Intelligent control method and system for vehicle-mounted air conditioner and intelligent cabin
Through the combination of multimodal sensors and deep learning models, the operating parameters of the vehicle air conditioning system are dynamically adjusted, which solves the problem that traditional systems cannot adapt to the environment and user needs, and realizes intelligent and energy-saving air conditioning control, improving passenger comfort and System intelligence level.
Patent Information
- Application Number
- CN202411247678.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-19
AI Technical Summary
Traditional vehicle air conditioning systems cannot flexibly adapt to complex and changing environmental conditions and user personalized needs, resulting in reduced passenger comfort and waste of energy.
Through integrated multimodal sensors, real-time monitoring of the interior and exterior environment of the vehicle, the on-board computing unit is used to preprocess and data fusion of user behavior data, and combined with deep learning models to generate and identify environmental changes and user demand models, and dynamically adjust the operating parameters of the air conditioning system.
It realizes the intelligent decision-making ability of the vehicle, automatically selects the most energy-saving operating mode, continuously learns and optimizes control strategies, adapts to the preferences and needs of different users, reduces energy consumption, and improves the intelligent level and user experience of the air conditioning system.
Smart Images

Figure CN118977535A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a control method, a control system and a smart cockpit, and in particular to an intelligent control method, a control system and a smart cockpit for a vehicle air conditioner. Background Art
[0002] With the rapid development of artificial intelligence technology, large models such as Transformer and BERT have demonstrated powerful capabilities in many fields such as natural language processing, image recognition, and speech recognition. Through deep learning technology, these models can process and analyze large amounts of data, learn complex patterns and features from them, and achieve breakthrough performance in various tasks.
[0003] In the field of vehicle air conditioning systems, traditional control strategies are usually based on fixed algorithms and parameter settings. These strategies are often not flexible enough to adapt to complex and changing environmental conditions and the personalized needs of users. For example, traditional vehicle air conditioning systems may not be able to make real-time adjustments based on the temperature, humidity, light intensity inside and outside the vehicle, as well as the preferences and behavior patterns of passengers. This not only affects the comfort experience of passengers, but may also cause energy waste.
[0004] In order to solve these problems, the industry has been exploring more intelligent and energy-saving vehicle air conditioning control systems. However, most existing technologies are limited to the processing of a single data source, lack comprehensive analysis and application of multi-source data, and are difficult to achieve highly personalized and intelligent control. They can no longer meet people's requirements and are in urgent need of improvement. Summary of the invention
[0005] The purpose of the present invention is to provide a vehicle air-conditioning intelligent control method, control system and intelligent cockpit, so as to realize personalized and intelligent control of the vehicle air-conditioning and solve the shortcomings of the prior art.
[0006] The present invention provides the following scheme:
[0007] A vehicle air conditioner intelligent control method, applied to a vehicle air conditioner intelligent control system, comprising: Case No.: FAW041472-C-XCN1240627 1
[0008] The integrated multimodal sensor monitors the vehicle interior and exterior environment in real time to obtain user behavior data, and the vehicle computing unit pre-processes the user behavior data to obtain pre-processed data;
[0009] Analyzing and fusing the preprocessed data to fuse the preprocessed data from the multimodal sensor into a unified data set;
[0010] The unified data set is learned and trained through a deep learning model to generate a model for identifying environmental changes and user needs, and the operating parameters of the vehicle air conditioner are dynamically adjusted according to the model for identifying environmental changes and user needs.
[0011] Furthermore, the multimodal sensor includes: a temperature sensor, a humidity sensor, a light sensor, and a sound sensor.
[0012] Furthermore, the vehicle-mounted computing unit preprocesses the user behavior data to obtain preprocessed data, further comprising:
[0013] The vehicle-mounted computing unit receives the sensing signal from the multimodal sensor and performs data preprocessing, wherein the data preprocessing is specifically data cleaning or data normalization processing;
[0014] The principal component analysis algorithm is used to convert the sensing signals from the multimodal sensors into a set of linearly uncorrelated variables through orthogonal transformation;
[0015] Based on the linearly unrelated variables, the principal components of the sensing signal are obtained, and the corresponding eigenvalues and eigenvectors are calculated.
