In-vehicle light control method and light control equipment

Abstract

The invention relates to an in-vehicle light control method and light control equipment. The method comprises the following steps: firstly, in response to an in-vehicle light control request, obtaining current multi-dimensional sensing information collected by various types of sensors pre-installed in a vehicle, then determining an emotion quantized value and an environment comfort quantized value of at least one in-vehicle person in the vehicle based on the current multi-dimensional sensing information, and then, determining a control result of the in-vehicle light control request according to the emotion quantized value and the environment comfort quantized value of the at least one in-vehicle person in the vehicle. And performing decision analysis on the emotion quantized value and the environment comfort quantized value of at least one person in the vehicle through a preset decision model, generating an in-vehicle light control instruction, and finally, controlling the in-vehicle light based on the in-vehicle light control instruction. By adopting the method, the human factor adjustment of the in-vehicle light can be realized, and the flexibility of the in-vehicle light control is higher.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to an in-vehicle lighting control method and lighting control device. Background Technology

[0002] With the upgrading of vehicle humanization and intelligence, controlling the interior lighting can meet different driving needs of users. Currently, vehicle interior lighting control is usually done through physical operation, with users setting the lighting through the vehicle's central control screen or control buttons, and selecting different lighting modes for different scenarios.

[0003] However, current methods for controlling in-vehicle lighting are relatively simple and lack flexibility. Summary of the Invention

[0004] Therefore, it is necessary to provide an in-vehicle lighting control method and lighting control device to address the aforementioned technical problems.

[0005] In a first aspect, this application provides an in-vehicle lighting control method, applied to a lighting controller, the method comprising:

[0006] In response to a request to control the vehicle's interior lighting, the system acquires current multi-dimensional sensory information about the vehicle's interior. This information includes physiological parameter data of at least one occupant inside the vehicle, as well as data on light intensity, temperature, and humidity inside the vehicle.

[0007] Based on the current multi-dimensional perception information, determine the quantitative values ​​of the emotions and environmental comfort of at least one occupant inside the vehicle.

[0008] The system uses a pre-defined decision model to analyze the emotional and environmental comfort values ​​of at least one occupant inside the vehicle and generate in-vehicle lighting control commands.

[0009] The interior lights are controlled based on the in-vehicle lighting control commands.

[0010] The aforementioned in-vehicle lighting control method, applied to a lighting controller, firstly, in response to an in-vehicle lighting control request, acquires current multi-dimensional perception information collected by various types of sensors pre-installed inside the vehicle. Then, based on this multi-dimensional perception information, it determines the quantified values ​​of the emotion and environmental comfort of at least one occupant inside the vehicle. Next, it performs decision analysis on these values ​​using a pre-defined decision model, generating in-vehicle lighting control commands. Finally, it controls the in-vehicle lighting based on these commands. In this way, by acquiring data from multiple types of sensors and comprehensively considering the quantified values ​​of the occupants' emotions and environmental comfort when controlling the in-vehicle lighting, the control method is determined, achieving human-centered adjustment of the in-vehicle lighting and increasing the flexibility of in-vehicle lighting control.

[0011] In an optional embodiment of the first aspect, various types of sensors include a vision sensor, an illuminance sensor, and a temperature and humidity sensor; acquiring current multidimensional perception information inside the vehicle, including:

[0012] Acquire physiological parameter data collected by the visual sensor;

[0013] Acquire light intensity data collected by the illuminance sensor;

[0014] Acquire temperature and humidity data collected by the temperature and humidity sensor.

[0015] In the above embodiments, multiple dimensions of perception information are obtained by detecting various types of sensors, which enriches the types of collected data. This allows for comprehensive consideration of various factors when controlling in-vehicle lighting, thereby improving the accuracy of lighting control.

[0016] In an optional embodiment of the first aspect, determining the quantification values ​​of the emotion and environmental comfort of at least one occupant inside the vehicle based on current multidimensional perception information includes:

[0017] Based on the current multidimensional perception information and the preset emotion quantification model, the emotion quantification value is determined;

[0018] Based on the emotional quantification value, current multidimensional perception information, and a pre-set environmental comfort model, the environmental comfort quantification value is determined.

[0019] In the above embodiments, by using current perception information, emotion quantification model, and environmental comfort model, emotion quantification value and environmental comfort quantification value are calculated. By quantifying the emotions of the occupants and the in-vehicle environment, data support is provided for lighting control decisions.

[0020] In an optional embodiment of the first aspect, the physiological parameter data includes facial data of at least one occupant inside the vehicle; based on current multidimensional perception information and a preset emotion quantification model, an emotion quantification value is determined, including:

[0021] Based on facial data, determine the heart rate and blood pressure data of at least one occupant inside the vehicle;

[0022] Facial data, heart rate data, blood pressure data, temperature data, and humidity data are input into the emotion quantification model to obtain emotion quantification values.

[0023] In the above embodiments, the emotions of the people in the vehicle were quantified based on physiological parameter data, temperature data, and humidity data, which improved the comprehensiveness of the emotion quantification value calculation.

[0024] In an optional embodiment of the first aspect, determining the environmental comfort quantification value based on the emotion quantification value, current multidimensional perception information, and a preset environmental comfort model includes:

[0025] Based on the environmental comfort model, temperature data, humidity data, light intensity data, and emotional quantification values ​​are weighted and fused to generate a quantitative value for environmental comfort.

[0026] In the above embodiments, the environmental comfort quantification value was quantified based on temperature data, humidity data, light intensity data, and emotional quantification value, thereby improving the comprehensiveness of the environmental comfort quantification value calculation.

[0027] In an optional embodiment of the first aspect, the method further includes:

[0028] While controlling the interior lights based on the in-vehicle lighting control commands, the system acquires feedback information from the occupants and new multi-dimensional perception information collected by the vehicle's internal sensors.

[0029] Based on feedback information and new multidimensional perception information, the model parameters of the environmental comfort model are optimized.

[0030] And / or, based on feedback information and new multidimensional perception information, optimize the model parameters of the decision-making model.

[0031] In an optional embodiment of the first aspect, the environmental comfort model is an adaptive weighted fusion model, the decision model is an adaptive weighted fusion model, and the method further includes:

[0032] Based on feedback information and new multidimensional perception information, the weight parameters of each input parameter of the environmental comfort model are optimized.

