Method for adjusting light environment of intelligent automobile cabin and related equipment

Abstract

The invention provides an intelligent automobile cabin light environment adjusting method and related equipment, and is applied to the technical field of data processing. The method comprises the steps of obtaining a training sample set and target intelligent cabin light environment data; preprocessing the training sample set to generate a training sample set with identification information; processing the training sample set with the identification information based on a preset processing rule to generate a training set and a test set; acquiring a preset light environment evaluation index model matched with the identification information; training a preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model; preprocessing the target intelligent cabin light environment data to generate attribute information of a target user; processing the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index; and processing the light environment evaluation index based on the target light environment evaluation index model to generate target illuminance.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for adjusting the light environment of a smart car cabin and related equipment. Background Art

[0002] Light has two effects on the human body: visual and non-visual. The visual effect of light is through the photoreceptor cells and cone cells in the human retina, mainly perceiving the color, details and imaging of things; the non-visual effect of light is through the intrinsically photoreceptive retinal ganglion cells (ipRGCs) in the human retina, mainly manifesting as a regulation of the human circadian rhythm, alertness, work efficiency and mood. Studying the impact of the non-visual effects of light on human physiology and psychology in the smart cockpit is an important means to improve the performance of people in the smart cockpit and create a safe, comfortable and healthy light environment for smart car cockpits.

[0003] With the rapid development of smart cars, the scenes and needs in the cockpit are constantly changing, which brings new challenges to the creation of the light environment in the cockpit. First of all, the work type and status of the people in the cockpit will change. Especially with the development of unmanned cars, the people in the cabin will do more work, entertainment, rest and other activities unrelated to driving. The light environment design of the cockpit also needs to be dynamically adjusted for different activities and tasks. In addition, the improvement of the level of vehicle intelligence has brought about an increase and complexity of the number of light sources such as display screens in the car cockpit, making the light environment in the smart cockpit increasingly complex, increasing the possibility of light pollution that harms the physiological and mental health of the human body, and it is necessary to evaluate the overall light environment status in the cockpit.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present application is to provide a method for adjusting the light environment of a smart car cabin and related equipment, which at least overcomes the problems existing in the prior art to a certain extent. By simulating three typical smart cabin light environments, the physiological and psychological indicator data of the subjects are collected to obtain the melatonin concentration, attention level and comfort data of the subjects; the experimental data are statistically analyzed, a light environment evaluation index model is established, and a smart cabin healthy light environment evaluation index that takes the work scene of the cabin personnel as the weight and takes into account both physiological and psychological health is defined, thereby obtaining the illuminance when the light environment evaluation index is optimal, which not only meets the scene requirements but also is beneficial to the physiological and psychological health of the cabin personnel.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a method for adjusting the light environment of a smart car cabin is provided, comprising: obtaining a training sample set and target smart cabin light environment data, wherein the training sample set includes a number of different smart cabin light environment data and a subject in the smart cabin; preprocessing the training sample set to generate a training sample set with identification information, wherein the identification information is used to characterize the presence of an abnormality in the user's physiological state; processing the training sample set with the identification information based on a preset processing rule to generate a training set and a test set; obtaining a preset light environment evaluation index model matching the identification information; training the preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model; preprocessing the target smart cabin light environment data to generate attribute information of a target user; processing the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index; processing the light environment evaluation index based on the target light environment evaluation index model to generate a target illuminance.

[0008] In one embodiment of the present application, the training sample set with identification information is processed based on preset processing rules to generate a training set and a test set, including: extracting features from the training sample set to determine an original feature library; dividing each feature data set according to the original feature library to generate a training set and a test set; using a classifier to predict each test set divided from the original feature library to determine a prediction result; using a preset algorithm to train each training set divided from the original feature library to obtain a test set class prediction result; and generating a training sample with identification information based on the prediction result and the test set class prediction result.

[0009] In one embodiment of the present application, the feature extraction of the training sample set to determine the original feature library includes: processing the standard material information based on preset processing rules to generate key factors of non-visual impact of light, wherein the key factors of non-visual impact of light are the characteristics of the light environment in the cabin of a smart car that affects human physiology; processing the standardized features based on preset feature screening and dimensionality reduction rules to generate original features; and generating an original feature library from a number of original features.

[0010] In one embodiment of the present application, the preset light environment evaluation index model is trained based on the training set and the test set to generate a target light environment evaluation index model, including: extracting multiple data groups from the training set, wherein each data group contains a preset number of data samples, wherein at least one data sample includes identification information; training the initial light environment evaluation index model based on the data samples in the multiple data groups to generate a trained light environment evaluation index model; processing the trained light environment evaluation index model based on the test set to generate a test result; if the data sample containing the identification information in the test result indicates that there is an abnormality in the user's physiological state, then using the trained light environment evaluation index model as the target light environment evaluation index model.

[0011] In one embodiment of the present application, the preprocessing of the target smart cockpit light environment data to generate attribute information of the target user includes: preprocessing the target smart cockpit light environment data to generate an attention factor of the target user, a melatonin factor of the target user, a comfort factor of the target user, an attention influence weight of the target user, a melatonin concentration influence weight of the target user, and a comfort influence weight of the target user; based on the attention factor of the target user, the melatonin factor of the target user, the comfort factor of the target user, the attention influence weight of the target user, the melatonin concentration influence weight of the target user, and the comfort influence weight of the target user as the attribute information of the target user.

[0012] In one embodiment of the present application, the target light environment evaluation index model is used to process the attribute information of the target user to generate a light environment evaluation index, including: the target light environment evaluation index model includes a calculation formula for obtaining the light environment evaluation index, and the calculation formula is: I(x)=λ RT P RT x+λ MT P MT (x)+λ CF P CF (x); λ RT +λ MT +λ CF =1; where I(x) is the light environment evaluation index; λ RT , MT and λ CF They are the weight of attention, the weight of melatonin concentration, and the weight of comfort; P RT (x), P MT (x) and P CF (x) are the attention factor, melatonin factor and comfort factor that vary with x, and x is the light intensity (lx).