[0016] Furthermore, the vehicle-mounted computing unit preprocesses the user behavior data to obtain preprocessed data, further comprising:
[0017] The vehicle-mounted computing unit receives the sensing signal from the multimodal sensor and performs data preprocessing, wherein the data preprocessing is specifically data cleaning or data normalization processing;
[0018] Using an independent component analysis algorithm, a multivariate signal or a data set in the sensor signal is decomposed into statistically independent non-Gaussian signal sources. Using an independent component analysis algorithm, a multivariate signal or a data set in the sensor signal is decomposed into statistically independent non-Gaussian signal sources.
[0019] Using the kurtosis coefficient based on the non-Gaussianity measure as an indicator, the non-Gaussian distribution characteristics of the sensor signal are estimated in the on-board computing unit;
[0020] The kurtosis coefficient is used to measure the sharpness of the data distribution and the weight of the tail, and the Kurtosis value of the Gaussian distribution is detected. According to the difference in the Kurtosis value of the Gaussian distribution, the non-Gaussian characteristics of the data distribution are determined;
[0021] The FastICA iterative algorithm is used to find the independent components of the data, update the corresponding weight matrix, and identify and extract key features.
[0022] Furthermore, the Kurtosis value of the Gaussian distribution is detected, and the non-Gaussian characteristics of the data distribution are determined according to the difference in the Kurtosis value of the Gaussian distribution, specifically:
[0023] Check the Kurtosis value of the Gaussian distribution. If the Kurtosis value is greater than or equal to 3, the non-Gaussian characteristics of the data distribution are judged to be sharp distribution, or:
[0024] If the Kurtosis value is less than 3, the non-Gaussian characteristics of the data distribution are judged to be flat distribution.
[0025] Furthermore, the unified data set is learned and trained through a deep learning model to generate a model for identifying environmental changes and user needs, and the operating parameters of the vehicle air conditioner are dynamically adjusted according to the model for identifying environmental changes and user needs, further comprising:
[0026] The on-board computing unit uses a deep learning model to learn and train the unified data set through the deep learning model, wherein the deep learning model is specifically a convolutional neural network, a recurrent neural network or a Transformer model;
[0027] In the process of learning and training the unified data set using the deep learning model, the on-board computing unit identifies changes in the in-vehicle environment through supervised learning and generates a corresponding in-vehicle environment change model;
[0028] According to the calculation results of the in-vehicle environment change model, the vehicle-mounted computing unit automatically adjusts the operating parameters of the air-conditioning system and sends them to the vehicle air-conditioning control system.
[0029] An intelligent control system for a vehicle air conditioner, used to implement the intelligent control method for a vehicle air conditioner, comprising:
[0030] The multimodal sensor data acquisition module monitors the vehicle interior and exterior environment in real time through the integrated multimodal sensor to acquire user behavior data. The vehicle-mounted computing unit pre-processes the user behavior data to obtain pre-processed data.
[0031] A data fusion and unified data set generation module, which performs analysis and data fusion on the preprocessed data, and fuses the preprocessed data from the multimodal sensor into a unified data set;
[0032] The vehicle air-conditioning operating parameter dynamic adjustment module learns and trains the unified data set through a deep learning model to generate a model for identifying environmental changes and user needs, and dynamically adjusts the operating parameters of the vehicle air-conditioning according to the model for identifying environmental changes and user needs.
[0033] A smart cockpit is provided with the vehicle air-conditioning intelligent control system and executes the vehicle air-conditioning intelligent control method.
[0034] An electronic device comprises: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method.
[0035] A computer-readable storage medium stores a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the method.
[0036] Compared with the prior art, the present invention has the following advantages:
[0037] The vehicle air conditioner intelligent control method provided by the present invention is applied to a real vehicle, so that the vehicle has intelligent decision-making capabilities and can automatically select the most energy-saving operation mode according to the real-time monitored environmental parameters and user behavior data. For example, the air conditioner power is automatically reduced when the temperature difference between the inside and outside of the vehicle is small, and it is automatically switched to the energy-saving mode when the user leaves the vehicle, thereby effectively reducing energy consumption and realizing a green and environmentally friendly travel mode.
