Intelligent situation awareness vehicle-mounted atmosphere lamp control method and system and electronic equipment

Abstract

The invention discloses an intelligent situation awareness vehicle-mounted atmosphere lamp control method and system and electronic equipment. The method comprises the following steps: step 1, scene state modeling of multi-source data fusion; step 2, coupling control of the dynamic spectrum and environmental parameters; step 3, generating an emotion-driven light sequence; step 4, dynamically adjusting the noise-coordinated lamplight; step 5, storing and calling personalized parameters; and step 6, optimizing a control strategy of feedback driving. Through multi-source data fusion modeling and comprehensive analysis of the driving scene, the user state and the environmental parameters, the state recognition accuracy is improved, misjudgment is avoided, dynamic spectrum and environmental parameter coupling, emotion driving and noise collaborative light adjustment are achieved, diversified requirements are met, a personalized atmosphere is created, fatigue is relieved, and safety is improved. User parameters can be stored and called, personalized services are enhanced, and more comfortable and convenient driving experience is brought.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent vehicle-mounted environment control systems, in particular to an intelligent context-aware vehicle-mounted atmosphere lamp control method, system and electronic device. BACKGROUND

[0002] With the booming development of intelligent automobile technology, the comfort and safety of vehicle occupants have become the focus of the industry. As an important component to enhance the driving experience, the technology evolution of vehicle-mounted atmosphere lamps has attracted much attention. Traditional vehicle-mounted atmosphere lamp systems mostly use static preset mode, which can only adjust the brightness through fixed light color or simple external ambient light sensing. This static or simple reactive design has significant defects.

[0003] Firstly, the existing system lacks comprehensive analysis capability for driving scenarios, user states and environmental parameters. For example, in complex driving scenarios (such as high-speed driving, rainy road conditions or congested road sections), it is difficult to real-time perceive the driver's fatigue state, emotional changes or dynamic changes of in-vehicle environmental parameters (such as temperature, noise), resulting in a serious disconnection between the atmosphere lamp effect and actual needs, making it difficult to create an in-vehicle environment that meets the current situation, affecting the driving experience.

[0004] Secondly, the existing technology does not use effective multi-source data fusion technology to identify driving scenarios. Single data source (such as relying only on light sensors) is prone to state misjudgment, which cannot accurately determine the driving state of the vehicle (such as whether it is in autonomous driving mode, whether it has sudden braking, etc.), thus affecting the precise control of the atmosphere lamp.

[0005] In addition, the traditional system does not fully consider the coupling relationship between dynamic spectral control and environmental parameters. It is difficult to dynamically adjust the color temperature, illuminance and color of the light according to real-time environmental parameters such as vehicle speed, road vibration frequency, rainfall, etc., making it difficult to achieve personalized and environment-adaptive light effects, and unable to meet the diverse needs of different users in different scenarios.

[0006] In summary, the existing vehicle-mounted atmosphere lamp system has deficiencies in adaptability, accuracy of state recognition and intelligence level of light adjustment in complex scenarios. Therefore, an intelligent context-aware vehicle-mounted atmosphere lamp control method, system and electronic device are proposed. SUMMARY

[0007] In view of the deficiencies of the prior art, the present application provides an intelligent context-aware vehicle-mounted atmosphere lamp control method, system and electronic device to solve the problems raised in the background art.

[0008] To achieve the above purpose, the present application provides the following technical solution: an intelligent context-aware vehicle-mounted atmosphere lamp control method, comprising the following steps: Step one, scene state modeling of multi-source data fusion: Through the GPS trajectory analysis module, timestamp marking module and vehicle OBD data acquisition module, the vehicle state data of driving route, time sequence, vehicle speed and acceleration are obtained, and input into the Bayesian network algorithm model for driving scene probability modeling; At the same time, the light intensity is collected in real time by using the light sensor, and the scene state output by the model is calibrated and corrected, and a scene recognition mechanism integrating multi-dimensional data is established; Step two, coupling control of dynamic spectrum and environmental parameters: A three-channel RGB LED array modulated by PWM is used as a light source, and the data of speed sensor, road vibration sensor and rainfall sensor are received by the spectrum-environment parameter coupling controller. When the vehicle speed is higher than 80km / h, the high color temperature (≥5000K) cold light mode is triggered to improve attention; When the road vibration frequency is greater than 20Hz and the rainfall is greater than 1mm / min, the illuminance is automatically reduced to 150-200lux and switched to amber warning light. Through dynamic solution of color temperature (2000K-6500K) and illuminance (50lux-500lux), the Pareto optimal solution is realized to realize multi-dimensional environmental adaptation; Step three, emotion-driven light sequence generation: Based on the emotion calculation module, the stress indicators of driving time and sudden braking times are quantified. When continuous driving is greater than 2 hours or sudden braking is greater than or equal to 3 times, the stress value is mapped to the saturation parameter (≥70%) of the HSV color space, and a dynamic light sequence from warning red (HSV: 0°, 100%, 80%) to soothing purple (HSV: 270°, 60%, 50%) is generated through an asymmetric gradient algorithm. The transition time is 15 seconds by default, and the user can adjust the transition rate to 5-30 seconds through the capacitive touch screen (supporting gesture operation); Step four, noise-coordinated light dynamic adjustment: The in-vehicle noise (frequency range 20Hz-20kHz) is detected by a microphone array. When the music volume is greater than 60dB, the light brightness is increased to 300lux and the color contrast is enhanced; When the external traffic noise is greater than 75dB, the low saturation (≤40%) warm light mode is automatically switched to realize the coordinated adaptation of sound-light environment; Step five, storage and calling of personalized parameters: The non-volatile memory is set to store user-defined parameters (supporting ≥20 groups of presets). When it is detected that the current scene matches the user's preset keywords (such as "high-speed cruise" and "rainy mode") by more than 80%, the corresponding light parameters (including color temperature, illuminance and color transition curve) are automatically called to realize rapid scene switching; Step six, feedback-driven control strategy optimization: The facial expression features of the driver and passenger are collected by the in-vehicle camera, the light satisfaction is evaluated in combination with the body motion sensor data, the frequency of frowning is detected for 5 minutes, the weight parameters of the Bayesian network model are automatically adjusted, the solving rules of the light spectrum controller are corrected, and the closed-loop control link of "data collection-scene recognition-light adjustment-feedback optimization" is formed; In step one, the construction of the Bayesian network algorithm model, the collection range of historical driving data (such as urban roads, highways, etc.) needs to be further clarified, and the preprocessing steps (such as data cleaning, normalization, etc.) are detailed, at the same time, the key feature parameters (such as average speed, acceleration change rate, etc.) are extracted as network nodes, the conditional probability distribution between nodes is determined through machine learning algorithm (such as gradient descent method), and the initial model is formed. In practical application, the model parameters are adjusted online according to real-time data to improve the recognition accuracy. The intelligent context-aware vehicle ambient light control method realizes accurate identification of driving environment through multi-source data fusion scene state modeling, provides reliable basis for subsequent light adjustment, and the dynamic spectrum and environmental parameter coupling control mechanism can automatically adjust the light color temperature and illumination according to the vehicle speed, road vibration and rainfall and other environmental factors, which not only improves the driving safety, but also enhances the driving experience. The emotion-driven light sequence generation generates dynamic light effects with psychological soothing effect by quantifying driving stress indicators, effectively alleviating driving fatigue, and the noise-coordinated light dynamic adjustment function further optimizes the sound and light environment in the vehicle, improves the comfort, and the storage and calling of personalized parameters meet the personalized needs of different users, and realizes fast scene switching.

