CN116399002A

CN116399002A - Air conditioner control method and device and air conditioner

Info

Publication number: CN116399002A
Application number: CN202310549457.7A
Authority: CN
Inventors: 张文炫
Original assignee: Gree Electric Appliances Inc of Zhuhai
Current assignee: Gree Electric Appliances Inc of Zhuhai
Priority date: 2023-05-15
Filing date: 2023-05-15
Publication date: 2023-07-07

Abstract

The invention discloses a control method and device of an air conditioner and the air conditioner. Wherein the method comprises the following steps: acquiring a current voice segment of a space where an air conditioner is located, wherein the current voice segment is a voice segment acquired by voice acquisition equipment arranged in the space; matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result; when the matching result shows that the target labeling voice fragment with the similarity larger than the similarity threshold value with the current voice fragment exists in the voice recognition library, acquiring a target control strategy corresponding to the target labeling voice fragment; and controlling the air conditioner to operate according to the target control strategy. The invention solves the technical problems that the control mode of the air conditioner in the related art has lower intelligent degree, cannot meet the actual demands of users, and has lower user experience.

Description

Air conditioner control method and device and air conditioner

Technical Field

The invention relates to the technical field of intelligent household appliance control, in particular to a control method and device of an air conditioner and the air conditioner.

Background

At present, air conditioners tend to be more intelligent, but the air conditioners cannot meet the use requirements of users by controlling the air conditioners according to crowd types, scene environments and subjective feelings of people. In addition, the mode of controlling the preset command word and the air conditioning mode of the air conditioner through voice can not meet the personalized requirements of the user. With the development of reinforcement learning, a user makes a decision to control an air conditioner according to subjective intention of a person through a situational dialogue with the air conditioner.

However, the current method of controlling the air conditioner by the contextual dialogue method requires a specified command keyword and can only control the air supply function of the air conditioner. For example, in the prior art, an air conditioner voice control method for adjusting an air conditioner according to the cold and hot feeling of a user is proposed, and the air conditioner is controlled according to the analysis of the cold and hot feeling of the user voice feedback, but a trigger word and an air conditioner operation mode are required to be preset, and real-time self-adaptive update cannot be performed according to the personal requirement of the user. For another example, a control method for adjusting based on the environment in which the air conditioner is located is also proposed in the prior art, and the method can adaptively control the parameters of the air conditioner according to the subjective feeling of the user and the current environment state, but cannot intelligently understand the subjective feeling change of the dynamic behavior of the person in the same environment.

Aiming at the problems that the control mode of the air conditioner in the related technology is low in intelligent degree, the actual requirements of users cannot be met, and the user experience is low, an effective solution is not proposed at present.

Disclosure of Invention

The embodiment of the invention provides a control method and device of an air conditioner and the air conditioner, which at least solve the technical problems that the control mode of the air conditioner in the related art is low in intelligent degree, cannot meet the actual demands of users, and causes low user experience.

According to an aspect of the embodiment of the present invention, there is also provided a control method of an air conditioner, including: acquiring a current voice segment of a space where the air conditioner is located, wherein the current voice segment is a voice segment acquired by voice acquisition equipment arranged in the space; matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises the plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation of the plurality of sample voice fragments according to the correlation of the plurality of sample voice fragments with each control strategy of the air conditioner; when the matching result shows that a target labeling voice fragment with the similarity larger than a similarity threshold exists in the voice recognition library, acquiring a target control strategy corresponding to the target labeling voice fragment; and controlling the air conditioner to operate according to the target control strategy.

Optionally, the control method of the air conditioner further includes: acquiring the plurality of sample speech segments; determining the relativity of the plurality of sample voice fragments and the control strategies of the air conditioner respectively; performing relevance labeling on the plurality of sample voice fragments according to the relevance between the plurality of sample voice fragments and each control strategy respectively to obtain a plurality of labeled voice fragments; and generating the voice recognition library by utilizing the plurality of marked voice fragments.

Optionally, acquiring the plurality of sample speech segments includes: acquiring a plurality of general words and a plurality of visual descriptors, wherein the general words are words indirectly related to the control strategy of the air conditioner, and the visual words are words directly related to the control strategy of the air conditioner; and generating the correlation between the plurality of general words and the plurality of visual descriptors by using a natural language processing mode so as to obtain the plurality of sample voice fragments.