[0038] Through adaptive learning and user personalized settings, the present invention can continuously learn and optimize control strategies, automatically adjust parameters such as the temperature, wind speed, and air outlet direction of the air conditioner to adapt to the preferences and needs of different users. The vehicle air-conditioning intelligent control method has good scalability and can be easily linked and integrated with other vehicle systems, such as vehicle navigation, vehicle entertainment systems, etc., which not only improves the intelligence level of the vehicle air-conditioning system, but also provides the driver with a richer and more convenient driving experience, such as predicting changes in the environment ahead according to navigation information, adjusting the air-conditioning settings in advance, or automatically adjusting the atmosphere in the car according to the entertainment content.
[0039] The present invention provides a real-time user feedback mechanism that can collect users' evaluations and suggestions on air conditioning performance, and use these feedback data to further optimize the control strategy. Through continuous learning and iteration, the system can adapt to the ever-changing usage environment and user needs, achieve continuous performance improvement, and have high adaptability and robustness. Even in the case of sudden changes in environmental conditions or abnormal sensor data, the vehicle air conditioning system can respond quickly and make reasonable control decisions to ensure the stable operation of the air conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0041] Figure 1 It is a flow chart of the intelligent control method of vehicle air conditioning.
[0042] Figure 1A This is one of the flowcharts for preprocessing the user behavior data in step S1.
[0043] Figure 1B This is the second flowchart of preprocessing the user behavior data in step S1.
[0044] Figure 1C It is a flow chart of the optimization technical solution of step S3.
[0045] Figure 2 This is the architecture diagram of the vehicle air conditioning intelligent control system.
[0046] Figure 3 It is a structural diagram of an electronic device. DETAILED DESCRIPTION
[0047] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0048] like Figure 1 The vehicle air conditioner intelligent control method shown is applied to the vehicle air conditioner intelligent control system, including:
[0049] Step S1, real-time monitoring of the vehicle interior and exterior environment through an integrated multimodal sensor to obtain user behavior data, and the vehicle-mounted computing unit preprocesses the user behavior data to obtain preprocessed data; exemplarily, the multimodal sensor includes: a temperature sensor, a humidity sensor, a light sensor, and a sound sensor.
[0050] Step S2, analyzing and fusing the preprocessed data, fusing the preprocessed data from the multimodal sensor into a unified data set;
[0051] Step S3, learning and training the unified data set through a deep learning model to generate a model for identifying environmental changes and user needs, and dynamically adjusting the operating parameters of the vehicle air conditioner according to the model for identifying environmental changes and user needs; illustratively, the dynamic adjustment of the motion parameters of the vehicle air conditioner can be such as temperature, wind speed and air outlet direction, etc., to achieve the best energy saving effect and user comfort.
[0052] The technical solution provided in steps S1 to S3 realizes intelligent control of vehicle air conditioning by integrating a multimodal sensor system and performing sensor signal processing on the obtained multimodal sensors. The raw data obtained from the multimodal sensors are preprocessed (data cleaning, standardization and normalization, etc.) to improve data quality and lay a solid foundation for subsequent analysis. The preprocessed data from different sensors are then fused to form a unified data set. The unified data set is used to comprehensively reflect the inside and outside environment of the vehicle and the user status. The unified data set is then learned and trained through deep learning model training to generate a model that can accurately identify environmental changes and user needs. According to the recognition results of the deep learning model, the operating parameters of the vehicle air conditioner, such as temperature, wind speed and air outlet direction, are dynamically adjusted to achieve optimal energy saving effects and user comfort.
[0053] The technical solution provided in steps S1 to S3 can automatically understand and predict environmental changes and user needs, realize intelligent control, and reduce human intervention. By intelligently adjusting the air-conditioning operating parameters, the system can reduce energy consumption while ensuring comfort, achieve green energy saving and environmental protection, and can also provide customized comfort experience according to the user's personalized needs and preferences, and has the ability to quickly respond to environmental changes and user behavior, ensuring the real-time and accuracy of air-conditioning control.
[0054] like Figure 1A As shown, preferably, in step S1, the vehicle-mounted computing unit preprocesses the user behavior data to obtain preprocessed data, further comprising:
[0055] Step S11, the vehicle-mounted computing unit receives the sensing signal from the multimodal sensor and performs data preprocessing, wherein the data preprocessing is specifically data cleaning or data normalization processing;
[0056] Step S12, using a principal component analysis algorithm PCA to convert the sensing signal from the multimodal sensor into a set of linearly unrelated variables through orthogonal transformation;
[0057] Step S13, based on the linearly unrelated variables, obtain the principal components of the sensor signal, and calculate the corresponding eigenvalues and eigenvectors. Exemplarily, select the first ten to fifteen eigenvectors with the largest eigenvalues, and the eigenvectors represent the main change direction in the data.