[0033] And / or, based on feedback information and new multidimensional perception information, optimize the weight parameters of each input parameter of the decision model.

[0034] In the above embodiments, by acquiring feedback information after the execution of in-vehicle lighting control commands and new multi-dimensional perception information, the environmental comfort model and decision-making model are optimized to improve the accuracy of the environmental comfort model and decision-making model, thereby improving the accuracy of in-vehicle lighting control command generation and improving the lighting experience of in-vehicle occupants.

[0035] In an optional embodiment of the first aspect, a decision analysis is performed on the quantified values ​​of the emotions and environmental comfort of at least one occupant inside the vehicle using a preset decision model to generate in-vehicle lighting control commands, including:

[0036] The quantitative values ​​of emotion and the quantitative values ​​of environmental comfort are input into the decision model to determine the target control mode based on the quantitative values ​​of emotion and the quantitative values ​​of environmental comfort.

[0037] Based on the target control mode and the preset mapping table, determine the in-vehicle lighting control commands that are compatible with the target control mode. The mapping table includes the correspondence between multiple control modes and in-vehicle lighting control commands.

[0038] In the above embodiments, the decision model generates in-vehicle lighting control commands through emotion quantification and environmental comfort quantification, enabling in-vehicle lighting control to adaptively adjust according to the emotions of the occupants and the environment, thereby improving the intelligence and interactive experience of lighting control.

[0039] In an optional embodiment of the first aspect, controlling the interior lights based on interior light control commands includes:

[0040] The spectral modulation strategy is determined based on the in-vehicle lighting control commands.

[0041] The spectral modulation strategy drives the lighting circuit to control the spectrum and illuminance of the in-vehicle lights.

[0042] In the above embodiments, the light driving circuit is controlled by a spectral modulation strategy to control the spectrum and illuminance of the light, thereby meeting the lighting control needs in different scenarios and improving the comfort of in-vehicle lighting. At the same time, in scenarios where strong lighting is not required, controlling the light to be partially turned off or the illuminance to be reduced can also effectively reduce energy consumption and extend the service life of the in-vehicle LEDs.

[0043] In an optional embodiment of the first aspect, a spectral modulation strategy is used to drive a light driving circuit to control the spectrum and illuminance of the in-vehicle lights, including:

[0044] If the spectral modulation strategy is a wake-up modulation strategy, the light driving circuit is driven to increase the color temperature and illuminance of the interior lights and adjust the wavelength of the interior lights to the first wavelength.

[0045] If the spectral control strategy is a rest control strategy, the light drive circuit is driven to reduce the color temperature and illuminance of the interior lights and adjust the wavelength of the interior lights to a second wavelength, which is greater than the first wavelength.

[0046] In the above embodiments, different preset spectral control strategies are used to achieve human-centered adjustment of the vehicle's interior lighting.

[0047] Secondly, this application also provides an in-vehicle lighting control device, the device comprising:

[0048] The acquisition module is used to acquire the current multi-dimensional perception information inside the vehicle in response to the in-vehicle lighting control request. The current multi-dimensional perception information includes the physiological parameter data of at least one occupant inside the vehicle, as well as the light intensity data, temperature data, and humidity data inside the vehicle.

[0049] The determination module is used to determine the quantification values ​​of the emotions and environmental comfort of at least one occupant inside the vehicle based on the current multidimensional perception information.

[0050] The instruction generation module is used to perform decision analysis on the quantitative values ​​of the emotions and environmental comfort of at least one occupant inside the vehicle through a preset decision model, and generate in-vehicle lighting control instructions.

[0051] The control module is used to control the interior lights based on the interior light control commands.

[0052] Thirdly, this application also provides a lighting controller, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the first aspects above.

[0053] Fourthly, this application also provides a lighting control device, which includes a lighting controller, a sensor module, and a light-emitting diode (LED) module; the sensor module and the LED module are connected to the lighting controller; the lighting controller is connected to a vehicle controller; the lighting controller is used to implement the steps of the method described in any one of the first aspects above.

[0054] In an alternative embodiment of the fourth aspect, the lighting controller is connected to the vehicle controller via a controller area network bus; the lighting controller is connected to the sensor module via a serial peripheral interface.

[0055] Fifthly, this application also provides a vehicle including the lighting control device as described in the fourth aspect above.

[0056] In a sixth aspect, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects above.

[0057] In a seventh aspect, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects above.

[0058] The beneficial effects of any of the technical solutions in the second to fifth aspects mentioned above can be referred to the beneficial effects of the corresponding technical solutions in the first aspect, and the repeated parts will not be listed here. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a schematic diagram illustrating an optional application environment for the in-vehicle lighting control method in one embodiment.

[0061] Figure 2 This is a schematic diagram of an optional process for controlling in-vehicle lighting in one embodiment;

[0062] Figure 3 This is a schematic diagram of an optional process for obtaining current multidimensional sensing information in one embodiment;

[0063] Figure 4 This is an optional flowchart illustrating the steps for determining the quantification values ​​of emotion and environmental comfort in one embodiment.

[0064] Figure 5 This is an optional flowchart illustrating the steps for determining the emotion quantification value in one embodiment;

[0065] Figure 6 This is a schematic diagram of an optional process for the model optimization steps in one embodiment;

[0066] Figure 7 This is a schematic diagram of an optional process for determining the in-vehicle lighting control command in one embodiment;

[0067] Figure 8 This is a schematic diagram of an optional process for controlling the in-vehicle lighting in one embodiment;

[0068] Figure 9 This is a schematic diagram of an optional process for controlling in-vehicle lighting in another embodiment;

[0069] Figure 10 This is a schematic diagram of an optional structure of the in-vehicle lighting control device in one embodiment;

[0070] Figure 11 This is a schematic diagram of an optional internal structure of the lighting controller in one embodiment;

[0071] Figure 12 This is a schematic diagram of an optional structure of a lighting control device in one embodiment;

[0072] Figure 13 This is a schematic diagram of an optional structure of the sensor module in one embodiment. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0074] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0075] The in-vehicle lighting control method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the lighting controller 102 communicates with the sensor module 104 and the LED lamp module 106 via a network. The lighting controller 102 can be a microcontroller, and the sensor module 104 can include various types of sensors, such as optical sensors, vision sensors, illuminance sensors, temperature sensors, or humidity sensors, to collect various types of data from inside the vehicle. The LED lamp module 106 includes multiple LED lamps.

