Air conditioner control method and device, air conditioner and storage medium

Abstract

The invention discloses a control method and device of an air conditioner, the air conditioner and a storage medium. The invention relates to the technical field of air conditioners, and the method comprises the following steps: collecting voice data, and inputting the voice data into a sentiment classification model for sentiment classification to obtain a classification result; and adjusting the air conditioner according to the classification result and a preset emotion priority. According to the method, the voice data are input into the emotion classification model for classification to obtain the classification result, then the air conditioner is actively adjusted according to the classification result and the emotion priority, and the comfort requirement of a user is met to a certain degree.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of air conditioning, and in particular to a control method and device for an air conditioner, an air conditioner, and a storage medium. Background Art

[0002] With the rapid development of smart home technology, users are increasingly demanding personalized environmental control systems. Existing air conditioners generally rely on single-mode environmental parameters (such as temperature and humidity) or voice commands for control. When air conditioners use single-mode environmental parameters for control, there is a significant discrepancy between the user's actual comfort needs and the air conditioner system's response. This means that the temperature setting deviates from the user's actual comfort level, failing to meet user comfort requirements. Furthermore, when using voice control, it is susceptible to interference from ambient noise and language ambiguity, leading to low voice control recognition rates or errors, similarly failing to meet user comfort requirements. Summary of the Invention

[0003] The embodiments of the present invention provide a control method and device for an air conditioner, an air conditioner, and a storage medium, aiming to solve the problem that existing air conditioners cannot meet user comfort requirements.

[0004] In a first aspect, an embodiment of the present invention provides a method for controlling an air conditioner, comprising:

[0005] Collecting speech data and inputting the speech data into a sentiment classification model to perform sentiment classification to obtain a classification result;

[0006] The air conditioner is adjusted according to the classification result and the preset emotional priority.

[0007] In a second aspect, an embodiment of the present invention further provides a control device for an air conditioner, comprising:

[0008] A collection and classification unit is used to collect voice data and input the voice data into a sentiment classification model to perform sentiment classification to obtain a classification result;

[0009] An adjusting unit is used to adjust the air conditioner according to the classification result and the preset emotional priority.

[0010] In a third aspect, an embodiment of the present invention further provides an air conditioner, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0011] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program can implement the above method when executed by a processor.

[0012] Embodiments of the present invention provide an air conditioner control method, device, air conditioner, and storage medium. The method includes: collecting voice data, inputting the voice data into an emotion classification model for emotion classification to obtain a classification result; and adjusting the air conditioner based on the classification result and a preset emotion priority. The technical solution of the embodiments of the present invention first inputs the voice data into the emotion classification model for classification to obtain a classification result, and then actively adjusts the air conditioner based on the classification result and the emotion priority, thus meeting user comfort requirements to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 A flow chart of a method for controlling an air conditioner provided by one embodiment of the present invention;

[0015] Figure 2 This is a simplified flowchart of a sentiment classification model training process in an air conditioner control method provided by one embodiment of the present invention;

[0016] Figure 3 A schematic diagram of a sub-flow chart of a method for controlling an air conditioner provided by an embodiment of the present invention;

[0017] Figure 4 A schematic flow chart of a method for controlling an air conditioner according to another embodiment of the present invention;

[0018] Figure 5 This is a simplified flow chart of a method for controlling an air conditioner provided by one embodiment of the present invention;

[0019] Figure 6 A schematic block diagram of a control device for an air conditioner provided in an embodiment of the present invention;

[0020] Figure 7 A schematic block diagram of an air conditioner provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0023] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0026] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for controlling an air conditioner according to an embodiment of the present invention. The method for controlling an air conditioner is described in detail below. Figure 1 As shown, the method includes the following steps S110-S120.

[0027] S110 , collecting speech data, and inputting the speech data into a sentiment classification model to perform sentiment classification to obtain a classification result.