[0009] Preferably, in the step one, the construction process of the Bayesian network algorithm model includes collecting and preprocessing historical driving data, extracting key feature parameters as network nodes, and determining the conditional probability distribution between nodes through machine learning algorithm to form an initial Bayesian network model. In practical application, the model is updated and optimized online according to the real-time multi-source data collected to improve the accuracy of driving scene state recognition. In step one, the construction of the Bayesian network algorithm model, the collected historical driving data can further include GPS trajectory, timestamp, speed, acceleration, etc., data cleaning and normalization are performed during preprocessing, the extracted key feature parameters are used as network nodes, such as different time periods and different speed ranges, and machine learning algorithms such as EM algorithm are used to train and determine the conditional probability distribution between nodes to form an initial model. When online updating, the model parameters are adjusted and optimized by using incremental learning algorithm according to real-time multi-source data; The construction method of the Bayesian network algorithm model has many advantages. First, through the collection and detailed preprocessing of rich historical driving data, the data basis for model construction is solid and reliable, which provides guarantee for subsequent accurate identification of driving scene state. Second, the key feature parameters are extracted as network nodes, and the conditional probability distribution is determined by using machine learning algorithm, so that the model can accurately reflect the relationship between various factors in the driving scene. In practical application, the model is updated and optimized online through real-time data, which can continuously improve the accuracy of driving scene state recognition, and make the control of vehicle ambient light more suitable for the actual driving scene, providing a more comfortable and safe driving environment for the driver and passengers.

[0010] Preferably, in the step two, the color temperature adjustment range of the PWM modulated three-channel RGB LED array is 2000K-6500K, and the illumination adjustment range is 50lux-500lux; the sampling frequency of the vehicle speed sensor is not less than 10Hz, the sampling frequency of the road vibration sensor is not less than 50Hz, and the detection accuracy of the rainfall sensor is 0.1mm / min; By adjusting the PWM duty cycle of each channel (red, green, and blue), mixing different proportions of three primary colors, the color temperature is smoothly transitioned between 2000K and 6500K. At the same time, by adjusting the duty cycle or current intensity of the overall PWM signal, the total luminous intensity of the LED array is controlled, thereby realizing the adjustment of the illumination in the range of 50lux to 500lux. Sensor data is processed by the microcontroller to dynamically adjust the PWM signal to ensure real-time response to environmental changes. The detailed parameter settings of the color temperature and illumination adjustment of the PWM modulated three-channel RGB LED array, and the vehicle speed, road vibration, and rainfall sensors in step two bring significant advantages to the intelligent context-aware vehicle ambient light system. First, the wide range of color temperature and illumination adjustment enables the ambient light to adapt to different driving scenarios and user preferences, creating a variety of warm, focused, or warning atmospheres. Second, the high sampling frequency of the vehicle speed sensor ensures real-time capture of the vehicle's driving state, providing accurate basis for dynamic light adjustment. The high-frequency sampling of the road vibration sensor helps to detect road condition changes such as bumps and potholes in advance, so that the light can be adjusted in time to remind the driver. Finally, the high-precision rainfall sensor can accurately detect the intensity of rainfall and trigger the corresponding light mode, improving the safety of driving in the rain.

[0011] Preferably, in the step three, the saturation parameter of the HSV color space is in the range of 0-100%, and the transition time of the asymmetric gradient algorithm is dynamically adjusted between 5 seconds and 30 seconds according to user settings; the touch screen uses capacitive touch technology and supports multi-point touch and gesture operation. The specific implementation of the asymmetric gradual change algorithm is as follows: first, the starting color (such as warning red) and the target color (such as soothing purple) are determined according to the HSV saturation parameter of the pressure indicator mapping, then the intermediate color value at each time point is calculated through a nonlinear interpolation algorithm according to the user-set transition time, and the asymmetric gradual change transition from the starting color to the target color is realized, in this process, the capacitive touch screen receives the user gesture operation in real time and dynamically adjusts the transition rate to ensure the smoothness and personalization of the user experience; The combination of the HSV color space saturation parameter setting (0-100%) in step three and the asymmetric gradual change algorithm brings significant benefits to the vehicle-mounted atmosphere lamp, by precisely controlling the color saturation, the system can flexibly adjust the light color according to the driver's stress state, from high-saturation warning color to low-saturation soothing color, effectively relieving driving fatigue and improving driving safety, the application of the asymmetric gradual change algorithm makes the light transition more natural and smooth, avoiding the interference caused by abrupt color changes to the driver, at the same time, the capacitive touch screen supports multi-point touch and gesture operation, further enhancing the convenience and interest of user interaction, the driver can adjust the light transition effect at any time according to personal preference and enjoy personalized driving atmosphere.

