CN111312214A - Voice recognition method and device for air conditioner, air conditioner and readable storage medium - Google Patents
Voice recognition method and device for air conditioner, air conditioner and readable storage medium Download PDFInfo
- Publication number
- CN111312214A CN111312214A CN202010246368.1A CN202010246368A CN111312214A CN 111312214 A CN111312214 A CN 111312214A CN 202010246368 A CN202010246368 A CN 202010246368A CN 111312214 A CN111312214 A CN 111312214A
- Authority
- CN
- China
- Prior art keywords
- voice
- processing model
- air conditioner
- recognition
- commands
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/005—Language recognition
-
- 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
- F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
-
- 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
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The invention provides a voice recognition method and device of an air conditioner, the air conditioner and a storage medium, wherein the voice recognition method of the air conditioner comprises the following steps: controlling a voice recognition module to recognize the received voice instruction by adopting a first voice processing model within a preset time length of the operation of the air conditioner; and switching to a second voice processing model for recognition according to the recognition result of the voice command by the voice recognition module through the first voice processing model. Through the technical scheme of the invention, the efficiency, accuracy, reliability and diversity of voice command recognition can be improved, and the use experience of a user can be improved.
Description
Technical Field
The invention relates to the technical field of batteries, in particular to a voice recognition method of an air conditioner, a voice recognition device of the air conditioner, the air conditioner and a computer readable storage medium.
Background
The household appliances such as air conditioners, televisions, stereos and the like are all developed with voice recognition systems to recognize voice commands of users, most of the voice recognition systems only support the awakening and recognition of Mandarin, part of users feed back to the multiple dialects in home to communicate, and if the users use voice, the users need to switch to the Mandarin to feel something wrong.
In addition, most of the existing dialect identification technical schemes are single dialect awakening identification model schemes, and the situation that part of families have multiple dialect languages is difficult to meet.
Moreover, any discussion of the prior art throughout the specification is not an admission that the prior art is necessarily known to a person of ordinary skill in the art, and any discussion of the prior art throughout the specification is not an admission that the prior art is necessarily widely known or forms part of common general knowledge in the field.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art or the related art.
To this end, an object of the present invention is to provide a voice recognition method of an air conditioner.
Another object of the present invention is to provide a voice recognition apparatus of an air conditioner.
Another object of the present invention is to provide an air conditioner.
It is another object of the present invention to provide a computer-readable storage medium.
In order to achieve the above object, according to an embodiment of a first aspect of the present invention, there is provided a voice recognition method of an air conditioner, including: controlling a voice recognition module to recognize a received voice instruction by adopting a first voice processing model within a preset time period of the operation of the air conditioner; and switching to a second voice processing model for recognition according to the recognition result of the voice command by the voice recognition module through the first voice processing model.
In the technical scheme, the air conditioner is controlled to recognize the received voice instruction by adopting the first voice processing model within a preset time period of the operation of the air conditioner, the voice recognition module adopts the voice recognition module with the first voice processing model which can be preset as a high priority level set by a user, or the air conditioner determines the voice recognition module which is used by a specific user in a more habit or a voice recognition module which is used at a higher frequency through a machine learning process, so that the air conditioner can recognize the voice instruction of the specific user more quickly and accurately, especially for the user who is used to a dialect, the voice recognition module adopts the first voice processing model which can be a module corresponding to the dialect which is used by the user in a habit, and the use experience of the voice function of the user can be promoted, and the dialect can be northeast, southeast, Henan, Sichuan and Szechwan, Shanxi dialect, but not limited thereto.
In addition, the recognition result of the voice command is switched to the second voice processing model for recognition according to the voice recognition module by adopting the first voice processing model, and particularly when the voice command is failed to be recognized, the voice command is switched to the second voice processing model in time to continue to be recognized, so that the response rate of the air conditioner for recognizing the voice command is improved.
It should be noted that the first speech processing model adopted by the speech recognition module is a module which is used for performing speech instruction recognition by default in any operation period, and the second speech processing model is a module which is used for performing speech recognition instructions and is preferentially switched after the speech recognition module performs recognition by using the first speech processing model, but not limited thereto, the speech recognition module arranged in the air conditioner is not limited to the speech recognition module adopting the first speech processing model and the second speech processing model.
Wherein, the identification result can be success, failure, yes, no and the percentage corresponding to the accuracy.
In any of the above technical solutions, preferably, the usage frequency of the first speech processing model adopted by the speech recognition module is greater than that of the second speech processing model.
In the technical scheme, the voice recognition module is set to adopt the first voice processing model with the use frequency higher than that of the second voice processing model, so that the voice command can be switched to the second voice processing model which is used by a user more frequently as soon as possible when the voice command recognition fails, and the recognition response rate of the voice command is improved as much as possible.