[0028] In an embodiment of the present invention, a high-sensitivity microphone array is provided inside the air conditioner body. After the air conditioner is turned on, the microphone array collects the user's voice data within a preset time period, and the collected voice data is input into a sentiment classification model for sentiment classification to obtain a classification result, wherein the preset time period can be set according to actual needs and is not specifically limited here; the sentiment classification model is obtained by training a deep neural network using sample voice data and text data corresponding to the sample voice data, wherein the deep neural network can be a DialogueRNN (Dialogue Recurrent Neural Network) network, which is a recurrent neural network architecture designed specifically for dialogue scenarios. Its core goal is to achieve more accurate emotion detection and sentiment analysis by dynamically modeling the speaker state and context dependency in the dialogue.

[0029] Furthermore, the emotion classification model is obtained by training a deep neural network using sample speech data and text data corresponding to the sample speech data, including: collecting the sample speech data, and performing speech separation on the sample speech data to obtain separated speech data; distinguishing and marking the speech data of different users in the separated speech data to obtain marked speech data, and performing speech recognition on the marked speech data to generate the text data; performing feature extraction on the marked speech data to obtain speech features, and performing feature extraction on the text data to obtain text features; and training the deep neural network based on the speech features and the text features to obtain the emotion classification model. It should be noted that, in this embodiment, speech separation technology is used to perform speech separation on the sample speech data to obtain separated speech data, wherein the speech separation technology is to separate a clear speech stream of an independent speaker from a mixed speech signal of multiple people, which is particularly important in noisy scenarios or scenarios where multiple people are speaking at the same time. The speech separation technology includes frequency domain separation method and time domain end-to-end method. The voice data of different users in the separated voice data are distinguished and marked using the Pyannote library to obtain marked voice data. The Pyannote library is an open source Python library based on deep learning, specializing in speaker separation, that is, distinguishing different speakers in the audio and marking their speaking periods. It should also be noted that, in this embodiment, an existing speech recognition algorithm is used to perform speech recognition on the marked speech data to generate the text data, wherein the speech recognition algorithm includes but is not limited to RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory) and Transformer (Self-Attention Network); an existing speech feature extraction algorithm is used to extract features of the marked speech data to obtain the speech features, wherein the stylistic feature extraction algorithm includes but is not limited to Word2Vec (Word to Vector), GloVe (Global Vectors for Word Representation), TextCNN (Text Convolutional Neural Network) and BERT (Bidirectional Encoder Representations from Transformers) algorithm; an existing text feature extraction tool is used to extract features of the text data to obtain the text features, wherein the speech feature extraction tool includes but is not limited to the OpenSmile tool.

[0030] Furthermore, the step of training the deep neural network according to the speech features and the text features to obtain the sentiment classification model includes: fusing the speech features and the text features to obtain fused features; inputting the fused features into the deep neural network for training until a preset termination condition is met; and using the trained deep neural network as the sentiment classification model. It should be noted that, in this embodiment, the speech features and the text features are spliced ​​to obtain the fused features, and CCA (Canonical Correlation Analysis) and TFN (Tensor Fusion Network) can also be used to fuse the speech features and the text features to obtain the fused features. It should also be noted that, in this embodiment, the preset termination condition can be reaching a preset number of iterations, or the loss value during the training process tends to be stable.

[0031] See also Figure 2 , Figure 2 This is a flow chart of the emotion classification model training process in an air conditioner control method provided by one embodiment of the present invention. Figure 2 In the process, sample speech data is collected, separated and marked to obtain marked speech data, speech recognition is performed on the marked speech data to generate text data, features are performed on the marked speech data and text data to obtain speech features and text features, the speech features and text features are fused to obtain fused features, and the fused features are input into a deep neural network for model training. When the training termination conditions are met, the trained deep neural network is used as a sentiment classification model.

[0032] S120: Adjust the air conditioner according to the classification result and the preset emotional priority.