[0012] Preferably, in the step four, the environmental noise detector adopts microphone array technology, the detected noise frequency range is 20Hz-20kHz, and the noise level is divided into not less than 5 levels, each level corresponds to different light brightness and color temperature adjustment strategies; The environmental noise detector is realized by microphone array technology, specifically by arranging multiple microphones at different positions in the vehicle, collecting noise signals, and using digital signal processing technology to analyze the noise in the frequency range of 20Hz-20kHz, according to the energy distribution, frequency characteristics and other parameters of the noise, the noise level is divided into at least 5 levels (such as low, medium low, medium, medium high, high), each level is pre-set to correspond to the light brightness and color temperature adjustment strategy, such as maintaining normal brightness and color temperature in low noise, and reducing brightness to soft range and adjusting color temperature to warm tone in high noise to reduce visual interference; This technology accurately captures the environmental noise in the vehicle through microphone array technology, realizes fine division of noise level, and each level corresponds to different light adjustment strategies, which significantly improves the intelligent level of the vehicle-mounted atmosphere lamp system, it can automatically adjust the light brightness and color temperature according to the actual noise condition, it can create a comfortable atmosphere in a quiet environment, and it can reduce the visual pressure of the driver and improve the driving safety in a noisy environment.

[0013] Preferably, in the step five, the user-defined parameter storage module adopts a non-volatile memory to store not less than 20 groups of user-defined light parameters; The scene matching algorithm adopts fuzzy matching technology, and matches according to the similarity between the key feature parameters of the driving scene and the user-defined scene parameters; The user-defined parameter storage module uses EEPROM (Electrically Erasable Programmable Read-Only Memory) as a non-volatile memory, and is connected with the system main control chip through a serial communication interface to realize parameter writing and reading. The scene matching algorithm adopts fuzzy matching technology based on feature vectors. The key feature parameters of the driving scene (such as vehicle speed, light intensity, road conditions, etc.) are quantitatively processed with the user-defined scene parameters, and the similarity score between the two is calculated. When the score exceeds the preset threshold, it is determined as a successful match. The user-defined parameters are stored in the non-volatile memory, and the scene matching is realized by combining the fuzzy matching technology. This design brings significant benefits. The non-volatile memory ensures that the user-set light parameters will not be lost after power failure, providing stable and reliable personalized experience. Users can preset multiple light modes such as "high-speed cruising" and "night driving" according to their preferences and driving habits. When the system identifies a matching preset scene, it automatically calls the corresponding light parameters to achieve fast and accurate scene switching. The application of fuzzy matching technology makes scene matching more flexible and intelligent. Even if there are slight changes in the driving environment, the system can accurately identify and apply the most suitable light parameters to improve driving safety and comfort.

[0014] An intelligent context-aware vehicle ambient light control system, comprising: A multi-source data fusion state recognition module for collecting GPS trajectory, timestamp, vehicle OBD data and environmental light data, and performing driving scene state recognition through a Bayesian network algorithm. The output end of the multi-source data fusion state recognition module is electrically connected to the input end of the spectral-environment parameter coupling controller. A spectral-environment parameter coupling controller for receiving output data from the state recognition module and environmental parameters such as vehicle speed, road vibration and rainfall, controlling the color temperature and illuminance of the PWM modulated three-channel RGB LED array, and electrically connecting the output end of the spectral-environment parameter coupling controller to the control end of the RGB LED array. A light sequence generator based on emotional computing for generating light sequences according to pressure indicators such as driving duration and number of sudden braking, and receiving transition rate parameters input by the user through the touch screen. The output end of the light sequence generator based on emotional computing is electrically connected to the control end of the RGB LED array. An environmental noise detection module using microphone array technology to monitor the environmental noise in the vehicle in real time. The output end of the environmental noise detection module is electrically connected to the input end of the spectral-environment parameter coupling controller. A user interaction module, including a touch screen and a parameter storage unit, is used for user input of personalized parameters and storage calling, and an output end of the user interaction module is electrically connected with an input end of the light sequence generator based on emotional computing; A feedback optimization module, including a camera and a sensor, is used for collection of feedback information of the driver and passenger, and an output end of the feedback optimization module is electrically connected with a parameter adjustment end of the multi-source data fusion state recognition module, the spectrum-environment parameter coupling controller and the light sequence generator; A Bayesian network model is established through historical driving data, key feature parameters are determined as network nodes, and a machine learning algorithm is used for training and determination of conditional probability distribution between nodes. In actual application, the model is updated and optimized online by using real-time collected multi-source data (GPS trajectory, time stamp, vehicle OBD data and environmental illumination data), so as to improve the accuracy of driving scene state recognition; The multi-source data fusion state recognition module can comprehensively capture multi-dimensional features of the driving scene by integrating GPS trajectory, time stamp, vehicle OBD data and environmental illumination data, so as to improve the accuracy and reliability of scene recognition. The spectrum-environment parameter coupling controller intelligently adjusts the color temperature and illuminance of the RGB LED array according to the recognition result and real-time environmental parameters, so as to realize harmonious adaptation of light and environment, improve the driving experience, and generate personalized light sequences based on the driving time and the number of emergency braking, so as to effectively relieve driving stress. The environmental noise detection module monitors the noise in the vehicle in real time, and automatically adjusts the light to adapt to different sound environments. The user interaction module provides personalized setting and parameter storage functions to meet the preferences of different users. The feedback optimization module continuously optimizes the control strategy by collecting feedback from the driver and passenger, forms a closed loop control, and ensures continuous improvement of system performance.

[0015] Preferably, the multi-source data fusion state recognition module includes a GPS module, a time stamp module, an OBD data acquisition module and a light sensor module, the output ends of the modules are electrically connected with the input end of the Bayesian network algorithm processing unit, and the output end of the Bayesian network algorithm processing unit is electrically connected with the input end of the spectrum-environment parameter coupling controller; In the multi-source data fusion state recognition module, the GPS module is used to obtain the vehicle driving route, the time stamp module records the time point of data collection, the OBD data acquisition module collects vehicle state data such as vehicle speed and acceleration, and the light sensor module collects environmental illumination intensity in real time. These data are transmitted to the Bayesian network algorithm processing unit, which learns historical data through a pre-trained model, determines the conditional probability relationship between the data, realizes real-time probability modeling of the driving scene, and ensures the accuracy of state recognition; The state recognition module of multi-source data fusion integrates GPS, timestamp, OBD data acquisition and light sensor to build a comprehensive and accurate driving scene perception system. The advantage of this design is that it can integrate information from multiple data sources to improve the accuracy and robustness of driving scene recognition. GPS and timestamp provide the spatiotemporal context of vehicle travel, OBD data reflects the operating status of the vehicle, and light sensor captures changes in environmental lighting. After processing by Bayesian network algorithm, these data can more accurately depict the driving scene, providing a reliable basis for subsequent spectral-environmental parameter coupling control, thereby improving the intelligence and adaptability of the vehicle ambient light and creating a more comfortable and safe driving environment for drivers and passengers.