The frequency of use may be determined through a machine learning process or may be set for a specific user.
In any of the above technical solutions, preferably, switching to a second speech processing model for recognition according to a recognition result of the speech command by the speech recognition module using the first speech processing model specifically includes: judging whether the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to a preset success rate or not; and judging that the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to the preset success rate, and switching to a second voice processing model for recognition.
In the technical scheme, whether the recognition success rate of the voice recognition module to at least one voice instruction by adopting the first voice processing model is less than or equal to a preset success rate or not is judged, and the recognition success rate of the voice recognition module to at least one voice instruction by adopting the first voice processing model is less than or equal to the preset success rate is judged, and the second voice processing model is switched to recognize, so that the voice instruction which is failed in recognition by adopting the first voice processing model can be analyzed by the second voice processing model more quickly, and the use experience of the recognition function of a user is further improved.
In any of the above technical solutions, preferably, the method further includes: receiving a plurality of voice instructions within a preset time period of the operation of the air conditioner; determining spatial orientation information of a plurality of voice commands; and controlling a plurality of voice processing model blocks to simultaneously recognize a plurality of voice commands according to the space orientation information, or recognizing a plurality of voice commands by adopting a voice processing model corresponding to the space orientation information at the last time.
In the technical scheme, if multiple voice commands are received within a preset time period of the operation of the air conditioner, the spatial direction information of the multiple voice commands needs to be determined, and the sources of the voice commands can be determined through the spatial direction information.
Furthermore, according to the spatial orientation information, a plurality of voice processing model blocks are controlled to simultaneously recognize a plurality of voice commands, a plurality of voice commands from similar orientation sources can be screened to determine the voice commands which can be executed, or a voice processing model corresponding to the spatial orientation information at the last time is adopted to recognize the plurality of voice commands, namely, the voice commands in a plurality of different orientations are respectively recognized to recognize the voice commands which can be executed, so that the intelligence and the reliability of the voice function of the air conditioner are improved.
In any of the above technical solutions, preferably, according to the spatial orientation information, controlling a plurality of speech processing model blocks to simultaneously recognize a plurality of speech commands, or recognizing a plurality of speech commands by using a speech processing model corresponding to the spatial orientation information last time specifically includes: analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands; judging whether the similarity between the azimuth angles is smaller than a preset similarity or not; and judging that the similarity between the plurality of azimuth angles is smaller than the preset similarity, and sequentially adopting voice recognition modules corresponding to the azimuth angles to recognize according to the receiving sequence of the plurality of voice instructions.
In the technical scheme, the azimuth angle is determined by taking a reference line on a horizontal plane as a reference, a structural point of the air conditioner is taken as a reference point on the reference line, and an included angle between a connecting line between any user sending the voice command and the air conditioner and the reference line is taken as the azimuth angle, so that whether the voice commands are from similar spatial regions or different spatial regions can be determined based on the azimuth angle, and particularly when the voice commands are from different spatial regions, the voice commands are from different users, so that all the voice commands can be analyzed most timely, most accurately and most comprehensively by sequentially adopting voice recognition modules corresponding to the azimuth angle for recognition.
In any of the above technical solutions, preferably, according to the spatial orientation information, controlling a plurality of speech processing model blocks to simultaneously recognize a plurality of speech commands, or recognizing a plurality of speech commands by using a speech processing model corresponding to the spatial orientation information last time, further includes: analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands; judging whether the similarity among the azimuth angles is greater than or equal to a preset similarity or not; and judging that the similarity between the plurality of azimuth angles is greater than or equal to the preset similarity, and controlling a plurality of voice processing model blocks to simultaneously recognize the plurality of voice commands.
In the technical scheme, by judging that the similarity between a plurality of azimuth angles is greater than or equal to the preset similarity, a plurality of voice processing model blocks are controlled to simultaneously recognize a plurality of voice commands, namely, the voice commands from the same spatial region are simultaneously distinguished, so that the commands which can be executed in the plurality of voice commands are determined.
According to a second aspect of the present invention, there is provided a voice recognition device for an air conditioner, comprising: a memory configured to store a computer program, and a processor, wherein the computer program, when executed by the processor, is capable of implementing the steps of the voice recognition method of the air conditioner according to any one of the above technical aspects.
According to a third aspect of the present invention, there is provided an air conditioner comprising: a memory configured to store a computer program, and a processor, wherein the computer program, when executed by the processor, is capable of implementing the steps of the voice recognition method of the air conditioner according to any one of the above technical aspects.
According to an aspect of the fourth aspect of the present invention, there is provided an air conditioner including: the voice recognition device of the air conditioner is provided.
