Control method and device of air conditioner, air conditioner

Abstract

The application discloses a control method and device of an air conditioner and the air conditioner. The method comprises the following steps: obtaining a current voice segment of a space where the air conditioner is located, wherein the current voice segment is a voice segment collected by a voice collection device arranged in the space; matching the current voice segment with a plurality of labeled voice segments in a voice recognition library to obtain a matching result; when the matching result indicates that there is a target labeled voice segment in the voice recognition library, the similarity of which to the current voice segment is greater than a similarity threshold, obtaining a target control strategy corresponding to the target labeled voice segment; and controlling the air conditioner to operate according to the target control strategy. The application solves the technical problem that the control mode of the air conditioner in the related art has a relatively low intelligent degree, cannot meet the actual needs of users, and leads to a low user experience.

Description

Technical Field

[0001] This invention relates to the field of intelligent home appliance control technology, and more specifically, to a control method and device for an air conditioner, and an air conditioner. Background Technology

[0002] Currently, air conditioners are becoming increasingly intelligent, but controlling them based solely on user type, environment, and subjective feelings is no longer sufficient to meet user needs. Furthermore, pre-set command words and modes for voice control also fail to satisfy personalized user requirements. With the development of reinforcement learning, it's becoming possible for air conditioners to make decisions and control decisions based on user preferences through contextual dialogue.

[0003] However, current methods of controlling air conditioners through contextual dialogue require specified command keywords and can only control the air conditioner's airflow function. For example, existing technologies propose voice control methods that adjust the air conditioner based on the user's perceived temperature, analyzing the cause of the temperature sensation based on the user's voice feedback. However, these methods also require preset trigger words and air conditioner operating modes and cannot adaptively update in real time according to the user's individual needs. Another example is existing technologies that propose control methods based on the environment in which the air conditioner is located. This method can adaptively control the air conditioner parameters based on the user's subjective feelings and the current environmental conditions, but it cannot intelligently understand changes in subjective feelings caused by dynamic human behavior in the same environment.

[0004] There is currently no effective solution to the problem that the control methods of air conditioners in the aforementioned technologies have a low level of intelligence, which fails to meet the actual needs of users and results in a poor user experience. Summary of the Invention

[0005] This invention provides a control method and device for an air conditioner, as well as an air conditioner, to at least solve the technical problem in the related art where the control method of the air conditioner has a relatively low level of intelligence, fails to meet the actual needs of users, and results in a low user experience.

[0006] According to one aspect of the present invention, a method for controlling an air conditioner is also provided, comprising: acquiring a current speech segment in the space where the air conditioner is located, wherein the current speech segment is a speech segment acquired by a speech acquisition device disposed in the space; matching the current speech segment with a plurality of labeled speech segments in a speech recognition library to obtain a matching result, wherein the speech recognition library includes the plurality of labeled speech segments, the plurality of labeled speech segments being speech segments obtained by labeling the plurality of sample speech segments with relevance based on the relevance of the plurality of sample speech segments to each control strategy of the air conditioner; when the matching result indicates that there exists a target labeled speech segment in the speech recognition library with a similarity greater than a similarity threshold to the current speech segment, acquiring a target control strategy corresponding to the target labeled speech segment; and controlling the air conditioner to operate according to the target control strategy.

[0007] Optionally, the control method for the air conditioner further includes: acquiring the plurality of sample speech segments; determining the correlation between the plurality of sample speech segments and each of the control strategies of the air conditioner; labeling the plurality of sample speech segments with correlation based on the correlation between the plurality of sample speech segments and each of the control strategies to obtain the plurality of labeled speech segments; and generating the speech recognition library using the plurality of labeled speech segments.

[0008] Optionally, acquiring the plurality of sample speech segments includes: acquiring a plurality of general words and a plurality of intuitive descriptive words, wherein the plurality of general words are words indirectly related to the control strategy of the air conditioner, and the plurality of intuitive descriptive words are words directly related to the control strategy of the air conditioner; generating the correlation between the plurality of general words and the plurality of intuitive descriptive words using natural language processing to obtain the plurality of sample speech segments.

[0009] Optionally, the plurality of sample speech segments are labeled with relevance based on their relevance to each of the control strategies to obtain the plurality of labeled speech segments. This includes: determining a first relevance between a plurality of intuitive descriptive words in the plurality of sample speech segments and each of the control strategies; determining a second relevance between a plurality of general words in the plurality of sample speech segments and each of the control strategies based on the first relevance; and labeling the plurality of sample speech segments with relevance based on the first relevance and the second relevance to obtain the plurality of labeled speech segments.