[0058] The optimization technical solution provided in steps S11 to S13 is based on the results of principal component analysis, and calculates and selects the top ten to fifteen eigenvectors with the largest eigenvalues. These eigenvectors represent the main change directions in the data, significantly improving the data processing capability and intelligence level of the vehicle air-conditioning intelligent control system. Through data cleaning and normalization, the quality and consistency of the data are improved, providing a reliable data basis for subsequent analysis. The application of the PCA algorithm effectively reduces the dimension of the data, while extracting key features from the data and selecting the eigenvector with the largest eigenvalue. The above eigenvectors can more accurately reflect the main changes in the environment and user behavior, and can focus on the most important change information in the data, improving the efficiency and effect of data processing, and providing high-quality, high-dimensional input data for the training of deep learning models, which helps the model to better learn and predict environmental changes and user needs.
[0059] In summary, the optimization technical solutions provided in steps S11 to S13 obtain high-quality preprocessing and feature extraction results, so that the vehicle-mounted system can more accurately adapt to environmental changes and the personalized needs of users, thereby improving the intelligence level of the system.
[0060] like Figure 1B As shown, in step S1, the vehicle-mounted computing unit preprocesses the user behavior data to obtain preprocessed data, further comprising:
[0061] Step S14, the vehicle-mounted computing unit receives the sensing signal from the multimodal sensor and performs data preprocessing, wherein the data preprocessing is specifically data cleaning or data normalization processing;
[0062] Step S15, using an independent component analysis algorithm ICA to decompose a multivariate signal or a data set in the sensor signal into statistically independent non-Gaussian signal sources, using an independent component analysis algorithm ICA to decompose a multivariate signal or a data set in the sensor signal into statistically independent non-Gaussian signal sources;
[0063] Step S16, using Kurtosis based on non-Gaussian measurement as an indicator, estimating the non-Gaussian distribution characteristics of the sensor signal in the on-board computing unit;
[0064] Step S17, measuring the sharpness and tail weight of the data distribution according to the kurtosis coefficient Kurtosis, detecting the Kurtosis value of the Gaussian distribution, and determining the non-Gaussian characteristics of the data distribution according to the difference in the Kurtosis value of the Gaussian distribution;
[0065] Step S18, using the FastICA iterative algorithm to find the independent components of the data, update the corresponding weight matrix, and identify and extract key features.
[0066] The optimization technical solution provided in steps S14 to S18 performs data preprocessing and feature extraction on the user behavior data collected by the vehicle-mounted multimodal sensor through signal processing and data analysis technology, thereby enhancing the adaptability and analysis capabilities of the vehicle-mounted air-conditioning intelligent control system to complex data environments.
[0067] Steps S15 to S18 in the optimization technical solution provided by steps S14 to S18 are key contents. The ICA algorithm is applied to decompose the multivariate signal into statistically independent non-Gaussian signal sources to reveal the independent features behind the data, and the kurtosis coefficient (Kurtosis) is used as an indicator to estimate and measure the non-Gaussian distribution characteristics of the sensor signal, identify the sharpness and tail weight of the data distribution, for example, in step S18, the FastICA algorithm is used to iteratively find the independent components of the data, and the weights are updated by updating the case number: FAW041472-C-XCN1240627 8
[0068] The use of the FastICA algorithm effectively extracts key features from complex data sets. The above key features are crucial for understanding user behavior and environmental changes.
[0069] The optimization technical solution provided in step S14 to step S18 realizes data purification and feature independence. Data cleaning and normalization remove noise and outliers, improve the accuracy and availability of data, and the application of ICA algorithm helps to separate statistically independent signal sources from multivariate signals in a unified data set, providing clearer and independent features for subsequent analysis. In the calculation process of independent component analysis, the non-Gaussianity of data distribution is identified based on the Kurtosis value, and the independent components in the data are separated according to the non-Gaussianity of the data, and then the FastICA algorithm is used to effectively extract key features from the unified data set. The use of FastICA algorithm can effectively extract key features from complex data sets, which is crucial for understanding user behavior and environmental changes.
