Vehicle air-conditioner control method, vehicle, and storage medium

By acquiring user characteristics and environmental data for decision analysis and generating target control parameters, the problem of low control efficiency in traditional vehicle air conditioning systems is solved, realizing personalized and health-oriented air conditioning control and improving passenger comfort and experience.

WO2026233023A1PCT designated stage Publication Date: 2026-11-12CHERY AUTOMOBILE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2026/087815
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-09-04
Filing Date
2026-03-31
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

Traditional vehicle air conditioning systems cannot adjust in a timely and accurate manner to meet the comfort requirements of all passengers, especially when the external environment changes rapidly or passengers are diverse, resulting in low control efficiency and poor user experience.

Method used

By acquiring user characteristic data and environmental condition data associated with the target vehicle, and using deep learning and big data analysis technologies for decision analysis, target control parameters are generated to precisely adjust the operating status of the vehicle's air conditioning.

Benefits of technology

It enables personalized and health-oriented control of the air conditioning, improves riding comfort and health protection, ensures that air conditioning control is more in line with passenger needs, and enhances the overall riding experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2026087815_12112026_PF_FP_ABST
    Figure CN2026087815_12112026_PF_FP_ABST
Patent Text Reader

Abstract

A vehicle air-conditioner control method, a vehicle, and a storage medium. The vehicle air-conditioner control method comprises: acquiring user feature data and environmental condition data that are associated with a target vehicle, wherein the user feature data is configured to represent passenger attribute information corresponding to the target vehicle, and the environmental condition data is configured to represent out-of-vehicle environmental information and in-vehicle environmental information of the target vehicle (S11); performing decision analysis on the basis of the user feature data and the environmental condition data, so as to obtain a decision analysis result, wherein the decision analysis result is configured to determine an operating mode of a vehicle-mounted air conditioner of the target vehicle (S12); determining a target control parameter of the vehicle-mounted air conditioner on the basis of the decision analysis result, wherein the target control parameter is configured to adjust the operating state of the vehicle-mounted air conditioner (S13); and using the target control parameter to control the vehicle-mounted air conditioner (S14).
Need to check novelty before this filing date? Find Prior Art

Description

Vehicle air conditioning control methods, vehicles and storage media

[0001] Cross-reference

[0002] This disclosure claims priority to Chinese Patent Application No. 202511260644.9, filed on September 4, 2025, entitled "Vehicle Air Conditioning Control Method, Vehicle and Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of vehicle technology, and more specifically, to a vehicle air conditioning control method, a vehicle, and a storage medium. Background Technology

[0004] With the rapid development of the automotive industry, especially the popularization of new energy vehicles, intelligent functions have gradually become key to improving the driving experience. As the core of in-vehicle environment regulation, the air conditioning system directly affects passenger comfort. Traditional air conditioning systems mainly rely on manual adjustments by the user. Whether it's temperature, airflow, or airflow direction, users need to adjust these settings in real time based on their personal feelings. This adjustment method is not only cumbersome but also often fails to reflect the user's actual needs in a timely manner. For example, when the external environment changes rapidly, such as a sudden shift from hot summer to cool weather, or when multiple passengers with different body temperature preferences are in the vehicle, traditional air conditioning systems struggle to quickly and accurately adjust parameters to meet the comfort requirements of all passengers. While some high-end models are equipped with automatic air conditioning, these functions are limited to basic temperature adjustments based on signals from in-vehicle temperature sensors, resulting in low control efficiency and a poor user experience.

[0005] There is currently no good solution to the above problems. Summary of the Invention

[0006] This disclosure provides a vehicle air conditioning control method, a vehicle, and a storage medium to at least solve the technical problems of low control efficiency and poor user experience of vehicle air conditioning in related technologies.

[0007] According to one aspect of the present disclosure, a vehicle air conditioning control method is provided, comprising the following steps: Acquiring user characteristic data and environmental condition data associated with a target vehicle, wherein the user characteristic data is configured to represent passenger attribute information corresponding to the target vehicle, and the environmental condition data is configured to represent external environmental information and internal environmental information of the target vehicle. Performing decision analysis based on the user characteristic data and environmental condition data to obtain a decision analysis result, wherein the decision analysis result is used to determine the operating mode of the vehicle's air conditioning system. Determining target control parameters for the vehicle air conditioning system based on the decision analysis result, wherein the target control parameters are used to adjust the operating state of the vehicle air conditioning system. Controlling the vehicle air conditioning system using the target control parameters.

[0008] Optionally, obtaining user feature data associated with the target vehicle includes the following steps: In response to receiving key positioning information, first image data is acquired, wherein the first image data is configured to represent external user image data associated with the target vehicle. In response to receiving door opening information, second image data is acquired, wherein the second image data is configured to represent internal user image data of the target vehicle. Feature extraction is performed on the first image data and the second image data to obtain user feature data.

[0009] Optionally, feature extraction from the first image data and the second image data to obtain user feature data includes the following steps: Feature extraction is performed on the first image data to obtain human body envelope data, wherein the human body envelope data is set to represent the visual feature information of the target user. Feature extraction is performed on the second image data to obtain facial feature data of the target user. User feature data is determined based on the human body envelope data and the facial feature data.

[0010] Optionally, the decision analysis based on user characteristic data and environmental condition data, to obtain the decision analysis results, includes the following steps: Verifying the user characteristic data and environmental condition data using a preset pattern database to obtain a verification result, wherein the verification result is set to determine whether prior pattern information corresponding to the user characteristic data and environmental condition data exists in the preset pattern database. Decision analysis is then performed based on the verification result to obtain the decision analysis results.

