air conditioner is directly controlled to be switched to the elder care mode suitable for the old.
If the first confidence is smaller than the first threshold but larger than the second threshold, that is, between 70 and 80, it cannot be determined that the user is an elderly person, but it cannot be determined that the user is not an elderly person, and at this time, the first prompt is called by the air conditioner internal processor and played through a speaker preset on the air conditioner.
Alternatively, the first prompt may be a voice prompt such as "whether to turn on a lifetime care mode for you" or not, and the user asks whether the user turns on a similar lifetime care mode, which is not particularly limited to this invention.
Further, if the response voice of the user to the first prompt (referred to as a first response voice herein) is not received within a first preset duration (e.g., 30 seconds), the default user denies that it is an old person, i.e., the user is considered not to have to turn on the elder care mode.
Or the first answering voice of the user is received in 30 seconds, but through semantic recognition of the first answering voice, the recognized semantics are not completely relevant to whether the ancestor care mode is turned on, for example, the detected answering voice is: "now several hours" it is also assumed that the user does not need to turn on the elder care mode.
And under the condition that the user does not need to start the elder care mode, controlling the air conditioner to execute the original operation mode, namely, operating according to a normal starting mode, namely, operating based on the operation mode of the air conditioner at the end of the last operation period.
The air conditioner control method provided by the invention can automatically acquire the confidence coefficient that the current user belongs to the target population by adopting the voiceprint recognition technology, further adapt to the corresponding operation mode according to the confidence coefficient, realize the targeted adjustment and control of the original temperature, wind direction and wind speed of the air conditioner, realize the full-automatic regulation of the indoor temperature and wind speed, and achieve the effects of human-based recognition, classification treatment, accurate temperature regulation and harmonious air supply. Most importantly, a mode of re-inquiry is adopted in different intervals where the confidence coefficient is located, so that misoperation of a user can be effectively avoided.
As an alternative embodiment, referring to fig. 2, if a first response voice of the user to the first prompt is received within a first preset time period;
acquiring a first response semantic of the first response voice;
if the user intention is determined to be the opening of the first operation mode according to the first response semantics, controlling the air conditioner to be switched to the first operation mode;
and if the user intention is determined not to open the first operation mode according to the first response semantics, controlling the air conditioner to operate the original operation mode.
Taking the target population as the elderly as an example, the first operation mode is the lifetime caring mode.
If the first response voice input by the user is received within a first preset time (such as 30 seconds), performing semantic recognition on the first response voice to acquire a corresponding first response semantic.
Further, the user intent is identified according to the first answer semantic, if the first answer semantic is for wanting to open the ancestor care mode, for example, the converted first answer semantic is: an affirmative answer, right/yes/on/good, etc., controls the air conditioner to switch to the grand care mode.
However, if the converted first response semantics are: if the answer is negative, such as "don't care/don't turn on", it is determined that the first answer voice of the user is not made for the first prompt, that is, it is determined that the user does not want to turn on the elder care mode, and at this time, the air conditioner internal processor controls the air conditioner to continue to execute the original operation mode.
As another alternative embodiment, referring to fig. 2, if the air conditioner internal processor determines that the first confidence is less than or equal to the second threshold, the air conditioner is controlled to operate in the original operation mode.
When the first confidence coefficient of the target group of the user, namely the user belonging to the old people, is calculated by the server according to the awakening voice input by the user and is smaller than or equal to the second threshold value, the fact that the user is the old people cannot be accurately judged according to the awakening voice is indicated, and at the moment, the air conditioner can be controlled to operate in the original operation mode.
Optionally, after it is determined that the first confidence level is less than or equal to the second threshold, the user may also be prompted to re-input any segment of voice, so as to re-extract the voiceprint information of the user, and further re-identify the confidence level that the user belongs to the target group.
For example, play through a horn: "I did not hear your command clearly, bothers you to repeat over and over again". And when receiving the voice input again by the user, extracting corresponding voiceprint information, and further re-determining the confidence coefficient.
It should be noted that, if the confidence level that the determined user belongs to the target group is still less than or equal to the second threshold value again according to the voice input by the user, the air conditioner is directly controlled to operate in the original operation mode.