[0016] Preferably, the spectral-environmental parameter coupling controller includes a vehicle speed acquisition unit, a road surface vibration acquisition unit, a rainfall acquisition unit and a dynamic calculation unit. The output ends of the vehicle speed acquisition unit, the road surface vibration acquisition unit and the rainfall acquisition unit are electrically connected to the input end of the dynamic calculation unit. The output end of the dynamic calculation unit is electrically connected to the control end of the RGB LED array. The vehicle speed acquisition unit acquires vehicle speed data in real time through CAN bus. The road surface vibration acquisition unit uses an acceleration sensor fixed to the chassis to acquire vibration frequency through high-frequency sampling. The rainfall acquisition unit uses an optical rainfall sensor to quantify rainfall by detecting the degree of light obstruction by raindrops. After receiving the above data, the dynamic calculation unit combines the preset threshold (such as vehicle speed 80 km / h, vibration frequency 20 Hz, rainfall 1 mm / min), calculates and outputs the color temperature and illumination control signal of the RGB LED array through internal algorithm, and realizes dynamic adaptation of light and environment. By integrating vehicle speed, road surface vibration and rainfall acquisition units, comprehensive perception of vehicle driving state is achieved. This design enables the vehicle ambient light to automatically adjust color temperature and illumination according to real-time environmental changes, such as providing high-color-temperature cold light to improve attention during high-speed driving, and automatically switching to low-illumination amber warning light in adverse weather conditions, effectively enhancing driving safety. The introduction of the dynamic calculation unit enables the system to respond quickly to complex and variable driving environments, improving driving comfort and safety, and embodying the design concept of intelligence and individualization.

[0017] An electronic device comprising: a processor and a memory having a computer program stored thereon, the computer program, when executed by the processor, implements the steps of the intelligent context-aware vehicle ambient light control method according to any one of claims 1 to 7; The processor is a high-performance microcontroller, which has multi-core processing capability to cope with real-time data processing requirements; the memory is a high-speed flash memory, which ensures fast loading and execution of computer programs, and the programs are designed in a modular manner, integrating core functions such as multi-source data acquisition, scene recognition, light control, user interaction and feedback optimization, and data interaction between modules is realized through an efficient communication protocol to ensure stable operation of the system; The intelligent context-aware vehicle ambient light control method is integrated into the processor and the memory, realizing highly automated in-vehicle environment creation. This method accurately identifies driving scenarios through multi-source data fusion technology and dynamically adjusts light color temperature, illumination and color transition, which not only improves driving safety but also enhances driving comfort. The emotion-driven light sequence generation effectively relieves driving stress and promotes physical and mental health. Meanwhile, the personalized parameter storage and calling function meets the personalized needs of different users, improving user experience. The feedback-driven control strategy optimization mechanism ensures continuous learning and improvement of the system, maintaining the best working state.

[0018] In summary, compared with the prior art, the present application provides an intelligent context-aware vehicle ambient light control method, system and electronic device, which has the following advantages: The present application realizes comprehensive analysis of driving scenarios, user states and environmental parameters through multi-source data fusion scene state modeling. It uses GPS trajectory analysis, timestamp marking, vehicle OBD data acquisition and real-time environmental light intensity acquisition to combine with Bayesian network algorithm for driving scenario probability modeling, effectively improving the accuracy of state recognition. This innovative design overcomes the state misjudgment problem caused by single data source in traditional systems, and can more accurately determine the driving state of the vehicle, such as whether it is in high-speed driving, complex scenarios such as rainy road conditions, etc., thereby providing a reliable basis for precise control of ambient light and significantly improving the driving experience. Through dynamic spectrum and environmental parameter coupling control, emotion-driven light sequence generation and noise-coordinated light dynamic adjustment, the color temperature, illumination and color of the light are dynamically adjusted according to real-time environmental parameters such as vehicle speed, road vibration and rainfall. Based on driving duration and the number of sudden braking quantitative stress indicators, a dynamic light sequence from warning red to soothing purple is generated, and the light brightness and color contrast are adjusted according to the noise in the vehicle. This intelligent light adjustment method not only meets the diverse needs of different users in different scenarios, realizes personalized and environment-adaptive light effects, but also effectively relieves the fatigue state of the driver, improves driving safety. In addition, user-defined parameters are stored in non-volatile memory and automatically called when the current scenario matches the user's preset keywords, further enhancing the system's personalized service capabilities and providing users with a more comfortable and convenient driving experience. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is the step diagram of the intelligent context-aware vehicle ambient light control method of the application.

[0020] Figure 2 is the system schematic diagram of the intelligent context-aware vehicle ambient light control of the application. DETAILED DESCRIPTION