[0011] Optionally, decision analysis is performed based on the verification results to obtain the decision analysis results, including the following steps: The response determines, based on the verification results, that prior pattern information exists in the preset pattern database, and determines the decision analysis results based on the prior pattern information. The response determines, based on the verification results, that prior pattern information does not exist in the preset pattern database, and creates a pattern based on user characteristic data and environmental condition data to obtain the decision analysis results.

[0012] Optionally, pattern creation based on user characteristic data and environmental condition data to obtain decision analysis results includes the following steps: Analyzing and processing the user characteristic data and environmental condition data using a target state prediction network model to obtain target state prediction results, where the target state prediction results represent passenger state information of the target vehicle. Pattern creation based on the target state prediction results and a preset mapping relationship to obtain decision analysis results, where the preset mapping relationship records the mapping relationship between preset passenger states and preset air conditioning modes.

[0013] Optionally, the vehicle air conditioning control method further includes the following steps: Responding to a target user's touch operation on the air conditioning settings controls, obtaining prior mode information corresponding to the target user, wherein the prior mode information is set to represent the target user's air conditioning preference mode information. Constructing a preset mode database based on the prior mode information.

[0014] Optionally, the target control parameters include at least one of the following: function mode information, temperature information, air volume information, and air outlet angle information.

[0015] According to another aspect of the embodiments of this disclosure, a vehicle air conditioning control device is also provided, including the following modules: An acquisition module, configured to acquire user characteristic data and environmental condition data associated with a target vehicle, wherein the user characteristic data represents passenger attribute information corresponding to the target vehicle, and the environmental condition data represents external environmental information and internal environmental information of the target vehicle. An analysis module, configured to perform decision analysis based on the user characteristic data and environmental condition data to obtain a decision analysis result, wherein the decision analysis result is configured to determine the operating mode of the vehicle's air conditioning. A determination module, configured to determine target control parameters for the vehicle air conditioning based on the decision analysis result, wherein the target control parameters are configured to adjust the operating state of the vehicle air conditioning. A control module, configured to control the vehicle air conditioning using the target control parameters.

[0016] Optionally, the acquisition module is further configured to perform the following steps: In response to receiving key positioning information, acquire first image data, wherein the first image data is configured to represent external user image data associated with the target vehicle. In response to receiving door opening information, acquire second image data, wherein the second image data is configured to represent internal user image data of the target vehicle. Perform feature extraction on the first image data and the second image data to obtain user feature data.

[0017] Optionally, the acquisition module is further configured to perform the following steps: Extract features from the first image data to obtain human body envelope data, wherein the human body envelope data is configured to represent the visual feature information of the target user. Extract features from the second image data to obtain facial feature data of the target user; determine user feature data based on the human body envelope data and the facial feature data.

[0018] Optionally, the analysis module is further configured to perform the following steps: Verify the user feature data and environmental condition data using a preset pattern database to obtain a verification result, wherein the verification result is configured to determine whether prior pattern information corresponding to the user feature data and environmental condition data exists in the preset pattern database. Perform decision analysis based on the verification result to obtain the decision analysis result.

[0019] Optionally, the analysis module is further configured to perform the following steps: The response determines, based on the verification processing results, that prior pattern information exists in the preset pattern database, and determines the decision analysis result based on the prior pattern information. The response determines, based on the verification processing results, that prior pattern information does not exist in the preset pattern database, and creates a pattern based on user characteristic data and environmental condition data to obtain the decision analysis result.

[0020] Optionally, the analysis module is further configured to perform the following steps: Analyze and process user feature data and environmental condition data using a target state prediction network model to obtain a target state prediction result, wherein the target state prediction result represents passenger state information of the target vehicle. Create a pattern based on the target state prediction result and a preset mapping relationship to obtain a decision analysis result, wherein the preset mapping relationship records the mapping relationship between preset passenger states and preset air conditioning modes.

[0021] Optionally, the acquisition module is further configured to perform the following steps: In response to a target user's touch operation on the air conditioning settings control, acquire prior mode information corresponding to the target user, wherein the prior mode information is configured to represent the target user's air conditioning preference mode information. The vehicle air conditioning control device also includes the following module: A construction module, configured to construct a preset mode database based on the prior mode information.

[0022] Optionally, the target control parameters include at least one of the following: function mode information, temperature information, air volume information, and air outlet angle information.

[0023] According to another aspect of the present disclosure, a vehicle is also provided, including: a memory storing an executable program; and a processor configured to run the program, wherein the program executes the methods of various embodiments of the present disclosure when it runs.

[0024] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of the various embodiments of the present disclosure.

[0025] According to another aspect of the embodiments of this disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this disclosure.

[0026] According to another aspect of the embodiments of this disclosure, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods of various embodiments of this disclosure.

[0027] According to another aspect of the embodiments of this disclosure, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this disclosure.

[0028] In this embodiment, by acquiring user characteristic data and environmental condition data associated with the target vehicle, and then performing decision analysis based on the user characteristic data and environmental condition data, the target control parameters of the vehicle air conditioner are determined based on the decision analysis results. Finally, the vehicle air conditioner is controlled using the target control parameters, achieving the goal of personalized and health-oriented air conditioning control through intelligent analysis, thereby improving passenger comfort and health protection. Through deep learning and big data analysis technologies, comprehensive perception and intelligent decision-making regarding user characteristics and environmental conditions are achieved. This allows for rapid adjustment of air conditioning modes and parameters, ensuring that air conditioning control better meets passenger needs, improving the overall passenger experience, and thus solving the technical problems of low control efficiency and poor user experience in related technologies. Attached Figure Description

[0029] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are intended to explain the disclosure, but do not constitute an undue limitation thereof. In the drawings:

[0030] Figure 1 is a flowchart of a vehicle air conditioning control method according to an embodiment of the present disclosure;

[0031] Figure 2 is a schematic diagram of a feature extraction process according to an embodiment of the present disclosure;

[0032] Figure 3 is a schematic diagram of the architecture of an intelligent air conditioning control system according to an embodiment of the present disclosure;

[0033] Figure 4 is a schematic diagram of a vehicle air conditioning control method according to an embodiment of the present disclosure;

[0034] Figure 5 is a schematic diagram of another vehicle air conditioning control method according to an embodiment of the present disclosure;

[0035] Figure 6 is a structural block diagram of a vehicle air conditioning control device according to an embodiment of the present disclosure. Detailed Implementation

[0036] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are intended to distinguish similar objects and are not necessarily intended to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0038] According to an embodiment of this disclosure, a method embodiment for controlling a vehicle air conditioning system is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] This embodiment provides a vehicle air conditioning control method. Figure 1 is a flowchart of a vehicle air conditioning control method according to an embodiment of this disclosure. As shown in Figure 1, the process includes the following steps.

[0040] Step S11: Obtain user feature data and environmental condition data associated with the target vehicle. The user feature data is set to represent passenger attribute information corresponding to the target vehicle, and the environmental condition data is set to represent external environmental information and internal environmental information of the target vehicle.

[0041] Step S12: Decision analysis is performed based on user characteristic data and environmental condition data to obtain decision analysis results, wherein the decision analysis results are set to determine the working mode of the target vehicle's air conditioning.

[0042] Step S13: Determine the target control parameters of the vehicle air conditioner based on the decision analysis results, wherein the target control parameters are set to adjust the operating status of the vehicle air conditioner;

[0043] Step S14: Control the vehicle air conditioner using the target control parameters.

[0044] The user characteristic data associated with the target vehicle can be collected through cameras on the vehicle (such as surround view / panoramic view cameras, driver monitoring system (DMS) cameras) and other sensors (such as infrared temperature sensors). The user characteristic data is the physical characteristics and biometric data related to the current passengers in the target vehicle. The user characteristic data includes height, age, gender, health status, activity level, emotional state, etc.

[0045] The aforementioned environmental condition data covers environmental parameters inside and outside the target vehicle. This data includes, but is not limited to, information such as temperature, humidity, light intensity, and air quality outside the vehicle, as well as indicators such as temperature distribution, humidity level, and air quality index inside the vehicle. The environmental condition data can be obtained through sensors such as the vehicle's internal and external temperature sensors, humidity sensors, light sensors, and air quality sensors.

[0046] User characteristic data and environmental condition data can be collected by various sensors on the vehicle through the in-car control center (ICC) of the infotainment system, ensuring the comprehensiveness and real-time nature of the data and providing accurate reference for subsequent decision analysis.

[0047] Decision analysis is performed based on collected user characteristic data and environmental condition data to generate decision analysis results. This process involves complex deep learning computations, aiming to determine the optimal operating mode of the air conditioning by analyzing passengers' physical condition and environmental needs, in order to achieve an optimal balance between comfort and energy consumption. The above decision analysis results, derived from a comprehensive analysis of user characteristic data and environmental condition data, indicate the most suitable operating mode for the target vehicle's onboard air conditioning. These operating modes may include automatic mode, powerful cooling, rapid heating, airflow adjustment, and temperature setting, to meet passengers' comfort and health requirements.

[0048] Based on the decision analysis results, the target control parameters of the vehicle air conditioning system can be further clarified. This involves translating the decision analysis results into specific operational instructions. For example, an operational instruction could be to set the air conditioning temperature to 22°C, the fan speed to medium, and to use a combination of internal and external circulation to ensure the air conditioning system can respond quickly and adjust to the ideal state. Target control parameters are the operating parameters of the vehicle air conditioning system. These parameters include, but are not limited to, set temperature, fan speed, air circulation mode, and airflow mode (such as direct airflow to passengers or automatic air sweeping). These parameters are used to precisely adjust the operating status of the vehicle air conditioning system to adapt to the current passenger needs and environmental conditions.

[0049] The target control parameters determined in the decision analysis results are transmitted to the vehicle's air conditioning system through the vehicle's air conditioning system, thereby executing corresponding adjustments, such as changing the temperature setting, increasing or decreasing the air volume, switching between internal and external circulation, etc., to ensure that the in-vehicle environment reaches the ideal comfort state predicted in the decision analysis stage.

[0050] Based on steps S11 to S14 above, by acquiring user characteristic data and environmental condition data associated with the target vehicle, and then performing decision analysis based on this data, the target control parameters for the vehicle's air conditioning are determined. Finally, the vehicle's air conditioning is controlled using these target control parameters. This achieves the goal of personalized and health-oriented air conditioning control through intelligent analysis, thereby improving passenger comfort and health protection. Through deep learning and big data analytics, comprehensive perception and intelligent decision-making regarding user characteristics and environmental conditions are achieved. This allows for rapid adjustment of air conditioning modes and parameters, ensuring that air conditioning control better meets passenger needs and improves the overall passenger experience. This solves the technical problems of low control efficiency and poor user experience associated with vehicle air conditioning in related technologies.

[0051] The vehicle air conditioning control method in the embodiments of this disclosure will be further described below.

[0052] In one optional embodiment, obtaining user characteristic data associated with the target vehicle includes the following steps.

[0053] In response to receiving key location information, first image data is acquired, wherein the first image data is set to represent external user image data associated with the target vehicle.

[0054] In response to receiving door opening information, second image data is acquired, wherein the second image data is set to represent in-vehicle user image data of the target vehicle.