[0076] In one exemplary embodiment, such as Figure 2 As shown, a method for controlling in-vehicle lighting is provided, which can be applied to... Figure 1 Taking the lighting controller as an example, the explanation includes the following steps 201 to 204. Wherein:

[0077] Step 201: In response to the in-vehicle lighting control request, obtain the current multi-dimensional perception information inside the vehicle.

[0078] The current multi-dimensional sensing information includes physiological parameter data of at least one occupant inside the vehicle, as well as data on light intensity, temperature, and humidity inside the vehicle. Interior lighting control requests can be initiated by the occupant or automatically triggered by the vehicle's controller under preset conditions. For example, an occupant can initiate an interior lighting control request via voice or the vehicle's central control screen. Preset conditions can be time-based, meaning the vehicle controller triggers the interior lighting control request when a preset time is met; or they can be operational conditions, such as door opening or music playback, meaning the vehicle controller can automatically trigger the interior lighting control request when a door is open.

[0079] The lighting controller connects to the vehicle's overall controller. Upon receiving a request to control the interior lighting, it acquires multi-dimensional perception information from various types of sensors pre-installed inside the vehicle. These sensors can be pre-positioned at different locations within the vehicle, depending on actual needs. These sensors can include at least one of the following: optical sensors, vision sensors, infrared sensors, illuminance sensors, temperature sensors, humidity sensors, sound sensors, and air quality sensors. Based on the data collected by these sensors, the controller determines the current multi-dimensional perception information, providing comprehensive data support for subsequent interior lighting control.

[0080] Step 202: Based on the current multidimensional perception information, determine the quantification value of the emotion and the quantification value of the environmental comfort of at least one occupant inside the vehicle.

[0081] For example, if there is only one person in the vehicle, the emotion quantification value is the emotion quantification value corresponding to that person. If there are multiple people in the vehicle, the emotion quantification value can be obtained by weighting the emotion quantification values ​​corresponding to each person. The emotion quantification value is the quantification of the emotional state of the people in the vehicle, which can include calmness, anxiety, happiness, tension, or fatigue, etc. The physiological signals of the people in the vehicle are acquired through optical sensors, visual sensors, or infrared sensors, and the emotional state of the people in the vehicle can be obtained by analyzing the physiological signals.

[0082] Optionally, physiological signals can be input into a pre-trained emotion quantification model to obtain emotion quantification values. Alternatively, different threshold ranges can be set for different physiological signals, with different threshold ranges corresponding to different parameter quantification values, thereby converting each physiological signal into parameter quantification values, and calculating the emotion quantification value based on each parameter quantification value.

[0083] The environmental comfort quantification value is obtained by quantifying the comfort of the in-vehicle environment. Optionally, environmental parameters such as temperature, humidity, air quality, light intensity, and noise level inside the vehicle can be obtained through sensors such as light intensity sensors, temperature sensors, humidity sensors, sound sensors, and air quality sensors. The environmental parameters are then comprehensively evaluated to obtain the environmental comfort quantification value.

[0084] For example, the different environmental parameters mentioned above can be input into a pre-trained environmental comfort model, and the environmental comfort quantification value can be obtained based on the output of the environmental comfort model. Alternatively, different threshold ranges can be set for each environmental parameter, with different threshold ranges corresponding to different parameter quantification values, thereby converting each environmental parameter into a parameter quantification value, and the environmental comfort quantification value can be calculated based on each parameter quantification value.

[0085] Step 203: Analyze the emotional quantification value and environmental comfort quantification value of at least one occupant inside the vehicle using a preset decision model, and generate in-vehicle lighting control commands.

[0086] For example, the preset decision model can be a weighted summation model for solving multi-objective decision optimization problems. It performs weighted fusion processing on the quantitative values ​​of emotion and environmental comfort, performs pattern matching based on the fusion results, and generates in-vehicle lighting control commands based on the corresponding matching results.

[0087] The preset decision model can also be a multi-objective decision optimizer. An optimization function is constructed based on the quantified values ​​of emotion, the quantified values ​​of environmental comfort, the user-set goals, and historical lighting control data as variables. The lighting equipment parameters, the physiological comfort of the personnel, user preferences, environmental constraints, and time are used as constraints. By solving the optimization function, in-vehicle lighting control commands are generated.

[0088] Step 204: Control the interior lights based on the interior light control command.

[0089] Optionally, the lighting control instructions may include a spectral modulation strategy for multiple LED lights. The spectral modulation strategy is used to control the switching, brightness, color temperature, and time of each LED light, and each LED can be controlled independently.

[0090] For example, the lighting controller can send the generated interior lighting control commands to the control chip of the LED lamp module. The control chip then converts the interior lighting control commands into control signals and sends them to the LED driver circuit to drive each LED. Alternatively, the lighting controller can send the generated interior lighting control commands to the vehicle controller, which then forwards them to the control chip of the LED lamp module.

[0091] In the above embodiment, firstly, in response to an in-vehicle lighting control request, current multi-dimensional perception information collected by various types of sensors pre-installed inside the vehicle is acquired. Then, based on the current multi-dimensional perception information, the quantified values ​​of the emotion and environmental comfort of at least one occupant inside the vehicle are determined. Next, a preset decision model is used to analyze the quantified values ​​of the emotion and environmental comfort of at least one occupant inside the vehicle, generating an in-vehicle lighting control command. Finally, the in-vehicle lighting is controlled based on the in-vehicle lighting control command. In this way, when controlling the in-vehicle lighting, data from multiple types of sensors is acquired, and the quantified values ​​of the emotion and environmental comfort of the occupants are comprehensively considered to determine the control method for the in-vehicle lighting, achieving human-centered adjustment of the in-vehicle lighting and increasing the flexibility of in-vehicle lighting control.

[0092] In the embodiments of this application, various types of sensors include visual sensors, illuminance sensors, and temperature and humidity sensors; the current multidimensional sensing information includes physiological parameter data of at least one occupant inside the vehicle, and illuminance data, temperature data, and humidity data inside the vehicle; the steps for acquiring the current multidimensional sensing information collected by various types of sensors pre-installed inside the vehicle are as follows: Figure 3 As shown, it includes:

[0093] Step 301: Obtain physiological parameter data collected by the visual sensor.