[0010] Optionally, matching the current speech segment with multiple labeled speech segments in a speech recognition library includes: inputting the current speech segment into the speech recognition library, so as to use the speech recognition library to perform speech segment matching in the multiple labeled speech segments based on the current speech segment.

[0011] Optionally, after obtaining the target control strategy corresponding to the target labeled speech segment, the control method of the air conditioner further includes: sending the target control strategy to a target terminal; obtaining feedback information on the target control strategy through the target terminal; and sending the target control strategy to the air conditioner when the feedback information indicates that the air conditioner is running according to the target control strategy.

[0012] Optionally, the control method for the air conditioner further includes: acquiring adjustment instructions received during the operation of the air conditioner according to the target control strategy; and updating the voice recognition library based on the feedback information and the adjustment instructions.

[0013] According to another aspect of the present invention, a control device for an air conditioner is also provided, comprising: a first acquisition unit, configured to acquire a current speech segment in the space where the air conditioner is located, wherein the current speech segment is a speech segment acquired by a speech acquisition device disposed in the space; a matching unit, configured to match the current speech segment with a plurality of labeled speech segments in a speech recognition library to obtain a matching result, wherein the speech recognition library includes the plurality of labeled speech segments, and the plurality of labeled speech segments are speech segments obtained by labeling the plurality of sample speech segments with relevance based on the relevance of the plurality of sample speech segments to each control strategy of the air conditioner; a second acquisition unit, configured to acquire a target control strategy corresponding to the target labeled speech segment when the matching result indicates that there is a target labeled speech segment in the speech recognition library with a similarity greater than a similarity threshold to the current speech segment; and a control unit, configured to control the air conditioner to operate according to the target control strategy.

[0014] Optionally, the control device for the air conditioner further includes: a third acquisition unit for acquiring the plurality of sample speech segments; a determination unit for determining the relevance of the plurality of sample speech segments to each of the control strategies of the air conditioner; an annotation unit for annotating the plurality of sample speech segments according to their relevance to each of the control strategies, thereby obtaining the plurality of annotated speech segments; and a generation unit for generating the speech recognition library using the plurality of annotated speech segments.

[0015] Optionally, the third acquisition unit includes: a first acquisition module, used to acquire multiple general words and multiple intuitive descriptive words, wherein the multiple general words are words indirectly related to the control strategy of the air conditioner, and the multiple intuitive descriptive words are words directly related to the control strategy of the air conditioner; and a second acquisition module, used to generate the correlation between the multiple general words and the multiple intuitive descriptive words using natural language processing to obtain the multiple sample speech segments.

[0016] Optionally, the annotation unit includes: a first determining module, configured to determine a first relevance between the plurality of intuitive descriptive words in the plurality of sample speech segments and each of the control strategies; a second determining module, configured to determine a second relevance between the plurality of general words in the plurality of sample speech segments and each of the control strategies based on the first relevance; and an annotation module, configured to annotate the plurality of sample speech segments with relevance based on the first relevance and the second relevance, thereby obtaining the plurality of annotated speech segments.

[0017] Optionally, the matching unit includes: a processing module, configured to input the current speech segment into the speech recognition library, so as to use the speech recognition library to perform speech segment matching in the plurality of labeled speech segments based on the current speech segment.

[0018] Optionally, the control device of the air conditioner further includes: a sending unit, configured to send the target control strategy to a target terminal after acquiring the target control strategy corresponding to the target labeled voice segment; a third acquisition unit, configured to acquire feedback information on the target control strategy through the target terminal; and a sending unit, configured to send the target control strategy to the air conditioner when the feedback information indicates that the air conditioner is running according to the target control strategy.

[0019] Optionally, the control device of the air conditioner further includes: a fourth acquisition unit, used to acquire adjustment instructions received by the air conditioner during operation according to the target control strategy; and an update unit, used to update the voice recognition library according to the feedback information and the adjustment instructions.

[0020] According to another aspect of the present invention, an air conditioner is also provided, wherein the air conditioner uses the control method of any one of the above-described air conditioners.

[0021] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the control method of the air conditioner described in any one of the above embodiments.

[0022] According to another aspect of the present invention, a processor is also provided, the processor being configured to run a program, wherein the program, when running, executes the control method for an air conditioner as described in any of the above embodiments.