[0055] Feature extraction is performed on the first image data and the second image data to obtain user feature data.

[0056] The key location information mentioned above is provided by the digital key control module and includes the relative position data between the smart key and the vehicle (such as Bluetooth signal strength indicator (RSSI)). The key location information is set to trigger the external camera to collect the first image data in order to identify the characteristics of the person approaching the vehicle.

[0057] The aforementioned first image data can be images of users outside the vehicle captured by surround-view / panoramic-view cameras. The first image data is mainly set to analyze the appearance information and preliminary physical characteristics of the personnel (such as height, body shape, clothing, etc.), providing predictive data for subsequent accurate positioning and depth analysis of the in-vehicle cameras.

[0058] The aforementioned door opening information can be monitored and fed back by the area controller. The door opening information is set to indicate that the door is open, triggering the DMS camera to start working and collect facial details of the user inside the vehicle.

[0059] The aforementioned second image data refers to the in-vehicle user images captured by the DMS camera. The focus of the second image data is on the capture and analysis of facial features (such as facial expressions, whether sweating, etc.), which helps to understand the user's current emotions and physiological state more deeply.

[0060] Upon receiving key location information, the external camera is activated to collect first image data, which includes the appearance information of the person approaching the vehicle, providing preliminary visual data for subsequent feature extraction and user identification. Upon receiving door opening information, the in-vehicle DMS camera is activated to collect second image data (i.e., a high-resolution image of the user's face inside the vehicle) to further analyze the user's emotions and physiological state. Furthermore, deep feature extraction is performed on the first and second image data, including but not limited to the application of Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) algorithms, to obtain user feature data (including body envelope data and facial feature data). This user feature data can be used for intelligent decision-making and personalized adjustment of the air conditioning control system.

[0061] Based on the above optional embodiments, in response to receiving key positioning information, first image data is acquired, and then in response to receiving door opening information, second image data is acquired. Finally, feature extraction is performed on the first and second image data to obtain user feature data. This achieves comprehensive and automated collection and analysis of user feature data, providing a solid data foundation for intelligent air conditioning control and ensuring that the air conditioning system can make rapid and accurate adjustment responses based on the passenger's real-time physical characteristics and emotional state.

[0062] In one optional embodiment, feature extraction from the first image data and the second image data to obtain user feature data includes the following steps.

[0063] Feature extraction is performed on the first image data to obtain human body envelope data, wherein the human body envelope data is set to represent the visual feature information of the target user.

[0064] Feature extraction is performed on the second image data to obtain the facial feature data of the target user.

[0065] User characteristic data is determined based on human body envelope data and facial feature data.

[0066] The aforementioned human body envelope data can be a set of user body features extracted from the first image data. This set includes, but is not limited to, body contours, size, height, and limb posture. The human body envelope data is designed to quickly predict the user's basic body characteristics (such as whether they are a child, pregnant woman, or elderly person). This data is crucial for the initial selection of the air conditioning mode. Acquiring human body envelope data can quickly determine the user's basic type, providing rough guidance for subsequent more precise adjustments, reducing the air conditioning system's response time, and improving adjustment efficiency.

[0067] The aforementioned facial feature data can be specific facial features extracted from the second image data, such as facial temperature, sweat distribution, and skin color changes. This facial feature data reflects the user's emotional state and physiological needs, playing a crucial role in the refined control of intelligent air conditioning. Compared to the preliminary judgment based on body envelope data, facial feature data extraction is more precise, capable of capturing subtle physiological reactions and emotional changes in the user (e.g., sweating indicates overheating, while paleness signifies cold or discomfort). This feature limitation allows the air conditioning system to adjust according to the user's immediate physiological needs, greatly enhancing personalized adjustment capabilities and improving the user experience.

[0068] Figure 2 is a schematic diagram of a feature extraction process according to an embodiment of the present disclosure. As shown in Figure 2, when an image or video is introduced into a deep learning algorithm as an input source, the multimedia data is first fed into a convolutional neural network and a recurrent neural network for detailed feature extraction to parse the user's body appearance and other key visual information. Subsequently, 3D human keypoint detection technology is used to perform in-depth analysis of the extracted features, accurately locate various important parts of the body (such as elbows, knees, and heads), and construct a three-dimensional human body structure model. Next, by performing detailed analysis of the relative positions between joints and limbs, the topological structure between joints is established to ensure an accurate understanding of human posture and movement state, maintaining consistency and reliability of recognition even in complex environments. Based on this, the built-in point-by-point feasibility analyzer performs real-time tracking, keenly capturing subtle changes in human body position and determining whether there are occlusion issues to maintain the continuity and integrity of image analysis. Ultimately, human body envelope data is obtained. This human body envelope data includes detailed information such as the user's body size, gender classification, age group, and whether they are in a special condition (such as a child, elderly person, or pregnant woman). This data will be used by the entertainment host ICC. The human body envelope data serves as the core basis for adaptive air conditioning adjustment, thereby enabling refined and personalized adjustments to air conditioning parameters to meet the unique needs of different users in different scenarios and improve the comfort and intelligence level of the riding experience.

[0069] Based on the above optional embodiments, feature extraction is performed on the first image data to obtain human body envelope data, and then feature extraction is performed on the second image data to obtain the facial feature data of the target user. Finally, user feature data is determined based on the human body envelope data and facial feature data, realizing in-depth mining and accurate extraction of user feature data, which further significantly improves the intelligence level of air conditioning adjustment and user experience, especially the applicability and accuracy under different population groups and complex environmental conditions.

[0070] In one optional embodiment, decision analysis is performed based on user characteristic data and environmental condition data to obtain decision analysis results, including the following steps.