According to an aspect of the fifth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, the computer program, when executed, implementing the steps of the voice recognition method of an air conditioner as defined in any one of the above aspects.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart illustrating a voice recognition method of an air conditioner according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a voice recognition method of an air conditioner according to another embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating a voice recognition method of an air conditioner according to another embodiment of the present invention;
fig. 4 is a schematic block diagram illustrating a voice recognition apparatus of an air conditioner according to an embodiment of the present invention;
FIG. 5 illustrates a schematic block diagram of an air conditioner according to an embodiment of the present invention;
fig. 6 shows a schematic block diagram of an air conditioner according to another embodiment of the present invention;
FIG. 7 shows a schematic block diagram of a computer-readable storage medium according to an embodiment of the invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Embodiments of a voice recognition method and apparatus for an air conditioner, and a computer-readable storage medium according to embodiments of the present invention are specifically described below with reference to fig. 1 to 7.
As shown in fig. 1, a voice recognition method of an air conditioner according to an embodiment of the present invention includes: step S102, controlling a voice recognition module to recognize a received voice command by adopting a first voice processing model within a preset time length of the operation of the air conditioner; and step S104, switching to a second voice processing model for recognition according to the recognition result of the voice command by the voice recognition module through the first voice processing model.
In the technical scheme, the air conditioner is controlled to recognize the received voice instruction by adopting the first voice processing model within a preset time period of the operation of the air conditioner, the voice recognition module adopts the voice recognition module with the first voice processing model which can be preset as a high priority level set by a user, or the air conditioner determines the voice recognition module which is used by a specific user in a more habit or a voice recognition module which is used at a higher frequency through a machine learning process, so that the air conditioner can recognize the voice instruction of the specific user more quickly and accurately, especially for the user who is used to a dialect, the voice recognition module adopts the first voice processing model which can be a module corresponding to the dialect which is used by the user in a habit, and the use experience of the voice function of the user can be promoted, and the dialect can be northeast, southeast, Henan, Sichuan and Szechwan, Shanxi dialect, but not limited thereto.
In addition, the recognition result of the voice command is switched to the second voice processing model for recognition according to the voice recognition module by adopting the first voice processing model, and particularly when the voice command is failed to be recognized, the voice command is switched to the second voice processing model in time to continue to be recognized, so that the response rate of the air conditioner for recognizing the voice command is improved.
It should be noted that the first speech processing model adopted by the speech recognition module is a module which is used for performing speech instruction recognition by default in any operation period, and the second speech processing model is a module which is used for performing speech recognition instructions and is preferentially switched after the speech recognition module performs recognition by using the first speech processing model, but not limited thereto, the speech recognition module arranged in the air conditioner is not limited to the speech recognition module adopting the first speech processing model and the second speech processing model.
Wherein, the identification result can be success, failure, yes, no and the percentage corresponding to the accuracy.
In any of the above technical solutions, preferably, the usage frequency of the first speech processing model adopted by the speech recognition module is greater than that of the second speech processing model.
In the technical scheme, the voice recognition module is set to adopt the first voice processing model with the use frequency higher than that of the second voice processing model, so that the voice command can be switched to the second voice processing model which is used by a user more frequently as soon as possible when the voice command recognition fails, and the recognition response rate of the voice command is improved as much as possible.
The frequency of use may be determined through a machine learning process or may be set for a specific user.
In any of the above technical solutions, preferably, switching to a second speech processing model for recognition according to a recognition result of the speech command by the speech recognition module using the first speech processing model specifically includes: judging whether the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to a preset success rate or not; and judging that the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to the preset success rate, and switching to a second voice processing model for recognition.
In the technical scheme, whether the recognition success rate of the voice recognition module to at least one voice instruction by adopting the first voice processing model is less than or equal to a preset success rate or not is judged, and the recognition success rate of the voice recognition module to at least one voice instruction by adopting the first voice processing model is less than or equal to the preset success rate is judged, and the second voice processing model is switched to recognize, so that the voice instruction which is failed in recognition by adopting the first voice processing model can be analyzed by the second voice processing model more quickly, and the use experience of the recognition function of a user is further improved.
As shown in fig. 2, a voice recognition method of an air conditioner according to another embodiment of the present invention includes: step S202, receiving a plurality of voice commands within a preset time length of the operation of the air conditioner; step S204, determining the space direction information of a plurality of voice commands; and step S206, controlling a plurality of voice processing model blocks to simultaneously recognize a plurality of voice commands according to the space orientation information, or recognizing a plurality of voice commands by adopting a voice processing model corresponding to the space orientation information last time.
In the technical scheme, if multiple voice commands are received within a preset time period of the operation of the air conditioner, the spatial direction information of the multiple voice commands needs to be determined, and the sources of the voice commands can be determined through the spatial direction information.