Optionally, performing relevance labeling on the plurality of sample voice fragments according to relevance between the plurality of sample voice fragments and each control policy, to obtain the plurality of labeled voice fragments, including: respectively determining first relativity between the plurality of visual words in the plurality of sample voice fragments and each control strategy; respectively determining second relativity between the common words and each control strategy in the plurality of sample voice fragments according to the first relativity; and marking the correlation degree of the plurality of sample voice fragments according to the first correlation degree and the second correlation degree to obtain the plurality of marked voice fragments.

Optionally, matching the current speech segment with a plurality of labeled speech segments in a speech recognition library includes: inputting the current voice fragment into the voice recognition library so as to carry out voice fragment matching in the plurality of marked voice fragments according to the current voice fragment by utilizing the voice recognition library.

Optionally, after the target control policy corresponding to the target labeling voice segment is obtained, the control method of the air conditioner further includes: the target control strategy is sent to a target terminal; acquiring feedback information of the target control strategy through the target terminal; and when the feedback information indicates that the air conditioner is operated according to the target control strategy, the target control strategy is sent to the air conditioner.

Optionally, the control method of the air conditioner further includes: acquiring an adjustment instruction received by the air conditioner in the running process according to the target control strategy; and updating the voice recognition library according to the feedback information and the adjustment instruction.

According to another aspect of the embodiment of the present invention, there is also provided a control device for an air conditioner, including: the first acquisition unit is used for acquiring a current voice fragment of the space where the air conditioner is located, wherein the current voice fragment is a voice fragment acquired by voice acquisition equipment arranged in the space; the matching unit is used for matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises the plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation degree of the plurality of sample voice fragments according to the correlation degree of the plurality of sample voice fragments with each control strategy of the air conditioner; the second obtaining unit is used for obtaining a target control strategy corresponding to the target annotation voice fragment when the matching result shows that the target annotation voice fragment with the similarity larger than the similarity threshold exists in the voice recognition library; and the control unit is used for controlling the air conditioner to operate according to the target control strategy.

Optionally, the control device of the air conditioner further includes: a third acquisition unit configured to acquire the plurality of sample speech fragments; a determining unit, configured to determine a correlation degree between the plurality of sample speech segments and each of the control policies of the air conditioner, respectively; the labeling unit is used for labeling the correlation degree of the plurality of sample voice fragments according to the correlation degree of the plurality of sample voice fragments and each control strategy respectively, so as to obtain a plurality of labeled voice fragments; and the generating unit is used for generating the voice recognition library by utilizing the plurality of marked voice fragments.

Optionally, the third obtaining unit includes: the first acquisition module is used for acquiring a plurality of general words and a plurality of visual descriptors, wherein the general words are words indirectly related to the control strategy of the air conditioner, and the visual words are words directly related to the control strategy of the air conditioner; and the second acquisition module is used for generating the correlation between the plurality of general words and the plurality of visual descriptors by using a natural language processing mode so as to obtain the plurality of sample voice fragments.

Optionally, the labeling unit includes: the first determining module is used for respectively determining first relativity between the plurality of visual words in the plurality of sample voice fragments and each control strategy; the second determining module is used for respectively determining second relativity between the plurality of common words and each control strategy in the plurality of sample voice fragments according to the first relativity; and the labeling module is used for labeling the correlation degree of the plurality of sample voice fragments according to the first correlation degree and the second correlation degree to obtain a plurality of labeled voice fragments.

Optionally, the matching unit includes: and the processing module is used for inputting the current voice fragment into the voice recognition library so as to perform voice fragment matching in the plurality of marked voice fragments according to the current voice fragment by utilizing the voice recognition library.

Optionally, the control device of the air conditioner further includes: the sending unit is used for sending the target control strategy to a target terminal after obtaining the target control strategy corresponding to the target labeling voice fragment; the third acquisition unit is used for acquiring feedback information of the target control strategy through the target terminal; and the sending unit is used for sending the target control strategy to the air conditioner when the feedback information indicates that the air conditioner is operated according to the target control strategy.

Optionally, the control device of the air conditioner further includes: a fourth obtaining unit, configured to obtain an adjustment instruction received by the air conditioner in the running process according to the target control policy; and the updating unit is used for updating the voice recognition library according to the feedback information and the adjustment instruction.

According to another aspect of the embodiment of the present invention, there is also provided an air conditioner using the control method of any one of the above air conditioners.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium including a stored program, wherein the program executes the control method of the air conditioner of any one of the above.

According to another aspect of the embodiment of the present invention, there is provided a processor for executing a program, wherein the program executes the control method of the air conditioner according to any one of the above.