[0071] The user feature data and environmental condition data are validated using a preset pattern database to obtain a validation result. The validation result is set to determine whether there is prior pattern information corresponding to the user feature data and environmental condition data in the preset pattern database.

[0072] Decision analysis is performed based on the verification results to obtain the decision analysis results.

[0073] The above verification process involves the system's preliminary comparison and evaluation of user characteristic data and environmental condition data. The verification results are used to determine whether prior mode information matching the current scenario can be found in the preset mode database. Prior mode information refers to existing air conditioning control modes within the preset mode database, obtained through historical big data analysis. These prior mode information corresponds to specific user characteristics and environmental conditions and can be directly set to guide the intelligent adjustment of the air conditioning system. The preset mode database stores a series of air conditioning control modes formed through learning and historical data accumulation. It aims to cover the optimal air conditioning parameter settings under various combinations of user characteristics and environmental conditions. Through continuous learning and optimization, the preset mode database contains optimal air conditioning parameter settings for various combinations of user characteristics and environmental conditions, enabling rapid search and application of the most suitable control mode.

[0074] The decision analysis results mentioned above can be the final set of parameters generated after the verification process or the creation of the model. The set of parameters can be set to guide the actual operation of the air conditioning system. The set of parameters includes, but is not limited to, various function adjustment information such as temperature setting, air volume, and air direction control.

[0075] Based on the above optional embodiments, by using a preset pattern database to verify user feature data and environmental condition data, a verification result is obtained. Then, a decision analysis is performed based on the verification result to obtain the decision analysis result. This achieves high-precision and personalized adjustment of the air conditioning system control. It can quickly retrieve or generate matching air conditioning control modes according to the user's body type, emotional state, and real-time conditions such as external weather changes and in-vehicle temperature, significantly improving the comfort and convenience of the vehicle air conditioning.

[0076] In one optional embodiment, decision analysis is performed based on the verification process results, and the decision analysis results include the following steps.

[0077] The response determines that prior pattern information exists in the preset pattern database based on the verification processing results, and then determines the decision analysis results based on the prior pattern information.

[0078] The response determines that there is no prior pattern information in the preset pattern database based on the verification processing results. Pattern creation is performed based on user feature data and environmental condition data to obtain decision analysis results.

[0079] Specifically, when prior mode information exists in the preset mode database, the entertainment host ICC immediately retrieves the relevant prior mode information to generate decision analysis results and adjusts various parameters of the air conditioning system accordingly. When no prior mode information exists in the preset mode database, the system enters the mode creation stage. The entertainment host ICC combines user characteristic data and environmental condition data, using deep learning technology to create a new air conditioning control mode. This control mode more accurately reflects the user's personalized needs and environmental characteristics. Subsequently, this control mode, as part of the decision analysis results, is set to guide the intelligent adjustment of the air conditioning system.

[0080] Based on the above optional embodiments, by responding to the verification processing results to determine that prior pattern information exists in the preset pattern database, determining the decision analysis result based on the prior pattern information, and responding to the verification processing results to determine that prior pattern information does not exist in the preset pattern database, a pattern is created based on user feature data and environmental condition data to obtain the decision analysis result, which significantly enhances the response speed, decision accuracy and user adaptability of the air conditioning intelligent control system.

[0081] In one alternative embodiment, pattern creation based on user characteristic data and environmental condition data to obtain decision analysis results includes the following steps.

[0082] The target state prediction network model is used to analyze and process user feature data and environmental condition data to obtain target state prediction results, where the target state prediction results are set to represent the passenger state information of the target vehicle.

[0083] Based on the target state prediction results and the preset mapping relationship, a pattern is created to obtain the decision analysis results. The preset mapping relationship is set to record the mapping relationship between the preset passenger state and the preset air conditioning mode.

[0084] The aforementioned target state prediction network model is a deep learning model specifically designed to predict the state of passengers in a vehicle. The entertainment system (ICC) uses this model to comprehensively analyze collected user characteristic data and environmental condition data. Specifically, this analysis assesses the passenger's current feelings (e.g., cold, heat, comfort level) and potential health conditions (e.g., fatigue, anxiety), thereby obtaining the target state prediction result. This result characterizes the passenger's comfort level or health condition under specific environmental conditions; therefore, it serves as a crucial basis for subsequent air conditioning mode adjustments.

[0085] The aforementioned preset mapping relationship is an association rule that defines the pairing relationship between various passenger states and the most suitable air conditioning operating mode. For example, high body temperature is mapped to the cooling mode, and fatigue is associated with the mild ventilation mode.

[0086] By combining the target state prediction results and the preset mapping relationship, the entertainment host ICC can create or select an appropriate air conditioning mode and form specific air conditioning parameter adjustment instructions (i.e. decision analysis results). The decision analysis results include function configurations such as temperature setting, fan speed control, and air purification.

[0087] Based on the above optional embodiments, by using a target state prediction network model to analyze and process user feature data and environmental condition data, a target state prediction result is obtained. Then, based on the target state prediction result and a preset mapping relationship, a pattern is created to obtain a decision analysis result, which effectively improves the pertinence and flexibility of air conditioning control, and further improves the efficiency of air conditioning control and the user's riding experience.

[0088] In one optional embodiment, the vehicle air conditioning control method in this disclosure further includes the following steps.

[0089] In response to the target user's touch operation on the air conditioner settings control, the prior mode information corresponding to the target user is obtained, wherein the prior mode information is set to represent the target user's air conditioner preference mode information.

[0090] A predefined pattern database is constructed based on prior pattern information.