Furthermore, according to the spatial orientation information, a plurality of voice processing model blocks are controlled to simultaneously recognize a plurality of voice commands, a plurality of voice commands from similar orientation sources can be screened to determine the voice commands which can be executed, or a voice processing model corresponding to the spatial orientation information at the last time is adopted to recognize the plurality of voice commands, namely, the voice commands in a plurality of different orientations are respectively recognized to recognize the voice commands which can be executed, so that the intelligence and the reliability of the voice function of the air conditioner are improved.
In any of the above technical solutions, preferably, according to the spatial orientation information, controlling a plurality of speech processing model blocks to simultaneously recognize a plurality of speech commands, or recognizing a plurality of speech commands by using a speech processing model corresponding to the spatial orientation information last time specifically includes: analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands; judging whether the similarity between the azimuth angles is smaller than a preset similarity or not; and judging that the similarity between the plurality of azimuth angles is smaller than the preset similarity, and sequentially adopting voice recognition modules corresponding to the azimuth angles to recognize according to the receiving sequence of the plurality of voice instructions.
In the technical scheme, the azimuth angle is determined by taking a reference line on a horizontal plane as a reference, a structural point of the air conditioner is taken as a reference point on the reference line, and an included angle between a connecting line between any user sending the voice command and the air conditioner and the reference line is taken as the azimuth angle, so that whether the voice commands are from similar spatial regions or different spatial regions can be determined based on the azimuth angle, and particularly when the voice commands are from different spatial regions, the voice commands are from different users, so that all the voice commands can be analyzed most timely, most accurately and most comprehensively by sequentially adopting voice recognition modules corresponding to the azimuth angle for recognition.
In any of the above technical solutions, preferably, according to the spatial orientation information, controlling a plurality of speech processing model blocks to simultaneously recognize a plurality of speech commands, or recognizing a plurality of speech commands by using a speech processing model corresponding to the spatial orientation information last time, further includes: analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands; judging whether the similarity among the azimuth angles is greater than or equal to a preset similarity or not; and judging that the similarity between the plurality of azimuth angles is greater than or equal to the preset similarity, and controlling a plurality of voice processing model blocks to simultaneously recognize the plurality of voice commands.
In the technical scheme, by judging that the similarity between a plurality of azimuth angles is greater than or equal to the preset similarity, a plurality of voice processing model blocks are controlled to simultaneously recognize a plurality of voice commands, namely, the voice commands from the same spatial region are simultaneously distinguished, so that the commands which can be executed in the plurality of voice commands are determined.
As shown in fig. 3, a voice recognition method of an air conditioner according to another embodiment of the present invention includes: step S302, the APP terminal adds dialect language selection; step S304, when the system identifies that a plurality of dialect models are used, outputting azimuth angles corresponding to different dialect awakening models; step S306, the system detects that the same dialect is used within a certain running time; step S308, the model is preferentially switched into the dialect, and after the dialect model has no identification result, other dialect models are started; step S310, the system operation memory can be optimized and the time for switching different dialect models can be shortened; step S312, when the awakening azimuths of different dialects are close to the same; step S314, starting a plurality of dialect models simultaneously, increasing the memory of a real-time system, and delaying the feedback time compared with the other two conditions; step S316, when the difference of the awakening azimuth angles of different dialects is large; step S318, the dialect model is switched according to the awakening output azimuth angle in a short time, the fixed azimuth angle is switched into the fixed dialect identification model, the system memory is optimized, and the feedback time is shortened.
Specifically, the APP terminal is set to support the dialect language at present, and is set to support two or more languages, and the step of recognizing the voice command is as follows:
(1) if the dialect model is not switched within a certain time, the air conditioner is switched into the dialect model in a limited way, and the dialect model is switched into another dialect model for identification under the condition that the dialect model is not identified, so that the identification speed can be prompted.
(2) If two dialects are detected in the same direction in a short period, the recognition models of the two dialects are started in the system at the same time, the two models are ensured to be in an awakening recognition state, a data result is ensured not to be lost, and the feedback time length is slower than that of the scheme (1).
(3) If two different dialect models are detected in different directions within a short period of time, such as a couple at home, a Sichuan dialect on the left and a Cantonese on the right, the azimuth angles under the different dialect models are located according to the sound source location.
(4) When a user uses dialects to wake up, the azimuth angles of the corresponding languages and the corresponding dialects wake-up model are output, the languages of the dialects which are closer to each other are matched for recognition, if the azimuth angles are closer to the left side, the Cantonese recognition model is started, and if the azimuth angles are closer to the right side, the Sichuan recognition model is started, so that the positioning shortens the model switching time or solves the problem that the two wake-up models are started to run at the same time.