[0023] In this embodiment of the invention, the current speech segment in the space where the air conditioner is located is obtained. This current speech segment is acquired by a speech acquisition device located in the space. The current speech segment is then matched with multiple labeled speech segments in a speech recognition library to obtain a matching result. The speech recognition library includes multiple labeled speech segments, which are obtained by labeling multiple sample speech segments based on their relevance to various control strategies of the air conditioner. When the matching result indicates that a target labeled speech segment exists in the speech recognition library with a similarity greater than a similarity threshold to the current speech segment, the target control strategy corresponding to the target labeled speech segment is obtained. The air conditioner is then controlled to operate according to the target control strategy. The air conditioner control method provided by this invention achieves the goal of determining the air conditioner's control strategy based on different spoken expressions of the user, improving the intelligence level of the air conditioner and providing a more comfortable environment for the user. This solves the technical problem in related technologies where the control methods of air conditioners have a low level of intelligence, failing to meet the actual needs of users and resulting in a poor user experience. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0025] Figure 1 This is a hardware structure block diagram of a mobile terminal for an air conditioner control method according to an embodiment of the present invention.

[0026] Figure 2 This is a flowchart of an air conditioner control method according to an embodiment of the present invention;

[0027] Figure 3 This is a flowchart of a preset training model according to an embodiment of the present invention;

[0028] Figure 4 This is a flowchart of an optional air conditioner control method according to an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram illustrating the updating of the speech recognition library according to an embodiment of the present invention;

[0030] Figure 6 This is a schematic diagram of the control device of an air conditioner according to an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] As described in the background section, the control methods of air conditioners in related technologies have a relatively low level of intelligence, which fails to meet the actual needs of users and results in a poor user experience. Embodiments of this invention provide an air conditioner control method and apparatus, an air conditioner, a computer-readable storage medium, and a processor.

[0034] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0035] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for an air conditioner control method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the air conditioner control method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0037] According to an embodiment of the present invention, a method embodiment for controlling an air conditioner is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0038] Figure 2 This is a flowchart of an air conditioner control method according to an embodiment of the present invention, such as... Figure 2 As shown, the control method of this air conditioner includes the following steps:

[0039] Step S202: Obtain the current voice segment in the space where the air conditioner is located, wherein the current voice segment is a voice segment collected by a voice acquisition device set in the space.

[0040] Optionally, the current voice segment here can contain both general words, such as ① strongly related: action verbs like exercise, rest, and housework, and state words like human body state and weather; ② weakly related: nouns like objects and locations, and quantifiers; ③ irrelevant: subjects, modal particles, abstract concept nouns, and function words; or intuitive descriptive words, such as ① human sensations: sensation words like cold, hot, and noisy; ② scene descriptions: descriptive words like switch, temperature, humidity, wind speed, direction, noise, and time; ③ modifiers: modifiers like too, good, a little, very, ready, and want. This allows the air conditioner to adapt to various personalized spoken expressions, and for most voices uttered by the user, a corresponding control strategy can be found.

[0041] The correlation between general terms and intuitive descriptive terms is determined based on their relevance to air conditioning functions. Multiple terms are compared for relevance to the intuitive descriptive terms, and the combination with the highest relevance is used for judgment. For example, the statement "I'm going to exercise" which is strongly related to air conditioning functions has a strong correlation with the intuitive description of heat; the statement "Many people came to my house" has a weak correlation with the intuitive description of heat; statements unrelated to air conditioning functions are not subject to control strategies. The above relevance terms are only illustrative examples; the relevance should be determined based on the actual situation when labeling data.

[0042] In this embodiment, a voice acquisition device can be installed in the room where the air conditioner is located to collect the voice commands issued by the user, namely, the current voice segment mentioned above.

[0043] The aforementioned voice acquisition device can be a component integrated into an air conditioner or a separately installed voice acquisition component.

[0044] Step S204: Match the current speech segment with multiple labeled speech segments in the speech recognition library to obtain a matching result. The speech recognition library includes multiple labeled speech segments, which are speech segments obtained by labeling multiple sample speech segments with correlation based on the correlation between multiple sample speech segments and each control strategy of the air conditioner.

[0045] In this embodiment, the current speech segment can be matched with a pre-built speech recognition library to determine whether there are speech segments in the speech recognition library that are the same as or highly similar to the current speech segment, so as to determine the control strategy of the air conditioner.

[0046] The speech recognition database here includes multiple labeled speech segments. These labeled speech segments are obtained by annotating sample speech segments, and the content of the annotation is determined based on the correlation between the sample speech segments and the various control strategies of the air conditioner.