[0070] In summary, the optimization technical solution provided in steps S14 to S18 significantly improves the data processing capability of the vehicle air-conditioning intelligent control system by comprehensively using data preprocessing, ICA, non-Gaussian measurement and FastICA algorithm, providing a solid technical foundation for realizing more intelligent and personalized air-conditioning control.
[0071] Preferably, in step S16 to step S17, the Kurtosis value of the Gaussian distribution is detected, and the non-Gaussian characteristics of the data distribution are determined according to the difference in the Kurtosis value of the Gaussian distribution, specifically:
[0072] Check the Kurtosis value of the Gaussian distribution. If the Kurtosis value is greater than or equal to 3, the non-Gaussian characteristics of the data distribution are judged to be sharp distribution, or:
[0073] If the Kurtosis value is less than 3, the non-Gaussian characteristics of the data distribution are judged to be flat distribution.
[0074] The non-Gaussian characteristics of the data are evaluated and determined by quantitatively analyzing the kurtosis coefficient (Kurtosis) of the data distribution. The Gaussian characteristics are compared by comparing the Kurtosis value of the data with the Kurtosis value of the Gaussian distribution (the standard value is 3). This can measure the data distribution shape, especially the kurtosis and tail weight of the data.
[0075] The specific judgment logic of comparing Kurtosis values in step S16 to step S17 is:
[0076] Case No.: FAW041472-C-XCN1240627 9
[0077] If the Kurtosis value is greater than or equal to 3, the data distribution is sharper than the Gaussian distribution and has a heavier tail, which usually means that there are extreme values or outliers in the data, showing non-Gaussian characteristics.
[0078] If the Kurtosis value is less than 3, the data distribution is flatter than the Gaussian distribution and has a lighter tail, which usually means that the changes in the data are milder and also show non-Gaussian characteristics.
[0079] The detection of Kurtosis value can accurately identify the non-Gaussian characteristics of data distribution, provide important information for subsequent data analysis and processing, and understand the sharpness or flatness of data distribution, which helps to better understand the characteristics of data, lay the foundation for further processing and analysis of data, guide the parameter setting and iteration process of independent component analysis (ICA) algorithm, optimize the extraction process of independent components, and help algorithms such as FastICA to more accurately find independent components in data, thereby extracting more meaningful features. Based on in-depth quantitative analysis of data distribution, it provides algorithm data support for the subsequent dynamic adjustment of air-conditioning parameters.
[0080] like Figure 1C As shown, in step S3, the unified data set is learned and trained through a deep learning model to generate a model for identifying environmental changes and user needs, and the operating parameters of the vehicle air conditioner are dynamically adjusted according to the model for identifying environmental changes and user needs, further comprising:
[0081] Step S31, the on-board computing unit uses a deep learning model to learn and train the unified data set through the deep learning model, wherein the deep learning model is specifically a convolutional neural network, a recurrent neural network or a Transformer model;
[0082] Step S32, in the process of learning and training the unified data set using the deep learning model, the vehicle-mounted computing unit identifies changes in the vehicle interior environment through supervised learning and generates a corresponding vehicle interior environment change model;
[0083] Step S33: Based on the calculation results of the in-vehicle environment change model, the vehicle-mounted computing unit automatically adjusts the operating parameters of the air-conditioning system and sends them to the vehicle air-conditioning control system.
[0084] In the optimization technical solution from step S31 to step S33, deep learning is used to learn and train the unified data set through the vehicle computing unit, generating a model that can accurately identify changes in the vehicle environment and user needs, and dynamically adjust the operating parameters of the vehicle air conditioning system accordingly. Specifically:
[0085] The on-board computing unit adopts deep learning models such as convolutional neural network CNN, recurrent neural network RNN or Transformer to learn and train the data set, and uses the above models to process the complex data features and time series information related to the unified data set. During the training process, the on-board computing unit uses supervised learning to identify and understand the changes in the in-vehicle environment, generate an in-vehicle environment change model, capture the laws and trends of environmental changes, and according to the calculation results of the in-vehicle environment change model, the on-board computing unit automatically adjusts the operating parameters of the air-conditioning system, such as temperature, wind speed, etc., and sends adjustment instructions to the vehicle air-conditioning control system to achieve real-time control.