As shown in fig. 4, a voice recognition apparatus 400 of an air conditioner according to another embodiment of the present invention includes: a memory 402 and a processor 404, wherein the memory 402 is configured to store a computer program, and the computer program, when executed by the processor 404, is capable of implementing the steps of the voice recognition method of the air conditioner according to any one of the above technical solutions.
As shown in fig. 5, an air conditioner 500 according to another embodiment of the present invention includes: a memory 502 and a processor 504, wherein the memory 502 is configured to store a computer program, and the computer program, when executed by the processor 504, is capable of implementing the steps of the voice recognition method of the air conditioner according to any one of the above technical solutions.
As shown in fig. 6, an air conditioner 600 according to an embodiment of the present invention includes: such as the voice recognition apparatus 400 of the air conditioner.
As shown in fig. 7, according to a computer-readable storage medium 700 of an embodiment of the present invention, a computer program is stored on the computer-readable storage medium, and when the computer program is executed by an air conditioner 500(600), the method for recognizing a voice of an air conditioner as defined in any one of the above technical solutions is implemented, and specifically includes the following steps: controlling a voice recognition module to recognize a received voice instruction by adopting a first voice processing model within a preset time period of the operation of the air conditioner; and switching to a second voice processing model for recognition according to the recognition result of the voice command by the voice recognition module through the first voice processing model.
In summary, the speech recognition system supports various dialect wake-up models and recognition models, and has the following strategies and advantages:
(1) the voice recognition system can be arranged at the APP terminal and can start one or more dialect recognition systems at the same time.
(2) If the speech recognition system recognizes that only one dialect system exists in a period of time, the dialect model is preferentially switched to, and other dialect systems are started again under the dialect model without recognition results, so that the system memory and the response time are optimized.
(3) If in a short period, according to the output azimuth angle of the awakening model, two or more dialects are judged to be detected in the same direction, the identification models of the two or more dialects are started in the system at the same time, the multiple models are ensured to be in the awakening identification state, the data result is ensured not to be lost, and the feedback time length is slower than that of the scheme (2).
(4) If in a short period, a plurality of different dialect models are detected in different directions, when a user uses a dialect to wake up, the azimuth angles of the corresponding languages and the corresponding dialect wake-up models are output and are matched with the languages of the dialects closer to each other to be identified, and the positioning shortens the model switching time or solves the problem of time consumption of the simultaneous starting and running of a plurality of wake-up models.
In the technical scheme, the air conditioner is controlled to recognize the received voice instruction by adopting the first voice processing model within a preset time period of the operation of the air conditioner, the voice recognition module adopts the voice recognition module with the first voice processing model which can be preset as a high priority level set by a user, or the air conditioner determines the voice recognition module which is used by a specific user in a more habit or a voice recognition module which is used at a higher frequency through a machine learning process, so that the air conditioner can recognize the voice instruction of the specific user more quickly and accurately, especially for the user who is used to a dialect, the voice recognition module adopts the first voice processing model which can be a module corresponding to the dialect which is used by the user in a habit, and the use experience of the voice function of the user can be promoted, and the dialect can be northeast, southeast, Henan, Sichuan and Szechwan, Shanxi dialect, but not limited thereto.
In addition, the recognition result of the voice command is switched to the second voice processing model for recognition according to the voice recognition module by adopting the first voice processing model, and particularly when the voice command is failed to be recognized, the voice command is switched to the second voice processing model in time to continue to be recognized, so that the response rate of the air conditioner for recognizing the voice command is improved.
It should be noted that the first speech processing model adopted by the speech recognition module is a module which is used for performing speech instruction recognition by default in any operation period, and the second speech processing model is a module which is used for performing speech recognition instructions and is preferentially switched after the speech recognition module performs recognition by using the first speech processing model, but not limited thereto, the speech recognition module arranged in the air conditioner is not limited to the speech recognition module adopting the first speech processing model and the second speech processing model.
Wherein, the identification result can be success, failure, yes, no and the percentage corresponding to the accuracy.
In any of the above technical solutions, preferably, the usage frequency of the first speech processing model adopted by the speech recognition module is greater than that of the second speech processing model.
In the technical scheme, the voice recognition module is set to adopt the first voice processing model with the use frequency higher than that of the second voice processing model, so that the voice command can be switched to the second voice processing model which is used by a user more frequently as soon as possible when the voice command recognition fails, and the recognition response rate of the voice command is improved as much as possible.
The frequency of use may be determined through a machine learning process or may be set for a specific user.
In any of the above technical solutions, preferably, switching to a second speech processing model for recognition according to a recognition result of the speech command by the speech recognition module using the first speech processing model specifically includes: judging whether the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to a preset success rate or not; and judging that the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to the preset success rate, and switching to a second voice processing model for recognition.