[0047] Step S206: When the matching result indicates that there is a target labeled speech segment in the speech recognition library with a similarity greater than the similarity threshold to the current speech segment, obtain the target control strategy corresponding to the target labeled speech segment.

[0048] In this embodiment, when it is determined that there is a target labeled speech segment in the speech recognition library with a similarity greater than the similarity threshold to the current speech segment, the control strategy corresponding to the target labeled speech segment can be determined and used as the target control strategy.

[0049] Step S208: Control the air conditioner to operate according to the target control strategy.

[0050] As can be seen from the above, in this embodiment of the invention, the current speech segment in the space where the air conditioner is located can be obtained first. The current speech segment is a speech segment collected by a speech acquisition device set in the space. Then, the current speech segment is matched with multiple labeled speech segments in the speech recognition library to obtain a matching result. The speech recognition library includes multiple labeled speech segments, which are obtained by labeling multiple sample speech segments with relevance based on the relevance of multiple sample speech segments to each control strategy of the air conditioner. Next, when the matching result indicates that there is a target labeled speech segment in the speech recognition library with a similarity greater than a similarity threshold, the target control strategy corresponding to the target labeled speech segment is obtained. The air conditioner is then controlled to operate according to the target control strategy, which realizes the purpose of determining the control strategy of the air conditioner based on the user's different spoken expressions, improves the intelligence level of the air conditioner, and thus provides a more comfortable environment for the user.

[0051] Therefore, the technical solution provided by the embodiments of the present invention solves the technical problem that the control method of air conditioners in the related art has a low degree of intelligence, which cannot meet the actual needs of users and results in a low user experience.

[0052] According to the above embodiments of the present invention, the control method of the air conditioner further includes: acquiring multiple sample speech segments; determining the correlation between the multiple sample speech segments and each control strategy of the air conditioner; labeling the multiple sample speech segments according to their correlation with each control strategy to obtain multiple labeled speech segments; and generating a speech recognition library using the multiple labeled speech segments.

[0053] In this embodiment, multiple sample speech segments can be obtained first, which include general words and intuitive descriptive words respectively; then, the relevance of the multiple sample speech segments to each control strategy of the air conditioner can be determined; then, the multiple sample speech segments are labeled according to the determined relevance to obtain multiple labeled speech segments, thereby obtaining a speech recognition library containing multiple labeled speech segments.

[0054] Figure 3 This is a flowchart of a preset training model according to an embodiment of the present invention, such as... Figure 3 As shown, after obtaining multiple sample speech segments including general words and intuitive descriptive words, the multiple sample speech segments are processed by a natural speech processing model. For example, after word segmentation and filtering, intuitive descriptive words and general words are labeled to establish the correlation between general words and intuitive descriptive words, thus obtaining the above speech recognition library.

[0055] In the above embodiments, obtaining multiple sample speech segments includes: obtaining multiple general words and multiple intuitive descriptive words, wherein the multiple general words are words indirectly related to the control strategy of the air conditioner, and the multiple intuitive descriptive words are words directly related to the control strategy of the air conditioner; generating the correlation between the multiple general words and the multiple intuitive descriptive words using natural language processing to obtain multiple sample speech segments.

[0056] In this embodiment, after obtaining multiple general words and multiple intuitive descriptive words, natural language processing can be used to generate the correlation between the multiple general words and multiple intuitive descriptive words to obtain multiple sample speech segments.

[0057] For example Figure 3 As shown, after determining the speech recognition library, the control strategies of each sample of the air conditioner can be obtained. Then, the relationship between each labeled speech segment in the speech recognition library and each sample control strategy can be established to pre-train the model between the control strategy and the speech segment.

[0058] According to the above embodiments of the present invention, multiple sample speech segments are labeled with relevance based on their relevance to each control strategy to obtain multiple labeled speech segments. This includes: determining a first relevance between multiple intuitive descriptive words in the multiple sample speech segments and each control strategy; determining a second relevance between multiple general words in the multiple sample speech segments and each control strategy based on the first relevance; and labeling the multiple sample speech segments with relevance based on the first and second relevance to obtain multiple labeled speech segments.

[0059] In this embodiment, the pre-training data and model pre-training are used as a unified voice control standard, such as... Figure 3 The intuitive descriptive words in the pre-training data are divided into: ① human sensations: words describing feelings such as cold, hot, and noisy; ② scene descriptions: words describing on / off, temperature, humidity, wind speed, direction, noise, and time; ③ modifiers: words describing too, good, a little, very, ready, and want. Based on the above three categories of speech, the control strategy of the corresponding air conditioner can be determined: control strategies for power supply, temperature, humidity, wind speed, air guide direction, power, time, etc.