[0013] In one embodiment of the present application, the processing of the light environment evaluation index based on the target light environment evaluation index model to generate the target light illuminance includes: the target light environment evaluation index model includes a calculation formula for obtaining the target light illuminance, and the calculation formula is: Where x is the target illuminance; P i (x) is a factor that changes with light intensity; I(x) is a light environment evaluation index; λ i is the impact weight of the impact factor named after impact i, λ i The range is [0,1], and k is the total number of influencing factors.

[0014] Another aspect of the present application is a device for adjusting the light environment of a smart car cabin, characterized in that it includes: an acquisition module, used to acquire a training sample set and target smart cabin light environment data, wherein the training sample set includes a number of different smart cabin light environment data and a subject in the smart cabin; acquire a preset light environment evaluation index model that matches the identification information; a processing module, used to pre-process the training sample set to generate a training sample set with identification information, wherein the identification information is used to characterize the existence of an abnormality in the user's physiological state; based on a preset processing rule, the training sample set with identification information is processed to generate a training set and a test set; based on the training set and the test set, the preset light environment evaluation index model is trained to generate a target light environment evaluation index model; the target smart cabin light environment data is pre-processed to generate attribute information of a target user; based on the target light environment evaluation index model, the attribute information of the target user is processed to generate a light environment evaluation index; based on the target light environment evaluation index model, the light environment evaluation index is processed to generate a target illuminance.

[0015] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned method for adjusting the light environment of the smart car cabin by executing the executable instructions.

[0016] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the method for adjusting the light environment of the cabin of an intelligent vehicle is implemented.

[0017] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the computer program implements the above-mentioned method for adjusting the light environment of the smart car cabin.

[0018] The present application provides a method for adjusting the light environment of a smart car cabin and related equipment, wherein a server obtains a training sample set and target smart cabin light environment data, wherein the training sample set includes a number of different smart cabin light environment data and a subject in the smart cabin; the training sample set is preprocessed to generate a training sample set with identification information, wherein the identification information is used to characterize the abnormality of the user's physiological state; the training sample set with the identification information is processed based on a preset processing rule to generate a training set and a test set; a preset light environment evaluation index model matching the identification information is obtained; the preset light environment evaluation index model is trained based on the training set and the test set to generate a target light environment evaluation index model; the target smart cabin light environment data is preprocessed to generate attribute information of a target user; the attribute information of the target user is processed based on the target light environment evaluation index model to generate a light environment evaluation index; the light environment evaluation index is processed based on the target light environment evaluation index model to generate a target illuminance. By simulating three typical smart cockpit light environments, the physiological and psychological index data of the subjects were collected, and the melatonin concentration, attention level and comfort data of the subjects were obtained; the experimental data were statistically analyzed, and a light environment evaluation index model was established. The smart cockpit healthy light environment evaluation index was defined, which took the work scene of the cabin personnel as the weight and took into account both physiological and psychological health. Then, the illuminance when the light environment evaluation index was optimal was obtained, which not only met the scene requirements but also was beneficial to the physiological and psychological health of the cabin personnel.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart showing a method for adjusting the light environment of a smart car cabin provided by an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the structure of a device for adjusting the light environment of a smart car cabin provided by an embodiment of the present application is shown;

[0022] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0023] Figure 4 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0025] Combine the following Figure 1 To describe the method for adjusting the light environment of the smart car cabin according to the exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0026] In one implementation, the present application also proposes a method for adjusting the light environment of a smart car cabin and related equipment. Figure 1 The flowchart of a method for adjusting the light environment of a smart car cabin according to an embodiment of the present application is schematically shown. Figure 1 As shown, the method is applied to a server, comprising:

[0027] S101, obtaining a training sample set and target intelligent cockpit light environment data.

[0028] In one embodiment, the training sample set includes several different smart cockpit light environment data and subjects in the smart cockpit. The training sample set includes 23 healthy college students, who were subjected to physiological and psychological tests at three different light intensities in a space simulating the light environment of a car cockpit. In the experiment, the saliva of the subjects was collected to analyze the melatonin (MT) content to reflect the health level, the psychomotor vigilance task (PVT) was used to test the attention level of the subjects, and the subjective comfort questionnaire was used to conduct psychological tests on the subjects. After that, the experimental data was statistically analyzed, and a mathematical model of the physiological and psychological impact of the car cockpit light environment on the occupants was established. A smart cockpit task weighted (attention, health and comfort) light environment evaluation index model was designed according to the task requirements of the occupants, and a strategy for creating a healthy light environment was constructed, providing basic theoretical support for the design and optimization of the smart cockpit light environment.

[0029] In addition, the subjects are 23 college students with an average age of 21.91 years (standard deviation of 1.90 years), including 15 males and 8 females. The average height of males is 176cm (standard deviation of 6cm), the average weight is 74.57kg (standard deviation of 8.44kg), and the average height of females is 161cm (standard deviation of 4.81cm), and the average weight is 51kg (standard deviation of 4kg); they are healthy, have normal color vision, no oral disease, injury or inflammation, and no mental illness such as depression, anxiety, and mania. Since the 23 subjects are of similar age, similar height and weight between the same sex, and have similar circadian rhythms overall (including between men and women), individual and gender differences between subjects are ignored in the present invention.