[0086] The optimization technical solution provided in steps S31 to S33 can automatically learn and identify environmental changes, realize intelligent control, and make accurate control decisions without human intervention. It can quickly process data and generate models based on deep learning models, so that the vehicle air-conditioning system can respond to environmental changes in real time. By intelligently adjusting air-conditioning parameters, the vehicle air-conditioning system can optimize energy use and reduce energy consumption while ensuring comfort. According to the learned user needs and preferences, the generalization ability of the deep learning model is used to continuously learn and self-optimize the model, providing personalized air-conditioning control methods to improve passenger comfort, satisfaction and user experience.
[0087] For the method steps disclosed in the above embodiments, the method steps are described as a series of action combinations for the purpose of simple description, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
[0088] Any process or method description described in a flowchart or other manner may be understood as representing a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations, in which the order shown or discussed may not be followed, including executing and implementing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, or executing computer instructions and implementing the corresponding functions according to program structures such as loops and branches, which can be naturally understood by those skilled in the art when implementing the embodiments of the present invention.
[0089] like Figure 2 The vehicle air-conditioning intelligent control system shown is used to implement the vehicle air-conditioning intelligent control method described in any one of the embodiments of the present application, including:
[0090] The multimodal sensor data acquisition module monitors the vehicle interior and exterior environment in real time through the integrated multimodal sensor to acquire user behavior data. The vehicle-mounted computing unit pre-processes the user behavior data to obtain pre-processed data.
[0091] A data fusion and unified data set generation module, which performs analysis and data fusion on the preprocessed data, and fuses the preprocessed data from the multimodal sensor into a unified data set;
[0092] The vehicle air-conditioning operating parameter dynamic adjustment module learns and trains the unified data set through a deep learning model to generate a model for identifying environmental changes and user needs, and dynamically adjusts the operating parameters of the vehicle air-conditioning according to the model for identifying environmental changes and user needs.
[0093] The implementation methods of the system described above are merely illustrative, for example, the various functional modules, units or subsystems in the system may or may not be physically separated, or may or may not be physical units, that is, they may be located in the same place, or they may be distributed to multiple different systems and their subsystems or modules. Those skilled in the art may select some or all of the functional modules, units or subsystems according to actual needs to achieve the purpose of the embodiments of the present invention, and those of ordinary skill in the art may understand and implement the above-mentioned situations without creative work.
[0094] Based on the vehicle air conditioning intelligent control method and system provided in the above embodiments, the embodiments of the present invention implement the following specific implementation methods in specific application scenarios:
[0095] Multimodal data collection and processing:
[0096] The system integrates multiple sensors, including temperature sensors, humidity sensors, light sensors, sound sensors, etc., to collect environmental data inside and outside the vehicle in real time.
[0097] At the same time, the system also collects multimodal data such as users' voice commands, gestures, facial expressions, etc. to analyze users' intentions and needs.
[0098] The system pre-processes and fuses these multimodal data to form comprehensive and accurate environment and user status information.
[0099] Large model learning and optimization:
[0100] Use deep learning models (such as Transformer) as core algorithms to learn and analyze multimodal data.
[0101] By training the model with a large amount of historical data and real-time data, it can accurately predict changes in the environment inside and outside the vehicle and changes in user needs.
[0102] Based on the prediction results, the model automatically adjusts the operating parameters of the car air conditioner (such as temperature, wind speed, air outlet direction, etc.) to achieve the best energy-saving effect and comfortable experience.
[0103] Energy-saving optimization strategy:
[0104] The system intelligently selects the most energy-efficient operating mode based on the environmental parameters inside and outside the vehicle and the user's real-time needs.
[0105] For example, while the vehicle is driving, the system can automatically adjust the cooling or heating power of the air conditioner according to the vehicle speed and engine temperature; when parking and waiting, the system can automatically switch to low-energy consumption mode.
[0106] At the same time, the system can also automatically adjust the preset temperature and operating time of the air conditioner according to the user's personalized settings and habits, further reducing energy consumption.