[0091] In the smart cockpit of this disclosure embodiment, the target user can perform manual operations via the air conditioning settings controls on the vehicle's large screen. These manual operations can include adjusting the temperature, fan speed, and mode, thereby reflecting the target user's immediate preference for air conditioning comfort. The infotainment system (ICC) can perform deep learning and pattern recognition on the target user's touch operations to construct an information set reflecting the target user's historical air conditioning usage preferences and habits. This information set includes, but is not limited to, the target user's preferred air conditioning temperature, fan speed level, airflow direction selection, and air conditioning setting habits under specific environmental conditions.

[0092] The aforementioned preset mode database is configured to store prior mode information for all target users (including repeat users and new users), so that when a target user uses the vehicle again, the corresponding air conditioning preference mode can be quickly invoked to achieve personalized and intelligent air conditioning control.

[0093] Upon detecting a target user's touch operation of the air conditioning settings controls via the vehicle's infotainment screen, the data acquisition and processing flow is immediately initiated. After the target user completes the touch operation, the infotainment unit's ICC analyzes the operation details, combines them with the target user's historical data, extracts and updates prior mode information, ensuring that the database content remains consistent with the target user's latest preferences. The extracted and updated prior mode information is stored or updated to a preset mode database, forming a collection containing all target users' personalized air conditioning preference modes, providing a data foundation for future intelligent air conditioning control.

[0094] Based on the above optional embodiments, by responding to the target user's touch operation on the air conditioning setting control, the prior mode information corresponding to the target user is obtained, and then a preset mode database is constructed based on the prior mode information. This significantly improves the personalized service level and operating efficiency of the air conditioning intelligent control system. When the target user uses the vehicle again, this information can be quickly called up and the air conditioning parameters can be automatically adjusted to meet the target user's personalized needs without the target user having to make repeated settings, thereby greatly improving the convenience and comfort of riding in the vehicle.

[0095] In one optional embodiment, the target control parameters include at least one of the following: function mode information, temperature information, air volume information, and air outlet angle information.

[0096] The functional mode information covers various operating modes offered by the air conditioning system, including but not limited to cooling mode, heating mode, internal / external circulation switching mode, and air purification mode. This is one of the core components of intelligent air conditioning control. Temperature information refers to the target temperature value that the air conditioning system should be set to. It can intelligently adjust based on the temperature difference between the inside and outside of the vehicle and the passengers' personal preferences to achieve the ideal comfortable temperature. Airflow information relates to the speed and intensity of the airflow emitted from the air conditioning system's vents, which can be dynamically adjusted according to passenger location, number of passengers, and the current ventilation needs of the environment. Airflow angle information refers to the direction and distribution of the airflow from the air conditioning system. Airflow angle information includes modes such as automatic sweeping, direct airflow to people, and free-flow, aiming to ensure that the airflow can evenly cover or precisely direct the airflow to the passenger area.

[0097] In this embodiment, the target control parameters, including but not limited to function mode information, temperature information, air volume information, and air outlet angle information, are automatically generated by the entertainment host ICC. This enables intelligent and personalized adjustment of the air conditioning system, which can automatically optimize the air conditioning function according to the passenger's immediate needs and personalized preferences, providing a more comfortable and energy-saving riding environment without the need for frequent manual adjustments by the passenger, greatly improving the quality and convenience of the riding experience.

[0098] Figure 3 is a schematic diagram of the architecture of an intelligent air conditioning control system according to an embodiment of this disclosure. As shown in Figure 3, the surround-view camera and the DMS camera are connected to the infotainment unit (ICC) via the Low Voltage Differential Signaling (LVDS) protocol, and are configured to collect images of people inside and outside the vehicle, including human appearance, facial features, and key body information. The ICC communicates with the Zone Control Unit (ZCU) via Controller Area Network Flexible Data Rate (CANFD). The ZCU is responsible for the vehicle unlocking function and provides power mode information for the entire vehicle. The digital key module's Biometric Near Field Control Module (BNCM) is also connected to the ZCU via CANFD, and is configured to control the welcome unlocking and locking function, while simultaneously sending key location information to the infotainment unit. The Temperature Management System (TMS) interacts with the ZCU via CANFD, receiving air conditioning function parameter adjustment commands from the infotainment unit. The electric air vent module can be connected to the TMS via a Local Interconnect Network (LIN), adjusting the airflow direction and volume according to the commands from the TMS.

[0099] Figure 4 is a schematic diagram of a vehicle air conditioning control method according to an embodiment of the present disclosure. As shown in Figure 4, when a target user approaches the vehicle with a digital key (BNCM), the vehicle's welcome function is triggered, activating the surround-view camera for personnel feature recognition. When the user further opens the car door and enters the vehicle, the DMS camera is activated to perform efficient facial recognition, thereby confirming the user's identity and quickly retrieving the associated personalized air conditioning parameter information. Next, the infotainment system (ICC), acting as the processing center, comprehensively analyzes the user feature data from the DMS camera and real-time environmental data collected by external sensors (including but not limited to weather sensors and temperature difference sensors). Using deep learning algorithms, it generates a set of precise air conditioning adjustment instructions to match the current passenger status and environmental conditions. Subsequently, the air conditioning control module (TMS) receives the instructions from the ICC and immediately executes them, adjusting the operating mode of the air conditioning system. The adjustment of the operating mode specifically includes adjusting parameters such as temperature, airflow, and airflow direction to quickly create a suitable in-vehicle environment. Even after automatic adjustment, users can still manually adjust the air conditioning at any time. At this time, the infotainment system (ICC) will further learn the user's personalized preferences and update and optimize the big data model in real time to ensure that it can provide more appropriate and personalized air conditioning services in the future, so that users can enjoy an ideal and comfortable in-car climate every time they ride.