[0030] In order to simulate the cockpit environment, a light environment simulator with an internal space of 3000mm×2150mm×2800mm was built and placed in an indoor laboratory environment. The top, left, right and front four surfaces of the simulator can be adjusted for illumination and color temperature as needed to simulate different light environments in the cockpit environment. The bottom of the light environment simulator is directly in contact with the ground, and the rear is the entrance channel. During the test, the rear is blocked with an opaque black cloth, and the bottom and back cannot be adjusted for light.

[0031] According to the "Comparison Table of Illuminance and Environmental Standards" and "Common Natural Light Color Temperature" of the International Commission on Illumination (Commission Internationale de l'Eclairage, CIE), through the analysis of the spatiotemporal environmental characteristics of China's major traffic accidents between 2014 and 2018 and the temporal distribution law of China's road traffic accidents, combined with the light environment adjustment capability of the cabin light environment simulator, two representative light environments that are prone to major traffic accidents at the same color temperature level (5000k) were finally determined. Light1 and Light3 are used to simulate the car cabin light environment at noon and sunset on a sunny day, respectively, and a light environment Light2 with an illumination between the two in general weather to obtain more data to facilitate the establishment of a later mathematical model. Since the present invention mainly focuses on the impact of light illumination on the occupants in the cabin, in the actual experimental light environment, the measured data of light are shown in Table 1. The color temperatures of the three light environments do not have significant differences, so the influence of color temperature is ignored.

[0032] Table 1 Light environment parameters selected in the experiment and corresponding subject numbers

[0033]

[0034] S102: pre-process the training sample set to generate a training sample set with identification information.

[0035] In one embodiment, three light environments are tested for one day each, and two tests are conducted in the same light environment in the morning (10:00-11:30) and afternoon (14:00-15:30) every day, for a total of 6 experiments in 3 days. 23 subjects were randomly divided into 3 groups to receive tests in 3 different light environments. 3-4 subjects participated in one experiment, and 7-8 subjects participated in each light environment. In order to further control the impact of gender differences on the results, the ratio of men to women in each group of personnel was based on the overall gender ratio. Because the number of people was small, 1-2 female subjects were arranged in each group. The whole experiment was completed within 6 days. Each subject was tested in only one light environment, and the single test lasted 90 minutes, including a 30-minute preparation phase and a 60-minute test phase. The subjects arrived at the laboratory 10 minutes before the test experiment for preliminary preparation. The ambient temperature of the preparation phase and the test phase was controlled at 20-25°C.

[0036] Through experiments, it is possible to obtain the results of 60 minutes of exposure to three different light environments. From the beginning of entering the experimental environment, the melatonin concentration and the average correct PVT reaction time are measured every 20 minutes, and the subjective comfort process and overall score are performed after each group of experiments. Therefore, the experimental data includes the human saliva melatonin concentration, the average correct PVT reaction time and the subjective comfort data within 60 minutes of the experimental time under different light environments (illuminance). The identification information is used to characterize the abnormality of the user's physiological state.

[0037] Through the data analysis of melatonin concentration, PVT correct response time and subjective comfort evaluation in this experiment, the following findings can be obtained for the population represented by the subjects under the experimental conditions and environment, within the 60-min exposure time of the specific light environment:

[0038] 1) Melatonin concentration, PVT correct response time and subjective comfort evaluation are all related to light intensity, but have little to do with exposure time;

[0039] 2) Drastic changes in light intensity will cause drastic changes in melatonin concentration, PVT correct response time and comfort.

[0040] S103, processing the training sample set with identification information based on preset processing rules to generate a training set and a test set.

[0041] In one embodiment, feature extraction is performed on the training sample set to determine the original feature library; each feature data set is divided according to the original feature library to generate a training set and a test set; a classifier is used to predict each test set divided by the original feature library to determine the prediction result; a preset algorithm is used to divide each training set in the original feature library for training to obtain a test set class prediction result; and a training sample with identification information is generated according to the prediction result and the test set class prediction result. Among them, feature extraction includes four features: original features, statistical features, frequency domain features, and time domain features. The commonly used features extracted are specifically introduced as follows: Original features: Original features are the collected data, after preprocessing, using all the information in each sample data matrix for model training. In order not to lose sample information, each curve of sample Xi is directly expanded and stretched into a row vector. Statistical features: Statistical features consider the changing trend of all data points on the curve. By extracting statistical features, the dimension of the data sample can be reduced, which is convenient for analyzing genetic data and accelerating the convergence speed during model training. The extracted statistical features include maximum value, minimum value, mean, variance, and standard deviation. Frequency domain features: Perform wavelet transform on the data set, and use the coefficients obtained by the second-order wavelet transform as new features to form frequency domain features. Time domain features: Time domain features are mainly based on the time perspective to invent the changing laws of signals and systems. Time domain features can reflect the information of curve data in time changes. This process mainly extracts the first-order forward difference of the data set to form the first-order difference time domain features, and uses the exponential moving average feature processing method.

[0042] S104: Acquire a preset light environment evaluation index model that matches the identification information.

[0043] In one embodiment, the light environment evaluation index model is set based on the actual design changes of the smart cockpit received within a preset time period. This is because with the rapid development of smart cars, the scenes and needs in the smart cockpit are constantly changing, which brings new challenges to the creation of the light environment in the cockpit. First of all, the work type and status of the people in the cockpit will change. Especially with the development of unmanned cars, the people in the cabin will do more work, entertainment, rest and other activities that are not related to driving. The light environment design of the cabin also needs to be dynamically adjusted for different activity tasks. In addition, the improvement of the level of vehicle intelligence has brought about an increase and complexity of the number of light sources such as display screens in the car cockpit, making the light environment in the smart cockpit increasingly complex, increasing the possibility of light pollution that harms the physiological and mental health of the human body, and it is necessary to evaluate the overall light environment status in the cockpit.

[0044] S105 , training the preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model.