In the technical scheme, whether the recognition success rate of the voice recognition module to at least one voice instruction by adopting the first voice processing model is less than or equal to a preset success rate or not is judged, and the recognition success rate of the voice recognition module to at least one voice instruction by adopting the first voice processing model is less than or equal to the preset success rate is judged, and the second voice processing model is switched to recognize, so that the voice instruction which is failed in recognition by adopting the first voice processing model can be analyzed by the second voice processing model more quickly, and the use experience of the recognition function of a user is further improved.
In any of the above technical solutions, preferably, the method further includes: receiving a plurality of voice instructions within a preset time period of the operation of the air conditioner; determining spatial orientation information of a plurality of voice commands; and controlling a plurality of voice processing model blocks to simultaneously recognize a plurality of voice commands according to the space orientation information, or recognizing a plurality of voice commands by adopting a voice processing model corresponding to the space orientation information at the last time.
In the technical scheme, if multiple voice commands are received within a preset time period of the operation of the air conditioner, the spatial direction information of the multiple voice commands needs to be determined, and the sources of the voice commands can be determined through the spatial direction information.
Furthermore, according to the spatial orientation information, a plurality of voice processing model blocks are controlled to simultaneously recognize a plurality of voice commands, a plurality of voice commands from similar orientation sources can be screened to determine the voice commands which can be executed, or a voice processing model corresponding to the spatial orientation information at the last time is adopted to recognize the plurality of voice commands, namely, the voice commands in a plurality of different orientations are respectively recognized to recognize the voice commands which can be executed, so that the intelligence and the reliability of the voice function of the air conditioner are improved.
In any of the above technical solutions, preferably, according to the spatial orientation information, controlling a plurality of speech processing model blocks to simultaneously recognize a plurality of speech commands, or recognizing a plurality of speech commands by using a speech processing model corresponding to the spatial orientation information last time specifically includes: analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands; judging whether the similarity between the azimuth angles is smaller than a preset similarity or not; and judging that the similarity between the plurality of azimuth angles is smaller than the preset similarity, and sequentially adopting voice recognition modules corresponding to the azimuth angles to recognize according to the receiving sequence of the plurality of voice instructions.
In the technical scheme, the azimuth angle is determined by taking a reference line on a horizontal plane as a reference, a structural point of the air conditioner is taken as a reference point on the reference line, and an included angle between a connecting line between any user sending the voice command and the air conditioner and the reference line is taken as the azimuth angle, so that whether the voice commands are from similar spatial regions or different spatial regions can be determined based on the azimuth angle, and particularly when the voice commands are from different spatial regions, the voice commands are from different users, so that all the voice commands can be analyzed most timely, most accurately and most comprehensively by sequentially adopting voice recognition modules corresponding to the azimuth angle for recognition.
In any of the above technical solutions, preferably, according to the spatial orientation information, controlling a plurality of speech processing model blocks to simultaneously recognize a plurality of speech commands, or recognizing a plurality of speech commands by using a speech processing model corresponding to the spatial orientation information last time, further includes: analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands; judging whether the similarity among the azimuth angles is greater than or equal to a preset similarity or not; and judging that the similarity between the plurality of azimuth angles is greater than or equal to the preset similarity, and controlling a plurality of voice processing model blocks to simultaneously recognize the plurality of voice commands.
In the technical scheme, by judging that the similarity between a plurality of azimuth angles is greater than or equal to the preset similarity, a plurality of voice processing model blocks are controlled to simultaneously recognize a plurality of voice commands, namely, the voice commands from the same spatial region are simultaneously distinguished, so that the commands which can be executed in the plurality of voice commands are determined.
The technical scheme of the invention is described in detail above with reference to the accompanying drawings, and the invention provides a voice recognition method of an air conditioner, a voice recognition device of the air conditioner, the air conditioner and a computer readable storage medium, wherein the voice recognition method is set within a preset time period of the operation of the air conditioner, the voice recognition module is controlled to recognize a received voice instruction by using a first voice processing model, the voice recognition module uses a voice recognition module with a high priority level which can be preset as a user by using the first voice processing model, or a voice recognition module which is used by a specific user and is determined by the air conditioner through a machine learning process and is used by the specific user more frequently or a voice recognition module used by a higher frequency, so that the air conditioner can recognize the voice instruction of the specific user more quickly and accurately, especially for the user who is used to speak, the voice recognition module uses the first voice processing model and can be a module corresponding to the dialect which the user is used by the user, the method is beneficial to improving the use experience of the voice function of the user, and the dialect can be northeast speech, southern Fujian speech, southern Henan speech, Sichuan speech, Shanxi speech and the like, but is not limited to the method.
The steps in the method of the invention can be sequentially adjusted, combined and deleted according to actual needs.
The units in the device of the invention can be merged, divided and deleted according to actual needs.