As another alternative embodiment, as shown in fig. 2, after the air conditioner is determined to be in the on state, if a wake-up voice of the user is received, performing semantic recognition on the wake-up voice to obtain the current user intention.
For example, when the semantic converted from the wake-up voice input by the user includes opening the related semantic of the lifetime care mode, it is considered that the user intends to switch the existing operation mode of the air conditioner to the lifetime care mode. If the semantics converted from the awakening voice input by the user does not include the semantics related to the opening of the elder care mode, the existing operation mode of the air conditioner is continuously kept unchanged.
The air conditioner control method provided by the invention can be used for switching to the operation mode suitable for the target group to which the user belongs according to the input voice of the user in the starting stage and the operation stage of the air conditioner, the human-computer interaction process is simple and convenient, and the control by the user is convenient.
Based on the content of the foregoing embodiment, as an optional embodiment, the above obtaining the voiceprint information of the user according to the wake-up voice may include, but is not limited to, the following steps:
under the condition of non-strong noise, extracting the Mel frequency cepstrum coefficient characteristic of the awakening voice in the short-time frequency spectrum to be used as the voiceprint information;
and under the condition of strong noise, extracting at least one of the power normalization cepstrum coefficient characteristic, the Gamma atom frequency cepstrum coefficient characteristic and the time-frequency Gabor filtering characteristic of the awakening voice as the voiceprint information.
Characteristically, in the case of non-strong noise, a Mel-Frequency Cepstrum Coefficient (MFCC) feature based on a short-time spectrum may be adopted.
The Mel frequency is extracted based on the auditory characteristics of human ears, and forms a nonlinear corresponding relation with the Hz frequency. MFCC is then the Hz spectral signature calculated using this relationship between them. Extraction of MFCCs can generally take such several steps: pre-emphasis, framing, windowing, Fast Fourier Transform (FFT), mel filter bank, and Discrete Cosine Transform (DCT), and the specific implementation steps are not described herein.
Further, in the case of strong noise, other features based on auditory perception may be employed, such as Power-Normalized Cepstral coeffients (PNCC), Gamma Frequency Cepstral Coeffients (GFCC), time-frequency Gabor filtering features, and so forth.
Among the main new features of handling PNCCs compared to MFCCs are: the power-law nonlinearity is used for replacing the traditional logarithm nonlinearity used in the MFCC coefficient, and a noise suppression algorithm for suppressing background excitation based on asymmetric filtering and a module for realizing time masking are added.
The gamma atom filter in the GFCC can simulate well the frequency selective and spectral analysis characteristics of the basilar membrane. The invention can also provide an improved algorithm on the basis of analyzing the original characteristic extraction algorithm aiming at the extraction process of the cepstrum coefficient of the Gamma atom filter, namely, wavelet packet decomposition is used for replacing Fourier transform to carry out fine orthogonal decomposition of full-band multi-level frequency band division, and the pre-emphasis coefficient is adjusted at the same time to ensure that the frequency spectrum of the signal becomes flatter.
The main idea of extracting time-frequency Gabor filtering characteristics is to firstly extract the characteristics of analog quantity signals corresponding to awakening voice by adopting Gabor wavelet transformation, and take calculated Gabor characteristic vectors as initial characteristics of the awakening voice, thereby reducing the influence of other noises; and then, optimizing the Gabor feature vector through sparse representation to form enhanced Gabor filtering features, and taking the enhanced Gabor filtering features as voiceprint information corresponding to the awakening voice.
The air conditioner control method provided by the invention adopts different voiceprint information extraction methods for the awakening voice under different noise interference scenes, and can effectively improve the extraction precision of the voiceprint information.
Fig. 3 is a schematic flowchart of a process of obtaining voiceprint information according to the present invention, as an alternative embodiment, as shown in fig. 3, obtaining a first confidence that the user is attributed to a target group according to the voiceprint information includes:
comparing the voiceprint information with all voiceprint sample information in a voiceprint model library;
screening out target voiceprint sample information with the highest similarity to the voiceprint information in the voiceprint model library;
and taking the crowd corresponding to the target voiceprint sample information as a target crowd to which the user belongs, and taking the similarity as a first confidence coefficient of the target crowd to which the user belongs.