[0021] The application provides a technical solution, an intelligent context-aware vehicle ambient light control method, please refer to Figure 1 , comprising the following steps: Step one, scene state modeling of multi-source data fusion: Through the GPS trajectory analysis module, the time stamp marking module and the vehicle OBD data acquisition module, the vehicle state data of driving route, time sequence, vehicle speed and acceleration are obtained, and the driving scene probability modeling is performed by inputting the Bayesian network algorithm model; At the same time, the light intensity is collected in real time by using the light sensor, and the scene state output by the model is calibrated and corrected, and the scene recognition mechanism of fusing multi-dimensional data is established; Step two, coupling control of dynamic spectrum and environmental parameters: A three-channel RGB LED array modulated by PWM is used as a light source, and the data of the vehicle speed sensor, the road vibration sensor and the rainfall sensor are received by the spectrum-environment parameter coupling controller, when the vehicle speed is higher than 80km / h, the high color temperature (≥5000K) cold light mode is triggered to improve the attention; when the road vibration frequency is >20Hz and the rainfall is >1mm / min, the illuminance is automatically reduced to 150-200lux and switched to amber warning light, and through the dynamic solution of color temperature (2000K-6500K) and illuminance (50lux-500lux), the Pareto optimal solution is realized to realize multi-dimensional environmental adaptation; Step three, emotion-driven light sequence generation: Based on the emotion computing module, the stress indicators of driving time and sudden braking times are quantified, when the continuous driving is >2 hours or the sudden braking is ≥3 times, the stress value is mapped to the saturation parameter (≥70%) of the HSV color space, through the asymmetric gradual change algorithm, the dynamic light sequence from the warning red (HSV:0°,100%,80%) to the soothing purple (HSV:270°,60%,50%) is generated, the transition time is default 15 seconds, and the user adjusts the transition rate to 5-30 seconds through the capacitive touch screen (supporting gesture operation); Step four, noise coordination of light dynamic adjustment: The in-vehicle noise is detected by a microphone array (frequency range 20Hz-20kHz), when the music volume >60dB, the light intensity is increased to 300lux and the color contrast is enhanced; when the external traffic noise >75dB, it automatically switches to a low saturation (≤40%) warm light mode, realizing the coordinated adaptation of sound-light environment; Step five, storage and calling of personalized parameters: The non-volatile memory stores user-defined parameters (supporting ≥20 groups of presets), when the current scene is detected to match the user's preset keywords (such as "high-speed cruise" "rainy mode") by >80%, the corresponding light parameters (including color temperature, illuminance, color transition curve) are automatically called, realizing fast scene switching; Step six, feedback-driven control strategy optimization: Through the in-vehicle camera to collect the facial expression features of the driver and passengers, combined with body motion sensor data to evaluate the light satisfaction, continuously detect the frequency of frowning >3 times / minute for 5 minutes, automatically adjust the weight parameters of the Bayesian network model, and correct the solving rules of the spectral controller, forming a closed-loop control link of "data collection-scene recognition-light adjustment-feedback optimization"; In step one, the construction of the Bayesian network algorithm model, the collection range of historical driving data (such as urban road, highway scenes) needs to be further clarified, and the preprocessing steps (such as data cleaning, normalization, etc.) are detailed, at the same time, the key feature parameters (such as average speed, acceleration change rate, etc.) are extracted as network nodes, the conditional probability distribution between nodes is determined through machine learning algorithm (such as gradient descent method), forming the initial model, in practical application, the model parameters are adjusted online according to real-time data, to improve the recognition accuracy; The intelligent context-aware vehicle ambient light control method realizes the accurate identification of driving environment through multi-source data fusion scene state modeling, provides a reliable basis for subsequent light adjustment, the dynamic spectrum and environmental parameter coupling control mechanism can automatically adjust the light color temperature and illuminance according to the speed, road vibration and rainfall and other environmental factors, which not only improves the driving safety, but also enhances the driving experience, the emotion-driven light sequence generation generates dynamic light effects with psychological soothing effect by quantifying driving stress indicators, effectively alleviating driving fatigue, the noise-coordinated light dynamic adjustment function further optimizes the in-vehicle sound-light environment, improves the comfort, the storage and calling of personalized parameters meet the individual needs of different users, realizing fast scene switching.

[0022] Please refer to Figure 1In the step one, the construction process of the Bayesian network algorithm model includes collecting and preprocessing historical driving data, extracting key feature parameters as network nodes, determining the conditional probability distribution between nodes through machine learning algorithm training, and forming an initial Bayesian network model; in the actual application process, the model is updated and optimized online according to the real-time collected multi-source data, so as to improve the accuracy of driving scene state recognition; In the step one, the construction of the Bayesian network algorithm model can further collect historical driving data including GPS trajectory, time stamp, vehicle speed, acceleration, etc., and preprocess the data by cleaning and normalizing, and extract key feature parameters as network nodes, such as different time periods and different vehicle speed ranges, and use machine learning algorithms such as EM algorithm to train and determine the conditional probability distribution between nodes to form an initial model, and when updating online, the model parameters are adjusted and optimized by using incremental learning algorithm according to real-time multi-source data; The construction method of the Bayesian network algorithm model has many advantages. First, through the collection and detailed preprocessing of rich historical driving data, the data basis for model construction is solid and reliable, which provides guarantee for subsequent accurate recognition of driving scene state. Secondly, the key feature parameters are extracted as network nodes, and the machine learning algorithm is used to determine the conditional probability distribution, so that the model can accurately reflect the relationship between various factors in the driving scene. In actual application, the model is updated and optimized online through real-time data, which can continuously improve the accuracy of driving scene state recognition, and the control of the vehicle ambient light is more in line with the actual driving scene, providing a more comfortable and safe driving environment for the driver and passengers.

[0023] Please refer to Figure 1 In the step two, the color temperature adjustment range of the PWM modulated three-channel RGB LED array is 2000K-6500K, and the illumination adjustment range is 50lux-500lux; the sampling frequency of the vehicle speed sensor is not less than 10Hz, the sampling frequency of the road vibration sensor is not less than 50Hz, and the detection accuracy of the rain sensor is 0.1mm / min; By adjusting the PWM duty cycle of each channel (red, green, and blue), mixing different proportions of three primary colors, the color temperature is smoothly transitioned between 2000K and 6500K. At the same time, by adjusting the duty cycle or current intensity of the overall PWM signal, the total luminous intensity of the LED array is controlled, thereby realizing the adjustment of the illumination in the range of 50lux to 500lux. Sensor data is processed by the microcontroller to dynamically adjust the PWM signal to ensure real-time response to environmental changes; The detailed parameter settings of the color temperature and illumination adjustment of the three-channel RGB LED array with PWM modulation in Step Two, as well as the vehicle speed, road vibration, and rainfall sensors, bring significant advantages to the intelligent context-aware ambient light system. First, the wide range of color temperature and illumination adjustment capabilities enable the ambient light to adapt to different driving scenarios and user preferences, creating a variety of warm, focused, or warning atmospheres. Second, the high sampling frequency of the vehicle speed sensor ensures real-time capture of the vehicle's driving state, providing accurate basis for dynamic light adjustment. The high-frequency sampling of the road vibration sensor helps to anticipate road condition changes, such as bumps and potholes, allowing timely adjustments to the light to alert the driver. Finally, the high-precision rainfall sensor can accurately detect rainfall intensity, triggering corresponding light modes and improving safety during rainy driving.