[0100] Figure 5 is a schematic diagram of another vehicle air conditioning control method according to an embodiment of the present disclosure. As shown in Figure 5, the vehicle's welcome function is immediately activated the moment the target user approaches the vehicle with the digital key BNCM. The area controller ZCU sensitively captures the signal of the digital key BNCM, thereby activating the surround-view camera to begin collecting image data and perform preliminary identification of the person's height, type, and other characteristics. As the target user further opens the car door, the more refined DMS camera is activated, focusing on monitoring the facial features and current state of the driver or passenger, such as signs of fatigue or changes in body temperature, such as sweating. Next, the entertainment host ICC first attempts to identify whether the target user is a known authenticated user based on the information collected by the DMS camera. For authenticated users, the ICC will quickly match their personal account and retrieve the personalized air conditioning parameters bound to the user ID from the preset mode database, including preferred temperature, fan speed level, and airflow mode. For new users encountered for the first time, a series of feature recognition and ID creation processes will be carried out to establish their exclusive air conditioning adjustment record.

[0101] Whether for new or existing users, the infotainment system (ICC) employs deep learning algorithms, comprehensively considering human characteristic data and real-time environmental conditions to intelligently generate or optimize air conditioning settings. This demonstrates the adaptive control capability of the air conditioning system, ensuring it can fine-tune according to each passenger's specific needs, thus providing the most suitable in-car environment. Even after the system has automatically adjusted the air conditioning parameters, users can still manually adjust them based on personal preference, such as if the airflow is too strong or the temperature setting is uncomfortable. The ICC records every manual operation by the user, integrating it into prior mode information, continuously updating and improving the user model in the preset mode database, laying a solid foundation for the subsequent riding experience, and ensuring that the air conditioning control system can provide increasingly personalized services that closely match user expectations in future use.

[0102] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data set for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0103] According to the embodiments of this disclosure, an apparatus embodiment for a vehicle air conditioning control method is provided. It should be noted that the apparatus can be configured to execute the above-described vehicle air conditioning control method.

[0104] Figure 6 is a structural block diagram of a vehicle air conditioning control device according to an embodiment of the present disclosure. As shown in Figure 6, the device includes the following modules.

[0105] The acquisition module 601 is configured to acquire user characteristic data and environmental condition data associated with the target vehicle. The user characteristic data represents passenger attribute information corresponding to the target vehicle, and the environmental condition data represents external and internal environmental information of the target vehicle. The analysis module 602 is configured to perform decision analysis based on the user characteristic data and environmental condition data to obtain decision analysis results. These results determine the operating mode of the target vehicle's air conditioning system. The determination module 603 is configured to determine target control parameters for the air conditioning system based on the decision analysis results. These target control parameters adjust the operating state of the air conditioning system. The control module 604 is configured to control the air conditioning system using these target control parameters.

[0106] Optionally, the acquisition module 601 is further configured to perform the following steps: In response to receiving key positioning information, acquire first image data, wherein the first image data is configured to represent external user image data associated with the target vehicle. In response to receiving door opening information, acquire second image data, wherein the second image data is configured to represent internal user image data of the target vehicle. Perform feature extraction on the first image data and the second image data to obtain user feature data.

[0107] Optionally, the acquisition module 601 is further configured to perform the following steps: Extracting features from the first image data to obtain human body envelope data, wherein the human body envelope data is configured to represent the visual feature information of the target user. Extracting features from the second image data to obtain facial feature data of the target user. Determining user feature data based on the human body envelope data and the facial feature data.

[0108] Optionally, the analysis module 602 is further configured to perform the following steps: Verify the user feature data and environmental condition data using a preset pattern database to obtain a verification result, wherein the verification result is configured to determine whether prior pattern information corresponding to the user feature data and environmental condition data exists in the preset pattern database. Perform decision analysis based on the verification result to obtain a decision analysis result.

[0109] Optionally, the analysis module 602 is further configured to perform the following steps: The response determines, based on the verification processing results, that prior pattern information exists in the preset pattern database, and determines the decision analysis result based on the prior pattern information. The response determines, based on the verification processing results, that prior pattern information does not exist in the preset pattern database, and creates a pattern based on user characteristic data and environmental condition data to obtain the decision analysis result.

[0110] Optionally, the analysis module 602 is further configured to perform the following steps: Analyze and process user feature data and environmental condition data using a target state prediction network model to obtain a target state prediction result, wherein the target state prediction result represents passenger state information of the target vehicle. Create a pattern based on the target state prediction result and a preset mapping relationship to obtain a decision analysis result, wherein the preset mapping relationship records the mapping relationship between preset passenger states and preset air conditioning modes.

[0111] Optionally, the acquisition module 601 is further configured to perform the following steps: In response to a target user's touch operation on the air conditioning settings control, acquire prior mode information corresponding to the target user, wherein the prior mode information is set to represent the target user's air conditioning preference mode information. The vehicle air conditioning control device also includes the following module: A construction module 605, configured to construct a preset mode database based on the prior mode information.

[0112] Optionally, the target control parameters include at least one of the following: function mode information, temperature information, air volume information, and air outlet angle information.

[0113] Embodiments of this disclosure also provide a vehicle, including: a memory storing an executable program; and a processor configured to run the program, wherein the program executes the methods of various embodiments of this disclosure when it runs.

[0114] Embodiments of this disclosure also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium resides to perform the methods of the various embodiments of this disclosure.

[0115] Embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the methods of various embodiments of this disclosure.

[0116] Embodiments of this disclosure also provide a computer program product including a non-volatile computer-readable storage medium configured to store a computer program that, when executed by a processor, implements the methods described in various embodiments of this disclosure.

[0117] Embodiments of this disclosure also provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of this disclosure.