[0033] In an embodiment of the present invention, the classification results include but are not limited to emotion types such as anger, panic, sadness, fatigue, excitement, and calmness, and the preset emotion priorities are anger>panic (anxiety)>sadness>fatigue>excitement>calmness, that is, the priority of anger is higher than the priority of panic, the priority of panic is higher than the priority of sadness, the priority of sadness is higher than the priority of fatigue, the priority of fatigue is higher than the priority of excitement, and the priority of excitement is higher than the priority of calmness.

[0034] In one embodiment, such as this embodiment, Figure 3 As shown, step S120 includes S121-S123:

[0035] S121. Counting the frequency of each emotion type of the user in the time period corresponding to the voice data according to the classification result to obtain an emotion frequency dataset of the user;

[0036] S122: taking the emotion type with the highest emotion frequency in the emotion frequency data set corresponding to the user as the target emotion of the user;

[0037] S123: Adjust the air conditioner according to the target emotion and the emotion priority of the user.

[0038] In an embodiment of the present invention, it is assumed that there are three users, namely p1, p2, and p3. Within a preset time period n, the emotion frequency data sets of p1, p2, and p3 are respectively counted as: p1's emotion frequency data set (anger 30%, sadness 10%...), p2's emotion frequency data set (anger 20%, sadness 30%...), p3's emotion frequency data set (anger 20%, fatigue 30%...). It can be seen that the target emotion of user p1 is anger, the target emotion of user p2 is sadness, and the target emotion of user p3 is fatigue. The air conditioner is adjusted according to the target emotions and emotion priorities corresponding to users p1, p2, and p3.

[0039] Furthermore, step S123 includes: if there is only one user in the working environment of the air conditioner, then the target emotion of that user is used as the final target emotion; if there are multiple users in the working environment of the air conditioner, then the target emotions of all users are sorted according to the emotion priority, and the emotion type with the highest priority is used as the final target emotion; based on the final target emotion, control information is obtained from a preset library, and the air conditioner is adjusted according to the control information. It should be noted that in this embodiment, if there is only one user p1, anger, the target emotion corresponding to p1, is used as the final target emotion; if there are multiple users, such as p1, p2, and p3, then according to the emotion priority of anger > panic (anxiety) > sadness > fatigue > excitement > calm, the target emotions corresponding to p1, anger, p2, and p3 are prioritized, anger, the target emotion with the highest priority, is used as the final target emotion, control information is obtained from a preset library based on the final target emotion anger, and the air conditioner is adjusted according to the control information.

[0040] Furthermore, the preset library includes a first preset library and a second preset library, and the control information includes temperature and wind speed information and fragrance and oxygen enrichment information. Retrieving the control information from the preset library based on the final target emotion and adjusting the air conditioner based on the control information includes: retrieving the temperature and wind speed information from the first preset library based on the final target emotion; retrieving the fragrance and oxygen enrichment information from the second preset library based on the final target emotion; and if no video playback instruction is received, adjusting the air conditioner based on the temperature and wind speed information and the fragrance and oxygen enrichment information. It should be noted that in this embodiment, the first preset library is the emotion-air conditioning temperature / wind speed library, and the second preset library is the emotion-aroma / oxygen enrichment formula library. The emotion-air conditioning temperature / wind speed library and the emotion-aroma / oxygen enrichment formula library each have different control information for different emotion types. Specifically, in the emotion-air conditioning temperature / wind speed library, anger: lowers the temperature by 1°C-2°C, high wind speed; joy: maintains the current comfort range; sadness: raises the temperature by 1°C-2°C, low / medium wind speed. Anxiety: Maintain the current comfort range, low wind speed; Fatigue: Enable sleep mode or energy-saving mode, low wind speed; In the Emotion-Aroma / Oxygen Enrichment Recipe Library, the following recipes are available: Anger: Cedar / Bergamot, oxygen-enriched mode; Joy: Orange / Lemon; Sadness: Lavender / Rose / Jasmine; Anxiety: Lavender / Chamomile, oxygen-enriched mode; Fatigue: Rosemary / Mint, oxygen-enriched mode. Understandably, when the final target emotion is anger, the temperature and wind speed information indicates a 1°C-2°C temperature reduction, high wind speed; and the aroma and oxygen enrichment information indicates cedar / bergamot, oxygen-enriched mode. The air conditioner is proactively adjusted based on these temperature, wind speed, and aroma and oxygen enrichment information to enhance user comfort. It should also be noted that in this embodiment, if no video playback command is received, it indicates that the user has not enabled the immersive visual experience in the air conditioner's corresponding app. Therefore, the air conditioner only needs to be adjusted based on the temperature, wind speed, and aroma and oxygen enrichment information.