[0060] It should be noted that, in this embodiment of the invention, the speech recognition library annotation and pre-trained model are completed offline in advance, while the pre-trained model and the user's personalized model are called on the cloud platform.

[0061] According to the above embodiments of the present invention, matching the current speech segment with multiple labeled speech segments in the speech recognition library includes: inputting the current speech segment into the speech recognition library, so as to use the speech recognition library to perform speech segment matching among multiple labeled speech segments based on the current speech segment.

[0062] In this embodiment, the current speech segment can be input into a speech recognition library, and the speech recognition library can be used to perform speech segment matching among multiple labeled speech segments based on the current speech segment to determine whether there is a target speech segment in the speech recognition library that is highly relevant to the current speech segment.

[0063] Figure 4 This is a flowchart of an optional air conditioner control method according to an embodiment of the present invention, such as... Figure 4 As shown, when a user uses the air conditioner for the first time, a pre-trained model (i.e., the mapping relationship between the speech recognition library and the control strategy) is invoked; otherwise, a user-personalized training model is invoked. The pre-training data and model pre-training portion use the previously used pre-trained data and model pre-training as a unified voice control standard. The pre-training data has already been described above and will not be repeated here. When voice input is entered into the speech recognition library, speech recognition is performed. If no corresponding control strategy exists or the control strategy needs adjustment, model training continues; otherwise, the control strategy corresponding to the speech is used to control the air conditioner's operation. During the air conditioner's operation according to the above control strategy, control strategy feedback is provided. If the feedback is satisfactory, model training continues; otherwise, if the control strategy needs adjustment, the process returns to the voice input stage.

[0064] That is, in this embodiment of the invention, the control system of smart device APP-gateway-cloud platform can be used to call and update the model. The user sends voice through the smart device APP, the gateway sends it back to the cloud platform to obtain the control strategy, and then sends the control strategy back to the gateway to control the air conditioner. When the user uses it for the first time, the pre-trained model is called; otherwise, the user's personalized training model is called.

[0065] In this process, the user side updates the control strategy. For example, when a user inputs voice input, the cloud platform trains a model, and the air conditioner follows different procedures based on the recognition results: ① If a corresponding control strategy exists, the existing control strategy is applied; ② If neither voice input nor a corresponding control strategy exists, such as... Figure 4The process involves two steps: 1) Comparing the input speech with a speech recognition database for relevance, applying control strategies with high relevance, and updating the reinforcement learning model based on user feedback and the current state of the air conditioner; 2) If a corresponding control strategy exists but needs adjustment, updating the reinforcement learning model based on user feedback; 3) Adaptively updating the reinforcement learning model to accommodate different users' spoken expressions and control strategies, thus achieving a voice-controlled air conditioner method based on user language habits. When step ② or ③ is triggered, the speech received by the mobile app is transmitted back to the cloud platform via the gateway for reinforcement learning model training until the user is satisfied with the control strategy. The final updated reinforcement learning model is then saved as the user's personalized training model and used the next time the user uses the system.

[0066] According to the above embodiments of the present invention, after obtaining the target control strategy corresponding to the target labeled speech segment, the control method of the air conditioner may further include: sending the target control strategy to the target terminal; obtaining feedback information on the target control strategy through the target terminal; and sending the target control strategy to the air conditioner when the feedback information indicates that the air conditioner is running according to the target control strategy.

[0067] In this embodiment, a user feedback mechanism can be used to determine whether the control strategy meets the user's needs. For example, the target control strategy can be sent to the user's mobile phone. After viewing the target control strategy on the phone, the user can provide feedback. If the user agrees to use the target control strategy to control the air conditioner, they will provide a consent message. The cloud platform can then send the target control strategy to the air conditioner so that the air conditioner operates according to the target control strategy.

[0068] According to an embodiment of the present invention, the control method of the air conditioner may further include: acquiring adjustment instructions received during the operation of the air conditioner in accordance with the target control strategy; and updating the voice recognition library based on feedback information and adjustment instructions.

[0069] In this embodiment, if the air conditioner receives an adjustment command from the user while operating according to the target control strategy, the air conditioner will adjust its operating mode according to the adjustment command and operate according to the adjusted operating mode.

[0070] To enrich the speech segments stored in the speech recognition library and adapt to users' spoken expressions, the speech recognition library can be updated based on adjustment instructions and user feedback.