[0045] In one embodiment, multiple data groups are extracted from a training set, wherein each data group contains a preset number of data samples, wherein at least one data sample includes identification information; an initial light environment evaluation index model is trained based on the data samples in the multiple data groups to generate a trained light environment evaluation index model; the trained light environment evaluation index model is processed based on a test set to generate a test result; if the data sample containing the identification information in the test result indicates that a user's physiological state is abnormal, the trained light environment evaluation index model is used as a target light environment evaluation index model.

[0046] Since the data of the light environment evaluation index model for training may be too small and the proportion of each period in the training data is uneven, the Stable Diffusion model is used to generate training data. Divide the training set based on the identification information to generate a number of number class samples; obtain any number of smaller number class samples in the training set; generate adjacent samples based on the distance between any number of smaller number class samples and other number of smaller number class samples of the same category, wherein the adjacent samples include a preset number of any number of smaller number class samples; sample the adjacent samples to generate a preset number of sampled samples; determine the sampling ratio based on the number of samples of each number class in the training set; determine the sampling ratio based on the sampling ratio; sample the adjacent samples based on the sampling ratio to generate a preset number of sampled samples, and generate multiple data groups based on any minority class sample and each sampled sample.

[0047] S106, preprocessing the target smart cockpit light environment data to generate attribute information of the target user.

[0048] In one embodiment, the target smart cockpit light environment data is preprocessed to generate the target user's attention factor, the target user's melatonin factor, the target user's comfort factor, the target user's attention influence weight, the target user's melatonin concentration influence weight, and the target user's comfort influence weight; the target user's attention factor, the target user's melatonin factor, the target user's comfort factor, the target user's attention influence weight, the target user's melatonin concentration influence weight, and the target user's comfort influence weight are used as the target user's attribute information.

[0049] The key factors affecting the non-visual effects of light mainly include light intensity, spectral distribution, lighting time, lighting duration, lighting direction, and lighting history.

[0050] Among them, light intensity can quickly affect the non-visual effects of the human body. Experimental data show that the greater the light intensity, the stronger the inhibitory effect on melatonin secretion. Light intensity has a significant impact on human sleep, mental state, work efficiency and alertness. Long-term light that is inconsistent with the circadian rhythm affects melatonin secretion, causes circadian rhythm confusion, and reduces alertness and cognitive ability. Therefore, light intensity is one of the important non-visual influencing factors of this invention.

[0051] Since the reaction of non-visual effects is delayed, a certain length of light exposure is a necessary condition for producing non-visual effects. According to the "2023 China Major Cities Commuter Monitoring Report", about 12% of people have a one-way commuting time of more than 60 minutes. It can be judged that in major cities in China, the stay time of people in smart cockpits does not exceed 60 minutes, and in academic inventions, the illumination time is generally controlled within the range of 45 minutes to 6 hours. Therefore, the duration of light environment exposure in the present invention is set at 60 minutes.

[0052] The lighting time is related to the human body's circadian rhythm. In this experiment, each group of subjects was tested at the same time of the day, and it is believed that the human body's light rhythm level is basically the same. The effect of the lighting time on the individual circadian rhythm of the subjects was ignored in the experiment. At the same time, the environment in the smart car cabin is small, so it can be approximately considered that the spectral distribution in the space is basically the same. In addition, the direction of most seats in the cabin is consistent with the driving direction and the seat orientation is relatively fixed during driving, so the influence of the lighting direction is ignored in the experiment.

[0053] In current academic inventions of non-visual phenomena of light, the isolation time before illumination is usually controlled within the range of 15min-1h. In the present invention, the isolation time before the experiment is 30min, which can be considered to have basically eliminated the influence of the illumination history.

[0054] In summary, the present invention takes light intensity and illumination duration (60 minutes) as variables affecting the non-visual effects of light in the smart cockpit on the occupants. A 30-minute isolation is performed before the experiment to eliminate the influence of the illumination history. The experimental design basis of ignoring the influence of spectral distribution and illumination time is reasonable.

[0055] The focus of this invention is the non-visual impact of the intelligent cockpit light environment on the physiology and psychology of the occupants, and explores the effects of the light environment on the subjective feelings of alertness, attention level and comfort of the occupants. For details, please see the following text and will not be expanded here.

[0056] S107: Process the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index.

[0057] In one implementation, the target light environment evaluation index model includes a calculation formula for obtaining the light environment evaluation index. The specific calculation formula is as follows:

[0058] I(x)=λ RT P RT (x)+λ MT P MT (x)+λ CF P CF (x);

[0059] λ RT +λ MT +λ CF =1;

[0060] Among them, I(x) is the light environment evaluation index; λ RT , MT and λ CF They are the weight of attention, the weight of melatonin concentration, and the weight of comfort; P RT (x), P MT (x) and P CF (x) are the attention factor, melatonin factor and comfort factor that vary with x, and x is the light intensity (1x).

[0061] Through observation and analysis of the experimental data of the present invention, it can be known that during the day, the population represented by the subjects, exposed to a light environment for 60 minutes, the melatonin concentration (pg / mL), PVT correct reaction time (s) and overall comfort (dimensionless, [0-20]) did not change significantly with the exposure time, but changed significantly with the light intensity. Therefore, within the scope of the present invention, a healthy light environment can be regarded as a combination of three factors (attention factor, melatonin factor and comfort factor) that change with light intensity, and a light environment evaluation index composed of three factors of attention, melatonin concentration and comfort according to different weights is established. According to different needs and scenarios, different factor weights are combined to calculate the optimal light intensity, forming a light environment that is beneficial to the human body both physiologically and psychologically in the environment.