In the embodiment of the invention, a current voice segment of a space where an air conditioner is located is obtained, wherein the current voice segment is a voice segment acquired by voice acquisition equipment arranged in the space; matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises a plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation of the plurality of sample voice fragments according to the correlation of the plurality of sample voice fragments with each control strategy of the air conditioner; when the matching result shows that the target labeling voice fragment with the similarity larger than the similarity threshold value with the current voice fragment exists in the voice recognition library, acquiring a target control strategy corresponding to the target labeling voice fragment; and controlling the air conditioner to operate according to the target control strategy. The control method of the air conditioner provided by the invention realizes the purpose of determining the control strategy of the air conditioner according to different oral expressions of users, improves the intelligent degree of the air conditioner, and further provides a more comfortable environment for the users, and solves the technical problems that the control mode of the air conditioner in the related art is relatively low in intelligent degree, cannot meet the actual demands of the users, and causes lower user experience.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:

fig. 1 is a block diagram of a hardware configuration of a mobile terminal of a control method of an air conditioner according to an embodiment of the present invention;

fig. 2 is a flowchart of a control method of an air conditioner according to an embodiment of the present invention;

FIG. 3 is a flow chart of a preset training model according to an embodiment of the present invention;

fig. 4 is a flowchart of an alternative control method of an air conditioner according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a speech recognition library update according to an embodiment of the invention;

fig. 6 is a schematic view of a control device of an air conditioner according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

As introduced in the background art, the control mode of the air conditioner in the related art has low intelligent degree, and cannot meet the actual requirements of users, so that the defect of low user experience is caused. Embodiments of the invention provide a control method and device for an air conditioner, the air conditioner, a computer readable storage medium and a processor.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

The method embodiments provided in the embodiments of the present invention may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of the mobile terminal according to a control method of an air conditioner according to an embodiment of the present invention. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a control method of an air conditioner in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

According to an embodiment of the present invention, there is provided a method embodiment of a control method of an air conditioner, it should be noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that herein.

Fig. 2 is a flowchart of a control method of an air conditioner according to an embodiment of the present invention, and as shown in fig. 2, the control method of the air conditioner includes the steps of:

step S202, a current voice segment of a space where the air conditioner is located is obtained, wherein the current voice segment is a voice segment acquired by voice acquisition equipment arranged in the space.

Alternatively, the current speech segment herein may contain common words, for example, (1) strong correlations: the action verbs such as sports, rest, housework and the like, and the status words such as human body status, weather and the like; (2) weak correlation: nouns such as objects and places, graduated words and the like; (3) independent of: subject, mood assisted words, abstract concept nouns, imaginary words, etc.; visual words may also be included, for example, (1) human perception: cold, hot, noisy, etc. sense words; (2) scene description: switch, temperature, humidity, wind speed, direction, noise, time, etc.; (3) modifier: modifying words such as too, good, something, very, preparation, want and the like, so that the air conditioner can adapt to various personalized spoken language expressions, and a control strategy corresponding to most voices sent by users can be found.

The correlation between the general words and the visual description words is judged based on the air conditioning function, the correlation between the words and the visual description words is compared, and the judgment is carried out with the highest combination correlation. For example, a sentence strongly related to the air conditioning function is contained: "I prepare for exercise" has a strong correlation with heat in the visual description; weakly related statements: the visual description of 'many people come from home' is related to weak heat; statements not related to the air conditioning function do not make a control strategy. The above relativity words are only exemplified, and the relativity is divided according to actual conditions when the data are marked.

In this embodiment, a voice acquisition device may be disposed in a room where the air conditioner is located, so as to acquire a voice command issued by the user, that is, the current voice clip.

The voice collecting device can be a component integrated in the air conditioner or a voice collecting component arranged independently.

Step S204, matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises a plurality of marked voice fragments, and the marked voice fragments are voice fragments obtained by marking the correlation degree of the plurality of sample voice fragments according to the correlation degree of the plurality of sample voice fragments and each control strategy of the air conditioner.

In this embodiment, the current speech segment may be matched with a pre-constructed speech recognition library to determine whether a speech segment having the same or higher similarity to the current speech segment exists in the speech recognition library, so as to determine a control policy of the air conditioner as a reference.

The voice recognition library comprises a plurality of marked voice fragments, wherein the marked voice fragments are obtained by marking sample voice fragments, and the marked content is determined according to the correlation degree of the sample voice fragments and each control strategy of the air conditioner.