The distribution conditions of formants of voices of different users in a voice spectrogram are different, and the voiceprint information identification judges whether the voice of the user is the same person by comparing the vocalization of the two sections of voices on the same phoneme, so that the function of people perceiving the voice is realized. The main technical principle of voiceprint recognition is feature extraction and feature comparison.
The air conditioner control method provided by the invention realizes the identification of the voiceprint information through the cloud server.
It should be noted that a voiceprint model library is pre-constructed at the cloud server, voiceprint sample information of a plurality of users with pre-acquired identity information of different ages, different sexes, different professions and the like is stored in the voiceprint model library, and each voiceprint sample information has a corresponding information tag for marking the identity information of the corresponding user.
After the processor in the air conditioner collects the awakening voice of the user, the awakening voice is uploaded to the cloud server, and the cloud server extracts voiceprint information corresponding to the awakening voice.
And matching the voiceprint information of the user in a voiceprint model library to determine voiceprint sample information with the highest similarity to the voiceprint information as target voiceprint sample information.
Therefore, the user can be determined to be the target group according to the information label corresponding to the target voiceprint sample information.
For example: through comparison, the similarity between the voiceprint information of the user and the voiceprint sample information K in the voiceprint model library is the highest, the similarity between the voiceprint information of the user and the voiceprint sample information K in the voiceprint model library is 82 (the unit is percentage), and the voiceprint sample information K is used as target voiceprint sample information. Assuming that the age of the user described in the information tag of the voiceprint sample information K is 70 years, it can be determined that the target group to which the user belongs is an elderly person. Accordingly, the first confidence that the user is attributed as an elderly person is 82.
The invention provides a method for realizing user classification and identification by means of a cloud server, which can effectively improve the efficiency and the precision of classification and identification.
Based on the content of the foregoing embodiment, as an optional embodiment, the air conditioner control method provided by the present invention further includes: after obtaining the voiceprint information of the user, the method further comprises the following steps:
according to the voiceprint information, obtaining the confidence coefficient that the user is identified as any family member, and setting the highest confidence coefficient as a second confidence coefficient;
if the second confidence is determined to be larger than or equal to a third threshold, acquiring the identity information of the family member corresponding to the second confidence, and starting a function of replying a nickname; the identity information comprises nickname information;
if the second confidence coefficient is smaller than a third threshold value, outputting a second prompt; the second prompt is used for prompting the user to input a nickname;
if a second response voice of the user for the second prompt is received within a second preset time length;
and extracting nickname information from second response semantics corresponding to the second response voice, and storing the nickname information into a cloud platform family information base.
Fig. 4 is a schematic flow chart of the function of starting a reply with a nickname provided by the present invention, and as shown in fig. 4, the present invention can realize accurate identification of a user identity by using a home information base established at a cloud server.
Alternatively, after the air conditioner is installed in a family where the air conditioner is located, family members (i.e., users) of the family may perform authentication registration in advance to store personal identity information, including voiceprint information, age information, nicknames, and the like, in the family information base.
The registration mode may be that the user repeats more than two voice wakeup words to the air conditioner to complete voiceprint collection, and meanwhile, the user can upload the age, nickname, preference for the operation mode of the air conditioner and the like of the user to the family information base by using a voice input mode. In this way, the identity information of each family member is stored in the family information base on a per family basis (or per air conditioner basis).
As an optional embodiment, in the process of using the air conditioner by the user, the air conditioner collects data of ages, air conditioner use habits, ambient temperature, humidity, months and seasons and the like of different users on the basis of identifying the current user identity, and uploads and records the data to the family information base respectively, and trains the air conditioner operation mode decision model based on the data.
Therefore, in the subsequent use process, once the current user is identified according to the voiceprint information input by the current user, the operation mode meeting the preference of the current user can be directly switched for the current user by using the trained air conditioner operation mode decision model according to the age and the air conditioner use habit recorded by the identity information of the current user and the data such as the current environmental temperature, the current humidity, the month and the season and the like, so that more intelligent and more convenient experience is brought to the user.
Meanwhile, after the current user is identified according to the voiceprint information input by the current user, a function of recovering the nickname can be started in the man-machine interaction process, for example:
if the nickname of family member a is "prune", then after the function with the nickname is started, when inquiring whether family member a needs to start the elder care mode, it can output: "is you required to switch to elder care mode for you? The man-machine conversation is more vivid, and the use experience of the user is improved.