[0041] Furthermore, the preset library further includes a third preset library, and the control information further includes video playback information. After the step of adjusting the air conditioner based on the temperature, wind speed information, and the fragrance and oxygen enrichment information, the method further includes: upon receiving a preset video playback instruction, retrieving the video playback information from the third preset library based on the final target emotion; and adjusting the air conditioner based on the video playback information. It should be noted that in this embodiment, the third preset library is an emotion-video library, and different control information is configured for different emotion types within the emotion-video library. Specifically, anger: cool-toned dynamic fluid, such as deep-sea ripples; joy: warm-toned natural landscapes, such as a gentle spring breeze, birdsong, flowers, and lush grass; sadness: low-saturation natural landscapes, such as a forest in morning mist; anxiety: slow-paced natural scenes with low-saturation colors, such as slow-motion aerial shots of streams and lakes; fatigue: dynamic light and shadow changes, warm scenes, such as the entire sunset over a beach or mountain range. Understandably, if the final target emotion is anger, the video playback information will be cool-toned dynamic fluid, such as deep-sea ripples. After obtaining the video playback information, the pre-installed OLED (Organic Light-Emitting Diode) can be used to play the video on the air outlet windshield of the air conditioner, wherein OLED is a self-luminous display technology based on organic semiconductor materials. Its core principle is to drive organic materials to emit light through electric fields, without the need for a backlight module required by traditional LCDs (liquid crystal displays). It should also be noted that in this embodiment, if a video playback instruction is received, indicating that the user has chosen to turn on an immersive visual experience on the APP corresponding to the air conditioner, the air conditioner needs to be adjusted according to the video playback information, the temperature and wind speed information, and the fragrance and oxygen enrichment information.

[0042] Figure 4 A flow chart of a method for controlling an air conditioner according to another embodiment of the present invention is shown in FIG. Figure 4 As shown, in this embodiment, the method includes steps S110 to S140. That is, in this embodiment, the method further includes steps S130 to S140 after step S120 of the above embodiment.

[0043] S130: If a manual adjustment command is received, obtaining manual adjustment information according to the manual adjustment command, and updating the preset library according to the manual adjustment information and the final target emotion;

[0044] S140. If the preset interval time is reached, return to the step of collecting voice data and inputting the voice data into the emotion classification model for emotion classification to obtain a classification result, until a preset stop adjustment instruction or shutdown instruction is received.

[0045] In an embodiment of the present invention, if a manual adjustment command is received, manual adjustment information is obtained according to the manual adjustment command, wherein the manual adjustment information can be at least one of temperature and wind speed, fragrance and oxygen enrichment, and video playback. Afterwards, the preset library is updated according to the manual adjustment information and the final target emotion. Assuming that the manual adjustment information is temperature and wind speed, and the final target emotion is anger, the anger information in the first preset library is updated according to the manual adjustment information. It is understandable that if no manual adjustment command is received, the preset library is not updated. It should be noted that in this embodiment, when the preset interval time m is reached, the step of collecting voice data and inputting the voice data into the emotion classification model for emotion classification to obtain a classification result is returned until a preset stop adjustment instruction or a shutdown instruction is received, so as to actively adjust the air conditioner according to the user's emotional state.