Step S206, when the matching result shows that the target labeling voice fragments with the similarity larger than the similarity threshold value with the current voice fragments exist in the voice recognition library, acquiring a target control strategy corresponding to the target labeling voice fragments.

In this embodiment, when it is determined that there is a target labeled speech segment in the speech recognition library having a similarity greater than the similarity threshold with the current speech segment, a control policy corresponding to the target labeled speech segment may be determined and used as the target control policy.

Step S208, the air conditioner is controlled to operate according to the target control strategy.

As can be seen from the above, in the embodiment of the present invention, a current voice segment of a space where an air conditioner is located may be obtained first, where the current voice segment is a voice segment collected by a voice collecting device disposed in the space; then matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises a plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation degree of the plurality of sample voice fragments according to the correlation degree of the plurality of sample voice fragments and each control strategy of the air conditioner; then, when the matching result shows that the target labeling voice fragments with the similarity larger than the similarity threshold value exist in the voice recognition library, acquiring a target control strategy corresponding to the target labeling voice fragments; the air conditioner is controlled to run according to the target control strategy, so that the aim of determining the control strategy of the air conditioner according to different oral expressions of the user is fulfilled, the intelligent degree of the air conditioner is improved, and a more comfortable environment can be provided for the user.

Therefore, by the technical scheme provided by the embodiment of the invention, the technical problem that the control mode of the air conditioner in the related art is low in intelligent degree, cannot meet the actual requirements of users, and causes low user experience is solved.

According to the above embodiment of the present invention, the control method of the air conditioner further includes: acquiring a plurality of sample voice fragments; determining the relativity of a plurality of sample voice fragments and each control strategy of the air conditioner respectively; performing relevance labeling on the plurality of sample voice fragments according to the relevance of the plurality of sample voice fragments and each control strategy respectively to obtain a plurality of labeled voice fragments; a speech recognition library is generated using the plurality of tagged speech segments.

In this embodiment, a plurality of sample speech segments may be first obtained, where the plurality of sample speech segments also include a generic word and an intuitive word, respectively; and then determining the relevance of the plurality of sample voice fragments with each control strategy of the air conditioner respectively, and marking the relevance of the plurality of sample voice fragments according to the determined relevance to obtain a plurality of marked voice fragments, so that a voice recognition library comprising the plurality of marked voice fragments can be obtained.

Fig. 3 is a flowchart of a preset training model according to an embodiment of the present invention, as shown in fig. 3, after a plurality of sample speech segments including general words and visual descriptors are obtained, the plurality of sample speech segments are processed by a natural speech processing model, for example, after operations such as word segmentation, filtering, etc., the visual descriptors and general words are labeled, so as to establish a correlation between the general words and the visual descriptors, and the speech recognition library is obtained.

In the above embodiment, acquiring a plurality of sample speech segments includes: acquiring a plurality of general words and a plurality of visual descriptors, wherein the general words are words indirectly related to the control strategy of the air conditioner, and the visual words are words directly related to the control strategy of the air conditioner; and generating the correlation between the common words and the visual descriptors by using a natural language processing mode so as to obtain a plurality of sample voice fragments.

In this embodiment, after a plurality of general words and a plurality of visual descriptors are acquired, a correlation between the plurality of general words and the plurality of visual descriptors may be generated by using a natural language processing manner, so as to obtain a plurality of sample speech segments.

As further shown in fig. 3, after the voice recognition library is determined, each sample control policy of the air conditioner may be obtained, and then a relationship between each labeled voice segment and each sample control policy in the voice recognition library is established, so as to perform pre-training of the model between the control policy and the voice segment.

According to the embodiment of the present invention, a plurality of sample speech segments are labeled according to their relevance to each control policy, so as to obtain a plurality of labeled speech segments, including: respectively determining a first correlation degree between a plurality of visual words in a plurality of sample voice fragments and each control strategy; respectively determining second relativity between a plurality of common words in a plurality of sample voice fragments and each control strategy according to the first relativity; and labeling the correlation degree of the plurality of sample voice fragments according to the first correlation degree and the second correlation degree to obtain a plurality of labeled voice fragments.

