Vehicle light control method, device, system, vehicle, equipment, medium and product

Abstract

The application relates to a vehicle lamp control method, device, system, vehicle, equipment, medium and product. The method comprises the following steps: in the case that it is determined that a user in a target vehicle has a get-off intention, acquiring multi-source data, wherein the multi-source data comprises vehicle external environment illumination data, vehicle position data and user trajectory data; inputting the multi-source data into a pre-trained scene recognition model to obtain a target behavior scene after the user gets off; wherein the target behavior scene comprises a night home-coming scene and a non-night home-coming scene; determining a target lighting control strategy corresponding to the target behavior scene based on the target behavior scene; and controlling a vehicle lamp of the target vehicle according to the target lighting control strategy. The method can improve the activation accuracy of the accompany-me-home function.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, device, system, vehicle, equipment, medium, and product for controlling vehicle lights. Background Technology

[0002] Currently, the "Follow Me Home" function is an important feature in the field of automotive intelligence that enhances the user's experience when leaving the car at night. The core function is that after the user turns off the engine and gets out of the car, the vehicle's headlights can be turned off for a period of time to illuminate the way home for the user.

[0003] In related technologies, the "Follow Me Home" function is activated (i.e., the vehicle's headlights are turned on) as soon as the user gets out of the car, resulting in a low accuracy rate for the function's activation and a poor user experience. Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle light control method, device, computer equipment, storage medium, and program product that can improve the activation accuracy of the "Follow Me Home" function in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides a vehicle lighting control method, including:

[0006] When it is determined that the user in the target vehicle intends to leave the vehicle, multi-source data is acquired, including external ambient light data, vehicle location data, and user trajectory data.

[0007] The multi-source data is input into a pre-trained scene recognition model to obtain the target behavior scene after the user gets off the vehicle; wherein, the target behavior scene includes nighttime homecoming scene and non-nighttime homecoming scene;

[0008] Based on the target behavior scenario, determine the target lighting control strategy corresponding to the target behavior scenario;

[0009] The headlights of the target vehicle are controlled according to the target lighting control strategy.

[0010] In one embodiment, the method further includes: determining that the user intends to leave the vehicle when the target vehicle is detected to be in a turned-off state and the user's seat belt is unfastened; and determining that the user does not intend to leave the vehicle when the target vehicle is detected to be in a ignition state or the user's seat belt is unfastened.

[0011] In one embodiment, the target lighting control strategy includes lighting duration, and determining the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario includes: when the target behavior scenario is the nighttime homecoming scenario, determining the lighting duration corresponding to the nighttime homecoming scenario based on the vehicle location data and the preset home address.

[0012] In one embodiment, determining the lighting duration corresponding to the nighttime homecoming scenario based on the vehicle location data and a preset home address includes: determining the walking distance between the target vehicle and the home address based on the vehicle location data and the preset home address; determining the walking time based on the walking distance; and determining the lighting duration corresponding to the nighttime homecoming scenario based on the walking time and a preset safety factor.

[0013] In one embodiment, determining the lighting duration corresponding to the nighttime homecoming scenario based on the vehicle location data and the preset home address includes: determining the lighting duration corresponding to the nighttime homecoming scenario based on weather information, the vehicle location data, and the home address.

[0014] In one embodiment, the target lighting control strategy includes a light projection angle and a light projection area. The step of determining the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario includes: when the target behavior scenario is the nighttime homecoming scenario, determining the light projection angle corresponding to the nighttime homecoming scenario based on the angle between the user's travel direction and the vehicle's centerline; and determining the light projection area corresponding to the nighttime homecoming scenario based on the travel direction.

[0015] In one embodiment, the method further includes: when it is determined that the target behavior scenario is the nighttime homecoming scenario and there are obstacles in the user's travel path, controlling the vehicle lights to perform a preset warning action, and / or controlling the target vehicle to output voice prompt information.

[0016] In one embodiment, the non-nighttime homecoming scenario includes a nighttime temporary drop-off scenario, and the target lighting control strategy includes lighting duration; determining the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario includes: when the target behavior scenario is the nighttime temporary drop-off scenario, determining a preset duration as the lighting duration corresponding to the nighttime temporary drop-off scenario.

[0017] In one embodiment, the step of acquiring multi-source data when it is determined that the user in the target vehicle intends to leave the vehicle includes: acquiring the multi-source data when it is determined that the user in the target vehicle intends to leave the vehicle and the current time is within a preset time period.

[0018] Secondly, this application also provides a vehicle lighting control device, comprising:

[0019] The data acquisition module is used to acquire multi-source data when it is determined that the user in the target vehicle intends to leave the vehicle. The multi-source data includes external ambient light data, vehicle location data, and user trajectory data.

[0020] The data input module is used to input the multi-source data into a pre-trained scene recognition model to obtain the target behavior scene after the user gets off the vehicle; wherein, the target behavior scene includes a nighttime homecoming scene and a non-nighttime homecoming scene.

[0021] The strategy determination module is used to determine the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario;

[0022] The vehicle lighting control module is used to control the vehicle lights of the target vehicle according to the target lighting control strategy.

[0023] Thirdly, this application also provides a vehicle lighting control system, the system comprising: a multi-source sensing module for collecting multi-source data; and an on-board controller for executing the vehicle lighting control method provided in the first aspect of this application.

[0024] Fourthly, this application also provides a vehicle including the vehicle lighting control system provided in the third aspect of this application.

[0025] Fifthly, this application also provides an in-vehicle device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the vehicle light control method provided in the first aspect of this application.

[0026] Sixthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle light control method provided in the first aspect of this application.

[0027] In a seventh aspect, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the vehicle lighting control method provided in the first aspect of this application.

[0028] The aforementioned vehicle headlight control method, device, system, vehicle, in-vehicle equipment, computer-readable storage medium, and computer program product, upon determining that a user in the target vehicle intends to leave the vehicle, acquires multi-source data, including external ambient illuminance data, vehicle position data, and user trajectory data; inputs the multi-source data into a pre-trained scene recognition model to obtain the target behavior scene after the user gets out of the vehicle; wherein, the target behavior scene includes nighttime homecoming scenarios and non-nighttime homecoming scenarios; based on the target behavior scene, determines the target lighting control strategy corresponding to the target behavior scene; and controls the headlights of the target vehicle according to the target lighting control strategy. It can be seen that, in this embodiment, when the user intends to leave the vehicle, multi-source data perception, scene recognition, and determination of the target lighting control strategy based on the identified target behavior scene are performed sequentially. This allows the lighting control strategy to adapt to the user's actual behavior scene after leaving the vehicle, avoiding the false triggering problem caused by turning on the headlights immediately upon detecting the user getting out of the vehicle. This improves the accuracy of headlight control and the accuracy of activating the "Follow Me Home" function, thereby improving the user experience. Furthermore, multi-source data can comprehensively and accurately reflect the characteristics of the current scene, thus improving the accuracy of scene recognition. Attached Figure Description

[0029] 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.

[0030] Figure 1 This is an application environment diagram of the vehicle lighting control method in one embodiment;

[0031] Figure 2 This is a flowchart illustrating a vehicle headlight control method in one embodiment;

[0032] Figure 3 This is a flowchart illustrating the headlight control method in another embodiment;

[0033] Figure 4 This is a diagram illustrating location, user behavior, and vehicle status in an example.

[0034] Figure 5 This is a structural block diagram of a vehicle lighting control device in one embodiment;

[0035] Figure 6 This is an internal structure diagram of the vehicle-mounted device in one embodiment. Detailed Implementation

[0036] 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.

[0037] 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.

[0038] In related technologies, when a user in a target vehicle turns off the engine, the vehicle controller detects that the vehicle's ignition is off and simultaneously detects a door opening signal. At this time, if the user has previously triggered the "Follow Me Home" function or if the function is enabled by default, the vehicle controller will turn on the vehicle's headlights and start a timing module. Once the preset time (e.g., 30 seconds, 60 seconds) is reached, the headlights will turn off.

[0039] After in-depth analysis, the relevant technical solutions have the following two problems:

[0040] (1) Inability to identify whether the "Follow Me Home" function truly needs to be activated: The system cannot identify whether the current environment truly requires lighting. Even in broad daylight or in scenarios with bright streetlights, the system will still perform lighting operations, resulting in unnecessary power consumption. In addition, once the system detects that the user has gotten out of the car, it will activate the "Follow Me Home" function (i.e., turn on the vehicle's headlights). It cannot distinguish whether the user is temporarily getting out of the car (e.g., picking up a package), retrieving something from the trunk, or actually leaving the car to go home. This one-size-fits-all triggering logic leads to low accuracy in function activation and a poor user experience.

[0041] (2) Fixed and singular lighting path: The headlights can only illuminate the area directly in front of the vehicle and cannot be dynamically adjusted according to the user's actual walking path. When the user needs to walk to the side or rear of the vehicle or needs to turn into the building, the fixed-angle lighting often cannot provide effective path guidance.

[0042] To address the aforementioned issues, this application provides a vehicle lighting control method that enables the vehicle lighting control system to intelligently perceive the environment, autonomously determine whether the lighting function needs to be activated to avoid unnecessary energy consumption, identify the user's intention to leave the vehicle and their post-departure behavior (such as returning home or temporarily getting out of the vehicle), accurately activate the "follow me home" function, and dynamically match the lighting direction with the user's walking path to provide truly effective path guidance for the user.

[0043] The vehicle light control method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown is as follows. The target vehicle includes a vehicle lighting control system and vehicle lights. The vehicle lighting control system includes a multi-source sensing module 101 and an on-board controller 102. The multi-source sensing module 101 and the on-board controller 102 communicate via a network. The multi-source sensing module 101 is used to collect multi-source data, specifically including external ambient light data, vehicle position data, and user trajectory data; the on-board controller 102 is used to execute the vehicle lighting control method.

[0044] The multi-source perception module 101 belongs to the target vehicle itself or existing sensor components, including the following six sensor components:

[0045] Ambient light sensor: Installed inside the vehicle's windshield to detect external ambient light levels. The sensor output range is 0-65535 Lux, with an accuracy of ±5%. The system has a preset illuminance threshold of 10 Lux; when the detected value is below the threshold, it is determined to be a low-light environment.

[0046] Vehicle positioning module: Employs a GPS / BeiDou dual-mode positioning chip, combined with an inertial measurement unit (IMU) to achieve high-precision positioning. Positioning accuracy can reach the centimeter level, used to determine the positional relationship between the vehicle's current location and a preset "home".

[0047] In-vehicle cameras: These include Driver Monitoring System (DMS) cameras and Occupant Monitoring System (OMS) cameras, which are used to monitor the driver's status and behavior and identify the status and behavior of passengers in the vehicle, such as unfastening seat belts, opening doors, and getting out of the vehicle.

[0048] Exterior cameras: The system uses an Around View Monitoring (AVM) system, consisting of four wide-angle cameras installed at the front, rear, left, and right of the vehicle to identify the characteristics of the surrounding environment, such as road type, presence of streetlights, and presence of obstacles.

[0049] Millimeter-wave radar: Installed on the front and rear bumpers of the vehicle, it is used to accurately detect the user's movement trajectory and speed after leaving the vehicle, as well as to identify obstacles in the travel path.

[0050] Bluetooth / Ultra-Wideband (UWB) positioning unit: By detecting the signal strength of the Bluetooth key or smart terminal carried by the user or UWB ranging data, it can achieve accurate positioning of the user relative to the vehicle with a positioning accuracy of up to decimeter level, and has high-precision ranging capabilities.

[0051] The vehicle controller 102 obtains raw data from the multi-source sensing module 101, performs time synchronization, coordinate transformation and data format standardization, and controls the vehicle lights based on the multi-source sensing data, including lighting control under the Follow Me Home function.

[0052] In one exemplary embodiment, such as Figure 2 As shown, a vehicle lighting control method is provided, which is applied to... Figure 1 The following steps are used as an example to illustrate the process of using the vehicle controller 102, including steps 201 to 203. Wherein:

[0053] Step 201: If it is determined that the user in the target vehicle intends to leave the vehicle, acquire multi-source data, including external ambient light data, vehicle location data, and user trajectory data.

[0054] In this context, "user in the target vehicle" refers to any occupant inside the vehicle (such as the driver or a passenger). The vehicle lighting control method of this application is applicable to any occupant inside the target vehicle.

[0055] For example, when the vehicle controller 102 detects that the target vehicle is stationary, it determines whether the user intends to leave the vehicle based on the data collected by the in-vehicle camera. If so, the vehicle controller 102 obtains ambient light data from the ambient light sensor, vehicle position data from the vehicle positioning module, and user trajectory data from the millimeter-wave radar and / or the external camera.

[0056] In one possible implementation, if multiple users are determined to have the intention to leave the vehicle at the same time, multi-source data is acquired for each user. This multi-source data includes ambient light data outside the vehicle, vehicle location data, and user trajectory data. If the multi-source data of multiple users are the same or match (indicating that multiple users are going to the same destination), subsequent control procedures can be performed based on one set of multi-source data. If the multi-source data of multiple users are different or do not match (indicating that multiple users are going to different destinations), subsequent control procedures need to be performed based on a set of multi-source data for each user. Here, "different or mismatched multi-source data" generally refers to "different or mismatched user trajectory data."

[0057] Step 202: Input multi-source data into a pre-trained scene recognition model to obtain the target behavior scene after the user gets off the vehicle; wherein, the target behavior scene includes nighttime homecoming scene and non-nighttime homecoming scene.

[0058] The scene recognition model is pre-trained on a large number of multi-source data samples with real-world scene labels, achieving an accuracy of over 95%. The input to the scene recognition model is multi-source data, and the output is the user's behavioral scene and confidence level after getting out of the vehicle, corresponding to that multi-source data. Behavioral scenes include nighttime homecoming scenarios and non-nighttime homecoming scenarios (including temporary nighttime and daytime alighting scenarios). Temporary nighttime alighting scenarios include retrieving items from the trunk. Optionally, the scene recognition model is built based on deep learning neural networks or machine learning algorithms, such as Transformer architecture, random forest, and Support Vector Machine (SVM).

[0059] For example, firstly, the vehicle controller 102 preprocesses the acquired raw multi-source data, such as performing time synchronization, coordinate transformation, and data format standardization. It then uses a Kalman filter algorithm to fuse GPS data and IMU data acquired from the vehicle positioning module, improving positioning accuracy and reliability. Next, the vehicle controller 102 inputs the preprocessed multi-source data into a scene recognition model. The scene recognition model performs fusion analysis on the input multi-source data, outputting each behavioral scene and its confidence level, and identifying the behavioral scene with the highest confidence level as the target behavioral scene.

[0060] Optionally, the vehicle controller 102 continuously records the user's departure time (such as the moment the engine is turned off) and the corresponding behavioral scenario over a long period of time. After accumulating data multiple times, it uses machine learning algorithms to train the data and generate a scene recognition model. This model can predict the user's current departure behavior scenario based on the current departure time.

[0061] In one possible implementation, besides using a scene recognition model, the activation of the lighting function (i.e., whether to further determine the target lighting control strategy) can be determined based on external ambient illuminance data and vehicle location data. Specifically, if the external ambient illuminance data is greater than or equal to a preset illuminance, it is determined that the current situation is daytime (not a dark environment), and the lighting control strategy generation step is not triggered; if the external ambient illuminance data is less than the preset illuminance, and the current location of the target vehicle is less than or equal to a preset home address, it is determined to be a nighttime homecoming scenario, triggering the lighting control strategy generation step and activating the "Follow Me Home" function; if the parking space ambient illuminance data is less than the preset illuminance, and the current location of the target vehicle is greater than the preset home address, it is determined to be a normal nighttime getting out of the car scenario, triggering the lighting control strategy generation step but not activating the "Follow Me Home" function, and activating the lighting according to the default lighting strategy.

[0062] The preset illuminance and preset distance are set and stored in advance based on actual needs and historical experience. The preset illuminance can be 10 Lux and the preset distance can be about 50 meters.

[0063] Step 203: Based on the target behavior scenario, determine the target lighting control strategy corresponding to the target behavior scenario.

[0064] The target lighting control strategy includes parameter types and target values ​​for the parameters. The target lighting control strategy includes at least one of the following: lighting duration, light projection angle, light projection area, and light brightness level.

[0065] For example, after obtaining the target behavior scenario, the vehicle controller 102 generates a target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario and a preset rule base. The preset rule base includes a mapping relationship between preset behavior scenarios and the parameter types and calculation methods (or preset values ​​of parameters) of the preset lighting control strategies. Different preset behavior scenarios correspond to different preset lighting control strategies.

[0066] Optionally, the vehicle controller 102 queries the target parameter type and target parameter calculation method of the target lighting control strategy corresponding to the target behavior scenario from the preset rule base, and then calculates the target value of the target parameter according to the target parameter type and target parameter calculation method, so as to obtain the target lighting control strategy.

[0067] Optionally, the vehicle controller 102 can obtain the target lighting control strategy by querying the target parameter type and target value of the target lighting control strategy corresponding to the target behavior scenario from the preset rule base.

[0068] Step 204: Control the headlights of the target vehicle according to the target lighting control strategy.

[0069] The headlights include Adaptive Driving Beam (ADB), a headlight system that automatically adjusts the beam shape and direction according to road conditions. ADB headlights utilize Micro LED or Digital Light Processing (DLP) technology. Each headlight contains dozens to hundreds of independently controllable pixel units, each of which can be independently controlled for switching and brightness, achieving precise beam zoning control. The headlights can rotate horizontally by ±15° and vertically by ±5°.

[0070] For example, after obtaining the target lighting control strategy, the vehicle controller 102 generates control instructions according to the target lighting control strategy. The control instructions are used to instruct the control of the headlights of the target vehicle and send the control instructions to the execution module. After receiving the control instructions, the execution module controls the matrix ADB headlights of the target vehicle according to the control instructions.

[0071] Optionally, the vehicle controller 102 can be a vehicle domain controller, and the execution modules include a body control module (BCM), a headlight controller, matrix ADB headlights, and cornering lights (side auxiliary lights). The vehicle domain controller sends control commands to the body control module. The BCM communicates with the headlight controller via a CAN bus or Ethernet to realize functions such as switching the lights on and off, adjusting brightness, and adjusting angle. It can also send control commands to the cornering light controller to assist in illuminating the side areas of the vehicle through the cornering lights, thereby expanding the lighting coverage.

[0072] In the aforementioned vehicle headlight control method, when it is determined that the user in the target vehicle intends to leave the vehicle, multi-source data is acquired, including external ambient illuminance data, vehicle position data, and user trajectory data. This multi-source data is then input into a pre-trained scene recognition model to obtain the target behavior scene after the user gets out of the vehicle. The target behavior scene includes nighttime homecoming scenarios and non-nighttime homecoming scenarios. Based on the target behavior scene, a target lighting control strategy corresponding to the target behavior scene is determined. The vehicle headlights are then controlled according to the target lighting control strategy. As can be seen, this embodiment of the application sequentially performs multi-source data perception, scene recognition, and determination of the target lighting control strategy based on the identified target behavior scene when the user intends to leave the vehicle. This allows the lighting control strategy to adapt to the user's actual behavior scene after leaving the vehicle, avoiding false triggering caused by turning on the headlights immediately upon detecting the user getting out of the vehicle. This improves the accuracy of headlight control and the accuracy of activating the "Follow Me Home" function, thereby improving the user experience. Furthermore, multi-source data can comprehensively and accurately reflect the characteristics of the current scene, thus improving the accuracy of scene recognition.

[0073] It should be noted that before step 201, the vehicle controller 102 first determines whether the user in the target vehicle has the intention to leave the vehicle based on the perception data of the multi-source perception module 101.

[0074] In one exemplary embodiment, the method further includes: determining that the user intends to leave the vehicle when the target vehicle is detected to be in a turned-off state and the user's seat belt is unfastened; and determining that the user does not intend to leave the vehicle when the target vehicle is detected to be in a ignition state or the user's seat belt is unfastened.

[0075] In this context, "off state" refers to the target vehicle being in a power-off state, where the vehicle is not started / operating; "ignition state" refers to the target vehicle being connected to the power supply, in which the vehicle may or may not be started / operating. The driver performs a power-off or engine-off action to put the vehicle in the off state. The driver performs a power-on action to put the vehicle in the ignition state.

[0076] For example, for any user in the target vehicle, when the ignition state of the target vehicle is ON, the vehicle controller 102 is in standby mode and continuously monitors the vehicle status signal. When the ignition state is OFF (i.e., the engine is off) and a "user unbuckles seatbelt" signal is detected, it is determined that the user intends to get out of the vehicle, and the system enters the multi-source data perception and behavior scene recognition stage; when the target vehicle is detected to be ignited or no "user unbuckles seatbelt" signal is detected, it is determined that the user does not intend to get out of the vehicle.

[0077] Therefore, this embodiment determines whether the user inside the vehicle intends to leave the vehicle based on the status of the target vehicle and the seat belt unfastening signal, thus ensuring accurate monitoring of the intention to leave the vehicle.

[0078] In an exemplary embodiment, the target lighting control strategy includes lighting duration, and step 203 includes: when the target behavior scenario is a nighttime homecoming scenario, determining the lighting duration corresponding to the nighttime homecoming scenario based on vehicle location data and a preset home address.

[0079] For example, when the scene recognition model identifies the target behavior scene as a nighttime homecoming scene (i.e., the user needs to go home after getting off the car at night), the vehicle controller 102 obtains the preset home address and determines the distance between the target vehicle and the home address based on the vehicle location data and the home address. Based on this distance, it calculates the lighting duration, such as 30 seconds or 60 seconds, thereby activating the "Follow Me Home" function. After activating the function, it performs a function termination determination, that is, the vehicle controller determines whether any of the following function termination conditions are met: the lighting time reaches the lighting duration, the user's location enters the preset "Arrived Home" area (such as within the building access control range), and the user manually turns off the function through a mobile application or voice command. If so, it controls the headlights to turn off gently (using a gradual dimming effect to avoid sudden blackout), and the function ends. When the scene recognition model identifies the target behavior scene as a non-nighttime homecoming scene (such as temporarily getting out of the car at night, getting out of the car during the day, getting out of the car to check the trunk, etc.), the vehicle controller 102 does not need to calculate the lighting duration, but directly determines the lighting duration to a preset value (fixed value) that has been set and stored in advance, such as 60 seconds. That is, the "Follow Me Home" function is not activated at this time, and the normal lighting mode is activated.

[0080] Optionally, when the target behavior scenario is returning home at night, the vehicle's audio system is controlled to play an activation prompt for the "Follow Me Home" function. The vehicle controller plays an audio prompt via the audio system stating, "Darkness detected on the path home at night; path lighting has been activated for you." Simultaneously, the function status is displayed on the instrument panel or central control screen.

[0081] Therefore, in the scenario of returning home at night, this embodiment can ensure the accuracy of the activation of the "Follow Me Home" function. Furthermore, by determining the duration of lighting based on vehicle location data and the preset home address, the duration of lighting can cover the user's return home time, ensuring that the vehicle lights have sufficient lighting time to guide the user home.

[0082] In one example, the duration of lighting for a nighttime homecoming scenario is determined based on vehicle location data and a preset home address. This includes: determining the walking distance between the target vehicle and the home address based on the vehicle location data and the preset home address; determining the walking time based on the walking distance; and determining the duration of lighting for a nighttime homecoming scenario based on the walking time and a preset safety factor.

[0083] The walking distance refers to the actual walking path a user takes home along the pedestrian walkway, not the straight-line distance. A preset safety factor is used to compensate for potential delays during the actual walking process; this factor is greater than 1.

[0084] For example, the vehicle controller 102 first uses a path planning algorithm to calculate the walking distance between the target vehicle's door and the user's pre-set home address in the system. Then, it converts the walking distance into walking time based on a preset walking speed (e.g., 1 meter / second, or dynamically adjusted based on the user's historical walking speed). Finally, it multiplies the walking time by a preset safety factor (e.g., 1.2) to obtain the lighting duration, thus allowing a 20% safety margin in the lighting duration. The vehicle controller 102 controls the headlights to illuminate according to this lighting duration and turns them off after the timer expires.

[0085] Therefore, this embodiment dynamically calculates the lighting duration based on the walking distance between the user's vehicle and home address, rather than using a fixed duration. This allows the lighting duration to adaptively match the user's actual home journey length, avoiding situations where the fixed duration is too short, causing the lights to turn off before the user arrives home, or where the duration is too long, resulting in unnecessary energy waste. This improves the intelligence level and user experience of the "Follow Me Home" function.

[0086] In another example, the duration of lighting for a nighttime homecoming scenario is determined based on vehicle location data and a preset home address. This includes determining the duration of lighting for a nighttime homecoming scenario based on weather information, vehicle location data, and home address.

[0087] For example, the multi-source sensing module 101 also includes a rain sensor for detecting weather information such as rainfall level. The vehicle controller 102 first determines the lighting duration based on vehicle location data and the user's pre-set home address, and then adjusts the lighting duration based on weather information from the rain sensor, for example, automatically extending the lighting duration on rainy days.

[0088] Therefore, this embodiment also considers weather information when determining the duration of lighting, which can extend the lighting time on rainy days, ensure the lighting effect on rainy days, and effectively guide users.

[0089] In an exemplary embodiment, the target lighting control strategy includes a light projection angle and a light projection area. Step 203 includes: when the target behavior scenario is a nighttime homecoming scenario, determining the light projection angle corresponding to the nighttime homecoming scenario based on the angle between the user's direction of travel and the vehicle's centerline; and determining the light projection area corresponding to the nighttime homecoming scenario based on the direction of travel.

[0090] For example, when the system detects that a user has exited the vehicle and left with a Bluetooth key / phone, it initializes the headlight projection angle to face directly forward. It continuously monitors the user's real-time location via Bluetooth / UWB positioning and determines the user's direction of travel based on that location. The system calculates the angle between the direction of travel and the vehicle's centerline. If this angle is less than or equal to a preset angle, it maintains forward illumination, meaning the headlight projection angle remains forward. If the angle is greater than the preset angle, it adjusts the headlight projection angle, causing the matrix ADB headlights to rotate in the direction of travel. Simultaneously, through independent pixel control of the matrix ADB headlights, pixel areas not in the direction of travel and those facing away from the direction of travel are turned off, concentrating illumination on the user's direction of travel. Different lighting coverage areas are achieved by controlling the combined switching of the cornering lights and headlights.

[0091] Alternatively, the user's movement trajectory can be identified using an external vehicle camera, and the user's location can be achieved using a visual SLAM algorithm. This approach is relatively low-cost. Alternatively, multiple UWB anchor points can be deployed around the target vehicle, and the user's 3D positioning can be achieved using a Time Difference of Arrival (TDOA) algorithm, with an accuracy down to the centimeter level.

[0092] Therefore, this embodiment monitors the user's direction of travel in real time and dynamically adjusts the light projection angle and light projection area according to the direction of travel, avoiding fixed-angle lighting. This allows the lighting path to adapt to the user's walking path in real time, realizing the dynamic light following function and pixel-level area control of the headlights. This can further provide users with effective path guidance and improve the user experience.

[0093] In addition to guiding users home by activating the "Follow Me Home" feature, the system can also monitor path safety in real time during the user's walk to ensure safety.

[0094] In one exemplary embodiment, the method further includes: when the target behavior scenario is determined to be a nighttime homecoming scenario and there are obstacles in the user's travel path, controlling the vehicle lights to perform a preset warning action, and / or controlling the target vehicle to output voice prompt information.

[0095] For example, during a user's walk, millimeter-wave radar continuously monitors the user's walking path to identify any abnormalities, such as the presence of obstacles (e.g., bollards, steps) or moving creatures (e.g., cats, dogs, pedestrians). If so, the vehicle lights are controlled to perform preset warning actions, such as flashing warnings at a certain frequency, and the vehicle's audio system is controlled to issue a voice prompt to remind the user of potential safety hazards along the current walking path. If the walking path is normal, the current lighting mode is maintained, and the timer continues until the required lighting duration is reached, at which point the vehicle lights are turned off.

[0096] Therefore, this embodiment introduces a walking path safety monitoring function. When the radar or camera detects an obstacle in the user's walking path, it triggers light warnings and voice prompts to remind the user to pay attention to safety, further ensuring user safety and improving user experience.

[0097] The above embodiments describe how to activate, implement, and deactivate the "Follow Me Home" function when the target behavior scenario is a nighttime homecoming scenario. In practical applications, the target behavior scenario may also be a nighttime temporary vehicle exit scenario. This scenario can be understood as a scenario where one gets out of the car at night but does not go home, such as getting out of the car at night to check the trunk, adjust the seat, pick up a package, and quickly return to the car. In this case, it is not necessary to activate the "Follow Me Home" function, but short-term lighting is required.

[0098] In one exemplary embodiment, the non-nighttime homecoming scenario includes a nighttime temporary drop-off scenario, the target lighting control strategy includes lighting duration, and step 203 includes: when the target behavior scenario is a nighttime temporary drop-off scenario, the preset duration is determined as the lighting duration corresponding to the nighttime temporary drop-off scenario.

[0099] The lighting duration (i.e., the preset duration) for the nighttime temporary drop-off scenario is shorter than the lighting duration for the nighttime homecoming scenario. The preset duration can be pre-set and stored based on actual needs and historical experience, and is a fixed value.

[0100] For example, in the case of a target behavior scenario of temporary disembarkation at night, it is determined that the user is not actually leaving the vehicle to go home, but is only temporarily getting off. In this case, the vehicle controller 102 can obtain a preset duration corresponding to temporary disembarkation at night from a preset rule base, and determine this preset duration (e.g., 20 seconds) as the lighting duration corresponding to the temporary disembarkation scenario at night. The vehicle controller 102 controls the headlights to be on for this preset duration, and automatically turns them off after the preset duration ends. At the same time, in order to save energy and avoid interference, the dynamic light following function and the driving path safety warning function are not activated in this scenario.

[0101] Therefore, in the scenario of temporarily getting off the vehicle at night, the fixed preset duration can be directly set as the lighting duration, which can not only meet the basic lighting needs of users when they temporarily get off the vehicle, but also avoid the waste of electricity caused by long-term ineffective lighting.

[0102] In an exemplary embodiment, step 201 includes: acquiring multi-source data when it is determined that the user in the target vehicle intends to leave the vehicle and the current time is within a preset time period.

[0103] The preset time period is from 18:00 on the same day to 6:00 the next day, and can be dynamically adjusted according to the weather conditions.

[0104] For example, when it is determined that the user intends to leave the vehicle, the current time is obtained and it is determined whether the current time is within the period from 18:00 on the same day to 6:00 on the next day. If so, the multi-source perception module 101 is triggered to perceive multi-source data and instruct the subsequent scene recognition and lighting strategy generation steps; if not, the multi-source data perception steps are not triggered, and the lighting function (including the follow me home function) is not activated.

[0105] Therefore, this embodiment activates the intelligent lighting function only during nighttime hours, further saving system computing power and power, and avoiding accidental triggering during the day.

[0106] The vehicle light control method of this application is described below through a detailed embodiment.

[0107] like Figure 3 As shown, the vehicle headlight control method includes the following steps:

[0108] Step 301, System initialization;

[0109] When the vehicle is ignited (ON), the vehicle controller is in standby mode and continuously monitors the vehicle status signals.

[0110] Step 302: Determine whether the user in the target vehicle intends to leave the vehicle based on the vehicle status and the user's seat belt status;

[0111] If the target vehicle is detected to be turned off and the user's seatbelt is unfastened, it is determined that the user intends to leave the vehicle.

[0112] If the target vehicle is detected to be in the ignition state or the user's seat belt is not unfastened, it is determined that the user does not intend to leave the vehicle.

[0113] Step 303: If it is determined that the user in the target vehicle intends to leave the vehicle and the current time is within a preset time period, acquire multi-source data;

[0114] Step 304: Input the multi-source data into the pre-trained scene recognition model to obtain the target behavior scene after the user gets off the vehicle;

[0115] Step 305: When the target behavior scenario is a nighttime homecoming scenario, determine the lighting duration corresponding to the nighttime homecoming scenario based on vehicle location data and preset home address.

[0116] Step 306: Determine the light projection angle corresponding to the nighttime homecoming scenario based on the angle between the user's direction of travel and the vehicle's centerline.

[0117] Step 307: Determine the light projection area corresponding to the nighttime homecoming scene based on the direction of travel;

[0118] Step 308: If an obstacle is detected in the user's travel path, control the headlights to perform a preset warning action and control the target vehicle to output a voice prompt message.

[0119] Step 309: If the termination condition is met, control the headlights to turn off gently.

[0120] The termination condition is any of the following:

[0121] Condition 1: The lighting timer reaches the preset duration;

[0122] Condition 2: The user's location enters the preset "home" area (such as within the access control range of the building).

[0123] Condition 3: The user manually disables the function via a mobile application or voice command.

[0124] The following describes the implementation of this application's embodiments in a specific scenario (a user returning home late and parking their car):

[0125] Scenario description: User Zhang drove home at 9 pm and parked his car in a parking space on the side of the road in the community. The entrance to his apartment building is about 30 meters to the left rear of the car, and he needs to go through a dimly lit bend in the road.

[0126] Work steps:

[0127] S1: The user shifts to Park, turns off the engine, and unbuckles their seatbelt. The DMS camera detects the driver's action of getting out of the vehicle.

[0128] S2, the ambient light sensor detected an external illuminance of 3 Lux (low-light environment at night), the GPS showed that the vehicle was 28 meters away from the preset home address, and the millimeter-wave radar monitored the user's trajectory data in real time.

[0129] S3 inputs the external ambient light data, vehicle location data, and trajectory data into the scene recognition model to obtain the target behavior scene as a nighttime homecoming scene.

[0130] S4 calculates the walking time from the vehicle to the home address as approximately 40 seconds and sets the lighting duration to 48 seconds;

[0131] S5, the system plays a voice prompt: The path home at night is dark, and the path lighting has been turned on for you;

[0132] S6, the user gets out of the car and leaves with their mobile phone. The Bluetooth positioning unit detects that the user is moving to the left rear of the vehicle;

[0133] S7, ADB headlight dynamic adjustment: turns off the right pixel area, rotates 12 degrees to the left, and focuses the illumination on the direction the user is walking;

[0134] When the S8 driver approaches a left-turn intersection, the headlights automatically continue to turn left to illuminate the blind spot after the turn.

[0135] The S9's path safety monitoring function detects a low step on the road ahead, triggering the lights to flash twice rapidly and playing a voice prompt: "Caution: Step ahead."

[0136] S10: When a user enters the access control area of ​​the building, the system determines that the user has arrived at the destination and controls the headlights to gradually dim within 3 seconds.

[0137] The location, user behavior, and vehicle status involved in this embodiment are as follows: Figure 4 As shown.

[0138] In other words, this application embodiment achieves multi-source fusion-based intelligent scene perception: it fuses data from multiple sensing devices such as ambient light sensors, GPS positioning modules, in-vehicle / external cameras, and millimeter-wave radar to construct a three-dimensional perception model of "environment-location-trajectory". The ambient light sensor detects the external ambient illuminance in real time to determine if the vehicle is in a low-light environment; the GPS positioning module compares the data with a preset home address to determine if the vehicle is in a homecoming scenario; and the cameras and radar identify the complexity of the surrounding environment. This multi-source data fusion approach enables the system to comprehensively and accurately perceive the characteristics of the current scene; it also achieves algorithm-based behavioral scene recognition: a deep learning scene recognition model is introduced and deployed on the vehicle controller. This model can comprehensively analyze multi-source data, intelligently determine the user's behavioral scenario, and distinguish between different scenarios such as "returning home at night," "retrieving items from the trunk," and "temporarily getting out of the car," thus implementing differentiated lighting control strategies; it also achieves dynamic adaptive lighting guidance: using intelligent matrix ADB headlights, the system can locate the user's position in real time based on the Received Signal Strength Indicator (RSSI) from the Bluetooth key or mobile phone, and dynamically adjust the light projection angle and area. When there is an angle between the user's direction of travel and the vehicle's orientation, the system can turn off the pixel area in the direction of travel and concentrate the illumination on the user's walking path. This lighting guidance effect significantly improves the safety and convenience of leaving the vehicle at night.

[0139] In summary, the embodiments of this application have the following significant advantages:

[0140] (1) Significantly improved intelligence: The traditional passive lighting control mode has been upgraded to an active service mode. The system does not require manual operation by the user. It can autonomously judge environmental conditions and user intentions, automatically activate and adjust lighting parameters, greatly improving the user experience;

[0141] (2) Improved energy efficiency: Through behavioral scene recognition, the system only activates the function in the scene where lighting is really needed, avoiding the waste of electricity caused by ineffective lighting during the day or in bright environments;

[0142] (3) Enhanced targeted lighting effect: The lighting direction can be adjusted according to the user's actual walking path, solving the problem of only illuminating the front of the vehicle and providing users with truly effective path lighting;

[0143] (4) Enhanced security capabilities: The proactive security early warning mechanism can identify potential dangers on the user's travel path and issue timely warnings;

[0144] (5) Human-computer interaction experience optimization: The system supports voice prompt function, which can inform the user of the system status when activated, while retaining the manual switch option, reflecting the concept of combining intelligent assistance and user control.

[0145] 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.

[0146] Based on the same inventive concept, this application also provides a vehicle lighting control device for implementing the aforementioned vehicle lighting control method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of the one or more vehicle lighting control device embodiments provided below can be found in the limitations of the vehicle lighting control method described above, and will not be repeated here.

[0147] In one exemplary embodiment, such as Figure 5 As shown, a vehicle lighting control device is provided, including: a data acquisition module 501, a data input module 502, a strategy determination module 503, and a vehicle lighting control module 504, wherein:

[0148] The data acquisition module 501 is used to acquire multi-source data when it is determined that the user in the target vehicle intends to leave the vehicle. The multi-source data includes external ambient light data, vehicle location data and user trajectory data.

[0149] The data input module 502 is used to input the multi-source data into a pre-trained scene recognition model to obtain the target behavior scene after the user gets off the vehicle; wherein, the target behavior scene includes a nighttime homecoming scene and a non-nighttime homecoming scene.

[0150] The strategy determination module 503 is used to determine the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario;

[0151] The vehicle lighting control module 504 is used to control the vehicle lights of the target vehicle according to the target lighting control strategy.

[0152] In one embodiment, the device further includes: an intention to leave the vehicle module, configured to: determine that the user has an intention to leave the vehicle when the target vehicle is detected to be in a turned-off state and the user's seat belt is unfastened; and determine that the user does not have an intention to leave the vehicle when the target vehicle is detected to be in a ignition state or the user's seat belt is unfastened.

[0153] In one embodiment, the target lighting control strategy includes lighting duration, and the strategy determination module 503 is specifically used to: determine the lighting duration corresponding to the nighttime homecoming scenario based on the vehicle location data and the preset home address when the target behavior scenario is the nighttime homecoming scenario.

[0154] In one embodiment, when determining the lighting duration corresponding to a nighttime homecoming scenario, the strategy determination module 503 is specifically used to: determine the walking distance between the target vehicle and the home address based on the vehicle location data and the preset home address; determine the walking time based on the walking distance; and determine the lighting duration corresponding to the nighttime homecoming scenario based on the walking time and the preset safety factor.

[0155] In one embodiment, when determining the lighting duration corresponding to the nighttime homecoming scenario, the strategy determination module 503 is specifically used to: determine the lighting duration corresponding to the nighttime homecoming scenario based on weather information, the vehicle location data, and the home address.

[0156] In one embodiment, the target lighting control strategy includes a light projection angle and a light projection area. The strategy determination module 503 is specifically used to: determine the light projection angle corresponding to the nighttime homecoming scenario based on the angle between the user's travel direction and the vehicle's centerline when the target behavior scenario is the nighttime homecoming scenario; and determine the light projection area corresponding to the nighttime homecoming scenario based on the travel direction.

[0157] In one embodiment, the device further includes: a safety monitoring module, configured to control the vehicle lights to perform a preset warning action and / or control the target vehicle to output voice prompt information when the target behavior scenario is determined to be the nighttime homecoming scenario and there are obstacles in the user's travel path.

[0158] In one embodiment, the non-nighttime homecoming scenario includes a nighttime temporary drop-off scenario, and the target lighting control strategy includes lighting duration; the strategy determination module 503 is specifically used to: when the target behavior scenario is the nighttime temporary drop-off scenario, determine the preset duration as the lighting duration corresponding to the nighttime temporary drop-off scenario.

[0159] In one embodiment, the data acquisition module is specifically used to: acquire the multi-source data when it is determined that the user in the target vehicle intends to leave the vehicle and the current time is within a preset time period.

[0160] Each module in the aforementioned 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.

[0161] In one exemplary embodiment, refer to Figure 1 A vehicle lighting control system is provided, which includes a multi-source sensing module 101 and an on-board controller 102. The multi-source sensing module 101 is used to collect multi-source data, specifically including ambient light data outside the vehicle, vehicle position data, and user trajectory data; the on-board controller 102 is used to execute a vehicle lighting control method.

[0162] In one exemplary embodiment, a vehicle is provided, including the headlight control system of the above embodiment.

[0163] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores vehicle lighting control data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a vehicle lighting control method.

[0164] Those skilled in the art will understand that Figure 6 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 to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0165] In one exemplary embodiment, an in-vehicle device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a vehicle lighting control method.

[0166] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a vehicle lighting control method.

[0167] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements a vehicle lighting control method.

[0168] 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.

[0169] 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.

[0170] 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 vehicle headlight control method, characterized in that, The method includes: When it is determined that the user in the target vehicle intends to leave the vehicle, multi-source data is acquired, including external ambient light data, vehicle location data, and user trajectory data. The multi-source data is input into a pre-trained scene recognition model to obtain the target behavior scene after the user gets off the vehicle; wherein, the target behavior scene includes nighttime homecoming scene and non-nighttime homecoming scene; Based on the target behavior scenario, determine the target lighting control strategy corresponding to the target behavior scenario; The headlights of the target vehicle are controlled according to the target lighting control strategy.

2. The method according to claim 1, characterized in that, The method further includes: If the target vehicle is detected to be turned off and the user's seatbelt is unfastened, it is determined that the user intends to leave the vehicle. If the target vehicle is detected to be in an ignition state or the user's seat belt is not unfastened, it is determined that the user does not intend to leave the vehicle.

3. The method according to claim 1, characterized in that, The target lighting control strategy includes lighting duration, and determining the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario includes: When the target behavior scenario is the nighttime homecoming scenario, the lighting duration corresponding to the nighttime homecoming scenario is determined based on the vehicle location data and the preset home address.

4. The method according to claim 3, characterized in that, The step of determining the lighting duration corresponding to the nighttime homecoming scenario based on the vehicle location data and the preset home address includes: Based on the vehicle location data and the preset home address, the walking distance between the target vehicle and the home address is determined; The walking time is determined based on the walking distance. The duration of lighting for the nighttime homecoming scenario is determined based on the walking time and a preset safety factor.

5. The method according to claim 3, characterized in that, The step of determining the lighting duration corresponding to the nighttime homecoming scenario based on the vehicle location data and the preset home address includes: Based on weather information, vehicle location data, and home address, the duration of lighting corresponding to the nighttime homecoming scenario is determined.

6. The method according to claim 1, characterized in that, The target lighting control strategy includes the light projection angle and the light projection area. Determining the target lighting control strategy corresponding to the target behavior scene based on the target behavior scene includes: When the target behavior scenario is the nighttime homecoming scenario, the light projection angle corresponding to the nighttime homecoming scenario is determined based on the angle between the user's direction of travel and the vehicle's centerline. The light projection area corresponding to the nighttime homecoming scene is determined based on the direction of travel.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: If the target behavior scenario is determined to be the nighttime homecoming scenario, and there are obstacles in the user's travel path, the vehicle lights are controlled to perform a preset warning action, and / or the target vehicle is controlled to output voice prompt information.

8. The method according to any one of claims 1 to 6, characterized in that, The non-nighttime homecoming scenario includes a temporary nighttime drop-off scenario, and the target lighting control strategy includes the duration of lighting; The step of determining the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario includes: When the target behavior scenario is the temporary drop-off scenario at night, the preset duration is determined as the lighting duration corresponding to the temporary drop-off scenario at night.

9. The method according to any one of claims 1 to 6, characterized in that, When it is determined that the user in the target vehicle intends to leave the vehicle, the acquisition of multi-source data includes: If it is determined that the user in the target vehicle intends to leave the vehicle and the current time is within a preset time period, the multi-source data is acquired.

10. A vehicle lighting control device, characterized in that, The device includes: The data acquisition module is used to acquire multi-source data when it is determined that the user in the target vehicle intends to leave the vehicle. The multi-source data includes external ambient light data, vehicle location data, and user trajectory data. The data input module is used to input the multi-source data into a pre-trained scene recognition model to obtain the target behavior scene after the user gets off the vehicle; wherein, the target behavior scene includes a nighttime homecoming scene and a non-nighttime homecoming scene. The strategy determination module is used to determine the target lighting control strategy corresponding to the target behavior scenario based on the target behavior scenario; The vehicle lighting control module is used to control the vehicle lights of the target vehicle according to the target lighting control strategy.

11. A vehicle lighting control system, characterized in that, The system includes: Multi-source sensing module, used to collect data from multiple sources; An onboard controller for performing the method as described in any one of claims 1 to 9.

12. A vehicle, characterized in that, include: The vehicle lighting control system as described in claim 11.

13. An in-vehicle device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images