On the basis, the air conditioner control method provided by the invention can acquire the confidence coefficient that the user is identified as any family member according to the voiceprint information, and comprises the following steps:
comparing the voiceprint information with voiceprint sample information of each family member in a cloud platform family information base; and setting the comparison result as the confidence level that the user is identified as each family member.
It should be noted that, with a family as a unit, voiceprint information corresponding to any voice of each family member may be extracted in advance, and stored in the cloud platform family information base as voiceprint sample information of each family member.
After the awakening voice input by any family member is collected, the awakening voice is uploaded to the cloud platform server, and the voiceprint information corresponding to the awakening voice is extracted by the cloud platform server and then input to the cloud platform family information base for voiceprint recognition.
As an optional mode, each air conditioner has an equipment identification code, when the processor in the air conditioner uploads the awakening voice, the equipment identification code is uploaded to the cloud platform server as a label, the cloud platform server can accurately compare voiceprint information corresponding to the awakening voice with all voiceprint sample information of the family where the family member is located in the cloud platform family information base according to the equipment identification code, the voiceprint comparison range can be effectively reduced, and voiceprint comparison efficiency is improved.
Based on the content of the foregoing embodiment, as an optional embodiment, after controlling the air conditioner to switch to the first operation mode of the applicable target group, the method further includes:
receiving a control instruction input by the user to respond to the control instruction to control the air conditioner to be switched from the first operation mode to the second operation mode;
and uploading the second operation mode, the identity information of the user, the environment temperature and humidity information and the current date information to the cloud platform family information base together.
If the first operation mode is set as a grandparent care mode, when the air conditioner is operating in the grandparent care mode, if an operation instruction of a user is received, the operation instruction indicates that the current grandparent care mode is properly adjusted to reach a second operation mode, and the adjusted second operation mode and the identity information, the environment temperature and humidity information and the current date information of the user are uploaded to the cloud platform family information base together.
Therefore, when the air conditioner runs next time, if the identity information of the user is identified, the running mode of the air conditioner can be directly switched to the second running mode without the need of the user for adjustment.
Assuming that the current date information is 6 months (it is considered as summer), at 8 o 'clock at night, the air conditioner internal processor receives the user's control instruction as follows: and controlling the relevant components to raise the set temperature set in the original elder care mode (assuming that the temperature is adjusted by 1 ℃ every time), obtaining that the raised temperature is 26 ℃ and the nickname of the user is 'Lai', updating the relevant information of the user, namely 'Lai' stored in the cloud platform family information base in advance by utilizing the information, and taking the updated operation mode as a second operation mode.
Then, when the air conditioner enters the grandparent care mode in summer, the air conditioner is automatically switched to the second operation mode without the need for the "old plum" to control the temperature rise to 26 ℃ by itself, in the manner provided by the above embodiment.
The air conditioner control method provided by the invention can meet the use habits of different users, automatically records and stores the use habits of the users, automatically switches the operation modes of the users in the next same scene, and is more intelligent and humanized.
Based on the content of the foregoing embodiment, as an optional embodiment, after receiving a wake-up voice input by a user, the method further includes:
according to the awakening voice, determining the direction information of the user before the air conditioner;
and adjusting the direction of the swing blade of the air conditioner based on the direction information, so that the wind direction of the circulating wind blown out from the air outlet of the air conditioner deviates from the direction of the user.
As an optional embodiment, it is assumed that a microphone array is used for implementing collection of the wake-up voice of the air conditioner provided by the present invention, and the azimuth information of the user in front of the air conditioner can be automatically identified according to the wake-up voice input by the user. The present invention will not be described in detail.
It should be noted that after the azimuth information of the user is obtained, especially in the elder care mode, the direction of the swing blade of the air conditioner can be automatically adjusted, so that the wind direction of the circulating wind blown out from the air outlet of the air conditioner deviates from the azimuth of the old, the normal setting of the old for the air conditioner is met, and the use comfort of the user is further improved.
In summary, the air conditioner control method provided by the invention can automatically adjust the operation mode suitable for a specific user, can automatically identify the identities of different air conditioner users through the voiceprint recognition technology, and dynamically learns the preferences of the users such as temperature, wind speed and the like in different time periods, and after the air conditioner is opened by the different users through voice, the air conditioner automatically adjusts to the state suitable for the corresponding users; before the preference of the user is not learned, the age group of the user is judged according to the sound, and the care mode of the elder is automatically matched, so that the humanization, the intellectualization and the interaction of the air conditioner are greatly improved.