In this embodiment, as a pre-training data and model pre-training section, pre-training is performed as a unified speech control standard by pre-training data and model in advance, as shown in fig. 3: visual descriptors in the pre-training data are divided into: (1) human body feeling: cold, hot, noisy, etc. sense words; (2) scene description: switch, temperature, humidity, wind speed, direction, noise, time, etc.; (3) modifier: modifying words such as too, good, dotted, very, ready, want, etc., the control strategy of the corresponding air conditioner can be determined based on the above 3 kinds of voices: power supply, temperature, humidity, wind speed, air deflector direction, power, time, etc.

In the embodiment of the invention, the voice recognition library labeling and the pre-training model are finished in advance on line, and the pre-training model and the personalized model of the user are called by a cloud platform.

According to the above embodiment of the present invention, matching a current speech segment with a plurality of labeled speech segments in a speech recognition library includes: and inputting the current voice fragment into a voice recognition library so as to perform voice fragment matching in a plurality of labeled voice fragments according to the current voice fragment by utilizing the voice recognition library.

In this embodiment, the current speech segment may be input to the speech recognition library, so that the speech recognition library may be utilized to perform speech segment matching in a plurality of labeled speech segments according to the current speech segment to determine whether a target speech segment with a higher correlation degree with the current speech segment exists in the speech recognition library.

Fig. 4 is a flowchart of an alternative control method of an air conditioner according to an embodiment of the present invention, as shown in fig. 4, when a user first uses the air conditioner, a pre-training model (i.e., a mapping relationship between a voice recognition library and a control policy) is invoked, and otherwise, a user personalized training model is invoked. The pre-training data and the model pre-training part are used as unified voice control standards through pre-training data and model pre-training in the earlier stage, and the pre-training data are already described above and are not described in detail herein. After the voice is input into the voice recognition library, voice recognition is performed; when the control strategy corresponding to the voice does not exist or the control strategy needs to be adjusted, continuing model training; otherwise, the control strategy corresponding to the voice is used for controlling the operation of the air conditioner. Wherein, in the course that the air conditioner operates according to the above-mentioned control strategy, will control the tactics feedback, if satisfied, continue the model training; otherwise, the control strategy needs to be adjusted, and the voice input stage is returned.

That is, in the embodiment of the invention, the control system of the intelligent device APP-gateway-cloud platform can be used for calling and updating the model, the user sends voice through the intelligent device APP, the gateway returns the voice to the cloud platform to acquire the control strategy, and then the control strategy is returned to the gateway to control the air conditioner. When the user uses the model for the first time, a pre-training model is called, and otherwise, a user personalized training model is called.

The user side updates the control strategy, for example, the user inputs voice to call the cloud platform training model, and the air conditioner forms different flows according to the recognition result: (1) the corresponding control strategy exists, and the existing corresponding control strategy is applied; (2) no speech and corresponding control strategy is present, as in fig. 4: comparing the input voice with the voice recognition library in a correlation degree, applying a control strategy with high correlation degree, and updating different control strategies of a reinforcement learning model according to feedback of a user as reinforcement learning rewards and current state feedback of an air conditioner; (3) there is a corresponding control strategy but there is a need to adjust the control strategy: on the existing control strategy, the reinforcement learning model is updated according to the feedback of the user; and (3) through the two processes (2) and (3), the different spoken language expressions and the control strategies of different users are adaptively updated to strengthen the learning model so as to meet the requirements and the use habits of different users, thereby achieving the voice control air conditioning method based on the language habits of the users. When the process (2) or (3) is triggered, the voice received by the mobile phone APP is transmitted back to the cloud platform by the gateway to carry out reinforcement learning model training, and after the feedback control strategy of the user is satisfied, the reinforcement learning model which is updated finally is stored as a user personalized training model, and the model is called when the user uses the system next time.

According to the above embodiment of the present invention, after obtaining the target control policy corresponding to the target labeling voice segment, the control method of the air conditioner may further include: transmitting the target control strategy to the target terminal; acquiring feedback information of a target control strategy through a target terminal; and when the feedback information indicates that the running air conditioner runs according to the target control strategy, the target control strategy is sent to the air conditioner.

In this embodiment, it may be determined by a user feedback mechanism whether the control strategy meets the user's needs. For example, the target control policy may be sent to a mobile phone of the user, after the user views the target control policy through the mobile phone, the user may give a feedback, and if agreeing to control the air conditioner by adopting the target control policy, the agreement information may be fed back, so that the cloud platform may send the target control policy to the air conditioner, so that the air conditioner operates according to the target control policy.

According to an embodiment of the present invention, the control method of the air conditioner may further include: acquiring an adjustment instruction received by an air conditioner in the running process according to a target control strategy; and updating the voice recognition library according to the feedback information and the adjustment instruction.