[0118] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0119] In the several embodiments provided in this disclosure, it should be understood that the disclosed technical content can be implemented in other ways. The apparatus embodiments described above are illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0122] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0123] The above description represents the preferred embodiments of this disclosure. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure. Industrial applicability

[0124] This disclosure acquires user characteristic data and environmental condition data associated with the target vehicle, then performs decision analysis based on this data to obtain the decision analysis results. Subsequently, target control parameters for the vehicle's air conditioning are determined based on these results, and finally, the vehicle's air conditioning is controlled using these target control parameters. This achieves the goal of personalized and health-oriented air conditioning control through intelligent analysis, thereby improving passenger comfort and health protection. By utilizing deep learning and big data analytics, comprehensive perception and intelligent decision-making regarding user characteristics and environmental conditions are achieved. This allows for rapid adjustment of air conditioning modes and parameters, ensuring that air conditioning control better meets passenger needs and improves the overall passenger experience. This solves the technical problems of low control efficiency and poor user experience in related technologies for vehicle air conditioning.

Claims

1. A vehicle air conditioning control method, characterized in that, include: Acquire user feature data and environmental condition data associated with the target vehicle, wherein the user feature data is set to represent passenger attribute information corresponding to the target vehicle, and the environmental condition data is set to represent external environmental information and internal environmental information of the target vehicle; Decision analysis is performed based on the user characteristic data and the environmental condition data to obtain decision analysis results, wherein the decision analysis results are set to determine the working mode of the target vehicle's air conditioning. Based on the decision analysis results, the target control parameters of the vehicle air conditioner are determined, wherein the target control parameters are set to adjust the operating state of the vehicle air conditioner; The vehicle air conditioner is controlled using the target control parameters.

2. The method according to claim 1, characterized in that, The user characteristic data consists of the target passenger's physical characteristics and biometric data, which are collected by a surround-view camera and an infrared temperature sensor. The target passenger is the passenger corresponding to the target vehicle.

3. The method according to claim 1, characterized in that, The external environmental information includes external temperature, external humidity, external light intensity, and external air quality. The internal environmental information includes internal temperature distribution, internal humidity, and internal air quality. The environmental condition data is collected by multiple internal sensors, including internal and external temperature sensors, humidity sensors, light sensors, and air quality sensors.

4. The method according to claim 1, characterized in that, Obtaining the user feature data associated with the target vehicle includes: In response to receiving key location information, first image data is acquired, wherein the first image data is configured to represent external user image data associated with the target vehicle; In response to receiving door opening information, second image data is acquired, wherein the second image data is set to represent in-vehicle user image data of the target vehicle; Feature extraction is performed on the first image data and the second image data to obtain the user feature data.

5. The method according to claim 4, characterized in that, Feature extraction is performed on the first image data and the second image data to obtain the user feature data, which includes: Feature extraction is performed on the first image data to obtain human body envelope data, wherein the human body envelope data is set to represent the visual feature information of the target user; Feature extraction is performed on the second image data to obtain the facial feature data of the target user; The user feature data is determined based on the human body envelope data and the facial feature data.

6. The method according to claim 5, characterized in that, The human body envelope data is used to determine the basic type of the target user, which includes children, pregnant women, and the elderly.

7. The method according to claim 5, characterized in that, The facial feature data is used to determine the emotional state and physiological needs of the target user.

8. The method according to claim 1, characterized in that, The decision analysis results obtained based on the user characteristic data and the environmental condition data include: The user feature data and the environmental condition data are verified using a preset pattern database to obtain a verification result, wherein the verification result is set to determine whether there is prior pattern information corresponding to the user feature data and the environmental condition data in the preset pattern database. Decision analysis is performed based on the verification results to obtain the decision analysis results.

9. The method according to claim 8, characterized in that, Based on the verification process results, a decision analysis is performed, and the decision analysis results include: The response determines, based on the verification process result, that the prior pattern information exists in the preset pattern database, and determines the decision analysis result based on the prior pattern information. The response determines, based on the verification process result, that the prior pattern information does not exist in the preset pattern database, and performs pattern creation based on the user feature data and the environmental condition data to obtain the decision analysis result.

10. The method according to claim 9, characterized in that, Pattern creation based on the user characteristic data and the environmental condition data yields the following decision analysis results: The user feature data and the environmental condition data are analyzed and processed using a target state prediction network model to obtain a target state prediction result, wherein the target state prediction result is set to represent the passenger state information of the target vehicle. Based on the target state prediction results and the preset mapping relationship, a pattern is created to obtain the decision analysis results, wherein the preset mapping relationship is set to record the mapping relationship between the preset passenger state and the preset air conditioning mode.

11. The method according to claim 10, characterized in that, Based on the target state prediction results and the preset mapping relationship, pattern creation is performed to obtain the decision analysis results, including: A target air conditioning mode is created based on the target state prediction results and the preset mapping relationship; The target air conditioning parameter adjustment instructions are determined based on the target air conditioning mode, wherein the target air conditioning parameter adjustment instructions include temperature setting, fan speed control and air purification; The decision analysis result is determined based on the target air conditioning parameter adjustment command.

12. The method according to claim 8, characterized in that, The method further includes: In response to a target user's touch operation on the air conditioner settings controls, prior mode information corresponding to the target user is obtained, wherein the prior mode information is set to represent the target user's air conditioner preference mode information; The preset pattern database is constructed based on the prior pattern information.

13. The method according to claim 1, characterized in that, The target control parameters include at least one of the following: functional mode information, temperature information, air volume information, and air outlet angle information.

14. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor configured to run the program, wherein the program, when running, performs the method according to any one of claims 1 to 13.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 13.