[0024] Please refer to Figure 1 In Step Three, the saturation parameter of the HSV color space ranges from 0 to 100%, and the transition time of the asymmetric gradient algorithm is dynamically adjusted between 5 seconds and 30 seconds according to user settings. The touch screen uses capacitive touch technology, supporting multi-point touch and gesture operations. The specific implementation of the asymmetric gradient algorithm is as follows: first, determine the starting color (e.g., warning red) and target color (e.g., soothing purple) based on the HSV saturation parameter mapped by the pressure indicator. Then, calculate the intermediate color values at each time point based on the user-set transition time using a non-linear interpolation algorithm, achieving an asymmetric gradient transition from the starting color to the target color. During this process, the capacitive touch screen receives real-time user gesture operations and dynamically adjusts the transition rate to ensure smoothness and personalization of the user experience. The combination of the HSV color space saturation parameter setting (0-100%) and the asymmetric gradient algorithm in Step Three brings significant benefits to the vehicle ambient light. By precisely controlling color saturation, the system can flexibly adjust the light color based on the driver's stress state, from high-saturation warning colors to low-saturation soothing colors, effectively reducing driving fatigue and improving driving safety. The application of the asymmetric gradient algorithm makes the light transition more natural and smooth, avoiding abrupt color changes that may disturb the driver. Additionally, the capacitive touch screen supports multi-point touch and gesture operations, further enhancing the convenience and interest of user interaction. Drivers can adjust the light transition effect according to their personal preferences and enjoy personalized driving atmospheres.

[0025] Please refer to Figure 1 In Step Four, the environmental noise detector uses microphone array technology to detect noise frequencies ranging from 20 Hz to 20 kHz, with noise level classification levels not less than 5, each level corresponding to different light brightness and color temperature adjustment strategies. The environmental noise detector uses microphone array technology. Specifically, multiple microphones are placed in different positions inside the vehicle to collect noise signals. Digital signal processing technology is used to analyze the noise in the frequency range of 20Hz-20kHz. Based on parameters such as noise energy distribution and frequency characteristics, the noise level is divided into at least 5 levels (such as low, low-medium, medium, medium-high, and high). Each level has a pre-set corresponding light brightness and color temperature adjustment strategy. For example, when the noise is low, the normal brightness and color temperature are maintained, and when the noise is high, the brightness is reduced to a soft range and the color temperature is adjusted to a warm tone to reduce visual interference. This technology uses microphone array technology to accurately capture in-vehicle ambient noise and achieve fine-grained classification of noise levels. Each level corresponds to a different lighting adjustment strategy. This design significantly improves the intelligence level of the in-vehicle ambient lighting system. It can automatically adjust the brightness and color temperature of the lights according to the actual noise situation, creating a comfortable atmosphere in a quiet environment and reducing the driver's visual stress and improving driving safety in a noisy environment by adjusting the lights.

[0026] Please see Figure 1 In step five, the user-defined parameter storage module uses a non-volatile memory to store no less than 20 sets of user-defined lighting parameters. The scene matching algorithm uses fuzzy matching technology to match based on the similarity between key feature parameters of the driving scene and user-defined scene parameters; The user-defined parameter storage module uses EEPROM (Electrically Erasable Programmable Read-Only Memory) as a non-volatile memory. It is connected to the system main control chip through a serial communication interface to realize the writing and reading of parameters. The scene matching algorithm adopts fuzzy matching technology based on feature vectors. It quantifies the key feature parameters of the driving scene (such as vehicle speed, light intensity, road conditions, etc.) and the user-defined scene parameters, calculates the similarity score between the two, and determines that the match is successful when the score exceeds the preset threshold. The design utilizes non-volatile memory to store user-defined parameters and combines this with fuzzy matching technology for scene matching. This approach offers significant advantages. The non-volatile memory ensures that user-set lighting parameters are not lost after system power failure, providing a stable and reliable personalized experience. Users can preset various lighting modes according to their preferences and driving habits, such as "high-speed cruise" and "night driving." When the system identifies a match with a preset scene, it automatically calls up the corresponding lighting parameters, achieving fast and accurate scene switching. The application of fuzzy matching technology makes scene matching more flexible and intelligent. Even with subtle changes in the driving environment, the system can accurately identify and apply the most suitable lighting parameters by calculating similarity scores, thereby improving driving safety and comfort.

[0027] The application discloses an intelligent context-aware vehicle ambient light control system Figure 1 and Figure 2 , comprising: a multi-source data fusion state recognition module for collecting GPS trajectory, time stamp, vehicle OBD data and environmental light data, and performing driving scene state recognition through a Bayesian network algorithm, wherein an output end of the multi-source data fusion state recognition module is electrically connected with an input end of a spectrum-environment parameter coupling controller; the spectrum-environment parameter coupling controller is used for receiving output data of the state recognition module and environmental parameters of vehicle speed, road vibration and rainfall, and controlling color temperature and illumination of a PWM modulated three-channel RGB LED array, wherein an output end of the spectrum-environment parameter coupling controller is electrically connected with a control end of the RGB LED array; a light sequence generator based on emotional computing is used for generating a light sequence according to a pressure index of driving duration and emergency brake frequency, and receiving a transition rate parameter input by a user through a touch screen, wherein an output end of the light sequence generator based on emotional computing is electrically connected with the control end of the RGB LED array; an environmental noise detection module is used for monitoring in-vehicle environmental noise in real time through a microphone array technology, wherein an output end of the environmental noise detection module is electrically connected with an input end of the spectrum-environment parameter coupling controller; a user interaction module comprises a touch screen and a parameter storage unit, and is used for user input of personalized parameters and storage and calling, wherein an output end of the user interaction module is electrically connected with an input end of the light sequence generator based on emotional computing; a feedback optimization module comprises a camera and a sensor, and is used for collecting feedback information of a driver and a passenger, wherein an output end of the feedback optimization module is electrically connected with a parameter adjustment end of the multi-source data fusion state recognition module, the spectrum-environment parameter coupling controller and the light sequence generator based on emotional computing; a Bayesian network model is established through historical driving data, key characteristic parameters are determined as network nodes, a machine learning algorithm is used for training and determining conditional probability distribution between nodes, in actual application, the model is updated and optimized on line by using multi-source data (GPS trajectory, time stamp, vehicle OBD data and environmental light data) collected in real time, so that the accuracy of driving scene state recognition is improved; The multi-source data fusion state recognition module can comprehensively capture multi-dimensional features of the driving scene by integrating GPS trajectory, time stamp, vehicle OBD data and environmental light data, improve the accuracy and reliability of scene recognition, the spectral-environment parameter coupling controller intelligently adjusts the color temperature and illumination of the RGB LED array according to the recognition result and real-time environmental parameters, realizes the harmonious adaptation of light and environment, improves the driving experience, the light sequence generator based on emotional computing generates personalized light sequences combined with driving time and the number of emergency brakes, effectively relieves driving stress, the environmental noise detection module monitors the noise in the vehicle in real time, automatically adjusts the light to adapt to different sound environments, the user interaction module provides personalized settings and parameter storage functions to meet the preferences of different users, the feedback optimization module continuously optimizes the control strategy through the collection of driver feedback, forms a closed-loop control to ensure the continuous improvement of system performance.