[0062] In another embodiment, according to the experiment conducted by the present invention, the light environment evaluation index algorithm is simulated and tested for verification. First, according to the melatonin concentration, attention and comfort with light intensity in the experiment, the above formula is used to establish the data relationship between light intensity and these three influencing factors. By fitting the experimental data with a second-order polynomial, the following equation can be obtained:

[0063] RT(x)=-3×10 -7 x 2 +0.0009x+2.624;

[0064] MT(x)=-4×10-7 x 2 +0.0007x+2.3179;

[0065] CF(x)=-5×10 -6 x 2 +0.0093x+12.092.

[0066] In order to establish the light environment evaluation index, it is first necessary to process the data of these three different factors so that they can be calculated in the same coordinate system environment. The present invention uses z-score normalization to normalize and translate the data of the above three factors. After fitting the experimental data with a quadratic polynomial, the following mathematical formula with illuminance as a variable can be obtained:

[0067] P RT (x) = -2 × 10 -6 x 2 +0.0046x+98.3168;

[0068] P MT (x) = -2 × 10 -6 x 2 +0.0029x+100.0708;

[0069] P CF (x) = -2 × 10 -6 x 2 +0.0032x+100.0126.

[0070] In the intelligent cockpit light environment simulation unmanned driving scenario of the present invention, the occupants in the cockpit need to perform (non-driving) work, which requires relatively high attention. Taking into account health and comfort, the weights of the three factors can be initially considered: RT : MT : CF =6∶2∶2, the light environment evaluation index formula is:

[0071] I(x)=-2×10 -6 x 2 +0.0040x+99.0068.

[0072] S108: Process the light environment evaluation index based on the target light environment evaluation index model to generate a target illuminance.

[0073] In one implementation, the target light environment evaluation index model includes a calculation formula for obtaining the target light illuminance, and the specific calculation formula is as follows:

[0074]

[0075]

[0076]

[0077] Where x is the target illuminance; P i (x) is a factor that changes with light intensity; I(x) is a light environment evaluation index; λ i is the impact weight of the impact factor named after impact i, λ i The range is [0, 1], and k is the total number of influencing factors.

[0078] With the emergence of driverless cars, the design of the light environment in the smart cockpit will consider more scenarios unrelated to human driving, such as office, entertainment and rest, and the weights of the factors affecting the light environment will change. First, according to the requirements of different scenarios in the smart cockpit, the weights of the factors affecting the light environment in the formula are comprehensively adjusted to determine the weights of each factor; then, they are substituted into the formula. Since each factor is approximately fitted as a quadratic function with illuminance as the variable, there is a (relative) optimal solution for the light environment evaluation index; then, the formula is differentiated and the derivative is set to 0, and the illuminance when the light environment evaluation index is optimal can be obtained. This illuminance is the light intensity of the smart cockpit light environment that not only meets the scene requirements but also is beneficial to the physiological and mental health of the cabin personnel.

[0079]

[0080] Let the above formula When x is equal to 0, the illuminance value x corresponding to the maximum light environment evaluation index can be obtained, where x=1000lx. Substituting x into the other formulas above, the PVT reaction time (the inverse of attention), melatonin concentration and comfort level of a person under the optimal healthy light environment can be obtained, that is, the physiological and psychological indicators of the human body under the optimal healthy light environment within the scope of the present invention can be obtained.

[0081] For details, please refer to Table 2:

[0082] Table 2 Strategy for creating a healthy light environment within the illumination range of the present invention

[0083]

[0084] By comparing the attention level and comfort data in Table 3 with the data in the experiment, it can be seen that the attention level, melatonin concentration and comfort under the illumination in the table are all in the optimal range of the overall data, that is, while meeting the high performance, the physiological indicators are also taken into account and the comfort is improved, indicating that this healthy light environment creation strategy is feasible within the limited scope of the present invention.

[0085] Therefore, even without changing the shape and structure of the vehicle, by changing the light transmittance of the car windows and the intelligent cabin lighting system and other simple and efficient means, the light environment in the cabin can be adjusted, which can effectively enhance the alertness of the people in the cabin and improve the driving experience, providing the people in the cabin with an efficient and more physical and mental health and comfortable overall light environment.

[0086] The present invention simulates three typical intelligent cockpit light environments, collects physiological and psychological index data of 23 qualified subjects, and obtains the subjects' melatonin concentration, attention level and comfort data; statistically analyzes the experimental data, establishes a mathematical model of the change of human melatonin concentration, attention level and comfort with light intensity, defines the intelligent cockpit healthy light environment evaluation index that takes the work scene of the cabin personnel as the weight and takes into account both physiological and psychological health, and provides a strategy for creating a healthy light environment for the intelligent cockpit. The main findings and conclusions of the invention are as follows:

[0087] 1) Melatonin levels, attention levels, and comfort levels are sensitive to drastic changes in light intensity;

[0088] 2) There was no statistically significant change in melatonin concentration, attention level and comfort with exposure duration within 60 min, that is, under the conditions of the present invention, it can be considered that melatonin concentration, attention and comfort are unrelated to exposure duration;

[0089] 3) Melatonin concentration, attention level and comfort are all correlated with light intensity, that is, the stronger the light intensity, the lower the melatonin concentration, the higher the attention level and the lower the comfort level. However, too low light intensity will also lead to reduced comfort level;

[0090] 4) Melatonin concentration has a strong positive correlation with comfort, and melatonin concentration is correlated with attention level;

[0091] 5) There is a correlation between attention level and comfort;

[0092] 6) When the weight ratio of attention, melatonin and comfort is 6:2:2, the light environment with an illuminance of 1000lx is the healthiest. This illuminance not only provides high performance for the subjects, but also ensures that the melatonin concentration does not decrease and also provides high comfort.