Fig. 5 is a schematic structural diagram of an air conditioner control device provided by the present invention, and as shown in fig. 5, the present invention further provides an air conditioner control device, which mainly includes a voice collecting unit 11, a voiceprint extracting unit 12, a user identifying unit 13, and an operation control unit 14, wherein:
the voice acquisition unit 11 is mainly used for receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner;
the voiceprint extracting unit 12 is mainly configured to obtain voiceprint information of the user according to the wake-up voice;
the user identification unit 13 is mainly configured to obtain a first confidence that the user belongs to a target group according to the voiceprint information;
the operation control unit 14 is mainly configured to control the air conditioner to switch to the first operation mode suitable for the target group if it is determined that the first confidence level is greater than or equal to the first threshold.
It should be noted that, when the air conditioner control device provided in the embodiment of the present invention is in specific operation, the air conditioner control method described in any of the above embodiments may be executed, and details of this embodiment are not described herein.
Based on the content of the above embodiment, as an optional embodiment, the present invention further provides an air conditioner, mainly including: the air conditioner comprises an air conditioner body, wherein a processor, a voice acquisition device and a wireless communication device are arranged in the air conditioner body, and the voice acquisition device and the wireless communication device are arranged on the air conditioner body;
the air conditioner control method further comprises a memory and a program or an instruction which is stored on the memory and can be run on the processor, and the program or the instruction is executed by the processor to execute the air conditioner control method in any one of the above embodiments.
According to the air conditioner control device and the air conditioner, the voiceprint matching can be carried out according to the awakening voice of the user so as to determine the age identity of the user, the temperature and humidity control operation of the air conditioner can be automatically carried out so as to switch to the operation mode suitable for the age identity, the humanization, the intellectualization and the interaction of the air conditioner are effectively improved, convenience can be particularly provided for special people, and the most suitable experience and experience can be provided for the special people.
Fig. 6 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 6, the electronic device may include: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform an air conditioning control method comprising: receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner; acquiring voiceprint information of a user according to the awakening voice; acquiring a first confidence coefficient of a user belonging to a target group according to the voiceprint information; and if the first confidence coefficient is determined to be larger than or equal to a first threshold value, controlling the air conditioner to be switched to a first operation mode suitable for the target crowd.
In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the air conditioning control method provided by the above methods, the method comprising: receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner; acquiring voiceprint information of a user according to the awakening voice; acquiring a first confidence coefficient that a user belongs to a target group according to voiceprint information; and if the first confidence coefficient is determined to be larger than or equal to a first threshold value, controlling the air conditioner to be switched to a first operation mode suitable for the target crowd.
In still another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being implemented by a processor to perform the air conditioner control method provided in the above embodiments, the method including: receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner; acquiring voiceprint information of a user according to the awakening voice; acquiring a first confidence coefficient that a user belongs to a target group according to voiceprint information; and if the first confidence coefficient is determined to be larger than or equal to a first threshold value, controlling the air conditioner to be switched to a first operation mode suitable for the target crowd.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (12)
1. An air conditioner control method, comprising:
receiving a wake-up voice input by a user to respond to the wake-up voice to start the air conditioner;
acquiring voiceprint information of the user according to the awakening voice;
acquiring a first confidence coefficient that the user belongs to a target group according to the voiceprint information;
and if the first confidence coefficient is determined to be larger than or equal to a first threshold value, controlling the air conditioner to be switched to a first operation mode suitable for the target crowd.
2. The method of claim 1, further comprising, after obtaining a first confidence that the user is assigned to a target group of people:
if the first confidence coefficient is smaller than a first threshold value but larger than a second threshold value, outputting a first prompt;
if the first answer voice of the user aiming at the first prompt is not received within a first preset time length, controlling the air conditioner to operate in an original operation mode;
the first prompt is used for inquiring whether the user starts the first operation mode; the original operation mode is based on an operation mode of the air conditioner at the end of the last operation period.