In this embodiment, if the air conditioner is operated according to the target control policy, after receiving the adjustment instruction of the user, the air conditioner adjusts the operation mode according to the adjustment instruction and operates according to the adjusted operation mode.

In order to make the speech fragments stored in the speech recognition library richer to adapt to the spoken language expression of the user, the speech recognition library can be updated according to the adjustment instruction and the user feedback information.

FIG. 5 is a schematic diagram of updating a speech recognition library according to an embodiment of the present invention, as shown in FIG. 5, comparing unlabeled speech (for example, an adjustment instruction issued by a user) with the speech recognition library, searching for speech with high correlation with unlabeled speech in the speech recognition library, and controlling the operation of the air conditioner by using a control strategy corresponding to the speech with high correlation; then, using a reinforcement learning model to reinforcement learn the relation between the voice recognition library and the control strategy; then, control strategy feedback is carried out, and when the feedback is satisfied, the voice and the corresponding control strategy are updated; and if not satisfied, the control strategy is adjusted, so that the user can give different spoken language expressions to control the air conditioner, and the control modes of different demands of the user are met.

Therefore, through the technical scheme provided by the embodiment of the invention, the labeling visual description, the related voice and the corresponding control air conditioning strategy are adopted as the pre-training data training model, and the corresponding air conditioning control strategy is updated according to different oral expressions and using habits of the user by adopting the reinforcement learning technology at the user side. Has the following beneficial effects: 1) Decision control air conditioner is carried out according to the situational dialogue of the user, and the user does not need to speak a preset command word; 2) The personal spoken language expression and the corresponding air conditioner control strategy of the user are adaptively updated, so that the voice of the user can be intelligently recognized to control the air conditioner, the air conditioner control strategy can be updated according to different spoken language expressions of the user, and the comfort level of the user in using the air conditioner is improved.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.

According to an embodiment of the present invention, there is further provided a control device for an air conditioner for implementing the control method of an air conditioner, and fig. 6 is a schematic diagram of the control device for an air conditioner according to the embodiment of the present invention, as shown in fig. 6, the device includes: a first acquisition unit 61, a matching unit 63, a second acquisition unit 65, and a control unit 67. The control device of the air conditioner will be described below.

A first obtaining unit 61, configured to obtain a current voice segment of a space where the air conditioner is located, where the current voice segment is a voice segment collected by a voice collecting device disposed in the space.

The matching unit 63 is configured to match a current speech segment with a plurality of labeled speech segments in a speech recognition library to obtain a matching result, where the speech recognition library includes a plurality of labeled speech segments, and the plurality of labeled speech segments are speech segments obtained by labeling the correlation between the plurality of sample speech segments and each control policy of the air conditioner according to the correlation between the plurality of sample speech segments.

The second obtaining unit 65 is configured to obtain, when the matching result indicates that a target labeling voice segment with a similarity greater than a similarity threshold exists in the voice recognition library, a target control policy corresponding to the target labeling voice segment.

And a control unit 67 for controlling the air conditioner to operate according to the target control strategy.

Here, it should be noted that the first obtaining unit 61, the matching unit 63, the second obtaining unit 65, and the control unit 67 correspond to steps S202 to S210 in the above embodiments, and the four units are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in the above embodiments.

As can be seen from the above, in the solution described in the above embodiment of the present invention, the first obtaining unit may be used to obtain a current voice segment of a space where the air conditioner is located, where the current voice segment is a voice segment collected by a voice collecting device disposed in the space; then, matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library by using a matching unit to obtain a matching result, wherein the voice recognition library comprises a plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation of the plurality of sample voice fragments according to the correlation of the plurality of sample voice fragments with each control strategy of the air conditioner; then, when the matching result shows that the target labeling voice fragments with the similarity larger than the similarity threshold value exist in the voice recognition library, a second acquisition unit is utilized to acquire a target control strategy corresponding to the target labeling voice fragments; finally, the control unit is used for controlling the air conditioner to run according to the target control strategy, so that the aim of determining the control strategy of the air conditioner according to different oral expressions of the user is fulfilled, the intelligent degree of the air conditioner is improved, and a more comfortable environment can be provided for the user.