[0071] Figure 5 This is a schematic diagram of speech recognition library updating according to an embodiment of the present invention, such as... Figure 5As shown, unlabeled speech (e.g., user-issued adjustment commands) is compared with a speech recognition library. The library is then searched for speech with high relevance to the unlabeled speech, and the control strategy corresponding to the highly relevant speech is used to control the air conditioner. Next, a reinforcement learning model is used to reinforce the relationship between the speech recognition library and the control strategy. Then, the control strategy is fed back; if the feedback is satisfactory, the speech and corresponding control strategy are updated; otherwise, the control strategy is adjusted. This allows users to control the air conditioner with different spoken expressions, meeting diverse user needs.

[0072] Therefore, the technical solution provided by the above embodiments of the present invention uses labeled intuitive descriptions, related voice, and corresponding air conditioning control strategies as pre-trained data to train the model. On the user side, reinforcement learning technology is used to update the corresponding air conditioning control strategy based on the user's different spoken expressions and usage habits. This has the following beneficial effects: 1) It makes decisions to control the air conditioning based on the user's contextual dialogue, without requiring the user to utter preset command words; 2) It adaptively updates the user's personal spoken expressions and corresponding air conditioning control strategies, thereby intelligently recognizing the user's voice control of the air conditioning and updating the air conditioning control strategy according to the user's different spoken expressions, improving the user's comfort when using the air conditioning.

[0073] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0074] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0075] According to embodiments of the present invention, a control device for an air conditioner for implementing the above-described control method for an air conditioner is also provided. Figure 6 This is a schematic diagram of the control device of an air conditioner according to an embodiment of the present invention, such as... Figure 6As shown, 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.

[0076] The first acquisition unit 61 is used to acquire the current voice segment in the space where the air conditioner is located, wherein the current voice segment is a voice segment acquired by a voice acquisition device set in the space.

[0077] The matching unit 63 is used to match the current speech segment with multiple labeled speech segments in the speech recognition library to obtain a matching result. The speech recognition library includes multiple labeled speech segments, which are speech segments obtained by labeling multiple sample speech segments with relevance based on the relevance of multiple sample speech segments with each control strategy of the air conditioner.

[0078] The second acquisition unit 65 is used to acquire the target control strategy corresponding to the target labeled speech segment when the matching result indicates that there is a target labeled speech segment in the speech recognition library with a similarity greater than the similarity threshold.

[0079] Control unit 67 is used to control the air conditioner to operate according to the target control strategy.

[0080] It should be noted here that the first acquisition unit 61, the matching unit 63, the second acquisition unit 65 and the control unit 67 mentioned above correspond to steps S202 to S210 in the above embodiments. The four units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments.

[0081] As can be seen from the above, in the solution described in the above embodiments of the present invention, the first acquisition unit can acquire the current voice segment in the space where the air conditioner is located, wherein the current voice segment is acquired by a voice acquisition device set in the space; then, the matching unit uses a matching unit to match the current voice segment with multiple labeled voice segments in a voice recognition library to obtain a matching result, wherein the voice recognition library includes multiple labeled voice segments, which are voice segments obtained by labeling multiple sample voice segments with relevance to each control strategy of the air conditioner; next, when the matching result indicates that there is a target labeled voice segment in the voice recognition library with a similarity greater than a similarity threshold, the second acquisition unit acquires the target control strategy corresponding to the target labeled voice segment; finally, the control unit uses a control unit to control the air conditioner to operate according to the target control strategy, thereby achieving the purpose of determining the control strategy of the air conditioner based on the user's different spoken expressions, improving the intelligence level of the air conditioner, and thus providing a more comfortable environment for the user.

[0082] Therefore, the technical solution provided by the embodiments of the present invention solves the technical problem that the control method of air conditioners in the related art has a low degree of intelligence, which cannot meet the actual needs of users and results in a low user experience.

[0083] Optionally, the control device of the air conditioner further includes: a third acquisition unit for acquiring multiple sample speech segments; a determination unit for determining the correlation between the multiple sample speech segments and each control strategy of the air conditioner; a labeling unit for labeling the multiple sample speech segments according to their correlation with each control strategy to obtain multiple labeled speech segments; and a generation unit for generating a speech recognition library using the multiple labeled speech segments.

[0084] Optionally, the third acquisition unit includes: a first acquisition module, used to acquire multiple general words and multiple intuitive descriptive words, wherein the multiple general words are words indirectly related to the control strategy of the air conditioner, and the multiple intuitive descriptive words are words directly related to the control strategy of the air conditioner; and a second acquisition module, used to generate the correlation between the multiple general words and the multiple intuitive descriptive words using natural language processing to obtain multiple sample speech segments.