[0046] See also Figure 5 , Figure 5 This is a flow chart of a method for controlling an air conditioner according to an embodiment of the present invention. Figure 5 In the embodiment, the user's voice data within a preset time period is collected, and the voice data is input into the emotion classification model for classification to obtain a classification result; the user's target emotion is determined based on the classification result, and the target emotions are sorted according to the preset emotion priority, and the emotion type with the highest priority is used as the final target emotion; temperature and wind speed information and aroma and oxygen enrichment information are obtained from the emotion-air conditioning temperature / wind speed library and the emotion-aroma / oxygen enrichment formula library according to the final target emotion; if the user chooses to turn on the immersive visual experience on the APP corresponding to the air conditioner, video playback information is obtained from the emotion-video library according to the final target emotion, and the air conditioner is adjusted according to the video playback information, temperature and wind speed information, and aroma and oxygen enrichment information; if the user does not choose to turn on the immersive visual experience on the APP corresponding to the air conditioner, the air conditioner is adjusted according to the temperature and wind speed information and aroma and oxygen enrichment information; if the user makes manual adjustment, the preset library is updated according to the manual adjustment information. If no manual adjustment is made, it is determined whether the preset interval time has been reached. If so, the process returns to the step of collecting the user's voice data within the preset time period until a preset stop adjustment instruction or shutdown instruction is received.

[0047] To sum up, in this embodiment, during the training stage of the model, the user's voice data and text data are multimodally fused to obtain fusion features, and the DialogueRNN network in the deep neural network is trained through the fusion features to obtain a sentiment classification model, which can improve the accuracy of sentiment classification; the temperature, wind speed, fragrance enrichment and video playback of the air conditioner are actively adjusted according to the classification results and emotion priority, which can enhance the user's emotional interaction immersion, alleviate the user's emotional fluctuations, and meet the user's comfort requirements to a certain extent.

[0048] Figure 6 FIG. 2 is a schematic block diagram of a control device 200 for an air conditioner provided by an embodiment of the present invention. Figure 6 As shown, corresponding to the above air conditioner control method, the present invention also provides an air conditioner control device 200. The air conditioner control device 200 includes a unit for executing the above air conditioner control method, and the device can be configured in the air conditioner. Figure 6 The control device 200 of the air conditioner includes a collection and classification unit 201 and an adjustment unit 202.

[0049] Among them, the collection and classification unit 202 is used to collect voice data, and input the voice data into the emotion classification model for emotion classification to obtain a classification result, wherein the emotion classification model is obtained by training a deep neural network using sample voice data and text data corresponding to the sample voice data. The specific training process of the emotion classification model is: collecting the sample voice data, and performing voice separation on the sample voice data to obtain separated voice data; distinguishing and marking the voice data of different users in the separated voice data to obtain marked voice data, and performing voice recognition on the marked voice data to generate the text data; performing feature extraction on the marked voice data to obtain voice features, and performing feature extraction on the text data to obtain text features; performing feature fusion on the voice features and the text features to obtain fusion features; inputting the fusion features into the deep neural network for training until a preset termination condition is met; using the trained deep neural network as the emotion classification model; the adjustment unit 202 is used to adjust the air conditioner according to the classification result and the preset emotion priority.

[0050] In some embodiments, such as this embodiment, the adjustment unit 202 includes a statistics unit, a first operation unit, and a first adjustment sub-unit.

[0051] Among them, the statistical unit is used to count the frequency of occurrence of each emotion type of the user in the time period corresponding to the voice data according to the classification results, and obtain the user's emotion frequency data set; the first action unit is used to take the emotion type with the highest emotion frequency in the emotion frequency data set corresponding to the user as the target emotion of the user; the first adjustment subunit is used to adjust the air conditioner according to the user's target emotion and the emotion priority.

