Man-machine interaction air conditioning system based on deep learning and control method thereof
By combining deep learning technology with voice and gesture recognition, the problem of inflexible control methods in traditional automotive air conditioning systems has been solved, enabling natural interaction, personalized experience, and intelligent adjustment, thereby improving the response speed and user experience of the air conditioning system.
Patent Information
- Application Number
- CN202410952048.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional automotive air conditioning systems are not flexible enough, cannot provide a personalized user experience, have a slow response time, and can distract the driver.
Using deep learning technology, the system controls the air conditioner through voice and gesture recognition modules, and combines recurrent neural networks and convolutional neural networks for data processing to provide real-time feedback on the air conditioner status.
It enables natural interaction, personalized experience, and intelligent adjustment, improving driving comfort and air conditioning response speed.
Smart Images

Figure CN118952935A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of air conditioning regulation, and in particular to a human-computer interaction air conditioning system based on deep learning and a control method thereof. Background Art
[0002] Traditional car air conditioning systems can usually only be controlled by physical buttons or knobs. This control method may not be flexible enough, especially when driving, which may distract the driver. User experience is not user-friendly enough: Traditional car air conditioning systems may lack personalized user experience and cannot be adjusted intelligently according to the actual needs of drivers or passengers. Inconvenient for personalized settings: Traditional car air conditioning systems may only provide limited preset options and cannot be adjusted according to the personalized needs of users. Slow response speed: Traditional car air conditioning systems may have a slow adjustment response speed and cannot respond to changes in user needs immediately. Summary of the invention
[0003] The purpose of the present invention is to provide a human-computer interaction air-conditioning system and a control method thereof based on deep learning, so as to solve the technical problem of how to realize intelligent control of air-conditioning.
[0004] The present invention is implemented by adopting the following technical solution: a human-computer interactive air conditioning control method based on deep learning, comprising the following steps: S1: Acquire audio data and process the audio data to obtain a text representation of the voice command; S2: Acquire gesture image data, and process the gesture image data to obtain a classification result of the gesture action; S3: Complete the adjustment of the air conditioner according to the text representation of the voice command and the classification result of the gesture action; S4: Through the real-time feedback module, the current temperature setting of the air conditioner is fed back in real time to ensure that the air conditioner control operation is executed correctly.
[0005] Furthermore, step S1 is specifically as follows: using a deep learning model to recognize the passenger's voice and output a text representation of the passenger's voice command, wherein the deep learning model is a recurrent neural network speech recognition model or a converter speech recognition model.
[0006] Furthermore, the recurrent neural network speech recognition model uses a gated recurrent unit or a long short-term memory network to process time series data; the converter speech recognition model uses a self-attention mechanism to capture long-range dependencies in the input sequence.
[0007] Furthermore, step S2 is specifically as follows: using a deep learning algorithm to recognize the passenger's gesture image and output a classification result of the passenger's gesture action, wherein the deep learning algorithm is a convolutional neural network algorithm or a recurrent convolutional network algorithm.
[0008] Furthermore, the convolutional neural network algorithm uses a convolutional layer to extract features, reduces the dimension through a pooling layer, and finally performs classification through a fully connected layer; the recurrent convolutional network algorithm combines convolution and recurrent structures to process time series data and spatial information at the same time.
[0009] Furthermore, the classification results include temperature increase instructions, temperature decrease instructions, external loop instructions and internal loop instructions.
[0010] Furthermore, step S3 is specifically as follows: according to the text representation of the voice command, the air conditioner is adjusted to a specified temperature, and according to the classification result of the gesture action, corresponding parameters of the air conditioner are adjusted, and the parameters include heating, cooling, external circulation and internal circulation.
[0011] Furthermore, step S4 is specifically as follows: providing passengers with real-time feedback of the current temperature setting through voice prompts or display screens to ensure that the air conditioning control operation is correctly executed.
[0012] A human-computer interaction air conditioning system based on deep learning is used to implement the human-computer interaction air conditioning control method based on deep learning, including a speech recognition module, a gesture recognition module, a parameter adjustment module and a real-time feedback module, wherein: A speech recognition module is used to obtain audio data and process the audio data to obtain a text representation of the voice command; A gesture recognition module is used to obtain gesture image data and process the gesture image data to obtain a classification result of the gesture action; A parameter adjustment module is used to adjust the air conditioner according to the text representation of the voice command and the classification result of the gesture action; The real-time feedback module is used to provide real-time feedback on the current temperature setting of the air conditioner to ensure that the air conditioner control operation is executed correctly.
[0013] The beneficial effects of the present invention are: Natural interaction: The present invention can realize more natural interaction methods, such as voice commands and gesture control, so that drivers and passengers can communicate and operate the air conditioning system more conveniently without distracting their attention from driving.