[0085] Optionally, the annotation unit includes: a first determining module, used to determine the first correlation between multiple intuitive descriptive words in multiple sample speech segments and each control strategy respectively; a second determining module, used to determine the second correlation between multiple general words in multiple sample speech segments and each control strategy respectively based on the first correlation; and an annotation module, used to annotate the multiple sample speech segments according to the first correlation and the second correlation to obtain multiple annotated speech segments.

[0086] Optionally, the matching unit includes: a processing module for inputting the current speech segment into a speech recognition library, so as to use the speech recognition library to perform speech segment matching among multiple labeled speech segments based on the current speech segment.

[0087] Optionally, the control device of the air conditioner further includes: a sending unit, configured to send the target control strategy to the target terminal after acquiring the target control strategy corresponding to the target labeled voice segment; a third acquisition unit, configured to acquire feedback information on the target control strategy through the target terminal; and a sending unit, configured to send the target control strategy to the air conditioner when the feedback information indicates that the air conditioner is running according to the target control strategy.

[0088] Optionally, the control device of the air conditioner further includes: a fourth acquisition unit, used to acquire adjustment instructions received by the air conditioner during operation according to the target control strategy; and an update unit, used to update the voice recognition library based on feedback information and adjustment instructions.

[0089] According to another aspect of the present invention, an air conditioner is also provided, wherein the air conditioner uses the control method of any of the above-described air conditioners.

[0090] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the control method of an air conditioner according to any one of the above embodiments.

[0091] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any communication device in a group of communication devices.

[0092] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring the current speech segment in the space where the air conditioner is located, wherein the current speech segment is a speech segment acquired by a speech acquisition device installed in the space; matching the current speech segment with multiple labeled speech segments in a speech recognition library to obtain a matching result, wherein the speech recognition library includes multiple labeled speech segments, which are speech segments obtained by labeling multiple sample speech segments with relevance based on the relevance of multiple sample speech segments to each control strategy of the air conditioner; when the matching result indicates that there is a target labeled speech segment in the speech recognition library with a similarity greater than a similarity threshold to the current speech segment, acquiring the target control strategy corresponding to the target labeled speech segment; and controlling the air conditioner to operate according to the target control strategy.

[0093] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring multiple sample speech segments; determining the correlation between the multiple sample speech segments and each control strategy of the air conditioner; labeling the multiple sample speech segments according to their correlation with each control strategy to obtain multiple labeled speech segments; and generating a speech recognition library using the multiple labeled speech segments.

[0094] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining multiple general words and multiple intuitive descriptive words, wherein the multiple general words are words indirectly related to the control strategy of the air conditioner, and the multiple intuitive descriptive words are words directly related to the control strategy of the air conditioner; generating the correlation between the multiple general words and the multiple intuitive descriptive words using natural language processing to obtain multiple sample speech segments.

[0095] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining a first correlation between multiple intuitive descriptive words in multiple sample speech segments and each control strategy; determining a second correlation between multiple general words in multiple sample speech segments and each control strategy based on the first correlation; and labeling the multiple sample speech segments based on the first and second correlations to obtain multiple labeled speech segments.

[0096] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: inputting the current speech segment into a speech recognition library to use the speech recognition library to perform speech segment matching among multiple labeled speech segments based on the current speech segment.

[0097] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: sending a target control strategy to a target terminal; obtaining feedback information on the target control strategy through the target terminal; and sending the target control strategy to the air conditioner when the feedback information indicates that the air conditioner is running according to the target control strategy.

[0098] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring adjustment instructions received by the air conditioner during operation according to the target control strategy; and updating the voice recognition library based on feedback information and adjustment instructions.

[0099] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the control method of an air conditioner described above.