[0107] User Feedback and Adaptive Learning:
[0108] The system collects user feedback through voice interaction or other means, such as comfort evaluation, energy-saving effect evaluation, etc.
[0109] Based on user feedback, the system can automatically adjust control strategies and optimize parameters to suit the needs and preferences of different users.
[0110] Through continuous learning and optimization, the system can continuously improve energy saving effects and user experience. Case No.: FAW041472-C-XCN1240627 13
[0111] like Figure 3 As shown, the present invention not only provides a vehicle air conditioning intelligent control method and system, but also provides a corresponding intelligent cockpit, electronic equipment and storage medium:
[0112] A smart cockpit is provided with a vehicle air-conditioning intelligent control system, which executes the vehicle air-conditioning intelligent control method.
[0113] An electronic device comprises: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method.
[0114] A computer-readable storage medium stores a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the method.
[0115] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 The electronic device provided in the embodiment of the present invention includes: one or more processors 710 and a storage device 720; the processor 710 in the electronic device may be one or more, Figure 3 A processor 710 is taken as an example; the storage device 720 is used to store one or more programs; the one or more programs are executed by the one or more processors 710, so that the one or more processors 710 implement the vehicle air conditioning intelligent control method as described in any one of the embodiments of the present invention.
[0116] The electronic device may further include: an input device 730 and an output device 740 .
[0117] The processor 710, storage device 720, input device 730 and output device 740 in the electronic device can be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.
[0118] The storage device 720 in the electronic device is a computer-readable storage medium that can be used to store one or more programs, which can be software programs, computer executable programs, and modules, such as program instructions / modules corresponding to the vehicle air conditioning intelligent control method provided in the embodiment of the present invention. The processor 710 executes the software programs, instructions, and modules stored in the storage device 720.
[0119] The blocks are used to execute various functional applications and data processing of the electronic device, that is, to realize the vehicle air conditioning intelligent control method in the above method embodiment.
[0120] The storage device 720 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the storage device 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 720 may further include a memory remotely arranged relative to the processor 710, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0121] The input device 730 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 740 may include a display device such as a display screen.
[0122] Furthermore, when one or more programs included in the above-mentioned electronic device are executed by the one or more processors 710, the program executes the operating steps of the vehicle air-conditioning intelligent control method.
[0123] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0124] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, any one of the embodiments claimed in the claims can be used in any combination in the embodiments of the present invention.
[0125] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0126] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.
[0127] All features disclosed in this specification, or steps in all methods or processes disclosed, except mutually exclusive features and / or steps, can be combined in any way. Any feature disclosed in this specification, unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features. Throughout the specification, the same reference numerals indicate the same elements.
[0128] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and set in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition they can be divided into multiple submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including corresponding claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner can be combined in any combination. Unless otherwise explicitly stated, each feature disclosed in this specification (including corresponding claims, abstracts and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose.
[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified.
[0130] However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A vehicle air conditioner intelligent control method, applied to a vehicle air conditioner intelligent control system, characterized in that: include: The integrated multimodal sensor monitors the vehicle interior and exterior environment in real time to obtain user behavior data, and the vehicle computing unit pre-processes the user behavior data to obtain pre-processed data; Analyzing and fusing the preprocessed data to fuse the preprocessed data from the multimodal sensor into a unified data set; The unified data set is studied and trained through a deep learning model to generate a model for identifying environmental changes and user needs, and the operating parameters of the vehicle air conditioner are dynamically adjusted according to the model for identifying environmental changes and user needs.
2. The vehicle air conditioner intelligent control method according to claim 1, characterized in that: The multimodal sensor includes: a temperature sensor, a humidity sensor, a light sensor, and a sound sensor.
3. The vehicle air conditioner intelligent control method according to claim 1, characterized in that: The vehicle-mounted computing unit preprocesses the user behavior data to obtain preprocessed data, further comprising: The vehicle-mounted computing unit receives the sensing signal from the multimodal sensor and performs data preprocessing, wherein the data preprocessing is specifically data cleaning or data normalization processing; The principal component analysis algorithm is used to convert the sensing signals from the multimodal sensors into a set of linearly uncorrelated variables through orthogonal transformation; Based on the linearly unrelated variables, the principal components of the sensing signal are obtained, and the corresponding eigenvalues and eigenvectors are calculated.