[0093] In the present application, a server obtains a training sample set and target smart cockpit light environment data, wherein the training sample set includes a number of different smart cockpit light environment data and a subject in the smart cockpit; the training sample set is preprocessed to generate a training sample set with identification information, wherein the identification information is used to characterize the abnormality of the user's physiological state; the training sample set with identification information is processed based on preset processing rules to generate a training set and a test set; a preset light environment evaluation index model matching the identification information is obtained; the preset light environment evaluation index model is trained based on the training set and the test set to generate a target light environment evaluation index model; the target smart cockpit light environment data is preprocessed to generate attribute information of the target user; the attribute information of the target user is processed based on the target light environment evaluation index model to generate a light environment evaluation index; the light environment evaluation index is processed based on the target light environment evaluation index model to generate a target illuminance. By simulating three typical smart cockpit light environments, the physiological and psychological index data of the subjects were collected, and the melatonin concentration, attention level and comfort data of the subjects were obtained; the experimental data were statistically analyzed, and a light environment evaluation index model was established. The smart cockpit healthy light environment evaluation index was defined, which took the work scene of the cabin personnel as the weight and took into account both physiological and psychological health. Then, the illuminance when the light environment evaluation index was optimal was obtained, which not only met the scene requirements but also was beneficial to the physiological and psychological health of the cabin personnel.

[0094] Optionally, in another embodiment of the method of the present application, extracting features from the training sample set to determine an original feature library includes:

[0095] Processing the standard substance information based on preset processing rules to generate key factors of non-visual impact of light, wherein the key factors of non-visual impact of light are characteristics of the impact of the light environment in the cabin of the smart car on human physiology;

[0096] Processing the standardized features based on preset feature screening and dimension reduction rules to generate original features;

[0097] Generate a primitive feature library from several primitive features.

[0098] In one embodiment, the experiment selects objective alertness and attention levels as the main evaluation indicators, and selects visual perception (comfort) as the auxiliary evaluation indicator, as shown in Table 3.

[0099] Table 3 Human evaluation indexes and evaluation methods selected by the present invention

[0100]

[0101] The attention level was evaluated using the psychomotor vigilance task (PVT), which is a performance test used to evaluate visual performance / sustained attention. The evaluation dimensions mainly include response accuracy, attention neglect rate, response omission rate, average correct response time, etc.; since the PVT is a simple response test to obvious visual signals, it does not require prior learning and adaptation and will not be affected by differences in individual abilities.

[0102] Alertness is evaluated by melatonin level (MT), which is a biochemical index measurement method for evaluating alertness. Measuring the content of melatonin (MT) in the human body can reflect circadian rhythm and alertness. The present invention measures the level of melatonin (MT) in the human body by using an enzyme-linked immunosorbent assay (ELISA) on the saliva sample of the subject to measure the hormone content in the human body fluid sample.

[0103] Comfortability is in the form of a comfort questionnaire, and a comprehensive evaluation of the test process is conducted after the test. The subjects score the overall comfort of the experiment and the comfort of each stage from -10 (very uncomfortable) to 10 (very comfortable) on a subjective scale, reflecting the impact and changes of comfort under different light environments.

[0104] By applying the above technical solution, the server obtains a training sample set and target smart cockpit light environment data, wherein the training sample set includes several different smart cockpit light environment data and subjects in the smart cockpit; the training sample set is preprocessed to generate a training sample set with identification information, wherein the identification information is used to characterize the abnormality of the user's physiological state; the standard material information is processed based on preset processing rules to generate non-visual key factors of light, wherein the non-visual key factors of light are the characteristics of the light environment in the smart car cockpit that affects human physiology; the standardized features are processed based on preset feature screening and dimensionality reduction rules to generate original features; several original features are used to generate an original feature library; each feature data set is divided according to the original feature library to generate a training set and a test set; the classifier is used to predict each test set divided by the original feature library to determine the prediction result; the preset algorithm is used to divide each training set in the original feature library for training to obtain the test set class prediction result; according to the prediction result and the test set class prediction result, a training sample with identification information is generated.

[0105] Acquire a preset light environment evaluation index model that matches the identification information; extract multiple data groups from a training set, wherein each data group contains a preset number of data samples, wherein at least one data sample includes identification information; train an initial light environment evaluation index model based on the data samples in the multiple data groups to generate a trained light environment evaluation index model; process the trained light environment evaluation index model based on a test set to generate a test result; if the data sample containing the identification information in the test result indicates that the user's physiological state is abnormal, then use the trained light environment evaluation index model as the target light environment evaluation index model. Preprocess the target intelligent cockpit light environment data to generate the target user's attention factor, the target user's melatonin factor, the target user's comfort factor, the target user's attention influence weight, the target user's melatonin concentration influence weight, and the target user's comfort influence weight; use the target user's attention factor, the target user's melatonin factor, the target user's comfort factor, the target user's attention influence weight, the target user's melatonin concentration influence weight, and the target user's comfort influence weight as the target user's attribute information; process the target user's attribute information based on the target light environment evaluation index model to generate a light environment evaluation index.

[0106] The target light environment evaluation index model includes a calculation formula for obtaining the light environment evaluation index, and the calculation formula is: I(x) = λ RT P RT (x)+λ MT P MT (x)+λ CF P CF (x); λ RT +λ MT +λ CF =1; where I(x) is the light environment evaluation index; λ RT , MT and λ CF They are the weight of attention, the weight of melatonin concentration, and the weight of comfort; P RT (x), P MT (x) and P CF (x) are the attention factor, melatonin factor and comfort factor that change with x, respectively, and x is the illuminance (1x); the light environment evaluation index is processed based on the target light environment evaluation index model to generate the target illuminance; the target light environment evaluation index model includes a calculation formula for obtaining the target illuminance, and the calculation formula is: Where x is the target illuminance; P i (x) is a factor that changes with light intensity; I(x) is a light environment evaluation index; λ i is the impact weight of the impact factor named after impact i, λi The range is [0, 1], and k is the total number of influencing factors. By simulating three typical intelligent cockpit light environments, the subjects' physiological and psychological indicators were collected to obtain the subjects' melatonin concentration, attention level and comfort data; the experimental data were statistically analyzed, and a light environment evaluation index model was established. The intelligent cockpit healthy light environment evaluation index that takes the work scene of the cabin personnel as the weight and takes into account the physiological and psychological health was defined, and then the illuminance when the light environment evaluation index is optimal was obtained. This illuminance not only meets the scene requirements, but also is conducive to the physiological and psychological health of the cabin personnel.