3. The air conditioner control method according to claim 2, wherein if a first response voice of the user to the first prompt is received within a first preset time period;
acquiring a first response semantic of the first response voice;
if the user intention is determined to be the opening of the first operation mode according to the first response semantics, controlling the air conditioner to be switched to the first operation mode;
and if the user intention is determined not to start the first operation mode according to the first response semantics, controlling the air conditioner to operate the original operation mode.
4. The air conditioner control method according to claim 2, wherein if it is determined that the first confidence is less than or equal to the second threshold, the air conditioner is controlled to operate the original operation mode.
5. The air conditioner control method according to claim 1, wherein the obtaining voiceprint information of the user according to the wake-up voice comprises:
under the condition of non-strong noise, extracting the Mel frequency cepstrum coefficient characteristic of the awakening voice in the short-time frequency spectrum to be used as the voiceprint information;
and under the condition of strong noise, extracting at least one of the power normalization cepstrum coefficient characteristic, the Gamma atom frequency cepstrum coefficient characteristic and the time-frequency Gabor filtering characteristic of the awakening voice as the voiceprint information.
6. The air conditioner control method according to claim 1, wherein obtaining a first confidence that the user is assigned to a target group according to the voiceprint information comprises:
comparing the voiceprint information with all voiceprint sample information in a voiceprint model library;
screening out target voiceprint sample information with the highest similarity to the voiceprint information in the voiceprint model library;
and taking the crowd corresponding to the target voiceprint sample information as a target crowd to which the user is attributed, and taking the similarity as a first confidence coefficient of the target crowd to which the user is attributed.
7. The air conditioner control method according to claim 1, further comprising: after obtaining the voiceprint information of the user, the method further comprises the following steps:
according to the voiceprint information, obtaining the confidence coefficient that the user is identified as any family member, and setting the highest confidence coefficient as a second confidence coefficient;
if the second confidence is determined to be larger than or equal to a third threshold, acquiring the identity information of the family member corresponding to the second confidence, and starting a function of replying a nickname; the identity information comprises nickname information;
if the second confidence is smaller than a third threshold value, outputting a second prompt; the second prompt is used for prompting the user to input a nickname;
if a second response voice of the user for the second prompt is received within a second preset time length;
and extracting nickname information from second response semantics corresponding to the second response voice, and storing the nickname information into a cloud platform family information base.
8. The air conditioner control method according to claim 7, wherein the obtaining the confidence that the user is identified as any family member according to the voiceprint information comprises:
comparing the voiceprint information with voiceprint sample information of each family member in the cloud platform family information base;
and setting the comparison result as the confidence level of the user identified as each family member.
9. The method for controlling an air conditioner according to claim 8, further comprising, after controlling the air conditioner to switch to the first operation mode suitable for the target group of people:
receiving a control instruction input by the user to respond to the control instruction to control the air conditioner to be switched from the first operation mode to a second operation mode;
and uploading the second operation mode, the identity information of the user, the environment temperature and humidity information and the current date information to the cloud platform family information base together.
10. The air conditioner control method according to any one of claims 1-9, further comprising, after receiving a user input wake-up voice:
according to the awakening voice, determining the direction information of the user before the air conditioner;
and adjusting the direction of the swing blade of the air conditioner based on the direction information, so that the wind direction of the circulating wind blown out from the air outlet of the air conditioner deviates from the direction of the user.
11. An air conditioning control device, characterized by comprising:
the voice acquisition unit receives a wake-up voice input by a user so as to respond to the wake-up voice to start the air conditioner;
a voiceprint extracting unit, configured to obtain voiceprint information of the user according to the wake-up voice;
the user identification unit is used for acquiring a first confidence coefficient that the user belongs to a target group according to the voiceprint information;
and the operation control unit is used for controlling the air conditioner to be switched to a first operation mode suitable for the target crowd under the condition that the first confidence coefficient is determined to be greater than or equal to a first threshold value.