[0014] Personalized experience: The present invention can realize personalized recognition and response to user behaviors by recognizing and understanding passengers' voice commands, gestures, etc., thereby providing customized air-conditioning settings for each user and improving the comfort of driving experience.
[0015] Intelligent adjustment: The present invention can automatically adjust air-conditioning parameters by learning and analyzing user behavior patterns and preferences to adapt to different driving scenarios and external environments, providing more intelligent air-conditioning control.
[0016] Real-time response: The present invention has strong real-time processing capabilities, can quickly and accurately identify and understand user instructions and actions, and instantly adjust air-conditioning parameters to improve the response speed of the air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.
[0018] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.
[0020] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0021] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0022] See also Figure 1 , a human-computer interaction air conditioning control method based on deep learning, comprising the following steps: S1: Acquire audio data and process the audio data to obtain a text representation of the voice command; S2: Acquire gesture image data, and process the gesture image data to obtain a classification result of the gesture action; S3: Complete the adjustment of the air conditioner according to the text representation of the voice command and the classification result of the gesture action; S4: Through the real-time feedback module, the current temperature setting of the air conditioner is fed back in real time to ensure that the air conditioner control operation is executed correctly.
[0023] In this embodiment, step S1 is specifically as follows: after the passenger enters the car, the voice recognition function is started to prepare to receive control instructions, such as the passenger saying the command, "lower the temperature to 22 degrees". A deep learning model is specifically used, such as a recurrent neural network (RNN) or a transformer model (Transformer). Input: audio data, output: text representation of voice instructions. Detailed description: The RNN-based speech recognition model can use a gated recurrent unit (GRU) or a long short-term memory network (LSTM) to process time series data, and finally output a text representation of the voice instruction. The Transformer-based speech recognition model uses a self-attention mechanism to capture long-range dependencies in the input sequence, and finally outputs a text representation of the voice instruction.
[0024] In this embodiment, step S2 is specifically as follows: start the gesture recognition function, and the passenger can also use gestures, such as swiping his arm downward, to indicate lowering the temperature. Issue an instruction: The passenger says the voice instruction "lower the temperature to 22 degrees", and the gesture indicates the action of lowering the temperature. Algorithm implementation process: Use deep learning models, such as convolutional neural networks (CNN) or recurrent convolutional networks (CRNN). Input: gesture image data, output: classification results of gesture actions. Detailed description: The gesture recognition model based on CNN usually uses a convolutional layer to extract features, then reduces the dimension through a pooling layer, and finally classifies through a fully connected layer to obtain the classification results of the gesture actions. The gesture recognition model based on CRNN combines convolution and recurrent structures, and can simultaneously process time series data and spatial information, and the classification results of gesture actions.
[0025] In this embodiment, step S3 is specifically as follows: the voice command of "lowering the temperature to 22 degrees" is converted into text through the voice recognition model (recurrent neural network or converter model). The gesture recognition model (convolutional neural network or recurrent convolutional network) recognizes the passenger's gesture as an operation to lower the temperature, and the air conditioning system adjusts the temperature to 22 degrees according to the recognition result. Recognition and understanding: The deep learning model recognizes and understands the voice command and gesture at the same time, and converts them into corresponding control instructions. The air conditioning system adjusts the temperature to 22 degrees according to the voice command recognition result, and adjusts the corresponding parameters according to the gesture, such as cooling, heating, internal circulation, external circulation, etc.
[0026] In this embodiment, step S4 specifically includes: providing real-time feedback of the current temperature setting to the passenger through voice prompts or display screens to ensure that the passenger has successfully completed the air conditioning control operation.
[0027] A human-computer interaction air conditioning system based on deep learning is used to implement the human-computer interaction air conditioning control method based on deep learning, including a speech recognition module, a gesture recognition module, a parameter adjustment module and a real-time feedback module, wherein: A speech recognition module is used to obtain audio data and process the audio data to obtain a text representation of the voice command; A gesture recognition module is used to obtain gesture image data and process the gesture image data to obtain a classification result of the gesture action; A parameter adjustment module is used to adjust the air conditioner according to the text representation of the voice command and the classification result of the gesture action; The real-time feedback module is used to provide real-time feedback on the current temperature setting of the air conditioner to ensure that the air conditioner control operation is executed correctly.
[0028] Based on the above embodiments, the present invention has at least the following technical effects: Natural interaction: The present invention can realize more natural interaction methods, such as voice commands and gesture control, so that drivers and passengers can communicate and operate the air conditioning system more conveniently without distracting their attention from driving.