[0107] In one embodiment, if Figure 2 As shown, the present application also provides a device for adjusting the light environment of a smart car cabin, comprising:

[0108] The acquisition module 201 is used to acquire a training sample set and target smart cockpit light environment data, wherein the training sample set includes a number of different smart cockpit light environment data and subjects in the smart cockpit; and acquire a preset light environment evaluation index model that matches the identification information;

[0109] The processing module 202 is used to preprocess the training sample set to generate a training sample set with identification information, wherein the identification information is used to characterize the presence of abnormalities in the user's physiological state; process the training sample set with identification information based on preset processing rules to generate a training set and a test set; train the preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model; preprocess the target smart cockpit light environment data to generate attribute information of the target user; process the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index; process the light environment evaluation index based on the target light environment evaluation index model to generate a target illuminance.

[0110] In another embodiment of the present application, the processing module 202 is configured to pre-process the training sample set to generate a training sample set with identification information, including:

[0111] Extracting features from the training sample set to determine an original feature library;

[0112] Divide each feature data set according to the original feature library to generate a training set and a test set;

[0113] Use the classifier to divide the original feature library into various test sets for prediction and determine the prediction results;

[0114] Use the preset algorithm to divide each training set in the original feature library for training, and obtain the prediction results of the test set class;

[0115] Based on the prediction results and the test set class prediction results, training samples with identification information are generated.

[0116] In another embodiment of the present application, the processing module 202 is configured to extract features from the training sample set and determine an original feature library, including:

[0117] Processing the standard substance information based on preset processing rules to generate key factors of non-visual impact of light, wherein the key factors of non-visual impact of light are characteristics of the impact of the light environment in the cabin of the smart car on human physiology;

[0118] Processing the standardized features based on preset feature screening and dimension reduction rules to generate original features;

[0119] Generate a primitive feature library from several primitive features.

[0120] In another embodiment of the present application, the processing module 202 is configured to train the preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model, including:

[0121] Extracting a plurality of data groups from the training set, wherein each data group includes a preset number of data samples, wherein at least one data sample includes identification information;

[0122] Training the initial light environment evaluation index model based on the data samples in the plurality of data groups to generate a trained light environment evaluation index model;

[0123] Processing the trained light environment evaluation index model based on the test set to generate a test result;

[0124] If the data sample containing identification information in the test result indicates that the physiological state of the user is abnormal, the trained light environment evaluation index model is used as the target light environment evaluation index model.

[0125] In another embodiment of the present application, the processing module 202 is configured to pre-process the target smart cockpit light environment data to generate attribute information of the target user, including:

[0126] Preprocessing the target smart cockpit light environment data to generate a target user's attention factor, a target user's melatonin factor, a target user's comfort factor, a target user's attention influence weight, a target user's melatonin concentration influence weight, and a target user's comfort influence weight;

[0127] Based on the target user's attention factor, the target user's melatonin factor, the target user's comfort factor, the target user's attention influence weight, the target user's melatonin concentration influence weight, and the target user's comfort influence weight as the target user's attribute information.

[0128] In another embodiment of the present application, the processing module 202 is configured to process the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index, including:

[0129] The target light environment evaluation index model includes a calculation formula for obtaining the light environment evaluation index, and the calculation formula is:

[0130] I(x)=λ RT P RT (x)+λ MT P MT (x)+λ CF P CF (x);

[0131] λ RT +λ MT +λ CF =1;

[0132] Among them, I(x) is the light environment evaluation index; λ RT , MT and λ CF They are the weight of attention, the weight of melatonin concentration, and the weight of comfort; P RT (x), P MT (x) and P CF (x) are the attention factor, melatonin factor and comfort factor that vary with x, and x is the light intensity (lx).

[0133] In another embodiment of the present application, the processing module 202 is configured to process the light environment evaluation index based on the target light environment evaluation index model to generate a target light illuminance, including:

[0134] The target light environment evaluation index model includes a calculation formula for obtaining the target light illumination, and the calculation formula is:

[0135]

[0136]

[0137]

[0138] Where x is the target illuminance; P i x is a factor that changes with light intensity; I(x) is a light environment evaluation index; λ i is the impact weight of the impact factor named after impact i, λ i The range is [0,1], and k is the total number of influencing factors.

[0139] The present application embodiment provides an electronic device, such as Figure 3 As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302 and a communication interface 303. The first processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; the memory 301 stores a computer program that can be run on the first processor 300, and when the first processor 300 runs the computer program, the method for adjusting the light environment of the smart car cabin provided in any of the aforementioned embodiments of the present application is executed.

[0140] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0141] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store a program, and the first processor 300 executes the program after receiving an execution instruction. The method for adjusting the light environment of the smart car cabin disclosed in any implementation of the embodiment of the present application may be applied to the first processor 300, or implemented by the first processor 300.

[0142] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 300. The above-mentioned first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor to be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0143] The electronic device provided in the above-mentioned embodiments of the present application and the method for adjusting the light environment of the smart car cabin provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0144] The present application embodiment provides a computer-readable storage medium, such as Figure 4 As shown, the computer-readable storage medium 401 stores a computer program, and when the computer program is read and executed by the second processor 402, the aforementioned method for adjusting the light environment of the smart car cabin is implemented.