12. An air conditioner, comprising: the air conditioner comprises an air conditioner body, wherein a processor, a voice acquisition device and a wireless communication device are arranged in the air conditioner body, and the voice acquisition device and the wireless communication device are arranged on the air conditioner body;
the air conditioner control method further comprises a memory and a program or an instruction which is stored on the memory and can be run on the processor, and the program or the instruction is executed by the processor to execute the air conditioner control method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210456438.5A CN114999472A (en) | 2022-04-27 | 2022-04-27 | Air conditioner control method and device and air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210456438.5A CN114999472A (en) | 2022-04-27 | 2022-04-27 | Air conditioner control method and device and air conditioner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114999472A true CN114999472A (en) | 2022-09-02 |
Family
ID=83026085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210456438.5A Pending CN114999472A (en) | 2022-04-27 | 2022-04-27 | Air conditioner control method and device and air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114999472A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112463102A (en) * | 2019-09-06 | 2021-03-09 | 佛山市顺德区美的电热电器制造有限公司 | Household appliance, interaction method and interaction device thereof, and electronic device |
| CN116857805A (en) * | 2023-08-23 | 2023-10-10 | 德州隆达空调设备集团有限公司 | Intelligent fan and fire prevention valve monitoring system |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103943111A (en) * | 2014-04-25 | 2014-07-23 | 海信集团有限公司 | Method and device for identity recognition |
| CN106292592A (en) * | 2016-08-19 | 2017-01-04 | 北京小米移动软件有限公司 | The control method of household electrical appliances and device |
| CN106683673A (en) * | 2016-12-30 | 2017-05-17 | 智车优行科技（北京）有限公司 | Method, device and system for adjusting driving modes and vehicle |
| CN108305615A (en) * | 2017-10-23 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of object identifying method and its equipment, storage medium, terminal |
| CN108766446A (en) * | 2018-04-18 | 2018-11-06 | 上海问之信息科技有限公司 | Method for recognizing sound-groove, device, storage medium and speaker |
| CN108882032A (en) * | 2018-06-08 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN110176229A (en) * | 2019-05-28 | 2019-08-27 | 北京增强智能科技有限公司 | A kind of method of speech processing and device |
| US20200020341A1 (en) * | 2017-10-26 | 2020-01-16 | Shenzhen Skyworth-Rgb Electronic Co., Ltd. | Voice interaction method, voice interaction control device, and storage medium for television |
| CN111223490A (en) * | 2020-03-12 | 2020-06-02 | Oppo广东移动通信有限公司 | Voiceprint awakening method and device, equipment and storage medium |
| CN112628975A (en) * | 2020-12-11 | 2021-04-09 | 珠海格力电器股份有限公司 | Control method and device of air conditioner, storage medium and processor |
| US20210397686A1 (en) * | 2018-10-31 | 2021-12-23 | Huawei Technologies Co., Ltd. | Audio Control Method and Electronic Device |
| CN113836508A (en) * | 2021-08-30 | 2021-12-24 | 青岛海尔科技有限公司 | Method and device for determining starting mode, storage medium and electronic device |
| CN113855542A (en) * | 2021-09-08 | 2021-12-31 | 广州灵聚信息科技有限公司 | Method and device for realizing intelligent massage based on intelligent voice interaction |
| CN114842843A (en) * | 2022-03-29 | 2022-08-02 | 青岛海尔空调器有限总公司 | Terminal device control method and device, electronic device and storage medium |
| CN114863932A (en) * | 2022-03-29 | 2022-08-05 | 青岛海尔空调器有限总公司 | Working mode setting method and device |
-
2022
- 2022-04-27 CN CN202210456438.5A patent/CN114999472A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103943111A (en) * | 2014-04-25 | 2014-07-23 | 海信集团有限公司 | Method and device for identity recognition |
| CN106292592A (en) * | 2016-08-19 | 2017-01-04 | 北京小米移动软件有限公司 | The control method of household electrical appliances and device |
| CN106683673A (en) * | 2016-12-30 | 2017-05-17 | 智车优行科技（北京）有限公司 | Method, device and system for adjusting driving modes and vehicle |
| CN108305615A (en) * | 2017-10-23 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of object identifying method and its equipment, storage medium, terminal |
| US20200020341A1 (en) * | 2017-10-26 | 2020-01-16 | Shenzhen Skyworth-Rgb Electronic Co., Ltd. | Voice interaction method, voice interaction control device, and storage medium for television |