Optionally, the control device of the air conditioner further includes: a third acquisition unit configured to acquire a plurality of sample speech fragments; the determining unit is used for determining the correlation degree of the plurality of sample voice fragments and each control strategy of the air conditioner respectively; the labeling unit is used for labeling the correlation degree of the plurality of sample voice fragments according to the correlation degree of the plurality of sample voice fragments with each control strategy respectively to obtain a plurality of labeled voice fragments; and the generating unit is used for generating a voice recognition library by utilizing the plurality of marked voice fragments.

Optionally, the third obtaining unit includes: the first acquisition module is used for acquiring a plurality of general words and a plurality of visual descriptors, wherein the general words are words indirectly related to the control strategy of the air conditioner, and the visual words are words directly related to the control strategy of the air conditioner; and the second acquisition module is used for generating the correlation between the common words and the visual description words by using a natural language processing mode so as to obtain a plurality of sample voice fragments.

Optionally, the labeling unit includes: the first determining module is used for respectively determining first relativity between a plurality of visual words in a plurality of sample voice fragments and each control strategy; the second determining module is used for respectively determining second correlation degrees between a plurality of common words in a plurality of sample voice fragments and each control strategy according to the first correlation degrees; and the labeling module is used for labeling the correlation degree of the plurality of sample voice fragments according to the first correlation degree and the second correlation degree to obtain a plurality of labeled voice fragments.

Optionally, the matching unit includes: the processing module is used for inputting the current voice fragment into the voice recognition library so as to carry out voice fragment matching in a plurality of marked voice fragments according to the current voice fragment by utilizing the voice recognition library.

Optionally, the control device of the air conditioner further includes: the sending unit is used for sending the target control strategy to the target terminal after the target control strategy corresponding to the target labeling voice fragment is obtained; the third acquisition unit is used for acquiring feedback information of the target control strategy through the target terminal; and the sending unit is used for sending the target control strategy to the air conditioner when the feedback information indicates that the running air conditioner runs according to the target control strategy.

Optionally, the control device of the air conditioner further includes: the fourth acquisition unit is used for acquiring an adjustment instruction received in the running process of the air conditioner according to the target control strategy; and the updating unit is used for updating the voice recognition library according to the feedback information and the adjustment instruction.

According to another aspect of the embodiment of the present invention, there is also provided an air conditioner, and a control method of the air conditioner using any one of the above.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium including a stored program, wherein the program performs the control method of the air conditioner of any one of the above.

Alternatively, in the present embodiment, the above-described computer-readable storage medium may be located in any one of a group of computer terminals in a computer network, or in any one of a group of communication devices.

Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: acquiring a current voice segment of a space where an air conditioner is located, wherein the current voice segment is a voice segment acquired by voice acquisition equipment arranged in the space; matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises a plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation of the plurality of sample voice fragments according to the correlation of the plurality of sample voice fragments with each control strategy of the air conditioner; when the matching result shows that the target labeling voice fragment with the similarity larger than the similarity threshold value with the current voice fragment exists in the voice recognition library, acquiring a target control strategy corresponding to the target labeling voice fragment; and controlling the air conditioner to operate according to the target control strategy.

Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: acquiring a plurality of sample voice fragments; determining the relativity of a plurality of sample voice fragments and each control strategy of the air conditioner respectively; performing relevance labeling on the plurality of sample voice fragments according to the relevance of the plurality of sample voice fragments and each control strategy respectively to obtain a plurality of labeled voice fragments; a speech recognition library is generated using the plurality of tagged speech segments.

Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: acquiring a plurality of general words and a plurality of visual descriptors, wherein the general words are words indirectly related to the control strategy of the air conditioner, and the visual words are words directly related to the control strategy of the air conditioner; and generating the correlation between the common words and the visual descriptors by using a natural language processing mode so as to obtain a plurality of sample voice fragments.

Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: respectively determining a first correlation degree between a plurality of visual words in a plurality of sample voice fragments and each control strategy; respectively determining second relativity between a plurality of common words in a plurality of sample voice fragments and each control strategy according to the first relativity; and labeling the correlation degree of the plurality of sample voice fragments according to the first correlation degree and the second correlation degree to obtain a plurality of labeled voice fragments.

Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: and inputting the current voice fragment into a voice recognition library so as to perform voice fragment matching in a plurality of labeled voice fragments according to the current voice fragment by utilizing the voice recognition library.

Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: transmitting the target control strategy to the target terminal; acquiring feedback information of a target control strategy through a target terminal; and when the feedback information indicates that the running air conditioner runs according to the target control strategy, the target control strategy is sent to the air conditioner.