[0145] The technical solution of the embodiment of the present application, 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, which is stored in a storage medium and includes several instructions for enabling an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0146] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method for adjusting the intelligent vehicle cabin light environment provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0147] An embodiment of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a third processor to implement the method described above.

[0148] The computer program product provided in the above-mentioned embodiments of the present application and the method for adjusting the intelligent vehicle cabin light environment provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0149] It should be noted that, in this application, relational terms such as first and second, etc. 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 these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0150] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the method for evaluating the adjustment of the light environment in the cabin of a smart car, the electronic device, the electronic device, and the readable storage medium, since they are basically similar to the embodiment of the method for adjusting the light environment in the cabin of a smart car, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiment of the method for adjusting the light environment in the cabin of a smart car.

[0151] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A method for adjusting the light environment of a smart car cabin, characterized in that: include: Acquire a training sample set and target smart cockpit light environment data, wherein the training sample set includes a plurality of different smart cockpit light environment data and subjects in the smart cockpit; Preprocessing the training sample set to generate a training sample set with identification information, wherein the identification information is used to indicate that there is an abnormality in the user's physiological state; Processing the training sample set with identification information based on preset processing rules to generate a training set and a test set; Acquire a preset light environment evaluation index model that matches the identification information; Training the preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model; Preprocessing the target smart cockpit light environment data to generate attribute information of the target user; Processing the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index; The light environment evaluation index is processed based on the target light environment evaluation index model to generate a target illuminance.

2. The method according to claim 1, characterized in that The processing of the training sample set with identification information based on a preset processing rule to generate a training set and a test set includes: Extracting features from the training sample set to determine an original feature library; Divide each feature data set according to the original feature library to generate a training set and a test set; Use the classifier to divide the original feature library into various test sets for prediction and determine the prediction results; Use the preset algorithm to divide each training set in the original feature library for training, and obtain the prediction results of the test set class; Based on the prediction results and the test set class prediction results, training samples with identification information are generated.

3. The method according to claim 2, characterized in that The step of extracting features from the training sample set to determine an original feature library includes: Processing the standard material information based on preset processing rules to generate key factors of non-visual impact of light, wherein the key factors of non-visual impact of light are characteristics of the impact of the light environment in the cabin of the smart car on human physiology; Processing the standardized features based on preset feature screening and dimension reduction rules to generate original features; Generate a primitive feature library from several primitive features.

4. The method according to claim 1, characterized in that The step of training the preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model includes: Extracting a plurality of data groups from the training set, wherein each data group includes a preset number of data samples, wherein at least one data sample includes identification information; Training the initial light environment evaluation index model based on the data samples in the plurality of data groups to generate a trained light environment evaluation index model; Processing the trained light environment evaluation index model based on the test set to generate a test result; If the data sample containing identification information in the test result indicates that the physiological state of the user is abnormal, the trained light environment evaluation index model is used as the target light environment evaluation index model.

5. The method according to claim 1, characterized in that The preprocessing of the target smart cockpit light environment data to generate attribute information of the target user includes: Preprocessing the target smart cockpit light environment data to generate a target user's attention factor, a target user's melatonin factor, a target user's comfort factor, a target user's attention influence weight, a target user's melatonin concentration influence weight, and a target user's comfort influence weight; Based on the target user's attention factor, the target user's melatonin factor, the target user's comfort factor, the target user's attention influence weight, the target user's melatonin concentration influence weight, and the target user's comfort influence weight as the target user's attribute information.

6. The method according to claim 5, characterized in that The processing of the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index includes: The target light environment evaluation index model includes a calculation formula for obtaining the light environment evaluation index, and the calculation formula is: I(x)=λ RT P RT (x)+λ MT P MT (x)+λ CF P CF (x); l RT +λ MT +λ CF =1; Among them, I(x) is the light environment evaluation index; λ RT , MT and λ CF They are the weight of attention, the weight of melatonin concentration, and the weight of comfort; P RT (x), P MT (x) and P CF (x) are the attention factor, melatonin factor and comfort factor that vary with x, and x is the light intensity (lx).

7. The method according to claim 6, characterized in that The processing of the light environment evaluation index based on the target light environment evaluation index model to generate a target light illuminance includes: The target light environment evaluation index model includes a calculation formula for obtaining the target light illumination, and the calculation formula is: Where x is the target illuminance; P i (x) is a factor that changes with light intensity; I(x) is a light environment evaluation index; λ i is the impact weight of the impact factor named after impact i, λ i The range is [0,1], and k is the total number of influencing factors.

8. A device for adjusting the light environment of a smart car cabin, characterized in that: The device comprises: An acquisition module is used to acquire a training sample set and target smart cockpit light environment data, wherein the training sample set includes a number of different smart cockpit light environment data and subjects in the smart cockpit; and acquire a preset light environment evaluation index model that matches the identification information; A processing module is used to preprocess the training sample set to generate a training sample set with identification information, wherein the identification information is used to characterize the presence of abnormalities in the user's physiological state; process the training sample set with identification information based on preset processing rules to generate a training set and a test set; train the preset light environment evaluation index model based on the training set and the test set to generate a target light environment evaluation index model; preprocess the target smart cockpit light environment data to generate attribute information of a target user; process the attribute information of the target user based on the target light environment evaluation index model to generate a light environment evaluation index; process the light environment evaluation index based on the target light environment evaluation index model to generate a target illuminance.

9. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the method for adjusting the light environment of the smart car cabin as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the method for adjusting the light environment of the smart car cabin as claimed in any one of claims 1 to 7 is implemented.

Images