[0029] Personalized experience: The present invention can realize personalized recognition and response to user behaviors by recognizing and understanding passengers' voice commands, gestures, etc., thereby providing customized air-conditioning settings for each user and improving the comfort of driving experience.
[0030] Intelligent adjustment: The present invention can automatically adjust air-conditioning parameters by learning and analyzing user behavior patterns and preferences to adapt to different driving scenarios and external environments, providing more intelligent air-conditioning control.
[0031] Real-time response: The present invention has strong real-time processing capabilities, can quickly and accurately identify and understand user instructions and actions, and instantly adjust air-conditioning parameters to improve the response speed of the air-conditioning system.
[0032] For the aforementioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily required by the present application.
[0033] The above embodiments describe the basic principles and main features of the present invention and the advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the changes and modifications made by those skilled in the art shall be within the scope of protection of the appended claims of the present invention without departing from the spirit and scope of the present invention.
Claims
1. A human-computer interactive air conditioning control method based on deep learning, characterized in that: The steps include: S1: Acquire audio data and process the audio data to obtain a text representation of the voice command; S2: Acquire gesture image data, and process the gesture image data to obtain a classification result of the gesture action; S3: Complete the adjustment of the air conditioner according to the text representation of the voice command and the classification result of the gesture action; S4: Through the real-time feedback module, the current temperature setting of the air conditioner is fed back in real time to ensure that the air conditioner control operation is executed correctly.
2. A human-computer interactive air conditioning control method based on deep learning as claimed in claim 1, characterized in that: Step S1 specifically includes: using a deep learning model to recognize the passenger's voice and output a text representation of the passenger's voice command, wherein the deep learning model is a recurrent neural network speech recognition model or a converter speech recognition model.
3. A human-computer interactive air conditioning control method based on deep learning as claimed in claim 2, characterized in that: The recurrent neural network speech recognition model uses a gated recurrent unit or a long short-term memory network to process time series data; the converter speech recognition model uses a self-attention mechanism to capture long-range dependencies in the input sequence.
4. The human-computer interactive air conditioning control method based on deep learning as claimed in claim 1, characterized in that: Step S2 specifically includes: using a deep learning algorithm to recognize the passenger's gesture image and output a classification result of the passenger's gesture action, wherein the deep learning algorithm is a convolutional neural network algorithm or a recurrent convolutional network algorithm.
5. The human-computer interactive air conditioning control method based on deep learning as claimed in claim 4, characterized in that: The convolutional neural network algorithm uses a convolutional layer to extract features, reduces the dimension through a pooling layer, and finally performs classification through a fully connected layer; the recurrent convolutional network algorithm combines convolution and recurrent structures to process time series data and spatial information at the same time.
6. The human-computer interactive air conditioning control method based on deep learning as claimed in claim 5, characterized in that: The classification results include temperature increase instructions, temperature decrease instructions, outer loop instructions and inner loop instructions.
7. The human-computer interactive air conditioning control method based on deep learning as claimed in claim 1, characterized in that: Step S3 is specifically as follows: according to the text representation of the voice command, the air conditioner is adjusted to a specified temperature, and according to the classification result of the gesture action, corresponding parameters of the air conditioner are adjusted, and the parameters include heating, cooling, external circulation and internal circulation.
8. The human-computer interactive air conditioning control method based on deep learning as claimed in claim 1, characterized in that: Step S4 specifically includes: providing real-time feedback of the current temperature setting to the passenger through voice prompts or display screens to ensure that the air conditioning control operation is correctly executed.
9. A human-computer interaction air conditioning system based on deep learning, used to implement a human-computer interaction air conditioning control method based on deep learning according to any one of claims 1 to 8, characterized in that: It includes a speech recognition module, a gesture recognition module, a parameter adjustment module and a real-time feedback module, among which: A speech recognition module is used to obtain audio data and process the audio data to obtain a text representation of the voice command; A gesture recognition module is used to obtain gesture image data and process the gesture image data to obtain a classification result of the gesture action; A parameter adjustment module is used to adjust the air conditioner according to the text representation of the voice command and the classification result of the gesture action; The real-time feedback module is used to provide real-time feedback on the current temperature setting of the air conditioner to ensure that the air conditioner control operation is executed correctly.
Citation Information
Patent Citations
Control method and system for air conditioner and air conditioner
CN106225174A
Method and device for adjusting running state of target equipment, storage medium and electronic device
CN111435596A
Automobile air conditioner air outlet control method, storage medium and electronic equipment
CN111959232A
Integrated control method, device and equipment for vehicle-mounted air conditioner, medium and vehicle
CN114889403A
Multi-dimensional interactive smart television set top box system
CN118138818A