[0028] Please refer to Figure 1 and Figure 2 The multi-source data fusion state recognition module includes a GPS module, a time stamp module, an OBD data acquisition module and a light sensor module, the output ends of each module are electrically connected with the input end of the Bayesian network algorithm processing unit, and the output end of the Bayesian network algorithm processing unit is electrically connected with the input end of the spectral-environment parameter coupling controller. In the multi-source data fusion state recognition module, the GPS module is used to obtain the vehicle driving route, the time stamp module records the time point of data acquisition, the OBD data acquisition module collects vehicle state data such as vehicle speed and acceleration, and the light sensor module real-time acquires environmental light intensity. These data are transmitted to the Bayesian network algorithm processing unit, which learns historical data through a pre-trained model to determine the conditional probability relationship between each data, realize real-time probability modeling of the driving scene, and ensure the accuracy of state recognition. The multi-source data fusion state recognition module integrates GPS, time stamp, OBD data acquisition and light sensor to build a comprehensive and accurate driving scene perception system. The advantage of this design is that it can integrate information from multiple data sources to improve the accuracy and robustness of driving scene recognition. GPS and time stamp provide the spatiotemporal background of vehicle driving, OBD data reflects the running state of the vehicle, and light sensor captures the change of environmental light. After these data are processed by the Bayesian network algorithm, the driving scene can be accurately described, providing a reliable basis for subsequent spectral-environment parameter coupling control, thereby improving the intelligence and adaptability of the vehicle ambient light, and creating a more comfortable and safe driving environment for the driver and passengers.

[0029] Please refer to Figure 1 and Figure 2The spectrum-environment parameter coupling controller comprises a vehicle speed acquisition unit, a road surface vibration acquisition unit, a rainfall acquisition unit and a dynamic calculation unit, the output ends of the vehicle speed acquisition unit, the road surface vibration acquisition unit and the rainfall acquisition unit are electrically connected with the input end of the dynamic calculation unit, and the output end of the dynamic calculation unit is electrically connected with the control end of the RGB LED array. The vehicle speed acquisition unit acquires vehicle driving speed data in real time through a CAN bus; the road surface vibration acquisition unit is fixed to a chassis through an acceleration sensor and acquires vibration frequency through high-frequency sampling; the rainfall acquisition unit uses an optical rainfall sensor to quantify rainfall by detecting the degree of light blocking of raindrops; after receiving the above data, the dynamic calculation unit combines preset thresholds (such as a vehicle speed of 80 km / h, a vibration frequency of 20 Hz and a rainfall of 1 mm / min), calculates and outputs color temperature and illumination control signals of the RGB LED array through an internal algorithm, and realizes dynamic adaptation of light and environment. Through the integration of the vehicle speed acquisition unit, the road surface vibration acquisition unit and the rainfall acquisition unit, comprehensive perception of the driving state of the vehicle is realized, which enables the vehicle-mounted atmosphere lamp to automatically adjust the color temperature and the illumination according to real-time environmental changes, such as providing high-color-temperature cold light to improve attention during high-speed driving and automatically switching to low-illumination amber warning light in adverse weather conditions, thereby effectively enhancing driving safety. The introduction of the dynamic calculation unit enables the system to respond quickly according to complex and changeable driving environments, thereby improving driving comfort and safety and embodying the design concepts of intelligence and individualization.

[0030] An electronic device comprises: A processor and a memory, wherein the memory stores a computer program, and the computer program realizes the steps of the intelligent context-aware vehicle-mounted atmosphere lamp control method according to any one of claims 1 to 7 when the computer program is run by the processor. The processor is a high-performance microcontroller with multi-core processing capability to meet real-time data processing requirements; the memory is a high-speed flash memory to ensure fast loading and execution of the computer program; the program is designed in a modular manner and integrates core functions such as multi-source data acquisition, scene recognition, light control, user interaction and feedback optimization; data interaction is realized among the modules through an efficient communication protocol to ensure stable operation of the system. The intelligent context-aware vehicle ambient light control method is integrated in the processor and the memory, a highly automated in-vehicle environment is created, the method accurately identifies the driving scene through multi-source data fusion technology, dynamically adjusts the light color temperature, illumination and color transition, not only improves the driving safety, but also enhances the driving comfort, the light sequence generated by emotion driving effectively relieves the driving pressure, promotes the physical and mental health, at the same time, the personalized parameter storage and calling function meets the personalized needs of different users, improves the user experience, the feedback-driven control strategy optimization mechanism ensures the continuous learning and improvement of the system, and keeps the best working state.