Optionally, in the present embodiment, the computer readable storage medium is configured to store program code for performing the steps of: acquiring an adjustment instruction received by an air conditioner in the running process according to a target control strategy; and updating the voice recognition library according to the feedback information and the adjustment instruction.

According to another aspect of the embodiment of the present invention, there is also provided a processor for running a program, wherein the program runs to execute the control method of the air conditioner of any one of the above.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.

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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform 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 Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims

1. A control method of an air conditioner, comprising:

acquiring a current voice segment of a space where the air conditioner is located, wherein the current voice segment is a voice segment acquired by voice acquisition equipment arranged in the space;

matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises the plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation of the plurality of sample voice fragments according to the correlation of the plurality of sample voice fragments with each control strategy of the air conditioner;

when the matching result shows that a target labeling voice fragment with the similarity larger than a similarity threshold exists in the voice recognition library, acquiring a target control strategy corresponding to the target labeling voice fragment;

And controlling the air conditioner to operate according to the target control strategy.

2. The control method of an air conditioner according to claim 1, further comprising:

acquiring the plurality of sample speech segments;

determining the relativity of the plurality of sample voice fragments and the control strategies of the air conditioner respectively;

performing relevance labeling on the plurality of sample voice fragments according to the relevance between the plurality of sample voice fragments and each control strategy respectively to obtain a plurality of labeled voice fragments;

and generating the voice recognition library by utilizing the plurality of marked voice fragments.

3. The method of controlling an air conditioner according to claim 2, wherein obtaining the plurality of sample speech segments comprises:

acquiring a plurality of general words and a plurality of visual descriptors, wherein the general words are words indirectly related to the control strategy of the air conditioner, and the visual words are words directly related to the control strategy of the air conditioner;

and generating the correlation between the plurality of general words and the plurality of visual descriptors by using a natural language processing mode so as to obtain the plurality of sample voice fragments.

4. The method for controlling an air conditioner according to claim 3, wherein performing relevance labeling on the plurality of sample speech segments according to relevance between the plurality of sample speech segments and each of the control policies, to obtain the plurality of labeled speech segments, includes:

respectively determining first relativity between the plurality of visual words in the plurality of sample voice fragments and each control strategy;

respectively determining second relativity between the common words and each control strategy in the plurality of sample voice fragments according to the first relativity;

and marking the correlation degree of the plurality of sample voice fragments according to the first correlation degree and the second correlation degree to obtain the plurality of marked voice fragments.

5. The method for controlling an air conditioner according to claim 1, wherein matching the current speech segment with a plurality of labeled speech segments in a speech recognition library comprises:

inputting the current voice fragment into the voice recognition library so as to carry out voice fragment matching in the plurality of marked voice fragments according to the current voice fragment by utilizing the voice recognition library.

6. The method for controlling an air conditioner according to any one of claims 1 to 5, further comprising, after obtaining a target control policy corresponding to the target labeling voice segment:

the target control strategy is sent to a target terminal;

acquiring feedback information of the target control strategy through the target terminal;

and when the feedback information indicates that the air conditioner is operated according to the target control strategy, the target control strategy is sent to the air conditioner.

7. The control method of an air conditioner according to claim 6, further comprising:

acquiring an adjustment instruction received by the air conditioner in the running process according to the target control strategy;

and updating the voice recognition library according to the feedback information and the adjustment instruction.

8. A control device of an air conditioner, comprising:

the first acquisition unit is used for acquiring a current voice fragment of the space where the air conditioner is located, wherein the current voice fragment is a voice fragment acquired by voice acquisition equipment arranged in the space;

the matching unit is used for matching the current voice fragment with a plurality of marked voice fragments in a voice recognition library to obtain a matching result, wherein the voice recognition library comprises the plurality of marked voice fragments, and the plurality of marked voice fragments are voice fragments obtained by marking the correlation degree of the plurality of sample voice fragments according to the correlation degree of the plurality of sample voice fragments with each control strategy of the air conditioner;

The second obtaining unit is used for obtaining a target control strategy corresponding to the target annotation voice fragment when the matching result shows that the target annotation voice fragment with the similarity larger than the similarity threshold exists in the voice recognition library;

and the control unit is used for controlling the air conditioner to operate according to the target control strategy.

9. An air conditioner characterized in that the air conditioner uses the control method of the air conditioner according to any one of the above claims 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored program, wherein the program executes the control method of the air conditioner of any one of claims 1 to 7.

11. A processor for running a program, wherein the program runs to execute the control method of the air conditioner according to any one of claims 1 to 7.