[0052] In some embodiments, such as the present embodiment, the first regulating subunit further includes a second acting unit, a sorting unit, and a second regulating subunit.

[0053] Among them, the second acting unit is used to take the target emotion of the user as the final target emotion if there is only one user in the working environment of the air conditioner; the sorting unit is used to sort the target emotions of all users according to the emotion priority if there are multiple users in the working environment of the air conditioner, and take the emotion type with the highest priority as the final target emotion; the second regulating subunit is used to obtain control information from a preset library according to the final target emotion, and adjust the air conditioner according to the control information.

[0054] In certain embodiments, such as the present embodiment, the second regulating subunit is further used to: obtain the temperature and wind speed information from the first preset library according to the final target emotion; obtain the fragrance and oxygen enrichment information from the second preset library according to the final target emotion; if no video playback instruction is received, adjust the air conditioner according to the temperature and wind speed information and the fragrance and oxygen enrichment information; if the preset video playback instruction is received, obtain the video playback information from the third preset library according to the final target emotion; and adjust the air conditioner according to the video playback information, the temperature and wind speed information, and the fragrance and oxygen enrichment information.

[0055] In some embodiments, such as this embodiment, the air conditioner control device 200 further includes an updating unit and a return execution unit.

[0056] Among them, the update unit is used to obtain manual adjustment information according to the manual adjustment command if a manual adjustment command is received, and update the preset library according to the manual adjustment information and the final target emotion; the return execution unit is used to return to execute the steps of collecting voice data and inputting the voice data into the emotion classification model for emotion classification to obtain classification results if a preset interval time is reached, until a preset stop adjustment instruction or shutdown instruction is received.

[0057] The control device of the air conditioner can be realized in the form of a computer program. The computer program can be used in Figure 7 The air conditioner shown is running.

[0058] See also Figure 7 , Figure 7 1 is a schematic block diagram of an air conditioner provided by an embodiment of the present invention. The air conditioner 300 is a device with a compensation and adjustment function.

[0059] See Figure 7 The air conditioner 300 includes a processor 302 , a memory, and a network interface 305 connected via a system bus 301 , wherein the memory may include a non-volatile storage medium 303 and an internal memory 304 .

[0060] The non-volatile storage medium 303 can store an operating system 3031 and a computer program 3032. When the computer program 3032 is executed, the processor 302 can execute a method for controlling an air conditioner.

[0061] The processor 302 is used to provide computing and control capabilities to support the operation of the entire air conditioner 300 .

[0062] The internal memory 304 provides an environment for the operation of the computer program 3032 in the non-volatile storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can execute a method for controlling an air conditioner.

[0063] The network interface 305 is used to communicate with other devices through the network. Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the air conditioner 300 to which the solution of the present invention is applied. The specific air conditioner 300 may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0064] The processor 302 is configured to run a computer program 3032 stored in a memory to implement any embodiment of the above-mentioned air conditioner control method.

[0065] It should be understood that in the embodiment of the present invention, the processor 302 may be a central processing unit (CPU), and the processor 302 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0066] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0067] Therefore, the present invention further provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to execute any embodiment of the air conditioner control method.

[0068] The storage medium may be any computer-readable storage medium that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0069] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0070] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the various units is merely a logical functional division, and actual implementation may employ other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0071] The steps in the methods of the embodiments of the present invention may be adjusted in order, combined, or deleted as needed. The units in the devices of the embodiments of the present invention may be combined, divided, or deleted as needed. Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0072] If this integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, or the portion 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, stored in a storage medium, includes several instructions for causing an air conditioner to execute all or part of the steps of the method described in various embodiments of the present invention.

[0073] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0074] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, to the extent such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to encompass such changes and modifications.