4. The vehicle air conditioner intelligent control method according to claim 1, characterized in that: The vehicle-mounted computing unit preprocesses the user behavior data to obtain preprocessed data, further comprising: The vehicle-mounted computing unit receives the sensing signal from the multimodal sensor and performs data preprocessing, wherein the data preprocessing is specifically data cleaning or data normalization processing; Using an independent component analysis algorithm, a multivariate signal or a data set in the sensor signal is decomposed into statistically independent non-Gaussian signal sources. Using an independent component analysis algorithm, a multivariate signal or a data set in the sensor signal is decomposed into statistically independent non-Gaussian signal sources. Using the kurtosis coefficient based on the non-Gaussianity measure as an indicator, the non-Gaussian distribution characteristics of the sensor signal are estimated in the on-board computing unit; The kurtosis coefficient is used to measure the sharpness of the data distribution and the weight of the tail, and the Kurtosis value of the Gaussian distribution is detected. According to the difference in the Kurtosis value of the Gaussian distribution, the non-Gaussian characteristics of the data distribution are determined; The FastICA iterative algorithm is used to find the independent components of the data, update the corresponding weight matrix, and identify and extract key features.
5. The vehicle air conditioner intelligent control method according to claim 4, characterized in that: The Kurtosis value of the Gaussian distribution is detected, and the non-Gaussian characteristics of the data distribution are determined according to the difference of the Kurtosis value of the Gaussian distribution, specifically: Check the Kurtosis value of the Gaussian distribution. If the Kurtosis value is greater than or equal to 3, the non-Gaussian characteristics of the data distribution are judged to be sharp distribution, or: If the Kurtosis value is less than 3, the non-Gaussian characteristics of the data distribution are judged to be flat distribution.
6. The vehicle air conditioner intelligent control method according to claim 1, characterized in that: The method further includes: learning and training the unified data set through a deep learning model to generate a model for identifying environmental changes and user needs, and dynamically adjusting the operating parameters of the vehicle air conditioner according to the model for identifying environmental changes and user needs, and: The on-board computing unit uses a deep learning model to learn and train the unified data set through the deep learning model, wherein the deep learning model is specifically a convolutional neural network, a recurrent neural network or a Transformer model; In the process of learning and training the unified data set using the deep learning model, the on-board computing unit identifies changes in the in-vehicle environment through supervised learning and generates a corresponding in-vehicle environment change model; According to the calculation results of the in-vehicle environment change model, the vehicle-mounted computing unit automatically adjusts the operating parameters of the air-conditioning system and sends them to the vehicle air-conditioning control system.
7. A vehicle air-conditioning intelligent control system, used to implement the vehicle air-conditioning intelligent control method according to any one of claims 1 to 6, characterized in that: include: The multimodal sensor data acquisition module monitors the vehicle interior and exterior environment in real time through the integrated multimodal sensor to acquire user behavior data. The vehicle-mounted computing unit pre-processes the user behavior data to obtain pre-processed data. A data fusion and unified data set generation module, which performs analysis and data fusion on the preprocessed data, and fuses the preprocessed data from the multimodal sensor into a unified data set; The vehicle air-conditioning operating parameter dynamic adjustment module learns and trains the unified data set through a deep learning model to generate a model for identifying environmental changes and user needs, and dynamically adjusts the operating parameters of the vehicle air-conditioning according to the model for identifying environmental changes and user needs.
8. A smart cockpit, characterized in that: The smart cockpit is provided with the vehicle air conditioning intelligent control system according to claim 7, and executes the vehicle air conditioning intelligent control method according to any one of claims 1 to 6.
9. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: It stores a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the steps of the method described in any one of claims 1 to 6.
Citation Information
Patent Citations
Vehicle-mounted air conditioner intelligent adjusting method and system based on Internet of Vehicles and big data
CN111251819A
Identification method under multi-target acoustic signal aliasing
CN112185412A
Vehicle-mounted air conditioner temperature adjusting method and related device
CN114379325A
Intelligent analysis output method and system serving big data denoising optimization
CN116383610A
Air conditioner energy-saving control method and system based on reinforcement learning and digital twinborn model
CN118031385A
Cited By
Air conditioner energy-saving control method and system based on smart cloud analysis
CN119983484A