[0100] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0101] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0102] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0103] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0104] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0105] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0106] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A control method for an air conditioner, characterized in that, include: The current voice segment of the space where the air conditioner is located is obtained, wherein the current voice segment is a voice segment collected by a voice acquisition device installed in the space; The current speech segment is matched with multiple labeled speech segments in the speech recognition library to obtain a matching result. The speech recognition library includes the multiple labeled speech segments, which are speech segments obtained by labeling the multiple sample speech segments with relevance based on the relevance of the multiple sample speech segments with each control strategy of the air conditioner. When the matching result indicates that there is a target labeled speech segment in the speech recognition library with a similarity greater than the similarity threshold to the current speech segment, the target control strategy corresponding to the target labeled speech segment is obtained; Control the air conditioner to operate according to the target control strategy; The method further includes: acquiring the plurality of sample speech segments; determining the correlation between the plurality of sample speech segments and each of the control strategies of the air conditioner; labeling the plurality of sample speech segments according to their correlation with each of the control strategies to obtain the plurality of labeled speech segments; and generating the speech recognition library using the plurality of labeled speech segments. The process of acquiring the multiple sample speech segments includes: acquiring multiple general words and multiple intuitive descriptive words, wherein the multiple general words are words indirectly related to the control strategy of the air conditioner, and the multiple intuitive descriptive words are words directly related to the control strategy of the air conditioner; and generating the correlation between the multiple general words and the multiple intuitive descriptive words using natural language processing to obtain the multiple sample speech segments. Specifically, the process of labeling the multiple sample speech segments with relevance to each of the control strategies to obtain the multiple labeled speech segments includes: determining a first relevance between multiple intuitive descriptive words in the multiple sample speech segments and each of the control strategies; determining a second relevance between multiple general words in the multiple sample speech segments and each of the control strategies based on the first relevance; and labeling the multiple sample speech segments with relevance based on the first and second relevance to obtain the multiple labeled speech segments.

2. The control method for an air conditioner according to claim 1, characterized in that, Matching the current speech segment with multiple labeled speech segments in the speech recognition library includes: The current speech segment is input into the speech recognition library, so that the speech recognition library can be used to perform speech segment matching in the multiple labeled speech segments based on the current speech segment.

3. The control method for an air conditioner according to claim 1 or 2, characterized in that, After obtaining the target control strategy corresponding to the target-annotated speech segment, the method further includes: Send the target control strategy to the target terminal; Obtain feedback information on the target control strategy through the target terminal; When the feedback information indicates that the air conditioner is running according to the target control strategy, the target control strategy is sent to the air conditioner.

4. The control method for an air conditioner according to claim 3, characterized in that, Also includes: Obtain adjustment instructions received by the air conditioner during operation according to the target control strategy; The speech recognition library is updated based on the feedback information and the adjustment instructions.

5. A control device for an air conditioner, characterized in that, include: The first acquisition unit is used to acquire the current voice segment of the space where the air conditioner is located, wherein the current voice segment is a voice segment acquired by a voice acquisition device installed in the space; A matching unit is used to match the current speech segment with multiple labeled speech segments in a speech recognition library to obtain a matching result. The speech recognition library includes the multiple labeled speech segments, which are speech segments obtained by labeling the multiple sample speech segments with relevance based on the relevance of the multiple sample speech segments with each control strategy of the air conditioner. The second acquisition unit is used to acquire the target control strategy corresponding to the target labeled speech segment when the matching result indicates that there is a target labeled speech segment in the speech recognition library with a similarity greater than the similarity threshold to the current speech segment; A control unit is used to control the air conditioner to operate according to the target control strategy; The control device for the air conditioner further includes: a third acquisition unit for acquiring the plurality of sample speech segments; a determination unit for determining the relevance of the plurality of sample speech segments to each of the control strategies of the air conditioner; an annotation unit for annotating the plurality of sample speech segments according to their relevance to each of the control strategies, thereby obtaining the plurality of annotated speech segments; and a generation unit for generating the speech recognition library using the plurality of annotated speech segments. The third acquisition unit includes: a first acquisition module, used to acquire multiple general words and multiple intuitive descriptive words, wherein the multiple general words are words indirectly related to the control strategy of the air conditioner, and the multiple intuitive descriptive words are words directly related to the control strategy of the air conditioner; and a second acquisition module, used to generate the correlation between the multiple general words and the multiple intuitive descriptive words using natural language processing to obtain the multiple sample speech segments. The annotation unit includes: a first determining module, configured to determine a first relevance between the plurality of intuitive descriptive words in the plurality of sample speech segments and each of the control strategies; a second determining module, configured to determine a second relevance between the plurality of general words in the plurality of sample speech segments and each of the control strategies based on the first relevance; and an annotation module, configured to annotate the plurality of sample speech segments with relevance based on the first relevance and the second relevance, thereby obtaining the plurality of annotated speech segments.

6. An air conditioner, characterized in that, The air conditioner uses the control method of any one of claims 1 to 4.

7. 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 according to any one of claims 1 to 4.

8. A processor, characterized in that, The processor is used to run a program, wherein the program executes the control method of the air conditioner according to any one of claims 1 to 4.

Images