[0075] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for controlling an air conditioner, characterized in that: include: Collecting speech data and inputting the speech data into a sentiment classification model to perform sentiment classification to obtain a classification result; The air conditioner is adjusted according to the classification result and the preset emotional priority.

2. The method according to claim 1, characterized in that The adjusting the air conditioner according to the classification result and the preset emotional priority includes: According to the classification result, the frequency of each emotion type of the user in the time period corresponding to the voice data is counted to obtain the user's emotion frequency data set; The emotion type with the highest emotion frequency in the emotion frequency dataset corresponding to the user is used as the target emotion of the user; The air conditioner is adjusted according to the target emotion and the emotion priority of the user.

3. The method according to claim 2, characterized in that The adjusting the air conditioner according to the target emotion and the emotion priority of the user includes: If there is only one user in the working environment of the air conditioner, the target emotion of the user is used as the final target emotion; If there are multiple users in the working environment of the air conditioner, sorting the target emotions of all users according to the emotion priority, and taking the emotion type with the highest priority as the final target emotion; Control information is obtained from a preset library according to the final target emotion, and the air conditioner is adjusted according to the control information.

4. The method according to claim 3, characterized in that The preset library includes a first preset library and a second preset library, the control information includes temperature and wind speed information and fragrance and oxygen enrichment information, and the control information is obtained from the preset library according to the final target emotion, and the air conditioner is adjusted according to the control information, including: Acquiring the temperature and wind speed information from the first preset library according to the final target emotion; acquiring the aroma oxygen enrichment information from the second preset library according to the final target emotion; If the video play instruction is not received, the air conditioner is adjusted according to the temperature and wind speed information and the fragrance and oxygen enrichment information.

5. The method according to claim 4, characterized in that The preset library further includes a third preset library, the control information further includes video playback information, and after the step of adjusting the air conditioner according to the temperature and wind speed information and the fragrance and oxygen enrichment information, the method further includes: If the preset video playback instruction is received, obtaining the video playback information from the third preset library according to the final target emotion; The air conditioner is adjusted according to the video playback information, the temperature and wind speed information, and the fragrance and oxygen enrichment information.

6. The method according to claim 3, characterized in that The method further comprises: If a manual adjustment command is received, obtaining manual adjustment information according to the manual adjustment command, and updating the preset library according to the manual adjustment information and the final target emotion; If the preset interval time is reached, the process returns to the step of collecting voice data and inputting the voice data into the emotion classification model for emotion classification to obtain a classification result, until a preset stop adjustment instruction or shutdown instruction is received.

7. The method according to any one of claims 1 to 6, characterized in that The sentiment classification model is obtained by training a deep neural network using sample speech data and text data corresponding to the sample speech data.

8. The method according to claim 7, characterized in that The emotion classification model is obtained by training a deep neural network using sample speech data and text data corresponding to the sample speech data, including: Collecting the sample voice data, and performing voice separation on the sample voice data to obtain separated voice data; Distinguishing and marking the voice data of different users in the separated voice data to obtain marked voice data, and performing voice recognition on the marked voice data to generate the text data; Performing feature extraction on the marked speech data to obtain speech features, and performing feature extraction on the text data to obtain text features; The deep neural network is trained according to the speech features and the text features to obtain the emotion classification model.

9. The method according to claim 8, characterized in that The step of training the deep neural network according to the speech features and the text features to obtain the sentiment classification model comprises: Fusing the speech feature and the text feature to obtain a fused feature; Inputting the fused features into the deep neural network for training until a preset termination condition is met; The trained deep neural network is used as the sentiment classification model.

10. A control device for an air conditioner, characterized in that: include: A collection and classification unit is used to collect voice data and input the voice data into a sentiment classification model to perform sentiment classification to obtain a classification result; An adjusting unit is used to adjust the air conditioner according to the classification result and the preset emotional priority.

11. An air conditioner, characterized in that: The air conditioner includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the method according to any one of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 can be implemented.

Images