[0094] The physiological parameter data collected by visual sensors installed inside the vehicle can be facial data, such as facial video data, of at least one occupant inside the vehicle. The visual sensors can be positioned directly in front of each seat in the vehicle to clearly acquire facial video data of each occupant.

[0095] Step 302: Obtain the light intensity data collected by the illuminance sensor.

[0096] The illuminance sensor detects changes in ambient light intensity using built-in photosensitive components. It generates different output currents based on the light intensity, and the ambient light intensity data is determined from the output current. Optionally, there can be one illuminance sensor, or multiple sensors to improve detection accuracy. When multiple sensors are used, the average light intensity detected by each sensor is taken as the ambient light intensity inside the vehicle.

[0097] Step 303: Obtain temperature and humidity data collected by the temperature and humidity sensor.

[0098] For example, temperature and humidity data inside the vehicle can be detected using separate temperature and humidity sensors, or by integrating a single temperature and humidity sensor. Similar to the setup of the illuminance sensor described above, one temperature and humidity sensor can be used, or multiple sensors can be used to improve detection accuracy. When multiple sensors are used, the average of the temperature and humidity data detected by the different sensors is taken as the temperature and humidity data inside the vehicle.

[0099] In the above embodiments, multiple dimensions of perception information are obtained by detecting various types of sensors, which enriches the types of collected data. This allows for comprehensive consideration of various factors when controlling in-vehicle lighting, thereby improving the accuracy of lighting control.

[0100] In one embodiment, the steps for determining the quantitative values ​​of the emotions and environmental comfort of at least one occupant inside the vehicle are as follows: Figure 4 ,include:

[0101] Step 401: Determine the emotion quantification value based on the current multidimensional perception information and the preset emotion quantification model.

[0102] The emotion quantification model can be a model that integrates psychological emotion classification theory with machine learning algorithms, capable of analyzing collected multi-dimensional information and determining emotion quantification values. For example, the emotion quantification model may include a data input layer, a feature extraction and fusion layer, an emotion calculation and classification layer, and an output layer. The data input layer receives the current multi-dimensional perceptual information and performs data preprocessing, such as data cleaning and outlier imputation. The feature extraction and fusion layer extracts features from the preprocessed multi-dimensional perceptual information. The emotion calculation and classification model classifies the emotions based on the extracted features and outputs each emotion and its corresponding confidence level. The output layer determines the emotion quantification value based on each emotion and its corresponding confidence level and outputs it.

[0103] For example, when the current multidimensional sensory information detects facial expressions such as frowning and downturned corners of the mouth, and simultaneously physiological indicators show increased heart rate, elevated blood pressure, and changes in temperature and humidity, the model combines these comprehensive signals and calculates the corresponding emotion quantification value through weight allocation and feature matching. For instance, the emotion quantification value can be presented in numerical form, possibly ranging from 0 to 100. Different values ​​represent different emotional states, and the specific numerical division depends on the emotion label dataset used during the training of the emotion quantification model, ensuring the accuracy and objectivity of the emotion quantification results.

[0104] In one embodiment, the current multidimensional sensing information may include physiological parameter data of at least one occupant inside the vehicle, temperature data and humidity data inside the vehicle, and the physiological parameter data may include facial data of at least one occupant inside the vehicle. The steps for determining the emotion quantification value are as follows: Figure 5 As shown, it may include:

[0105] Step 501: Determine the heart rate and blood pressure data of at least one occupant inside the vehicle based on facial data.

[0106] For example, facial data can be facial video data. Non-contact calculation of heart rate and blood pressure based on facial video data is typically based on the principle of remote photoplethysmography (TPM). By analyzing the minute color changes of the facial skin of an occupant in the facial video data as the heartbeat cycle progresses, the pulse wave synchronized with the heartbeat is separated. The periodicity of the pulse wave is analyzed, and the heart rate is estimated using frequency domain or time domain methods. Similarly, for blood pressure data, an estimated blood pressure value can be output based on the pulse wave and a pre-trained blood pressure model. The blood pressure model can be trained based on the pulse wave from the video data and measurements from a standard blood pressure monitor.

[0107] Optionally, heart rate and blood pressure data can also be obtained through wearable smart devices connected to occupants in the vehicle, thereby improving the accuracy of heart rate and blood pressure monitoring.

[0108] Normally, when a person is excited or nervous, their heart rate will increase significantly, while it tends to stabilize when calm or relaxed. Emotional excitement may lead to increased blood pressure, while blood pressure may be low when feeling depressed or tired. Therefore, by acquiring the heart rate and blood pressure data of people in the vehicle, it can be used to help detect the emotional state of the people in the vehicle.

[0109] Step 502: Input facial data, heart rate data, blood pressure data, temperature data, and humidity data into the emotion quantification model to obtain emotion quantification values.

[0110] Facial data can include subtle changes in expression, such as a slight furrowing of the eyebrows, a slight upturn or downturn of the corners of the mouth, the frequency of eye blinking, and the tension of facial muscles. Different temperatures and humidity levels can also affect the mood of occupants. Typically, a preset comfortable temperature and humidity range is established. The temperature range can be a perceived temperature of 22-26 degrees Celsius, and the humidity range can be a relative humidity of 40%-60%. When the temperature and humidity deviate from the preset comfortable range, it may affect the mood of the occupants. Therefore, the emotion quantification model, by integrating facial data, heart rate data, blood pressure data, temperature data, and humidity data, determines numerical values ​​that can quantify different emotional states. These emotional quantification values ​​can intuitively reflect the intensity and type of an individual's emotions, such as the quantified expression of anxiety, pleasure, calmness, and anger.

[0111] For example, an emotion quantification model can be a linear regression model. By establishing an independent weighted linear regression model for each emotion, it can determine the quantification value corresponding to different types of emotions based on input facial data, heart rate data, blood pressure data, temperature data, and humidity data, and finally output the emotion quantification value. Taking an emotion quantification model with three emotion types as an example, representing low / nervous / happy respectively, Ek (k=1,2,3), the quantification value of emotion Ek can be as follows:

[0112] Ek= W k1 *fn(x1)+W k2 *fn(x2)+…+W k3 *fn(xn)+…+b k

[0113] Where fn(#) is the normalization function, and x1, x2, ..., xn are the input features, such as facial data, heart rate data, blood pressure data, temperature data, and humidity data. The normalization function fn normalizes the input features of different dimensions. k =[W k1 ,...,W kn [b] represents the weight vector corresponding to the emotion. k This is the bias value.

[0114] Different emotions can correspond to different weight vectors and bias values, which can be adjusted using historical big data and custom settings. A weighted linear regression model can be used to calculate the quantified value of each emotion. Based on these quantified values, the output of the emotion quantification model is further determined. Optionally, a single emotion value can be obtained by weighting the quantified values ​​of different emotions. For example, E1 represents sadness (0.1), E2 represents tension (0.2), and E3 represents happiness (0.7). By weighting E1, E2, and E3, the emotion quantification model ultimately outputs a single emotion quantification value. The weight values ​​corresponding to the quantified values ​​of different emotions can be set according to actual circumstances; this application does not impose any restrictions on this.

[0115] In the above embodiments, the emotions of the people in the vehicle were quantified based on physiological parameter data, temperature data, and humidity data, which improved the comprehensiveness of the emotion quantification value calculation.

[0116] Step 402: Determine the environmental comfort quantification value based on the emotion quantification value, the current multidimensional perception information, and the preset environmental comfort model.

[0117] The preset environmental comfort model is a normalized weighted summation model established based on extensive user surveys and environmental psychology research. It determines the quantifiable value of environmental comfort by weighted summation of various parameters from the current multidimensional perceptual information, based on quantified emotion values. This quantifiable value is presented as a single numerical value; a higher value indicates a higher level of comfort for the user, thus providing a precise basis for intelligent lighting adjustments and creating a more comfortable environment that meets human needs.

[0118] In one embodiment, the multidimensional sensing information includes light intensity data, temperature data, and humidity data. The step of determining the environmental comfort quantification value may include: performing a weighted fusion calculation on the temperature data, humidity data, light intensity data, and emotion quantification value according to the environmental comfort model to generate the environmental comfort quantification value.

[0119] The algorithm formula for the environmental comfort model can be shown below:

[0120] CI=Wt*fn(T)+Wh* fn(H)+Wl* fn(L)+ We* fn(E)

[0121] Where CI is the quantified value of environmental comfort, fn(#) is the normalization function, T is temperature, H is humidity, L is light intensity, E is the quantified value of mood, and Wt, Wh, Wl, and We are their respective weight values, with Wt+Wh+Wl+We=1. These weight values ​​can be adjusted through historical big data and custom settings. The quantified value of environmental comfort can be calculated from the above environmental comfort model. Optionally, each normalization function can be set with different values ​​according to different data ranges, and this embodiment does not limit this.

[0122] For example, taking light intensity as an example, fn(L) can be a minimum-maximum normalization function. By mapping the minimum value in the light intensity data to 0 and the maximum value to 1, other values ​​in the light intensity can be mapped to the range [0,1] according to the formula, thus achieving normalization of the light intensity. The formula can be as follows:

[0123] x′=[x-min(x)] / [max(x)-min(x)]

[0124] Wherein, min(x) and max(x) are the minimum and maximum values ​​in the light intensity dataset, respectively, x is the original value of the light intensity, and x′ is the normalized light intensity value. The normalization function for other parameters can be the same as that for the light intensity, or it can be another type of normalization function, as long as it can achieve the normalization processing of the dataset. This application embodiment does not impose any restrictions on this.

[0125] The environmental comfort quantification was performed by combining temperature data, humidity data, light intensity data, and emotional quantification values, thus improving the comprehensiveness of the environmental comfort quantification calculation.

[0126] In the above embodiments, by using current perceived information, emotion quantification model, and environmental comfort model, emotion quantification value and environmental comfort quantification value are calculated. By quantifying the emotions of the occupants and the in-vehicle environment, data support is provided for lighting control decisions.

[0127] In the embodiments of this application, such as Figure 6 As shown, the method also includes:

[0128] Step 601: After controlling the interior lights based on the interior light control command, obtain feedback information from the occupants and new multi-dimensional perception information collected by the vehicle's internal sensors.

[0129] After controlling the interior lighting based on in-vehicle lighting control commands, feedback information from occupants is obtained. This feedback can include voice commands to adjust the lights sent by occupants, as well as commands to adjust the lights via the central control screen. Based on this feedback, the intuitive feelings of occupants regarding operations such as light brightness, color temperature, and mode switching can be determined. For example, whether occupants feel comfortable and pleasant about the current ambient lighting color change. Simultaneously, acquiring new multi-dimensional perceptual information in real time from various types of sensors forms the data foundation for optimizing in-vehicle lighting control.

[0130] Step 602: Optimize the model parameters of the environmental comfort model based on feedback information and new multidimensional perception information, and / or optimize the model parameters of the decision model based on feedback information and new multidimensional perception information.

[0131] For example, the weight parameters of each input parameter of the environmental comfort model are optimized based on feedback information and new multidimensional perception information; and / or, the weight parameters of each input parameter of the decision model are optimized based on feedback information and new multidimensional perception information.

[0132] Feedback information and new multi-dimensional sensory information are combined into a set of data to form a learnable set of experience data. This experience data is analyzed, and the corresponding in-vehicle lighting control commands are scored to determine reward values. For example, if the execution of the in-vehicle lighting control command increases the emotional quantification value of the occupants, or the feedback information indicates that the user did not manually adjust the lights; conversely, if the execution of the in-vehicle lighting control command decreases the emotional quantification value of the occupants, or the feedback information indicates that the user manually adjusted the lights, a low reward or even a penalty is given. The level of reward indicates the quality of the generated in-vehicle lighting control commands. After a period of time, the collected experience data and the corresponding reward values ​​are aggregated to obtain a training sample (feedback information, multi-dimensional sensory information, reward value). This training sample can be used to optimize the environmental comfort model. For example, using reinforcement learning algorithms, the environmental comfort model updates the weight values ​​corresponding to each input parameter by repeatedly learning from these training samples.

[0133] Based on feedback information and new multi-dimensional perception information, the model parameters of the decision-making model are optimized. As in the above embodiment, the model parameters of the decision-making model are optimized based on the obtained training samples. By learning from the training samples, the decision-making model updates the weight values ​​of each input parameter, thereby enabling the in-vehicle lighting control command to receive a higher reward value.

[0134] The optimized environmental comfort model or decision model can be rigorously tested in a simulation environment containing a large number of historical scenarios to ensure that the performance of the optimized environmental comfort model or decision model is better than the old version and that it is safe and reliable, and then it can be deployed online.

[0135] In the above embodiments, by acquiring feedback information after the execution of in-vehicle lighting control commands and new multi-dimensional perception information, the environmental comfort model and decision-making model are optimized to improve the accuracy of the environmental comfort model and decision-making model, thereby improving the accuracy of in-vehicle lighting control command generation and improving the lighting experience of in-vehicle occupants.

[0136] In one embodiment, a preset decision model is used to analyze the quantitative values ​​of the emotions and environmental comfort of at least one occupant inside the vehicle, and generate in-vehicle lighting control commands, such as... Figure 7 As shown, it includes:

[0137] Step 701: Input the quantified value of emotion and the quantified value of environmental comfort into the decision model to determine the target control mode based on the quantified value of emotion and the quantified value of environmental comfort.

[0138] The quantified emotion value and quantified environmental comfort value calculated in the above embodiments are input into the decision model. The decision model can be a weighted fusion model, which performs weighted calculations based on the quantified emotion value, the quantified environmental comfort value, and their respective weight values ​​to determine the target control mode. Alternatively, the decision model can be a pre-set normal distribution curve, using the quantified emotion value and the quantified environmental comfort value as the x-axis and y-axis, respectively. The normal distribution curve can determine the target area. Since the area formed by different x-axis and y-axis coordinates corresponds to a control mode, the corresponding target control mode is determined based on the target area.

[0139] Step 702: Determine the in-vehicle lighting control command that matches the target control mode based on the target control mode and the preset mapping table.

[0140] The mapping table includes the correspondence between multiple control modes and in-vehicle lighting control commands. Optionally, the mapping table can be pre-configured with suitable in-vehicle lighting control commands for different control modes. After determining the target control mode, the mapping table can be queried to determine the in-vehicle lighting control commands that are compatible with the target control mode.

[0141] Optionally, when the light intensity data indicates a significant change in interior light intensity, such as when entering a tunnel or at nightfall, the control mode can be set to tunnel or night mode. The interior lighting control command can increase the brightness of the interior lights and set a comfortable nighttime spectrum value to avoid visual stimulation or blind spots caused by sudden changes in light, helping the driver's vision transition smoothly and maintaining optimal pupillary function at night. When the emotion quantification value indicates that the driver is fatigued, the control mode can be set to an enhanced attention mode. The interior lighting control command can increase the brightness of the interior lights and set a high color temperature spectrum value to make the driver more alert. Alternatively, when a high level of driver tension is detected, the interior lighting control command can adjust the color temperature of the interior lights to a softer, warmer yellow and appropriately increase the brightness to alleviate the driver's tension. If the current temperature is detected to be high, the interior lighting control command can reduce the light brightness to reduce heat generation and switch to a cooler light tone to create a cooling effect. Alternatively, the control mode could be a human-based circadian rhythm adjustment mode, which simulates high color temperature and high brightness morning light to suppress melatonin and make the people in the car more awake, based on the current time. At night, it gradually transitions to low color temperature and low illuminance warm yellow light to promote melatonin secretion and prepare the non-drivers in the car to rest.

[0142] It is understandable that, for different scenario needs, such as night driving, long-distance driving or leisure mode, the decision model will preset different control modes and correspondences with in-vehicle lighting control commands to ensure that the generated in-vehicle lighting control commands can accurately respond to the emotional changes and environmental needs of the occupants. The correspondence can be set according to the actual control situation, and this application embodiment does not limit it.

[0143] In the above embodiments, the decision model generates in-vehicle lighting control commands through emotion quantification and environmental comfort quantification, enabling in-vehicle lighting control to adaptively adjust according to the emotions of the occupants and the environment, thereby improving the intelligence and interactive experience of lighting control.

[0144] In one embodiment, the interior lights are controlled based on interior lighting control commands, such as... Figure 8 As shown, it includes:

[0145] Step 801: Determine the spectral control strategy based on the in-vehicle lighting control command.

[0146] To achieve more flexible lighting control, the lights inside the vehicle can be selected as full-spectrum LED lights. Full-spectrum LED lights typically use a violet light chip to excite a variety of phosphors with special ratios, such as blue, cyan, green, and red phosphors, instead of traditional blue light chips. This avoids the problem of excessively high harmful blue light peaks from the light source perspective and completes the important short-wave and long-wave spectrum of sunlight, making the spectrum as close as possible to sunlight.

[0147] The lighting control command can be a sequence containing multiple control quadruples. Each control quadruple corresponds to the spectral modulation strategy of a light-emitting diode lamp. Each control quadruple includes a switch signal, brightness value, color temperature value, and duration.

[0148] Different spectral control strategies correspond to different control needs of in-vehicle lighting. For example, some strategies aim to simulate natural light to enhance driver alertness, while others seek to create a warm and comfortable ambient light to relax occupants. Still others adjust the lighting for specific scenarios such as nighttime driving or reading mode, or link it to different holidays or occasions. Finally, some strategies detect abnormalities among occupants and provide gentle yet effective alerts by adjusting brightness or switching to flashing lights. Different spectral parameters correspond to different scenarios, such as a warm-toned spectrum (color temperature 2700K-3000K) to simulate sunrise and sunset, a neutral spectrum (color temperature 5000K-6500K) to simulate midday sunlight, and a soft spectrum (color temperature 3000K-4000K) to simulate twilight.

[0149] Step 802: By using a spectral modulation strategy, the light drive circuit is driven to control the spectrum and illuminance of the in-vehicle lights.

[0150] After generating the spectral control strategy, the corresponding pulse width modulation signal is determined, and the pulse width adjustment signal is sent to the lighting drive circuit. The lighting drive circuit then controls the switching, spectrum, and illuminance of the interior lights. This allows for dynamic adjustment of the spectral composition and brightness of the lights according to different usage scenarios and needs, such as driving mode, occupant rest mode, or atmosphere creation mode.

[0151] In the above embodiments, the light driving circuit is controlled by a spectral modulation strategy to control the spectrum and illuminance of the light, thereby meeting the lighting control needs in different scenarios and improving the comfort of in-vehicle lighting. At the same time, in scenarios where strong lighting is not required, controlling the light to be partially turned off or the illuminance to be reduced can also effectively reduce energy consumption and extend the service life of the in-vehicle LEDs.

[0152] In the embodiments of this application, lighting control through spectral modulation strategies includes various methods.

[0153] In the first method, if the spectral control strategy is a wake-up control strategy, the light driving circuit is driven to increase the color temperature and illuminance of the interior lights and adjust the wavelength of the interior lights to the first wavelength.

[0154] Different spectral modulation strategies can correspond to different light adjustment methods. For example, if the spectral modulation strategy is a wake-up modulation strategy, the color temperature and illuminance of the in-vehicle lights are increased, and the wavelength of the in-vehicle lights is adjusted to the first wavelength to simulate high color temperature and high brightness morning light to suppress melatonin and wake people up. The first wavelength can be short wavelength blue light.

[0155] The second approach involves using a rest-control strategy to drive the light drive circuit, reducing the color temperature and illuminance of the interior lights, and adjusting the wavelength of the interior lights to a second wavelength that is greater than the first wavelength.

[0156] If the spectral control strategy is a rest control strategy, then the people in the car may stop driving and need to rest in the car. In this case, the color temperature and illuminance of the car interior lights are reduced, and the wavelength of the car interior lights is adjusted to the second wavelength to achieve warm yellow light with low color temperature and low illuminance, which promotes melatonin secretion and prepares for sleep. The second wavelength can be long-wavelength red light.

[0157] In the above embodiments, different preset spectral control strategies are used to achieve human-centered adjustment of the vehicle's interior lighting.

[0158] In the embodiments of this application, such as Figure 9 As shown, a method for controlling in-vehicle lighting is provided, including:

[0159] Step 901: In response to the in-vehicle lighting control request, obtain the current multi-dimensional perception information inside the vehicle.

[0160] Step 902: Determine the heart rate and blood pressure data of at least one occupant inside the vehicle based on facial data.

[0161] Step 903: Input facial data, heart rate data, blood pressure data, temperature data, and humidity data into the emotion quantification model to obtain emotion quantification values.

[0162] Step 904: Based on the environmental comfort model, perform weighted fusion calculation on temperature data, humidity data, light intensity data, and emotional quantification values ​​to generate environmental comfort quantification values.

[0163] Step 905: Input the quantified value of emotion and the quantified value of environmental comfort into the decision model to determine the target control mode based on the quantified value of emotion and the quantified value of environmental comfort.

[0164] Step 906: Determine the in-vehicle lighting control command that matches the target control mode based on the target control mode and the preset mapping table.

[0165] Step 907: Determine the spectral control strategy based on the in-vehicle lighting control command.

[0166] Step 908: The light drive circuit is driven by a spectral modulation strategy to control the spectrum and illuminance of the in-vehicle lights.

[0167] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0168] Based on the same inventive concept, this application also provides an interior lighting control device for implementing the aforementioned interior lighting control method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more interior lighting control device embodiments provided below can be found in the limitations of the interior lighting control method described above, and will not be repeated here.

[0169] In one exemplary embodiment, such as Figure 10 As shown, an in-vehicle lighting control device 1000 is provided, including: an acquisition module 1001, a determination module 1002, an instruction generation module 1003, and a control module 1004, wherein:

[0170] The acquisition module 1001 is used to acquire current multi-dimensional perception information collected by various types of sensors pre-installed inside the vehicle in response to the in-vehicle lighting control request.

[0171] The determination module 1002 is used to determine the quantification value of the emotion and the quantification value of the environmental comfort of at least one occupant inside the vehicle based on the current multidimensional perception information.

[0172] The instruction generation module 1003 is used to perform decision analysis on the quantitative values ​​of the emotions and environmental comfort of at least one person inside the vehicle through a preset decision model, and generate in-vehicle lighting control instructions.

[0173] The control module 1004 is used to control the interior lights based on the interior light control commands.

[0174] In one embodiment, the various types of sensors include a vision sensor, an illuminance sensor, and a temperature and humidity sensor; the current multidimensional sensing information includes physiological parameter data of at least one occupant inside the vehicle, light intensity data, temperature data, and humidity data inside the vehicle; the acquisition module 1001 is specifically used to acquire the physiological parameter data collected by the vision sensor; acquire the light intensity data collected by the illuminance sensor; and acquire the temperature and humidity data collected by the temperature and humidity sensor.

[0175] In one embodiment, the determining module 1002 is specifically used to determine an emotion quantification value based on the current multidimensional perception information and a preset emotion quantification model; and to determine an environmental comfort quantification value based on the emotion quantification value, the current multidimensional perception information and a preset environmental comfort model.

[0176] In one embodiment, the current multidimensional sensing information includes physiological parameter data of at least one occupant inside the vehicle, temperature data and humidity data inside the vehicle, and the physiological parameter data includes facial data of at least one occupant inside the vehicle; the determining module 1002 is specifically used to determine the heart rate data and blood pressure data of at least one occupant inside the vehicle based on the facial data; the facial data, heart rate data, blood pressure data, temperature data and humidity data are input into the emotion quantification model to obtain the emotion quantification value.

[0177] In one embodiment, the multidimensional sensing information includes light intensity data, temperature data, and humidity data. The determining module 1002 is specifically used to generate an environmental comfort quantification value by performing a weighted fusion calculation based on the temperature data, humidity data, light intensity data, and emotion quantification value according to the environmental comfort model.

[0178] In one embodiment, the device further includes an optimization module, which, after controlling the interior lights based on the interior light control command, acquires feedback information from occupants and new multi-dimensional perception information collected by sensors inside the vehicle; and optimizes the environmental comfort model and decision model based on the feedback information and the new multi-dimensional perception information.

[0179] In one embodiment, the instruction generation module 1003 is specifically used to input the emotion quantification value and the environmental comfort quantification value into the decision model to determine the target control mode based on the emotion quantification value and the environmental comfort quantification value; and to determine the in-vehicle lighting control instruction that is compatible with the target control mode based on the target control mode and a preset mapping relationship table, wherein the mapping relationship table includes multiple sets of correspondences between control modes and in-vehicle lighting control instructions.

[0180] In one embodiment, the control module 1004 is specifically used to determine a spectral modulation strategy based on the in-vehicle lighting control command; and to drive the lighting drive circuit through the spectral modulation strategy to control the spectrum and illuminance of the in-vehicle lighting.

[0181] The modules in the aforementioned in-vehicle lighting control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0182] In one exemplary embodiment, a lighting controller is provided, the internal structure of which can be shown in the following diagram. Figure 11 As shown, the lighting controller includes a processor and a memory. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium storing a computer program. When executed by the processor, the computer program implements an in-vehicle lighting control method.

[0183] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device (lighting controller) to which the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0184] In one embodiment, this application also provides a lighting control device, such as... Figure 12 As shown, the lighting control device includes a lighting controller, a sensor module, and an LED lamp module; the sensor module and the LED lamp module are connected to the lighting controller; the lighting controller is connected to the vehicle controller; the lighting controller is used to implement the steps of the method described in any one of the above method embodiments.

[0185] For example, the lighting controller is connected to the vehicle controller via a controller area network bus; the lighting controller is connected to the sensor module via a serial peripheral interface.

[0186] like Figure 12As shown, the lighting controller connects to the vehicle controller via the Controller Area Network (CAN) bus and to the sensor modules via the Serial Peripheral Interface (SPI). LIN-1 to LIN-6 are LED lights, and UART-CAN1 and UART-CAN2 are LED lights of different types. LDO-5V and LDO-3V3 are power supply ports, and flash memory is the storage unit. When a system upgrade is required, only the lighting controller needs to be upgraded. Figure 13 The diagram shows the structure of the sensor module. The integrated circuit bus multiplexer 2-to-1 module is used to select the input sensor signal or the user's voice signal. When the user inputs voice, the user's voice signal is transmitted to the lighting controller, and the lighting is controlled according to the user's voice signal. When the user does not input voice, the multi-dimensional perception information collected by the sensor is sent to the lighting controller, so that the lighting control command is generated through the lighting control method of the lighting controller, and the interior lights are controlled.

[0187] In one embodiment, this application also provides a vehicle, including Figure 12 The lighting control device described herein.

[0188] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0189] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0190] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0191] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0192] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0193] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for controlling in-vehicle lighting, characterized in that, Applied to a lighting controller, the method includes: In response to a request to control the in-vehicle lighting, the system acquires current multi-dimensional sensing information about the vehicle interior, including physiological parameter data of at least one occupant inside the vehicle, as well as light intensity data, temperature data, and humidity data inside the vehicle. Based on the current multidimensional perception information, at least one quantified value of the emotion of the person in the vehicle and a quantified value of the environmental comfort are determined. The system uses a pre-defined decision model to analyze the emotional and environmental comfort values ​​of at least one occupant inside the vehicle and generates in-vehicle lighting control commands. The interior lights are controlled based on the interior lighting control commands.

2. The method according to claim 1, characterized in that, The step of determining the quantified values ​​of the emotions and environmental comfort of at least one occupant inside the vehicle based on the current multidimensional perception information includes: Based on the current multidimensional perception information and the preset emotion quantification model, the emotion quantification value is determined; Based on the emotion quantification value, the current multidimensional perception information, and the preset environmental comfort model, the environmental comfort quantification value is determined.

3. The method according to claim 2, characterized in that, The physiological parameter data includes facial data of at least one occupant inside the vehicle; determining the emotion quantification value based on the current multidimensional perception information and a preset emotion quantification model includes: Based on the facial data, determine the heart rate and blood pressure data of at least one occupant inside the vehicle; The facial data, heart rate data, blood pressure data, temperature data, and humidity data are input into the emotion quantification model to obtain the emotion quantification value.

4. The method according to claim 2, characterized in that, The process of determining the environmental comfort quantification value based on the emotion quantification value, the current multidimensional perception information, and the preset environmental comfort model includes: The environmental comfort quantification is generated by weighting and fusing the temperature data, humidity data, light intensity data, and emotion quantification value according to the environmental comfort model.

5. The method according to claim 2, characterized in that, The method further includes: When the vehicle interior lights are controlled based on the vehicle interior light control command, feedback information from the occupants and new multi-dimensional perception information collected by the vehicle interior sensors are obtained. Based on the feedback information and the new multidimensional perception information, the model parameters of the environmental comfort model are optimized; And / or, based on the feedback information and the new multidimensional perception information, the model parameters of the decision model are optimized.

6. The method according to claim 5, characterized in that, The environmental comfort model is an adaptive weighted fusion model, the decision model is an adaptive weighted fusion model, and the method further includes: Based on the feedback information and the new multidimensional perception information, the weight parameters of each input parameter of the environmental comfort model are optimized. And / or, based on the feedback information and the new multidimensional perception information, optimize the weight parameters of each input parameter of the decision model.

7. The method according to any one of claims 1 or 2, characterized in that, The step involves using a preset decision model to analyze the quantified emotional values ​​and environmental comfort values ​​of at least one occupant inside the vehicle, and generating in-vehicle lighting control commands, including: The quantified emotion value and the quantified environmental comfort value are input into the decision model to determine the target control mode based on the quantified emotion value and the quantified environmental comfort value. Based on the target control mode and a preset mapping table, determine the in-vehicle lighting control command that is compatible with the target control mode. The mapping table includes multiple sets of correspondences between control modes and in-vehicle lighting control commands.

8. The method according to claim 1 or 2, characterized in that, The control of the interior lights based on the interior light control command includes: The spectral modulation strategy is determined based on the in-vehicle lighting control command. The spectral modulation strategy is used to drive the lighting drive circuit, thereby controlling the spectrum and illuminance of the in-vehicle lights.

9. The method according to claim 8, characterized in that, The step of controlling the spectrum and illuminance of the vehicle interior lights by driving the light driving circuit through the spectral modulation strategy includes: If the spectral modulation strategy is a wake-up modulation strategy, the light driving circuit is driven to increase the color temperature and illuminance of the interior lights and adjust the wavelength of the interior lights to the first wavelength. If the spectral control strategy is a rest control strategy, the light driving circuit is driven to reduce the color temperature and illuminance of the interior lights and adjust the wavelength of the interior lights to a second wavelength, which is greater than the first wavelength.

10. A lighting control device, characterized in that, The lighting control device includes a lighting controller, a sensor module, and an LED lamp module; the sensor module and the LED lamp module are connected to the lighting controller; the lighting controller is connected to the vehicle controller. The lighting controller is used to implement the steps of the method according to any one of claims 1 to 9.

Images