It will be understood by those skilled in the art that all or part of the steps in the methods of the embodiments described above may be implemented by instructions associated with a program, which may be stored in a computer-readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), compact disc-Read-Only Memory (CD-ROM), or other Memory, magnetic disk, magnetic tape, or magnetic tape, Or any other medium which can be used to carry or store data and which can be read by a computer.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A voice recognition method of an air conditioner is characterized by comprising the following steps:
controlling a voice recognition module to recognize a received voice instruction by adopting a first voice processing model within a preset time period of the operation of the air conditioner;
and switching to a second voice processing model for recognition according to the recognition result of the voice command by the voice recognition module through the first voice processing model.
2. The voice recognition method of an air conditioner according to claim 1,
the voice recognition module adopts the first voice processing model with the use frequency larger than that of the second voice processing model.
3. The method for recognizing the voice of the air conditioner according to claim 1 or 2, wherein switching to a second voice processing model for recognition according to the recognition result of the voice command by the voice recognition module through a first voice processing model specifically comprises:
judging whether the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to a preset success rate or not;
and judging that the recognition success rate of the voice recognition module on at least one voice instruction by adopting a first voice processing model is less than or equal to the preset success rate, and switching to a second voice processing model for recognition.
4. The voice recognition method of an air conditioner according to claim 1 or 2, further comprising:
receiving a plurality of voice instructions within a preset time period of the operation of the air conditioner;
determining spatial orientation information of a plurality of voice commands;
and controlling a plurality of voice processing model blocks to simultaneously recognize a plurality of voice commands according to the space orientation information, or recognizing a plurality of voice commands by adopting a voice processing model corresponding to the space orientation information at the last time.
5. The method of claim 4, wherein the controlling a plurality of speech processing model blocks to simultaneously recognize a plurality of speech commands according to the spatial orientation information, or recognizing a plurality of speech commands by using a speech processing model corresponding to the spatial orientation information last time comprises:
analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands;
judging whether the similarity between the azimuth angles is smaller than a preset similarity or not;
and judging that the similarity between the plurality of azimuth angles is smaller than the preset similarity, and sequentially adopting voice recognition modules corresponding to the azimuth angles to recognize according to the receiving sequence of the plurality of voice instructions.
6. The method of claim 4, wherein a plurality of speech processing model blocks are controlled to simultaneously recognize a plurality of speech commands according to the spatial orientation information, or a speech processing model corresponding to the spatial orientation information is used to recognize a plurality of speech commands, and the method further comprises:
analyzing the spatial azimuth information to determine azimuth angles of a plurality of voice commands;
judging whether the similarity among the azimuth angles is greater than or equal to a preset similarity or not;
and judging that the similarity between the plurality of azimuth angles is greater than or equal to the preset similarity, and controlling a plurality of voice processing model blocks to simultaneously recognize the plurality of voice commands.
7. A voice recognition apparatus of an air conditioner, comprising:
a memory configured to be able to store a computer program that, when executed by the processor, is able to implement the steps of the voice recognition method of an air conditioner according to any one of claims 1 to 6.
8. An air conditioner, comprising:
a memory configured to be able to store a computer program that, when executed by the processor, is able to implement the steps of the voice recognition method of an air conditioner according to any one of claims 1 to 6.
9. An air conditioner, comprising:
the voice recognition apparatus of an air conditioner as claimed in claim 7.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which when executed, implements the voice recognition method of an air conditioner according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010246368.1A CN111312214B (en) | 2020-03-31 | 2020-03-31 | Voice recognition method and device for air conditioner, air conditioner and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010246368.1A CN111312214B (en) | 2020-03-31 | 2020-03-31 | Voice recognition method and device for air conditioner, air conditioner and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111312214A true CN111312214A (en) | 2020-06-19 |
| CN111312214B CN111312214B (en) | 2022-12-16 |
Family