[0031] It should be noted that, in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0032] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for controlling intelligent context-aware in-vehicle ambient lighting, characterized in that, Includes the following steps: Step 1: Scenario state modeling based on multi-source data fusion: Vehicle state data, including driving route, time series, vehicle speed, and acceleration, are obtained through the GPS trajectory analysis module, timestamp marking module, and vehicle OBD data acquisition module. These data are then input into a Bayesian network algorithm model for probabilistic modeling of driving scenarios. Simultaneously, the ambient light intensity is collected in real time using a light sensor to calibrate and correct the scene state output by the model, and a scene recognition mechanism that integrates multi-dimensional data is established. Step 2: Coupling control of dynamic spectral and environmental parameters: A three-channel RGB LED array with PWM modulation is used as the light source. Data from vehicle speed sensor, road vibration sensor and rain sensor are received through a spectrum-environment parameter coupling controller. When the vehicle speed is higher than 80km / h, the high color temperature cold light mode is triggered. Step 3: Generation of Emotion-Driven Light Sequences: Based on the emotion computing module, the stress index of driving time and number of emergency braking is quantified. When continuous driving is >2 hours or emergency braking is ≥3 times, the stress value is mapped to the saturation parameter of HSV color space, and a dynamic light sequence from warning red to soothing purple is generated through an asymmetric gradient algorithm. Step 4: Dynamic adjustment of lighting in coordination with noise: The system detects in-vehicle noise using a microphone array. When the music volume is greater than 60dB, the headlight brightness is increased to 300 lux and the color contrast is enhanced. Step 5: Storing and retrieving personalized parameters: The system is configured to store user-defined parameters in non-volatile memory. When the current scene is detected to have a match rate of >80% with the user's preset keywords, the corresponding lighting parameters will be automatically invoked. Step Six: Optimization of Feedback-Driven Control Strategy By collecting facial expression features of drivers and passengers through in-vehicle cameras and combining them with motion sensor data to assess lighting satisfaction, and detecting a frowning frequency of >3 times / minute for 5 consecutive minutes, the weight parameters of the Bayesian network model are automatically adjusted.

2. The intelligent context-aware vehicle ambient lighting control method according to claim 1, characterized in that: In step one, the process of constructing the Bayesian network algorithm model includes collecting and preprocessing historical driving data, extracting key feature parameters as network nodes, training with machine learning algorithms to determine the conditional probability distribution between nodes, and forming an initial Bayesian network model. In practical applications, the model is updated and optimized online based on real-time collected multi-source data.

3. The intelligent context-aware vehicle ambient lighting control method according to claim 1, characterized in that: In step two, the color temperature adjustment range of the PWM-modulated three-channel RGB LED array is 2000K-6500K, and the illuminance adjustment range is 50lux-500lux; the sampling frequency of the vehicle speed sensor is not less than 10Hz, the sampling frequency of the road vibration sensor is not less than 50Hz, and the detection accuracy of the rain sensor is 0.1mm / min.

4. The intelligent context-aware vehicle ambient lighting control method according to claim 1, characterized in that: In step three, the saturation parameter of the HSV color space ranges from 0 to 100%, and the transition time of the asymmetric gradient algorithm is dynamically adjusted between 5 and 30 seconds according to the user setting.

5. The intelligent context-aware vehicle ambient lighting control method according to claim 1, characterized in that: In step four, the environmental noise detector uses microphone array technology to detect noise frequencies ranging from 20Hz to 20kHz. The noise level is divided into no fewer than five levels, with each level corresponding to different light brightness and color temperature adjustment strategies.

6. The intelligent context-aware vehicle ambient lighting control method according to claim 1, characterized in that: In step five, the user-defined parameter storage module uses non-volatile memory to store no less than 20 sets of user-defined lighting parameters; The scene matching algorithm uses fuzzy matching technology to match the key feature parameters of the driving scene with the user-defined scene parameters.

7. A system for intelligent context-aware vehicle ambient lighting control, employing the intelligent context-aware vehicle ambient lighting control method as described in any one of claims 1-6, characterized in that, include: The multi-source data fusion state recognition module is used to collect GPS trajectory, timestamp, vehicle OBD data and ambient light data, and to perform driving scene state recognition through Bayesian network algorithm. The output of the multi-source data fusion state recognition module is electrically connected to the input of the spectral-environment parameter coupling controller. The spectral-environmental parameter coupling controller is used to receive the output data of the state recognition module and environmental parameters such as vehicle speed, road vibration and rainfall, and control the color temperature and illuminance of the PWM modulated three-channel RGB LED array. The output terminal of the spectral-environmental parameter coupling controller is electrically connected to the control terminal of the RGB LED array. The emotion-based light sequence generator is used to generate light sequences based on stress indicators such as driving duration and number of emergency brakings, and receives transition rate parameters input by the user through a touch screen. The output of the emotion-based light sequence generator is electrically connected to the control terminal of the RGB LED array. The environmental noise detection module uses microphone array technology to monitor the in-vehicle environmental noise in real time. The output of the environmental noise detection module is electrically connected to the input of the spectrum-environmental parameter coupling controller. The user interaction module includes a touch screen and a parameter storage unit for users to input personalized parameters and store and recall them. The output of the user interaction module is electrically connected to the input of the emotion computing-based light sequence generator. The feedback optimization module, including a camera and sensors, is used to collect feedback information from drivers and passengers. The output of the feedback optimization module is electrically connected to the parameter adjustment terminals of the multi-source data fusion state recognition module, the spectral-environment parameter coupling controller, and the light sequence generator.

8. The intelligent context-aware vehicle ambient lighting control system according to claim 7, characterized in that: The multi-source data fusion state recognition module includes a GPS module, a timestamp module, an OBD data acquisition module, and a light sensor module. The output of each module is electrically connected to the input of the Bayesian network algorithm processing unit, and the output of the Bayesian network algorithm processing unit is electrically connected to the input of the spectral-environmental parameter coupling controller.

9. The intelligent context-aware vehicle ambient lighting control system according to claim 7, characterized in that: The spectral-environmental parameter coupling controller includes a vehicle speed acquisition unit, a road vibration acquisition unit, a rainfall acquisition unit, and a dynamic calculation unit. The output terminals of the vehicle speed acquisition unit, the road vibration acquisition unit, and the rainfall acquisition unit are all electrically connected to the input terminal of the dynamic calculation unit, and the output terminal of the dynamic calculation unit is electrically connected to the control terminal of the RGB LED array.

10. An electronic device, characterized in that, include: The processor and memory, wherein the memory stores a computer program that, when executed by the processor, implements the steps of the intelligent context-aware vehicle ambient lighting control method as described in any one of claims 1 to 7.

Images