| CN108766446A (en) * | 2018-04-18 | 2018-11-06 | 上海问之信息科技有限公司 | Method for recognizing sound-groove, device, storage medium and speaker |
| CN108882032A (en) * | 2018-06-08 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| US20210397686A1 (en) * | 2018-10-31 | 2021-12-23 | Huawei Technologies Co., Ltd. | Audio Control Method and Electronic Device |
| CN110176229A (en) * | 2019-05-28 | 2019-08-27 | 北京增强智能科技有限公司 | A kind of method of speech processing and device |
| CN111223490A (en) * | 2020-03-12 | 2020-06-02 | Oppo广东移动通信有限公司 | Voiceprint awakening method and device, equipment and storage medium |
| CN112628975A (en) * | 2020-12-11 | 2021-04-09 | 珠海格力电器股份有限公司 | Control method and device of air conditioner, storage medium and processor |
| CN113836508A (en) * | 2021-08-30 | 2021-12-24 | 青岛海尔科技有限公司 | Method and device for determining starting mode, storage medium and electronic device |
| CN113855542A (en) * | 2021-09-08 | 2021-12-31 | 广州灵聚信息科技有限公司 | Method and device for realizing intelligent massage based on intelligent voice interaction |
| CN114842843A (en) * | 2022-03-29 | 2022-08-02 | 青岛海尔空调器有限总公司 | Terminal device control method and device, electronic device and storage medium |
| CN114863932A (en) * | 2022-03-29 | 2022-08-05 | 青岛海尔空调器有限总公司 | Working mode setting method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112463102A (en) * | 2019-09-06 | 2021-03-09 | 佛山市顺德区美的电热电器制造有限公司 | Household appliance, interaction method and interaction device thereof, and electronic device |
| CN112463102B (en) * | 2019-09-06 | 2024-03-22 | 佛山市顺德区美的电热电器制造有限公司 | Household appliance, interaction method and interaction device thereof, and electronic equipment |
| CN116857805A (en) * | 2023-08-23 | 2023-10-10 | 德州隆达空调设备集团有限公司 | Intelligent fan and fire prevention valve monitoring system |
| CN116857805B (en) * | 2023-08-23 | 2024-01-05 | 德州隆达空调设备集团有限公司 | Intelligent fan and fire prevention valve monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107342076B (en) | Intelligent home control system and method compatible with abnormal voice | |
| CA2676380C (en) | System and method for detection and analysis of speech | |
| CN102404278A (en) | Song requesting system based on voiceprint recognition and application method thereof | |
| CN114999472A (en) | Air conditioner control method and device and air conditioner | |
| ATE158889T1 (en) | SYSTEM FOR PROCESSING CONTINUOUS SPEECH | |
| CN107871499B (en) | Speech recognition method, system, computer device and computer-readable storage medium | |
| CN108922541A (en) | Multidimensional characteristic parameter method for recognizing sound-groove based on DTW and GMM model | |
| CN109036395A (en) | Personalized speaker control method, system, intelligent sound box and storage medium | |
| CN117041807B (en) | Bluetooth headset play control method | |
| CN109599094A (en) | The method of sound beauty and emotion modification | |
| CN112562681B (en) | Speech recognition method and apparatus, and storage medium | |
| CN1312656C (en) | Speaking person standarding method and speech identifying apparatus using the same | |
| US20230206924A1 (en) | Voice wakeup method and voice wakeup device | |
| CN110689887A (en) | Audio verification method and device, storage medium and electronic equipment | |
| Wang et al. | Application of speech recognition technology in IoT smart home | |
| CN110060682B (en) | Sound box control method and device | |
| WO2023185007A1 (en) | Sleep scene setting method and apparatus | |
| EP2321981A1 (en) | Automatic performance optimization for perceptual devices | |
| CN112863476A (en) | Method and device for constructing personalized speech synthesis model, method and device for speech synthesis and testing | |
| CN112885326A (en) | Method and device for creating personalized speech synthesis model, method and device for synthesizing and testing speech | |
| CN117253479A (en) | Voice control method and system applied to wax-melting aromatherapy lamp | |
| CN110970019A (en) | Control method and device of intelligent home system | |
| CN110895941A (en) | Voiceprint recognition method and device and storage device | |
| US20110301949A1 (en) | Speaker-cluster dependent speaker recognition (speaker-type automated speech recognition) | |
| Dai et al. | An improved model of masking effects for robust speech recognition system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |