Active safety driving reminding method and control system

Abstract

The application relates to an active safety driving reminding method and a control system. The active safety driving reminding method comprises the following steps: acquiring first information in the process of automobile driving, wherein the first information comprises road condition information and vehicle speed information; generating second information based on the first information according to a preset condition, wherein the second information comprises prompt information; sending the prompt information to a driver and acquiring feedback information of the driver; and controlling a lamp of the automobile to start a reminding function in response to affirmative information fed back by the driver. According to the method, the lamp of the automobile can be started in advance according to the road condition information, the driving safety of the automobile is improved, and the misjudgment under complex road conditions is reduced.

Description

Technical Field

[0001] This application relates to the automotive field, and in particular to active safety driving alert methods and control systems. Background Technology

[0002] With the continuous development of the country and the increasing national income and per capita vehicle ownership, vehicle safety has received increasing attention. While driving, drivers generally need to observe road conditions in their direction of travel. If a collision risk is detected, such as a rear-end collision, the driver needs to manually activate the car's lights to warn the driver behind and prevent a rear-end collision. However, this method has certain drawbacks. Sometimes safety hazards occur in the driver's blind spot, and sometimes the driver's reaction is not timely, both of which can lead to accidents.

[0003] Existing technology eliminates the need for manual driver control, automatically activating car lights to alert following vehicles based on road conditions. However, in complex road situations, this technology often misjudges the situation, resulting in wasted energy as the lights remain on. Because existing technology relies solely on preset conditions to identify road conditions and automatically activate lights, there's a possibility that the driver might not even notice the lights are on, leading to wasted energy.

[0004] Therefore, it is necessary to provide an improved reminder method and system to solve the above problems. Summary of the Invention

[0005] The purpose of this application is to provide an active safety driving reminder method and control system.

[0006] This application adopts the following technical solution: an active safety driving reminder method, comprising:

[0007] Acquire first information during vehicle operation, including road condition information and vehicle speed information;

[0008] Based on preset conditions, second information is generated from the first information, and the second information includes prompt information.

[0009] Send the aforementioned prompt message to the driver and obtain the driver's feedback; and

[0010] The system responds to positive feedback from the driver by controlling the activation of the vehicle's lighting components.

[0011] Furthermore, the road condition information includes surrounding weather information, surrounding traffic information, information on vehicles in front and behind, and information on pedestrians in the surrounding area; the preset conditions include the vehicle being at high speed, normal speed, and low speed.

[0012] Furthermore, the system identifies surrounding weather and traffic information at high speeds; identifies front and rear vehicle information at normal speeds; and identifies front and rear vehicle information and surrounding pedestrian information at low speeds. The front and rear vehicle information includes the distance to or number of vehicles in front or behind.

[0013] Furthermore, the prompt information includes voice prompts or visual prompts; in response to negative feedback from the driver, the operation of turning on the vehicle lights is not performed; when traffic conditions are severe, the prompt information is sent to the driver again, and the driver's feedback is obtained.

[0014] Furthermore, the reminder function is automatically turned off when the distance between the front and rear vehicles exceeds a set value or when the number of vehicles in front and behind decreases; the reminder function for the automotive lighting components includes: the front and rear taillights of the automotive lighting components flashing in high-speed and normal-speed states, and the front and rear brake lights of the automotive lighting components turning on in low-speed states.

[0015] Furthermore, it also includes establishing a machine learning model, obtaining a training dataset related to a specific driver, the training data including the first information, the second information, and the feedback information; training the machine learning model based on the training dataset, and using the trained machine learning model to optimize the reminder method.

[0016] Furthermore, the optimized reminder method includes generating a personalized reminder mode for a specific driver, wherein the personalized reminder mode includes changing preset conditions or changing the generation frequency or reminder method of the reminder information.

[0017] Furthermore, the training dataset includes at least 40 training data points; the road condition information also includes information about the city where the vehicle is located, the location where the vehicle is traveling, and the time period during which the vehicle is traveling.

[0018] Furthermore, it also includes controlling the trained machine learning model, the control including turning off the personalized prompt mode.

[0019] This application also provides an active safety driving control system, including an information collection module, a control module, a human-machine interaction module, and automotive lighting components; the information collection module collects first information, including road condition information and vehicle speed information; the control module controls the human-machine interaction module to output second information based on the first information, the second information including prompt information; the human-machine interaction module sends the prompt information to the driver and receives feedback information; the control module controls the automotive lighting components based on the feedback information.

[0020] Furthermore, the information collection module includes a distance sensing component, a weather information collection component, a traffic information collection component, a vehicle speed sensor, or a driving recorder; the distance sensing component includes radar or a camera.

[0021] Furthermore, the human-computer interaction module includes a voice interaction device, a touch interaction device, or a machine vision-based human-computer interaction device.

[0022] Furthermore, the control module includes an electronic control unit and a vehicle lighting control component; the electronic control unit includes a T-BOX, an ADAS controller, and a BCM; the vehicle lighting control component includes a headlight control component and a taillight control component; the vehicle lighting component includes a front combination lamp and a rear combination lamp; the headlight control component is connected to the front combination lamp; and the taillight control component is connected to the rear combination lamp.

[0023] Furthermore, the control module includes a machine learning module, which constructs a machine learning model to obtain road condition information, prompt information, and feedback information related to a specific driver, and optimizes and generates a personalized prompt mode based on the machine learning model.

[0024] Compared with existing technologies, this application can detect potential safety hazards in advance and remind drivers to react promptly to dangerous situations. It can automatically activate the warning function of the vehicle's lighting components based on driver feedback; in the event of a misjudgment by the control system, it allows for direct human intervention by the driver; ultimately, the driver decides whether to turn on the lights, which better aligns with the driver's preferences and driving habits.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0027] Figure 1 This is a flowchart of the active safety driving reminder method of this application.

[0028] Figure 2 This is a flowchart illustrating the active safety driving reminder method of this application.

[0029] Figure 3 The flowchart for the active safety driving reminder method of this application includes a machine learning method.

[0030] Figure 4 This is a schematic diagram of the active safety driving control system of this application.

[0031] Figure 5 This is a schematic diagram of the information collection module of the active safety driving control system of this application.

[0032] Figure 6 This is a schematic diagram of the control module of the active safety driving control system of this application.

[0033] Figure 7 This is a schematic diagram of the specific structure of the active safety driving control system of this application.

[0034] Figure 8 This is a schematic diagram of the control and connection structure of the active safety driving control system of this application.

[0035] Figure 9 This is a schematic diagram of the control and connection structure of the automotive lighting components in the active safety driving control system of this application.

[0036] Figure 10 This is a schematic diagram of the control and connection structure of the machine learning module of the active safety driving control system of this application.

[0037] Explanation of reference numerals in the attached diagram: 100, Information collection module; 101, Distance sensing component; 101a, Radar; 101b, Camera; 102, Weather information collection component; 103, Traffic information collection component; 200, Control module; 201, T-BOX; 202, ADAS controller; 203, BCM; 204, Vehicle lighting control component; 204a, Headlight control component; 204b, Taillight control component; 205, Machine learning module; 300, Human-machine interaction module; 400, Automotive lighting component; 401, Front combination lamp; 402, Rear combination lamp. Detailed Implementation

[0038] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0039] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the application. Unless otherwise defined, the technical or scientific terms used in this specification should be understood in their ordinary sense by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in this specification and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, "a" or "one," and similar terms do not indicate a quantity limitation, but rather indicate the presence of one. "A plurality" or "several" indicates two or more. Unless otherwise stated, terms such as "front," "rear," "lower," and / or "upper" are for ease of description only and are not limited to a location or spatial orientation. Terms such as "comprising" or "including" indicate that the elements or objects preceding "comprising" encompass the elements or objects listed following "comprising" or "including" and their equivalents, and do not exclude other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections and can include electrical connections, whether direct or indirect.

[0040] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0041] The embodiments described in this specification will now be explained in detail. Please refer to... Figure 1 As shown, this application provides an active safe driving reminder method, the main process of which includes:

[0042] Step 10: Obtain initial information about the vehicle's operation, including road conditions and vehicle speed. Road conditions include surrounding weather, traffic conditions, information on vehicles in front and behind, and information on pedestrians.

[0043] Step 20: Based on the preset conditions, generate the second information from the first information. The second information includes a prompt message. The prompt message includes "Do you want to turn on the car lights?". The preset conditions include whether the car is at high speed, normal speed, low speed, or safe driving status.

[0044] Step 30: Send a prompt message to the driver and obtain the driver's feedback. The feedback message includes whether or not to turn on the vehicle's lighting components.

[0045] Step 40: In response to positive feedback from the driver, control the vehicle's lighting components to activate the reminder function.

[0046] Please refer to Figure 2 As shown, this application corresponds to different preset conditions based on four detected vehicle speed states: high speed, normal speed, low speed, and safe driving state. In one implementation, the high speed state can be defined as a vehicle speed greater than 80 km / h; the normal speed state can be defined as a vehicle speed between 20-40 km / h; the low speed state can be defined as a vehicle speed less than 20 km / h; the remaining speed ranges are considered safe driving states, and the active safe driving control method provided in this application is not executed in these safe driving states. Furthermore, this speed range division is only one setting, and drivers can adjust it according to their own circumstances.

[0047] Step 11: When the vehicle speed is greater than 80km / h, the vehicle collects surrounding weather information and surrounding traffic information. Surrounding weather information includes various extreme weather conditions such as heavy rain, fog, and snow. Surrounding traffic information includes traffic jams, rear-end collisions, and car accidents. A warning message is generated at least 1km ahead of the relevant road conditions.

[0048] Step 12: When the vehicle speed is between 20-40 km / h, the vehicle collects information about the vehicles in front and behind, including the distance or number of vehicles in front and behind. If the distance between vehicles in front and behind is less than 50m or the number of vehicles in front and behind is greater than 2, a prompt message is generated.

[0049] Step 13: When the car speed is less than 20km / h, the vehicle collects information on vehicles in front and behind and pedestrians in the surrounding area. If the distance between vehicles in front and behind is less than 10m, or the number of vehicles in front and behind is greater than 2, or the number of pedestrians in the surrounding area is greater than 2, a prompt message is generated.

[0050] In step 31, during the process of outputting prompt information and receiving feedback information, the prompt information includes voice prompts and visual prompts. Voice prompts include those issued through the vehicle's speakers, such as "Potential risk detected, turn on vehicle lights?". Visual prompts include text or image prompts displayed on the vehicle's screen or dashboard. Text prompts include a high-frequency flashing red message, "Potential risk detected, turn on vehicle lights?". Image prompts include specific images such as a red exclamation mark. When a serious traffic situation is detected, such as severe traffic congestion, extremely low visibility, or a serious traffic accident, the prompt information is sent to the driver again.

[0051] In the specific execution process, step 40 includes two scenarios.

[0052] Step 41: Upon receiving feedback from the driver, control the vehicle's lighting reminder function. This function includes flashing the front and rear taillights at high and normal speeds; turning on the front and rear brake lights at low speeds; and switching the headlights from high beam to low beam when two vehicles are passing each other in low visibility conditions.

[0053] Step 42: Upon receiving a negative response from the driver, no action is taken.

[0054] Step 50: After activating the car headlight reminder function, check if the following distances are met: When the car speed is between 20-40 km / h, the distance between the front and rear vehicles is greater than 50m; or when the car speed is less than 20 km / h, the distance between the front and rear vehicles is greater than 10m. Check if the number of vehicles in front and behind is met: When the car speed is between 20-40 km / h, the number of vehicles in front and behind is less than 2; or when the car speed is less than 20 km / h, the number of vehicles in front and behind is less than 2.

[0055] Step 51: When the detected distance and number of vehicles meet the preset conditions, control the car lights to turn off and remind the driver to reduce energy waste.

[0056] Step 52: When the detected vehicle distance and number of vehicles do not meet the preset conditions, continue to maintain the vehicle lights on reminder function.

[0057] In the exemplary embodiments, there may be differences such as different cities, time periods, driving locations, and different driving habits of different drivers. The proactive safe driving reminder method provided in this application further introduces a machine learning method based on deep neural networks (DNNs) to create personalized proactive safe driving reminder methods for different drivers through data statistics, classification, and summarization.

[0058] Please refer to Figure 3 As shown, machine learning methods include:

[0059] Step 60: Establish a machine learning model, obtain a training dataset relevant to a specific driver, and preprocess and extract features from the training dataset. The training dataset consists of relevant data generated during the execution of the active safe driving control method provided in this application. The training data includes surrounding weather information, surrounding traffic information, information of vehicles in front and behind, information of pedestrians in the surrounding area, vehicle speed information, prompt information, and feedback information. The surrounding weather information, surrounding traffic information, information of vehicles in front and behind, and other relevant data input to the machine learning model, as well as the output value of whether to turn on the car lights, are set. The training dataset includes training data related to at least 40 feedback processes. The input values ​​of the machine learning model may also include information about the city where the car is located, the location where the car is traveling, and the time period during which the car is traveling.

[0060] Step 61: Train the machine learning model using the preprocessed training dataset and optimize the alert method. The machine learning model is trained using a multi-process parallel queue, reading and consuming data simultaneously across multiple GPUs to obtain the trained model. The trained model is then used to optimize the alert method. Optimization of the alert method includes generating personalized alert patterns for specific drivers. Personalized alert patterns include: changing preset conditions, such as preset vehicle speed ranges, preset distances between vehicles, and the number of vehicles in front and behind; changing the frequency or method of alert message generation, such as broadcasting an alert message every 30 seconds, or using different voices (male, female, child's voice, etc.) to broadcast the alert message.

[0061] The trained machine learning model is monitored, and the model is continuously adjusted and optimized based on feedback from the improved alert method. Drivers can also actively control the trained machine learning model, including turning off personalized alert modes.

[0062] Please refer to Figure 4 As shown, this application also provides an active safety driving reminder control system based on the above-described active safety driving reminder method, including: an information collection module 100, a control module 200, a human-machine interaction module 300, and an automotive lighting assembly 400. The information collection module 100 collects road condition information and vehicle speed information. The control module 200 controls the human-machine interaction module 300 to output reminder information based on the road condition information and vehicle speed information. The human-machine interaction module 300 sends reminder information to the driver and receives feedback information from the driver. The control module 200 controls the automotive lighting assembly 400 based on the feedback information.

[0063] Please refer to Figure 5 As shown, the information collection module 100 includes a distance sensing component 101, a weather information collection component 102, a traffic information collection component 103, a vehicle speed sensor, and a driving recorder. The distance sensing component 101 includes a radar 101a and a camera 101b.

[0064] The distance sensing component 101 can identify and collect information on the number of surrounding vehicles and pedestrians, as well as the distance between the surrounding vehicles and pedestrians and the vehicle itself. The weather information collection component 102 can collect surrounding weather information via network, including extreme weather conditions such as fog and snow. The traffic information collection component 103 can collect surrounding traffic information via network, including traffic jams and traffic accidents. The vehicle speed sensor can collect the vehicle's speed information.

[0065] Please refer to Figure 6As shown, the control module 200 includes an electronic control unit (ECU), a lighting control component 204, and a machine learning module 205. The ECU includes a T-BOX (Telematics Box) 201, an ADAS (Advanced Driving Assistance System) controller 202, and a BCM (Body Control Module) 203. The lighting control component 204 includes a headlight control component 204a and a taillight control component 204b. The BCM 203 connects to the T-BOX 201, the ADAS controller 202, the lighting control component 204, and the human-machine interface module 300.

[0066] The human-machine interaction module 300 includes a voice interaction device, a touch interaction device, and a machine vision-based human-machine interaction device. The voice interaction device includes sound playback devices such as speakers and sound recording devices such as microphones. The touch interaction device includes indicator buttons. The machine vision-based human-machine interaction device includes an in-vehicle camera, an in-vehicle display screen, ambient lighting, or a dashboard.

[0067] The vehicle lighting control assembly 204 includes a front light control assembly 204a and a taillight control assembly 204b. The vehicle lighting assembly 400 includes a front combination lamp 401 and a rear combination lamp 402. The front light control assembly 204a is connected to the front combination lamp 401, and the taillight control assembly 204b is connected to the rear combination lamp 402.

[0068] The automotive lighting assembly 400 turns on and, after a certain interval, outputs an on / off message to the control module 200. The control module 200 receives this message and, along with information collected by the information collection module 100, determines whether to keep the automotive lighting assembly 400 on or off. This interval can be a default time, such as 1 minute, or can be set by the driver.

[0069] The preset conditions are divided into four types based on vehicle speed: high speed, normal speed, low speed, and safe driving condition. High speed is defined as a vehicle speed greater than 80 km / h. Normal speed is defined as a vehicle speed between 20-40 km / h. Low speed is defined as a vehicle speed less than 20 km / h. The remaining speed ranges constitute the safe driving condition, during which the information collection module 100 temporarily ceases operation.

[0070] When the vehicle speed exceeds 80 km / h, the weather information collection component 102 collects surrounding weather information, and the traffic information collection component 103 collects road traffic information ahead of the vehicle. The control module 200 identifies the collected information and issues prompts through the human-machine interaction module 300. The identified surrounding weather information includes various extreme weather conditions such as heavy rain, dense fog, and snow. The identified road traffic information ahead includes traffic jams, rear-end collisions, and accidents.

[0071] When the vehicle speed is between 20-40 km / h, the distance sensing component 101 collects information about the vehicles in front and behind. The control module 200 identifies the collected information and issues a prompt message through the human-machine interaction module 300. The identified information about the vehicles in front and behind includes situations where the distance between the vehicles is less than 50 meters or the number of vehicles in front and behind is greater than two.

[0072] When the vehicle speed is less than 20 km / h, the distance sensing component 101 collects information about vehicles in front and behind, as well as information about pedestrians in the surrounding area. The control module 200 identifies the collected information and issues a prompt message through the human-machine interaction module 300. The identified information about vehicles in front and behind includes distances of less than 10 meters, more than two vehicles in front and behind, or more than two pedestrians in the surrounding area.

[0073] The human-machine interface module 300 offers various information output prompts and can receive driver voice or gesture input as feedback. Driver voice feedback is received by a microphone, while gesture feedback is received by an in-vehicle camera. The system can be configured with a default feedback voice, or the driver can customize the feedback voice. A possible default voice message is "Potential accident risk detected; should you activate the front and rear lights?" The human-machine interface module 300 transmits this feedback to the BCM203, where its built-in AI analyzes and determines whether to activate the automotive lighting component 400.

[0074] The machine vision-based human-machine interaction device operates by displaying prompts via ambient lighting, in-vehicle displays, or dashboards. Ambient lighting can achieve the effect of displaying prompts through flashing patterns, color changes, or lighting effects. The flashing pattern can be 100 times per minute; lighting effects can include breathing, flame, and wave effects; and the ambient light color can be red. The ambient lighting prompts can also be customized by the driver.

[0075] Please refer to Figure 7-8 As shown, the automotive lighting control system provided in this application has different implementation methods depending on different preset conditions.

[0076] Implementation Method 1

[0077] When the vehicle speed sensor detects that the vehicle speed is greater than 80 km / h, the T-BOX201 controls the weather information collection component 102 and the traffic information collection component 103 to collect information and transmit it to the BCM203. The BCM203 determines that the information indicates a traffic jam or traffic accident has occurred 1 km ahead. In the event of extreme weather such as fog or snow, the system controls the voice interaction device, touch interaction device, or machine vision-based human-machine interaction device to output a prompt message. The driver receives this prompt message and provides feedback on whether to turn on the vehicle lighting component 400.

[0078] If the driver decides not to turn on the vehicle lighting assembly 400, the human-machine interface transmits this information to the BCM 203 without performing any further operations. If the driver decides to turn on the vehicle lighting assembly 400, the human-machine interface transmits this information to the BCM 203, and the BCM 203 controls the vehicle lighting control assembly 204 to turn on the vehicle lighting assembly 400.

[0079] Implementation Method 2

[0080] When the vehicle speed sensor detects a vehicle speed between 20-40 km / h, the ADAS controller 202 controls the radar 101a and camera 101b to collect distance information and transmit it to the BCM 203. If the BCM 203 determines that the distance to vehicles in front or behind is less than 50m, or that there are more than two vehicles on either side, it controls the voice interaction device, touch interaction device, or machine vision-based human-machine interaction device to output a prompt. The driver receives this prompt and provides feedback on whether to turn on the vehicle lighting assembly 400.

[0081] If the driver decides not to turn on the vehicle lighting assembly 400, the human-machine interface transmits this information to the BCM 203 without any further action. If the driver decides to turn on the vehicle lighting assembly 400, the human-machine interface transmits this information to the BCM 203, and the BCM 203 controls the vehicle lighting control assembly 204 to turn on the vehicle lighting assembly 400.

[0082] Implementation Method 3

[0083] When the vehicle speed sensor 104 detects a vehicle speed of less than 20 km / h, the ADAS controller 202 controls the radar 101a and camera 101b to collect distance information and transmit it to the BCM 203. If the BCM 203 determines that the distance to vehicles in front or behind is less than 10m, there are more than two vehicles on either side, or there are more than two pedestrians nearby, it controls the voice interaction device, touch interaction device, or machine vision-based human-machine interaction device to output a prompt. The driver receives this prompt and provides feedback on whether to turn on the vehicle lighting assembly 400.

[0084] If the driver decides not to turn on the vehicle lighting assembly 400, the human-machine interface transmits this information to the BCM 203 without any further action. If the driver decides to turn on the vehicle lighting assembly 400, the human-machine interface transmits this information to the BCM 203, and the BCM 203 controls the vehicle lighting control assembly 204 to turn on the vehicle lighting assembly 400.

[0085] Since the automotive lighting assembly 400 includes a front combination lamp 401 and a rear combination lamp 402, the driver can therefore decide to turn on only the front combination lamp 401 or the rear combination lamp 402, or both simultaneously. Upon receiving feedback that the automotive lighting assembly 400 is activated, the BCM 203, by default, activates the front combination lamp 401 and the rear combination lamp 402 via the front light control assembly 204a and the taillight control assembly 204b respectively, to alert vehicles on the left, right, and in front and behind, encouraging them to maintain a safe distance and enhancing driving safety. The driver can also manually set only the front combination lamp 401 or the rear combination lamp 402 to reduce unnecessary energy waste.

[0086] Please refer to Figure 9 As shown, when the vehicle lighting assembly 400 is detected to be turned on, the BCM203 activates the radar 101a and camera 101b via the ADAS controller 202. The radar 101a and camera 101b collect information about vehicles and pedestrians in front and behind, and transmit it to the BCM203 via the ADAS controller 202.

[0087] BCM203 simultaneously receives vehicle speed information from vehicle speed sensor 104 and information on vehicles ahead and behind, as well as pedestrian information from ADAS controller 202. When the vehicle speed is greater than 40 km / h, or between 20-40 km / h, and the distance between the vehicle in front or behind is greater than 50 m, or there is only one vehicle on each side, it controls the automotive lighting assembly 400 to turn off. When the vehicle speed is less than 20 km / h, and the distance between the vehicle in front or behind is greater than 10 m, and there is only one vehicle on each side, or there are fewer than two pedestrians nearby, it controls the automotive lighting assembly 400 to turn off.

[0088] Since this method can automatically turn off the on-screen car lights 400 based on actual road conditions without driver confirmation, it can prevent drivers from forgetting to turn off the car lights after turning them on, thus greatly saving car energy.

[0089] Please refer to Figure 10As shown, the automotive lighting control system provided in this application also includes a machine learning module 205. The machine learning module 205 constructs a machine learning model based on a deep neural network, obtains a training dataset relevant to a specific driver, and preprocesses and extracts features from the training dataset. The training dataset includes surrounding weather information, surrounding traffic information, information of vehicles in front and behind, information of pedestrians in the surrounding area, vehicle speed information, prompt information, and feedback information.

[0090] The machine learning model is input with data including surrounding weather information, traffic information, information about vehicles in front and behind, and whether the car lights are on. The training dataset must contain at least 40 training data points. The machine learning model may also input with information about the city where the car is located, the location where the car is traveling, and the time period during which the car was traveling.

[0091] The machine learning module 205 trains a machine learning model using the preprocessed training dataset and optimizes the alert method. The machine learning model is trained using a multi-process parallel queue, reading and consuming data simultaneously. The alert method optimization includes generating personalized alert patterns for specific drivers. Personalized alert patterns include: changing preset conditions, such as preset vehicle speed ranges, preset distances to vehicles in front and behind, and the number of vehicles in front and behind; changing the frequency or method of alert message generation, such as broadcasting an alert message every 30 seconds, or using different voices (male, female, child's voice, etc.) to broadcast the alert message.

[0092] The machine learning module 205 obtains an optimized automatic control system based on the trained machine learning model. The active safety driving control system provided in this application controls the vehicle lighting component 400 to activate its reminder function based on collected road condition and vehicle speed information. When the vehicle lighting component 400 is activated, a prompt message is output to the driver. The driver can determine whether the vehicle lights need to be automatically activated based on the prompt message and control the activation or deactivation of this function through the human-machine interaction module 300.

[0093] The driver can also actively control the trained machine learning module through the human-machine interaction module 300. Active control includes turning off the personalized prompt mode.

[0094] In summary, the automotive lighting control system provided in this application can collect road condition information in advance, make judgments on the road condition information and provide it to the driver for reference to decide whether to turn on the automotive lights. Therefore, it can detect and identify potential safety hazards in advance, remind the driver to react to dangerous situations in a timely manner, and nip risks in the bud.

[0095] The active safety driving reminder method and control system provided in this application can activate the reminder function of the vehicle's lighting components and issue a warning based on the driver's positive feedback, without requiring the driver to manually operate the vehicle's lighting components. The final decision on whether to activate the lights is made by the driver, allowing for direct human intervention in case of a misjudgment by the reminder system, and is more in line with the driver's preferences and driving habits.

[0096] When the vehicle lights are detected to be on, this application can also automatically determine whether to turn them off based on road conditions, thus preventing drivers from wasting vehicle energy by forgetting to turn them off.

[0097] Meanwhile, the active safety driving reminder method and control system provided in this application has a certain degree of intelligence, which can record the different driving habits of different drivers in the same vehicle, change the reminder method and control mode, and create a customized active safety driving reminder method and control system for drivers.

[0098] The active safety driving reminder method and control system provided in this application are adaptable and can be adjusted according to the driver's changing driving habits as driving time increases, thereby improving the driver's user experience and tailoring an active safety driving reminder method and control system to each driver.

[0099] Other embodiments of this specification will readily occur to those skilled in the art upon consideration of the specification and practice of the invention claimed herein. This specification is intended to cover any variations, uses, or adaptations that follow the general principles of this specification and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this specification are indicated by the following claims.

[0100] It should be understood that this specification is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this specification is limited only by the appended claims.

[0101] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A proactive safety driving reminder method, comprising: Acquire first information during vehicle operation, including road condition information and vehicle speed information; Based on preset conditions, second information is generated from the first information, and the second information includes prompt information. Send the notification message to the driver and obtain the driver's feedback. and The system responds to positive feedback from the driver by activating a reminder function to turn on the vehicle's lighting components. The road condition information includes surrounding weather information, surrounding traffic information, information on vehicles in front and behind, and information on pedestrians in the surrounding area; the preset conditions include the vehicle being at high speed, normal speed, and low speed. At high speed, the system identifies surrounding weather and traffic information; at normal speed, it identifies information about vehicles in front and behind; at low speed, it identifies information about vehicles in front and behind, as well as information about pedestrians in the vicinity. The information about vehicles in front and behind includes the distance to or number of vehicles in front and behind.

2. The active safe driving reminder method according to claim 1, characterized in that, The prompts include voice prompts or visual prompts; in response to negative feedback from the driver, the operation of turning on the vehicle lights is not performed; when traffic conditions are severe, the prompts are sent to the driver again, and the driver's feedback is obtained.

3. The active safe driving reminder method according to claim 1, characterized in that, The reminder function is automatically turned off when the distance between the vehicle and the vehicle exceeds the set value or when the number of vehicles in front and behind decreases. The reminder function for the automotive lighting components includes: the front and rear taillights of the automotive lighting components flashing in high-speed and normal-speed conditions, and the front and rear brake lights turning on in low-speed conditions.

4. The active safe driving reminder method according to claim 1, characterized in that, It also includes establishing a machine learning model, obtaining a training dataset related to a specific driver, the training data including the first information, the second information, and the feedback information; training the machine learning model based on the training dataset, and using the trained machine learning model to optimize the reminder method.

5. The active safe driving reminder method according to claim 4, characterized in that, The optimized reminder method includes generating a personalized reminder mode for a specific driver, wherein the personalized reminder mode includes changing preset conditions or changing the generation frequency or reminder method of the reminder information.

6. The active safe driving reminder method according to claim 4, characterized in that, The training dataset includes at least 40 training data points; the road condition information also includes information about the city where the vehicle is located, the location where the vehicle is traveling, and the time period during which the vehicle is traveling.

7. The active safe driving reminder method according to claim 5, characterized in that, It also includes controlling the trained machine learning model, including turning off the personalized prompt mode.

8. An active safety driving control system, characterized in that, The system includes an information collection module, a control module, a human-machine interaction module, and automotive lighting components. The information collection module collects first information, including road condition information and vehicle speed information. The control module, based on the first information and preset conditions, controls the human-machine interaction module to output second information, including prompt information. The human-machine interaction module sends the prompt information to the driver and receives feedback information. The control module controls the automotive lighting components based on the feedback information. The road condition information includes surrounding weather information, surrounding traffic information, information on vehicles in front and behind, and information on pedestrians in the surrounding area; the preset conditions include the vehicle being at high speed, normal speed, and low speed. At high speed, the system identifies surrounding weather and traffic information; at normal speed, it identifies information about vehicles in front and behind; at low speed, it identifies information about vehicles in front and behind, as well as information about pedestrians in the vicinity. The information about vehicles in front and behind includes the distance to or number of vehicles in front and behind.

9. The active safety driving control system according to claim 8, characterized in that, The information collection module includes a distance sensing component, a weather information collection component, a traffic information collection component, a vehicle speed sensor, or a driving recorder; the distance sensing component includes radar or a camera.

10. The active safety driving control system according to claim 8, characterized in that, The human-computer interaction module includes a voice interaction device, a touch interaction device, or a human-computer interaction device based on machine vision.

11. The active safety driving control system according to claim 8, characterized in that, The control module includes an electronic control unit and a vehicle lighting control component; the electronic control unit includes a T-BOX, an ADAS controller, and a BCM; the vehicle lighting control component includes a headlight control component and a taillight control component; the vehicle lighting component includes a front combination lamp and a rear combination lamp; the headlight control component is connected to the front combination lamp; the taillight control component is connected to the rear combination lamp.

12. The active safety driving control system according to claim 8, characterized in that, The control module includes a machine learning module, which constructs a machine learning model to obtain road condition information, prompt information and feedback information related to a specific driver, and optimizes and generates a personalized prompt mode based on the machine learning model.

Images