ID=71151635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010246368.1A Active CN111312214B (en) | 2020-03-31 | 2020-03-31 | Voice recognition method and device for air conditioner, air conditioner and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111312214B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724766A (en) * | 2020-06-29 | 2020-09-29 | 合肥讯飞数码科技有限公司 | Language identification method, related equipment and readable storage medium |
| CN112349276A (en) * | 2020-12-03 | 2021-02-09 | 恒大新能源汽车投资控股集团有限公司 | Vehicle-mounted voice interaction method and device and electronic equipment |
| CN113959029A (en) * | 2021-11-15 | 2022-01-21 | 王毅 | Voice-controlled atomizer and control method thereof |
| WO2023082891A1 (en) * | 2021-11-11 | 2023-05-19 | 青岛海尔空调器有限总公司 | Control method and apparatus for voice air conditioner, voice air conditioner, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180268808A1 (en) * | 2015-10-21 | 2018-09-20 | Samsung Electronics Co., Ltd. | Electronic apparatus, speech recognition method thereof, and non-transitory computer readable recording medium |
| CN108735227A (en) * | 2018-06-22 | 2018-11-02 | 北京三听科技有限公司 | A kind of voice signal for being picked up to microphone array carries out the method and system of Sound seperation |
| CN109360563A (en) * | 2018-12-10 | 2019-02-19 | 珠海格力电器股份有限公司 | A kind of sound control method, device, storage medium and air-conditioning |
| CN109584876A (en) * | 2018-12-26 | 2019-04-05 | 珠海格力电器股份有限公司 | Processing method, device and the voice air conditioner of voice data |
| CN110400562A (en) * | 2019-06-24 | 2019-11-01 | 歌尔科技有限公司 | Interaction processing method, device, equipment and audio frequency apparatus |
-
2020
- 2020-03-31 CN CN202010246368.1A patent/CN111312214B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180268808A1 (en) * | 2015-10-21 | 2018-09-20 | Samsung Electronics Co., Ltd. | Electronic apparatus, speech recognition method thereof, and non-transitory computer readable recording medium |
| CN108735227A (en) * | 2018-06-22 | 2018-11-02 | 北京三听科技有限公司 | A kind of voice signal for being picked up to microphone array carries out the method and system of Sound seperation |
| CN109360563A (en) * | 2018-12-10 | 2019-02-19 | 珠海格力电器股份有限公司 | A kind of sound control method, device, storage medium and air-conditioning |
| CN109584876A (en) * | 2018-12-26 | 2019-04-05 | 珠海格力电器股份有限公司 | Processing method, device and the voice air conditioner of voice data |
| CN110400562A (en) * | 2019-06-24 | 2019-11-01 | 歌尔科技有限公司 | Interaction processing method, device, equipment and audio frequency apparatus |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724766A (en) * | 2020-06-29 | 2020-09-29 | 合肥讯飞数码科技有限公司 | Language identification method, related equipment and readable storage medium |
| CN111724766B (en) * | 2020-06-29 | 2024-01-05 | 合肥讯飞数码科技有限公司 | Language identification method, related equipment and readable storage medium |
| CN112349276A (en) * | 2020-12-03 | 2021-02-09 | 恒大新能源汽车投资控股集团有限公司 | Vehicle-mounted voice interaction method and device and electronic equipment |
| WO2023082891A1 (en) * | 2021-11-11 | 2023-05-19 | 青岛海尔空调器有限总公司 | Control method and apparatus for voice air conditioner, voice air conditioner, and storage medium |
| CN113959029A (en) * | 2021-11-15 | 2022-01-21 | 王毅 | Voice-controlled atomizer and control method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111312214B (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111312214B (en) | Voice recognition method and device for air conditioner, air conditioner and readable storage medium | |
| CN108183844B (en) | Intelligent household appliance voice control method, device and system | |
| CN108831469B (en) | Voice command customizing method, device and equipment and computer storage medium | |
| CN107644638B (en) | Audio recognition method, device, terminal and computer readable storage medium | |
| JP4363076B2 (en) | Voice control device | |
| JP4446312B2 (en) | Method and system for displaying a variable number of alternative words during speech recognition | |
| US20060195323A1 (en) | Distributed speech recognition system | |
| US7689424B2 (en) | Distributed speech recognition method | |
| CN109360563B (en) | Voice control method and device, storage medium and air conditioner | |
| JP6675078B2 (en) | Misrecognition and correction method, misrecognition and correction device, and misrecognition and correction program | |
| CN111883118A (en) | Vehicle control method and device based on personalized voice and storage medium | |
| CN103051781A (en) | Method for controlling backstage through voice and mobile terminal | |
| CN110288990B (en) | Voice control optimization method, storage medium and intelligent terminal | |
| WO2020024620A1 (en) | Voice information processing method and device, apparatus, and storage medium | |
| CN111312253A (en) | Voice control method, cloud server and terminal equipment | |
| CN105609105B (en) | Speech recognition system and speech recognition method | |
| CN105825848A (en) | Method, device and terminal for voice recognition | |
| CN113851124A (en) | Method and apparatus for controlling home appliance, and storage medium | |
| CN113571096B (en) | Speech emotion classification model training method and device, computer equipment and medium | |
| JP2005234332A (en) | Electronic equipment controller | |
| KR20170051994A (en) | speech recognition device and here of control Method | |
| WO2021098318A1 (en) | Response method, terminal, and storage medium | |
| CN110400568B (en) | Awakening method of intelligent voice system, intelligent voice system and vehicle | |
| CN112863496A (en) | Voice endpoint detection method and device | |
| JP7192858B2 (en) | Equipment control device and control method for controlling equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |