Electric vehicle intelligent motion prediction and helmet illuminating lamp linkage method and system

Abstract

The invention relates to the field of data processing, and discloses an electric vehicle intelligent action prediction and helmet illuminating lamp linkage method and system. The method comprises the steps that a vehicle machine system of the electric vehicle monitors the working states of the vehicle and driving data of the electric vehicle in real time, the working states comprise the left and right steering lamp states, the double-flash signal state and the brake state, and the state information is packaged into a Bluetooth broadcast frame; the helmet Bluetooth equipment continuously monitors Bluetooth broadcast information from the electric vehicle, and analyzes state information in the broadcast frame when receiving the broadcast frame; according to the analyzed state information, an LED lamp on the helmet is controlled to carry out corresponding display; motion prediction and blind area monitoring of the electric vehicle are carried out based on the driving data of the electric vehicle, earphones on the helmet are controlled to give out corresponding prompt tones according to the prediction result and the monitoring result, and a warning light effect is automatically triggered to remind a driver of a following vehicle. The riding safety and convenience are improved, and the interaction experience between the user and other traffic participants is enhanced.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for intelligent action prediction of electric vehicles and linkage with helmet lighting. Background Art

[0002] With the acceleration of urbanization and the improvement of environmental awareness, electric vehicles, as a low-carbon and environmentally friendly means of transportation, have been widely popularized and applied around the world. Especially in short-distance travel in cities, electric vehicles have become the first choice for many people due to their flexibility and convenience. However, with the surge in the number of electric vehicles, road traffic safety issues have become increasingly prominent. Overtaking and cutting in between electric vehicles and pedestrians, electric vehicles and cars, and electric vehicles are inevitable, and various traffic accidents are very likely to occur. At present, the designs of electric vehicle taillights vary in size, height, brightness, and color, which often make people overwhelmed during the passage. Nowadays, some electric vehicles are equipped with helmet taillights, and use an external remote control handle on the handle to transmit signals through buttons to light up the corresponding taillights. Although this method improves the lighting effect to a certain extent, it also has the following technical problems:

[0003] The external remote control handle on the handlebars, which transmits signals to light up the corresponding taillights through buttons, is not an ergonomic structure designed by the original car, and the operation is not convenient and intelligent enough. There is usually a delay, or the rider is flustered and cannot send instructions correctly. Especially in an emergency, the rider may not be able to control the lights in a timely and accurate manner, thus affecting driving safety. Summary of the invention

[0004] One purpose of the present application is to provide a method for intelligent action prediction and helmet lighting linkage of an electric vehicle, at least to solve the technical problems that the prior art uses an external remote control handle on the handlebar to transmit signals to light up the corresponding taillights, which is not convenient and intelligent enough, and generally has a delay, or the rider is in a panic and cannot send instructions correctly, affecting driving safety.

[0005] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0006] In a first aspect, some embodiments of the present application provide a method for intelligent action prediction of an electric vehicle and linkage with a helmet lighting, the method comprising:

[0007] The vehicle computer system of the electric vehicle monitors the working status of the vehicle and the driving data of the electric vehicle in real time, wherein the working status includes the status of the left and right turn signals, the status of the double flash signal and the brake status, and encapsulates these status information into the Bluetooth broadcast frame;

[0008] The helmet Bluetooth device continuously monitors the Bluetooth broadcast information from the electric vehicle and parses the status information in the broadcast frame when it receives it;

[0009] Control the LED lights on the helmet to display accordingly according to the parsed status information, including but not limited to left and right turn indications, double flash indications, and brake indications;

[0010] Based on the driving data of the electric vehicle, the electric vehicle action prediction and blind spot monitoring are performed, and according to the prediction results and the monitoring results, the earphones on the helmet are controlled to emit corresponding prompt sounds, and the warning light effect is automatically triggered to remind the driver of the following vehicle;

[0011] The helmet is integrated with a Bluetooth headset with voice control function, and users can answer calls, start or close navigation, and send messages through voice commands.

[0012] According to a second aspect of the present application, there is provided an electric vehicle intelligent motion prediction and helmet lighting linkage system for implementing the method described in the first aspect, the system comprising:

[0013] The electric vehicle system is equipped with a Bluetooth module for real-time monitoring of the vehicle's working status and electric vehicle driving data, including the left and right turn signal status, double flash signal status, and brake status, and encapsulating these status information into Bluetooth broadcast frames;

[0014] A helmet with an integrated Bluetooth device is used to continuously monitor Bluetooth broadcast information from electric vehicles and parse the status information in the broadcast frame when it is received; according to the parsed status information, the LED lights on the helmet are controlled to display accordingly, including but not limited to left and right turn indications, double flash indications, and brake indications;

[0015] An intelligent monitoring module, used to predict the movement of the electric vehicle and monitor the blind spot based on the driving data of the electric vehicle, and to control the earphones on the helmet to emit corresponding prompt sounds according to the prediction results and monitoring results, and to automatically trigger the warning light effect to remind the driver of the following vehicle;

[0016] The Bluetooth headset is integrated into the helmet and has a voice control function. Users can answer calls, start or close navigation, and send messages through voice commands.

[0017] Compared with the related art, this application achieves the following beneficial effects:

[0018] In the scheme of the present application, by real-time monitoring of the working status and driving data of the electric vehicle, and combining with intelligent action prediction, the system can judge the possible actions of the vehicle in advance (such as steering, braking, etc.), and display them through the LED lights on the helmet, effectively reminding the driver of the following vehicle, and reducing traffic accidents caused by untimely response. The blind spot monitoring function can timely detect obstacles or other traffic participants around the vehicle, further reducing the risk of collision. The helmet integrates Bluetooth headsets and supports voice control functions. Users can easily answer calls, start or close navigation, send messages, etc. through voice commands without distracting the operation of mobile phones or vehicle control buttons, which improves the convenience and safety of riding. The LED lights on the helmet can automatically adjust the display according to the vehicle status, without the need for manual operation by the rider, reducing the complexity and delay of operation. The system can automatically predict the actions of electric vehicles and monitor blind spots, and automatically trigger the corresponding prompt sound and warning light effects according to the prediction results and monitoring results, which improves the intelligence and automation level of the system. Wireless communication between the vehicle and the helmet is realized through the encapsulation and transmission of Bluetooth broadcast frames, without the need for additional wired connections or external remote control handles, simplifying the system structure. Real-time monitoring and prediction of vehicle movements, as well as determining the distance between the vehicle and other traffic participants based on environmental information, enable the system to more accurately judge the safety conditions around the vehicle and improve the reliability of the system. By making predictions first, the frequency of real-time data acquisition can be reduced, thereby reducing data processing delays, improving response speed, and making operations such as light control more timely. The prediction process can be carried out in the background, avoiding the complexity of real-time data acquisition and processing, making the overall operation of the system more efficient. Predict the vehicle's movements and compare them with the actual movements to ensure that all behaviors are correctly identified and responded to, reducing misjudgments. Automatically control the helmet's lighting so that other traffic participants can better perceive the rider's intentions, thereby reducing the risk of traffic accidents. The helmet Bluetooth device continuously monitors Bluetooth broadcast information from electric vehicles to ensure timely reception and processing of information, reducing safety hazards caused by signal delays or loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0020] Figure 1 This is an exemplary flow chart of a method for intelligent action prediction of an electric vehicle and linkage with a helmet lighting provided in the first embodiment of the present application;

[0021] Figure 2This is a schematic flow chart of sub-steps included in step S140 of a method for intelligent action prediction of an electric vehicle and linkage with a helmet lighting provided in the first embodiment of the present application;

[0022] Figure 3 This is a schematic flow chart of sub-steps included in step S140 of a method for intelligent action prediction of an electric vehicle and linkage with a helmet lighting provided in the second embodiment of the present application;

[0023] Figure 4 This is a schematic flow chart of sub-steps included in step S140 of a method for intelligent action prediction of an electric vehicle and linkage with a helmet lighting provided in the third embodiment of the present application;

[0024] Figure 5 This is an exemplary structure of an electric vehicle intelligent action prediction and helmet lighting linkage system provided in Example 4 of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] First embodiment

[0027] The first embodiment of the present application relates to a method for linking intelligent action prediction of an electric vehicle with helmet lighting. Figure 1 As shown, the method comprises the following steps:

[0028] S110: The vehicle computer system of the electric vehicle monitors the working status of the vehicle and the driving data of the electric vehicle in real time, wherein the working status includes the status of the left and right turn signals, the status of the double flash signal, and the braking status, and encapsulates the status information into a Bluetooth broadcast frame;

[0029] The specific implementation process of step S110 includes:

[0030] 1. Bluetooth module configuration

[0031] The vehicle uses a Bluetooth chip that supports multi-group and multi-slave working modes.

[0032] When the vehicle Bluetooth module acts as a slave device (Slave), it has two main functions:

[0033] (1) Can initiate a broadcast to notify other listening Bluetooth peripherals of vehicle information through broadcast;

[0034] (2) The APP can actively connect to the vehicle's Bluetooth device

[0035] When the vehicle Bluetooth module acts as the master device (Master), it can also monitor the broadcasts of other Bluetooth devices, such as a Bluetooth tire pressure gauge.

[0036] 2. Broadcast settings

[0037] The present invention mainly uses the slave mode of the vehicle. After the vehicle is started, the Bluetooth module adopts the time-sharing working mode to provide an unconnectable BLE broadcast, which contains the vehicle's MAC address and basic warning information of the vehicle.

[0038] 3. Working status monitoring

[0039] The vehicle computer system of an electric vehicle integrates a variety of sensors and controllers, which can monitor the various working states and driving data of the vehicle in real time. The vehicle computer system monitors the working state of the vehicle in real time, such as left and right turn signals, double flash signals, brake status, etc. These status information are obtained through the internal interface of the vehicle computer system. Among them, the driving data of the electric vehicle can be information about the movement state of the electric vehicle collected in real time, specifically, including data such as the vehicle's driving speed and steering angle, which are used to analyze the dynamic behavior of the vehicle.

[0040] 4. Bluetooth broadcast frame encapsulation

[0041] The vehicle system encapsulates the monitored status information and driving data into Bluetooth broadcast frames, which contain sufficient information for the helmet Bluetooth device to parse and use. The broadcast frame also contains sufficient identifiers such as UU ID, MAC and status code so that the helmet Bluetooth device can recognize and parse it.

[0042] S120: The helmet Bluetooth device continuously monitors the Bluetooth broadcast information from the electric vehicle, and parses the status information in the broadcast frame when receiving the broadcast frame;

[0043] In step S120, the Bluetooth device integrated in the helmet has low power consumption and continuous monitoring capabilities to ensure that no broadcast information from the vehicle is missed during riding.

[0044] Listening to broadcasts: The Bluetooth device of the helmet works in the master mode (Master), configured as the listening mode, and the Bluetooth device continuously scans the surrounding Bluetooth broadcast frequency bands, looking for Bluetooth broadcast information from a specific vehicle (identified by pairing or preset ID). When a broadcast frame is received, the status information in it is parsed.

[0045] Receiving and parsing: Once a broadcast frame is received, the Bluetooth device immediately parses the status information and driving data in it and prepares for subsequent processing.

[0046] S130: Control the LED lights on the helmet to display corresponding information according to the parsed status information, including but not limited to left and right turn indication, double flash indication, and brake indication;

[0047] The specific implementation process of step S130 includes:

[0048] LED light control: Multiple sets of LED lights are integrated on the helmet to display different vehicle status.

[0049] Display logic: According to the parsed status information (such as left or right turn, double flash, brake, etc.), control the corresponding LED lights to light up or flash. Specifically, according to the parsed status information (such as left or right turn, double flash, brake, etc.), control the LED lights on the helmet to display accordingly. When a turn signal is received, the LED in the corresponding direction of the helmet flashes; when a double flash signal is received, the LEDs on both sides of the helmet flash quickly at the same time. When a brake signal is received, the LEDs on both sides of the helmet are always on at the same time.

[0050] User feedback: The display of LED lights can be designed to be intuitive and easy to understand so that other traffic participants can quickly identify the status of the vehicle. Preferably, the mobile phone, car computer and helmet are linked together, and mobile phone APP users can also customize the lighting effects.

[0051] S140: Predicting the movement of the electric vehicle and monitoring the blind spot based on the driving data of the electric vehicle, controlling the earphones on the helmet to emit corresponding prompt sounds according to the prediction results and the monitoring results, and automatically triggering a warning light effect to remind the driver of the following vehicle;

[0052] The helmet is integrated with a Bluetooth headset with voice control function. Users can answer calls, start or close navigation, and send messages through voice commands. This function is used to free the rider's hands and make riding safer. The microphone on the Bluetooth headset has a noise reduction function, which can eliminate wind noise during riding, ensure the call quality during riding, and ensure the accuracy of voice control.

[0053] Further, such as Figure 2 As shown, in this embodiment, step S140 performs electric vehicle motion prediction and blind spot monitoring based on the electric vehicle driving data, controls the earphones on the helmet to emit corresponding prompt sounds according to the prediction results and monitoring results, and automatically triggers the warning light effect to remind the driver of the following vehicle, which specifically includes the following sub-steps:

[0054] S141, inputting the electric vehicle driving data into a preset prediction model to obtain an electric vehicle action prediction result; wherein the electric vehicle driving data includes a vehicle driving speed and a vehicle steering angle; and the electric vehicle action prediction result includes at least one predicted action.

[0055] First of all, the usage scenario of the present application can be to predict the action of an electric vehicle, and pre-encapsulate the predicted results into a Bluetooth broadcast frame, and then determine the actual action in real time. If it is consistent with the predicted action, the pre-encapsulated Bluetooth broadcast frame is directly sent to the helmet Bluetooth module for the helmet Bluetooth module to control the corresponding lighting of the helmet for display.

[0056] Based on the above usage scenarios, it can be understood that the executor of the present application can be the linkage between the intelligent action prediction of electric vehicles and the helmet lighting, and no excessive limitations are made here.

[0057] The preset prediction model can be a model trained using machine learning or other algorithms, and is used to predict the future behavior of the vehicle based on input data.

[0058] The electric vehicle action prediction result can be a result obtained based on driving data and prediction models, indicating the actions that the vehicle may perform in the next period of time. Possible predicted actions include "turn left", "turn right", "brake", "accelerate", etc., depending on the current driving state and environment.

[0059] The vehicle travel speed may be the distance that the electric vehicle travels in a specific time period.

[0060] The vehicle steering angle may be the angle between the vehicle's forward direction and its actual direction of travel.

[0061] Predicted actions can be specific actions that electric vehicles may take in the future based on driving data and model analysis.

[0062] Speed ​​sensors and steering angle sensors can be installed on electric vehicles. Use a GPS module to obtain the real-time speed of the vehicle. Use an electronic steering angle sensor to obtain the steering angle. The vehicle's driving speed and steering angle are collected regularly (for example, every second) through the on-board computer system. These data are then stored in a buffer area for subsequent processing. The latest driving data (speed and steering angle) is read from the buffer area. The data is preprocessed, such as standardization and feature extraction, to ensure that the input meets the requirements of the model. Using a trained prediction model (for example, a machine learning-based model), the prepared driving data is input into the model. The model analyzes the dynamic behavior of the vehicle based on the input data. The prediction model outputs a result, which is usually a list of multiple possible actions, such as "turn left", "turn right", "brake", "accelerate", etc. The output format can be a category label (such as a string) or a probability distribution (such as a vector), indicating the probability of each action. Based on the output prediction results, the action with the highest probability is selected as the final predicted action. If necessary, a threshold can be set, and the action is considered valid only when the probability of an action is higher than this threshold.

[0063] Based on the above technical solution, the optional, preset prediction model training process includes:

[0064] Acquire historical action execution records, and determine historical actions, historical vehicle driving speeds, and historical vehicle steering angles according to the historical action execution records;

[0065] Marking the vehicle speed label of the historical action according to the historical vehicle speed, and marking the vehicle steering angle label of the historical action according to the historical vehicle steering angle;

[0066] Creating an action dataset based on the historical actions, the vehicle speed label, and the vehicle steering angle label;

[0067] Construct a prediction model and train the prediction model according to the action data set until the prediction model reaches a preset prediction model training standard.

[0068] In this solution, the historical action execution record may refer to a detailed record of all actions performed by the vehicle during past driving, including starting, braking, steering, etc.

[0069] The historical actions may be specific actions performed by the vehicle.

[0070] The historical vehicle driving speed may be speed data when the vehicle performs these historical actions.

[0071] The historical vehicle steering angle may be steering angle data when the vehicle performs these historical actions.

[0072] The vehicle speed tag may refer to a mark of the vehicle speed associated with each historical action, which is used to identify the speed when the action is executed.

[0073] The vehicle steering angle tag may be a steering angle mark associated with each historical action, used to identify the steering angle when the action is executed.

[0074] The action dataset can be a collection containing historical actions, corresponding driving speed labels, and steering angle labels, which is usually used for model training.

[0075] The preset prediction model training standard may refer to a set of standards or indicators used to evaluate the performance of the prediction model, such as accuracy, recall rate, etc., to ensure that the prediction ability of the model reaches a certain level.

[0076] Historical action execution records can be obtained from the vehicle recording system to ensure that the data covers multiple scenarios and conditions. The corresponding vehicle speed and steering angle are labeled for each historical action, and these annotations are combined with the action records. Then all historical actions, speed labels, and steering angle labels are integrated into a structured dataset for model training. Select a suitable machine learning algorithm and use the created action dataset for model training. Evaluate the performance of the model according to the preset criteria and adjust the model parameters or structure to meet the training criteria. Iterate the model training when necessary until the preset criteria are met.

[0077] In this solution, by recording and analyzing historical vehicle speeds and steering angles, the prediction model can learn the vehicle's behavior patterns in different driving scenarios, helping autonomous vehicles make more reasonable and safe decisions in complex road environments.

[0078] Based on the above technical solution, optionally, after sending the second Bluetooth broadcast frame to the helmet Bluetooth module, the method further includes:

[0079] Acquire an actual vehicle driving speed and an actual vehicle steering angle corresponding to the actual motion data, label the actual motion data with a vehicle driving speed label according to the actual vehicle driving speed, and label the actual motion data with a vehicle steering angle label according to the actual vehicle steering angle;

[0080] The actual action data, the corresponding vehicle speed label and the corresponding vehicle steering angle label are added to the action data set, and the prediction model is retrained according to the action data set until the prediction model reaches a preset prediction model training standard.

[0081] In this solution, the actual vehicle speed may refer to the real speed of the vehicle at a certain moment, which is usually monitored and recorded in real time by a speed sensor of the vehicle.

[0082] The actual vehicle steering angle may refer to the actual steering angle of the vehicle at a certain moment, which is monitored and recorded in real time by the vehicle's steering sensor.

[0083] The actual motion data can be obtained from the vehicle's sensor system. At the same time, the actual vehicle speed and steering angle at that moment are obtained. The corresponding vehicle speed label and steering angle label are recorded for each actual motion data. The actual motion data and its corresponding speed label and steering angle label are integrated and added to the existing motion data set. The prediction model is retrained using the updated motion data set. The model performance is evaluated until the preset training standard is met.

[0084] In this solution, continuously updating the data set can enhance the training basis of the model and improve its generalization ability. By introducing actual data, the model can be closer to the actual situation and improve the prediction accuracy.

[0085] S142, obtaining environmental information in real time through radar and camera, and determining distance data between the electric vehicle and other traffic participants according to the environmental information.

[0086] Environmental information may be external conditions and states around the electric vehicle, and may include surrounding traffic conditions: such as the number and behavior of other vehicles, pedestrians, bicycles, etc.

[0087] Other traffic participants can be various entities around electric vehicles that may affect their driving safety, including vehicles: other cars, motorcycles, etc. Pedestrians: pedestrians walking on the road. Cyclists: other electric vehicles, bicycles, etc.

[0088] Distance data can refer to the spatial distance between the electric vehicle and other traffic participants, usually measured in meters. This data helps to determine the potential risk of collision or safe distance.

[0089] Radars such as LiDAR, cameras and other sensors can be used to monitor the surrounding environment in real time and collect data such as road conditions and traffic flow. The sensor data is processed by algorithms to extract effective environmental information. Computer vision technology (such as object detection models such as YOLO) is used to identify surrounding traffic participants and obtain their categories, locations and movement directions. Combine data from different sensors to improve recognition accuracy and ensure the identification of all relevant traffic participants. Then, the distance between the electric vehicle and other traffic participants is measured by sensors (such as ultrasonic sensors or LiDAR). Based on the location information of the target participant and the current position of the electric vehicle, the relative distance data is calculated.

[0090] S143: If the distance data is higher than a preset distance threshold, encapsulate the electric vehicle action prediction result into a first Bluetooth broadcast frame.

[0091] The preset distance threshold may refer to a minimum safety distance set by the system according to a preset safety standard or driving environment. When the distance between the electric vehicle and other traffic participants exceeds this value, it indicates that the current driving is safe.

[0092] The first Bluetooth broadcast frame may refer to an encapsulated data packet used to transmit information in Bluetooth communication. It may include vehicle status information: such as action prediction results (steering, braking, etc.). Identifiers: such as the vehicle's MAC address and UU ID for the receiving device to identify. Other information: such as timestamps and signal strength, etc., to help the receiving end parse the data.

[0093] The distance data between the electric vehicle and other traffic participants can be obtained from the sensor in real time. The obtained distance data is compared with the preset distance threshold. If the distance is greater than the threshold, the action prediction results of the electric vehicle (such as steering, braking, etc.) are encapsulated into the data frame. Then add the identifier: add the vehicle's MAC address, UU ID and other information. Add a timestamp: record the generation time so that the receiving end can verify the timeliness of the data. And ensure that the data is encapsulated according to the protocol format of the Bluetooth broadcast frame, configure the Bluetooth module to broadcast mode, and prepare to send data frames.

[0094] S144, obtaining the actual motion data of the electric vehicle in real time. If the electric vehicle motion prediction result is consistent with the actual motion data of the electric vehicle, the first Bluetooth broadcast frame is sent to the helmet Bluetooth module, so that the helmet Bluetooth module can parse the first Bluetooth broadcast frame, obtain the electric vehicle motion prediction result, and control the corresponding lighting of the helmet for display according to the electric vehicle motion prediction result.

[0095] The actual action data of the electric vehicle may refer to the actual operation performed by the vehicle at a specific moment, and may include the turn signal status: directly obtained through the vehicle's signal control module, indicating whether the turn signal is on (turn left or right) or off. Brake status: obtained through the vehicle's brake sensor, indicating whether the brake is currently in use. Double flash status: obtained through the control status of the double flash signal, indicating whether the double flash lights are turned on. Driving status: including the acceleration, deceleration and current speed of the vehicle.

[0096] The helmet Bluetooth module can be a Bluetooth device integrated in the riding helmet, responsible for monitoring Bluetooth signals: continuously monitoring Bluetooth broadcasts from electric vehicles. Parsing broadcast content: extracting and parsing information in the broadcast frame, such as the action prediction results of the electric vehicle. Controlling LED lights: controlling the LED lights on the helmet to give corresponding prompts (such as steering, braking, etc.) according to the parsed results.

[0097] The working status of the vehicle can be monitored in real time through the internal interface of the vehicle system, and information such as the turn signal and brake status can be obtained. These status information are recorded as the actual action data of the electric vehicle. Then the action prediction result of the electric vehicle (such as the prediction that the left turn signal will be turned on) is compared with the actual action data obtained in real time. If the prediction result is consistent with the actual action data, the first Bluetooth broadcast frame is sent to the helmet Bluetooth module through the Bluetooth module. The helmet Bluetooth module parses the received first Bluetooth broadcast frame and parses out the action prediction result of the electric vehicle. According to the parsed action prediction result, the corresponding lights on the helmet are controlled (for example, the left light flashes when turning left).

[0098] It is not difficult to find that, compared with the related art, in the solution provided by the embodiment of the present application, the electric vehicle driving data is obtained in real time, and the electric vehicle driving data is input into a preset prediction model to obtain the electric vehicle action prediction result; wherein, the electric vehicle driving data includes the vehicle driving speed and the vehicle steering angle; the electric vehicle action prediction result includes at least one predicted action; environmental information is obtained, and the distance data between the electric vehicle and other traffic participants is determined according to the environmental information; if the distance data is higher than the preset distance threshold, the electric vehicle action prediction result is encapsulated as a first Bluetooth broadcast frame; the actual action data of the electric vehicle is obtained in real time, and if the electric vehicle action prediction result is consistent with the actual action data of the electric vehicle, the first Bluetooth broadcast frame is sent to the helmet Bluetooth module for the helmet Bluetooth module to parse the first Bluetooth broadcast frame, obtain the electric vehicle action prediction result, and control the corresponding lighting of the helmet to display according to the electric vehicle action prediction result. Through the above-mentioned electric vehicle intelligent action prediction and helmet lighting linkage method, by first predicting, the frequency of real-time data acquisition can be reduced, thereby reducing data processing delay, improving response speed, and making operations such as lighting control more timely. The prediction process can be carried out in the background, avoiding the complexity of real-time acquisition and processing of data, making the overall operation of the system more efficient. The vehicle's actions are predicted and compared with the actual actions to ensure that all behaviors are correctly identified and responded to, reducing misjudgments. The helmet's lighting is automatically controlled so that other traffic participants can better perceive the rider's intentions, thereby reducing the risk of traffic accidents.

[0099] On the basis of the above technical solution, optionally, after obtaining the actual motion data of the electric vehicle in real time, the method further includes:

[0100] If the electric vehicle motion prediction result is inconsistent with the electric vehicle actual motion data, encapsulating the electric vehicle actual motion data into a second Bluetooth broadcast frame;

[0101] The second Bluetooth broadcast frame is sent to the helmet Bluetooth module, so that the helmet Bluetooth module parses the second Bluetooth broadcast frame, obtains the actual action data of the electric vehicle, and controls the lighting corresponding to the helmet for display according to the actual action data of the electric vehicle.

[0102] In this solution, the second Bluetooth broadcast frame can be a Bluetooth broadcast message for transmitting the actual action data of the electric vehicle. It contains information about the current actual action of the electric vehicle, such as turning on the turn signal, braking status, etc. These data can help the helmet Bluetooth module to update the display status of the lighting in real time to reflect the actual situation of the electric vehicle.

[0103] The status information of the electric vehicle can be monitored in real time, for example, the internal interface of the vehicle system is used to obtain data such as turn signals and brake status. Compare the predicted results of the electric vehicle action with the actual action data. If the two are inconsistent, the obtained actual action data of the electric vehicle is formatted and encapsulated to form a second Bluetooth broadcast frame. Make sure that the frame contains necessary identifiers (such as UU ID) and actual action data. Use the Bluetooth module to send the second Bluetooth broadcast frame. Specifically, the sending function of the Bluetooth API can be called to send it. The helmet Bluetooth module is in listening mode and receives the second Bluetooth broadcast frame. The helmet Bluetooth module parses the second Bluetooth broadcast frame and extracts the actual action data of the electric vehicle. According to the parsed actual action data, the lighting on the helmet is controlled to display accordingly. For example, if the actual action data indicates that the turn signal is on, the LED light in the corresponding direction is turned on.

[0104] In this solution, even if the prediction model deviates, the system can still make adjustments based on actual data to keep the response flexible and accurate.

[0105] Second embodiment

[0106] The second embodiment of the present application relates to a method for linking intelligent action prediction of an electric vehicle with helmet lighting. The second embodiment is an improvement on the first embodiment. The second embodiment is substantially the same as the first embodiment, with the main difference being that Figure 3 As shown, step S140 performs electric vehicle motion prediction and blind spot monitoring based on the electric vehicle driving data, controls the earphones on the helmet to emit corresponding prompt sounds according to the prediction results and monitoring results, and automatically triggers the warning light effect to remind the driver of the following vehicle, which specifically includes the following sub-steps:

[0107] S241, inputting the electric vehicle driving data into a preset prediction model to obtain an electric vehicle action prediction result; wherein the electric vehicle driving data includes a vehicle driving speed and a vehicle steering angle; and the electric vehicle action prediction result includes at least one predicted action.

[0108] S242, obtaining environmental information in real time through radar and camera, and determining distance data between the electric vehicle and other traffic participants based on the environmental information.

[0109] S243: If the distance data is lower than a preset distance threshold, determine the traffic participant whose distance data is lower than the preset distance threshold as a target traffic participant.

[0110] Target traffic participants can refer to other traffic entities related to the driving behavior of electric vehicles in a specific scenario, including pedestrians, bicycles, cars, etc. When the distance data of the electric vehicle is lower than the preset threshold, these traffic participants are regarded as objects that may affect the driving safety of the electric vehicle.

[0111] Sensors (such as lidar, cameras or ultrasonic sensors) can be used to obtain the location information of traffic participants in the surrounding environment. According to the relative position between the electric vehicle and other traffic participants, the distance data of each traffic participant and the electric vehicle is calculated. A safety distance threshold (such as 2 meters, 5 meters, etc.) is preset, and the obtained distance data is compared with the preset distance threshold. If the distance data of a traffic participant is lower than the preset threshold, the participant is determined to be a target traffic participant.

[0112] S244, obtaining the position information of the target traffic participant, and determining the relative direction between the target traffic participant and the electric vehicle according to the position information.

[0113] Position information may refer to the coordinate data of the target traffic participant in space, which is usually obtained through sensors (such as cameras, lidar), including its position (x, y coordinates) and possible height information.

[0114] The relative direction may refer to the positional relationship of the target traffic participant relative to the electric vehicle, which may be divided into: directly in front (approaching in a straight line in front), directly behind (approaching in a straight line in the rear), left rear / right rear (approaching laterally, on the left or right side).

[0115] Sensors can be used to obtain data about the surrounding environment and extract the location information (such as coordinates) of the target traffic participant. The relative position relationship between the electric vehicle and the target traffic participant is calculated. The relative direction is determined based on the coordinate position: if the target position is in front of the electric vehicle, it is marked as "directly in front". If the target position is behind the electric vehicle, it is marked as "directly behind". If the target position is on the left and right sides of the electric vehicle, it is marked as "left rear / right rear".

[0116] S245, if the relative direction is the left rear / right rear, determine the movement direction of the target traffic participant, and determine the vehicle movement direction of the electric vehicle according to the electric vehicle action prediction result.

[0117] The moving direction of the target traffic participant may refer to the direction of its moving trajectory, which is usually calculated through its position information and time data.

[0118] The vehicle motion direction may refer to the direction in which the electric vehicle is traveling, which is typically determined by the vehicle's steering angle or navigation system.

[0119] If the relative direction is left rear / right rear, the direction of movement can be calculated by obtaining the position information of the target traffic participant at multiple time points (such as the current time and the position at the previous time point):

[0120] Movement direction = atan2(y2-y1,x2-x1);

[0121] Among them, (x1, y1) is the position of the previous time point; (x2, y2) is the position of the current time point; atan2(y2-y1, x2-x1) is used to calculate the direction angle (the angle relative to the x-axis) from the origin to the point (x2, y2), and can return a value ranging from -π to π (or -180° to 180°).

[0122] The direction of movement will be expressed in degrees or radians, relative to the direction of the electric vehicle.

[0123] The direction of movement of the electric vehicle is then calculated based on its speed and steering angle:

[0124] If the current speed of the electric vehicle is V and the steering angle is θ, the direction of motion is:

[0125] Vehicle moving direction = atan2(sin(θ),cos(θ));

[0126] Here, θ is the angle measured clockwise from true north.

[0127] S246, judging whether there is a collision risk according to the movement direction of the target traffic participant and the movement direction of the electric vehicle; if there is no collision risk, encapsulating the electric vehicle motion prediction result into a first Bluetooth broadcast frame.

[0128] The direction of motion of the target traffic participant can be compared with the vehicle motion direction of the electric vehicle and the angle between them can be calculated:

[0129] Angle = |movement direction of target traffic participant - movement direction of vehicle|;

[0130] If the angle is less than a certain threshold (e.g., 30 degrees), it is considered that the two may collide; otherwise, it is considered that there is no risk of collision. If the judgment result shows that there is no risk of collision, the action prediction result of the electric vehicle is encapsulated into a first Bluetooth broadcast frame, which includes the current state of the electric vehicle, the expected action and related information.

[0131] In this embodiment, by real-time monitoring and judging the distance and movement direction of the target traffic participant, the potential collision risk can be effectively identified, so that necessary preventive measures can be taken. By using real-time data and quickly responding to environmental changes, the system can adapt to dynamic driving scenarios and reduce the probability of accidents.

[0132] Based on the above technical solution, optionally, after determining whether there is a collision risk according to the moving direction of the target traffic participant and the moving direction of the electric vehicle, the method further includes:

[0133] If there is a risk of collision, a collision warning message is generated according to the direction of movement of the vehicle, and the collision warning message is sent to a helmet voice device, so that the helmet voice device plays the collision warning message to the rider to avoid the risk of collision.

[0134] In this solution, the collision warning information can be a warning content generated by the system to remind the rider of the potential risk of collision. The content may include specific instructions such as "Watch out for vehicles on the left" or "Pedestrians ahead, please slow down."

[0135] Answering calls and listening to navigation while riding are common scenarios. However, answering calls / listening to navigation with one hand and riding with one hand are very dangerous. This design integrates microphone headphones into the helmet and has a voice control function. You can wake up the voice assistant that comes with the mobile phone through voice and control the functions of the mobile phone. It can realize functions such as answering and hanging up calls, starting and closing navigation, freeing your hands and ensuring riding safety. The microphone with noise reduction function can eliminate riding wind noise and ensure the call quality while riding. Therefore, the helmet voice device can be a microphone headset in the helmet.

[0136] The system can obtain the location information and movement direction of the electric vehicle and surrounding traffic participants (such as pedestrians and vehicles) in real time. If the angle is less than a certain threshold (for example, 30 degrees), it is considered that the two may collide; otherwise, it is considered that there is no risk of collision. If the judgment result shows that there is a risk of collision, the system generates a warning message according to the direction of the vehicle's movement, such as: "Attention, the vehicle on the left is about to turn, please slow down." This information is specific according to the situation and may also include distance and speed information. The warning message is then sent to the helmet voice device through the vehicle communication system. The helmet voice device receives the information and plays the warning content through the speaker. After hearing the sound, the rider will be aware of the potential danger and can take measures such as slowing down or changing the driving route. For example, there is a pedestrian on the right rear of the electric vehicle preparing to cross the road. The system detects that the distance between the electric vehicle and the pedestrian is within 2 meters, and the system generates a warning: "There is a pedestrian on the right rear, please pay attention!" and sends it to the helmet voice device. After hearing the warning, the rider immediately slows down and observes the surroundings to avoid the potential risk of collision.

[0137] In this solution, real-time detection of surrounding traffic participants and potential collision risks, and timely reminders to cyclists to take measures can significantly reduce the accident rate and protect the safety of cyclists. Customized voice warnings are generated according to the direction of movement of the electric vehicle, which can issue warnings more accurately for specific scenarios rather than general prompts. This intelligence makes reminders more effective.

[0138] Based on the above technical solution, optionally, after obtaining the location information of the target traffic participant and determining the relative direction between the target traffic participant and the electric vehicle according to the location information, the method further includes:

[0139] If the relative direction is directly behind, rear-end collision warning information is generated according to the relative direction, and the rear-end collision warning information is sent to the helmet voice device, so that the helmet voice device plays the rear-end collision warning information to the rider to avoid the risk of rear-end collision.

[0140] In this solution, the rear-end collision warning information can be a safety warning generated when a rear-end collision risk is detected between an electric vehicle and other traffic participants. Its content usually includes prompting the rider to pay attention to the traffic conditions in front or behind, and take timely measures to avoid rear-end collision accidents. For example, the voice device will issue warning messages such as "The vehicle in front is too close, please slow down" or "There is a vehicle approaching from behind, please keep a safe distance."

[0141] When the distance data is lower than the preset distance threshold, the position information of the traffic participants (such as vehicles or pedestrians) in front or behind is obtained through the sensor, and the relative direction between the electric vehicle and these traffic participants is calculated. If the relative direction is directly in front or directly behind, it is considered that there is a potential risk of rear-end collision. Then, a rear-end collision warning message is generated according to the relative direction, including reminding the rider that the distance between the traffic participants in front or behind and the electric vehicle is too close, and it is recommended to take measures to avoid rear-end collision. If it is in front, the system may issue a voice prompt such as "The vehicle in front is too close, please slow down and keep your distance." If it is in the rear, the system may issue a warning such as "There is a vehicle approaching quickly from behind, please pay attention to keep your distance." The system then encapsulates the generated rear-end collision warning information and sends it to the vehicle's voice device via Bluetooth or other wireless communication methods. The helmet voice device is responsible for playing these voice warning messages to remind riders of potential dangers in front and behind.

[0142] In this solution, when the distance is less than the threshold and the relative position of the traffic participant and the vehicle is in front or behind, the voice reminder is sent, so that the cyclist can take preventive measures in advance to reduce the risk of rear-end collision. The system can not only monitor the situation in front, but also pay attention to the traffic participants behind, improving the safety of cyclists in complex traffic.

[0143] Third embodiment

[0144] The third embodiment of the present application relates to a method for linking intelligent action prediction of an electric vehicle with a helmet lighting. The third implementation is an improvement on the first embodiment. The specific improvement is as follows: Figure 4 As shown, step S140 performs electric vehicle motion prediction and blind spot monitoring based on the electric vehicle driving data, controls the earphones on the helmet to emit corresponding prompt sounds according to the prediction results and monitoring results, and automatically triggers the warning light effect to remind the driver of the following vehicle, which specifically includes the following sub-steps:

[0145] S341, inputting the electric vehicle driving data into a preset prediction model to obtain an electric vehicle action prediction result; wherein the electric vehicle driving data includes a vehicle driving speed and a vehicle steering angle; and the electric vehicle action prediction result includes at least one predicted action.

[0146] S342, obtaining environmental information in real time through radar and camera, and determining distance data between the electric vehicle and other traffic participants based on the environmental information.

[0147] S343: If the distance data is higher than a preset distance threshold, encapsulate the electric vehicle action prediction result into a first Bluetooth broadcast frame.

[0148] S344, obtaining the actual motion data of the electric vehicle in real time. If the electric vehicle motion prediction result is consistent with the actual motion data of the electric vehicle, the first Bluetooth broadcast frame is sent to the helmet Bluetooth module for the helmet Bluetooth module to parse the first Bluetooth broadcast frame, obtain the electric vehicle motion prediction result, and control the corresponding lighting of the helmet for display according to the electric vehicle motion prediction result.

[0149] S345, obtaining the maximum speed, number of emergency brakes, number of emergency turns and weather data of the electric vehicle at a preset collection time point every day, and determining the daily environmental coefficient according to the weather data and a preset environmental coefficient determination standard.

[0150] The preset collection time point may refer to the time when the system collects electric vehicle related data at a fixed time or interval every day. For example, 7 am, 12 pm and 6 pm every day can be set as the preset collection time points. The collection time point can be set according to the user's riding habits or the vehicle's operating time period.

[0151] Maximum driving speed may refer to the highest speed reached by the vehicle during driving that day, usually expressed in km / h or mph.

[0152] The number of emergency brakes can refer to the number of emergency brakes during driving. Emergency brakes usually refer to the sudden and drastic deceleration of the vehicle at a relatively fast speed.

[0153] The number of sharp turns may refer to the number of times a vehicle makes sudden or sharp turns while riding, which may represent risky driving behavior.

[0154] Weather data may refer to real-time information related to the weather, such as the temperature, humidity, rainfall, wind speed, etc. of the day. Weather data may be obtained through external meteorological services.

[0155] The preset environmental coefficient determination standard may refer to the system setting an influence coefficient for the daily riding environment based on weather data. For example, the environmental coefficient is higher when the weather is bad (such as heavy rain, ice and snow), and lower when the weather is good (such as sunny). These coefficients can be used to reflect the impact of different weather conditions on driving safety. For example, sunny day: environmental coefficient = 0.8, light rain: environmental coefficient = 1.0.

[0156] The daily environmental coefficient can be a result calculated based on the weather conditions of the day and the preset environmental coefficient determination standard. It reflects the impact of the external environment of the day on the driving risk. For example, the driving risk increases on rainy days, and the environmental coefficient also increases accordingly.

[0157] The system can preset daily collection time points, and you can choose fixed time periods (such as 7 am, 12 pm, and 5 pm every day) or dynamically adjust the time points (such as automatically collecting data every 4 hours). The data collection function is triggered regularly through the vehicle system or background server. Use a scheduled task scheduler (such as cron jobs or system timer) to start data collection on time. The vehicle's built-in GPS sensor or speed sensor records the vehicle's driving speed in real time. The on-board computing unit or background system continuously monitors the vehicle speed and retains the highest speed value of the day. At the daily collection time point, the system extracts the maximum driving speed of the day from the cache and records it. Monitor emergency braking events through the vehicle's built-in acceleration sensor or braking system. Emergency braking usually refers to a short period of time when the vehicle's deceleration exceeds a certain threshold (for example: -5m / s 2). Each time an emergency brake occurs, the system records an event. At the collection time point, the system will count and store the number of emergency brakes on that day. The steering situation of the vehicle is monitored through devices such as the vehicle steering wheel angle sensor or gyroscope. Emergency steering generally refers to a steering wheel rotation angle exceeding a preset threshold in a short period of time (for example: the rotation angle is greater than 30° and the time is less than 0.5 seconds). Similar to emergency braking, the system will record the number of emergency steering events. At the preset collection time point, the system will accumulate the number of emergency steering events on that day. Then, by integrating external weather API services (such as OpenWeather, AccuWeather, etc.), the system can obtain weather information at the current location of the vehicle in real time. Weather data usually includes temperature, humidity, precipitation, wind speed, visibility, road conditions, etc. The system can obtain the weather conditions at the current location based on the vehicle's GPS positioning data, and automatically pull the latest weather data at the collection time point. Then the system classifies the weather data obtained (such as rainfall, temperature, visibility, etc.), matches the weather conditions to the preset categories (such as sunny, rainy, snowy, etc.), and determines the environmental coefficient of the day. The system determines the environmental factor for the day based on the preset criteria and the currently acquired weather data. For example, if it rains heavily on that day and the precipitation exceeds 10 mm, the environmental factor is set to 1.2. If visibility is low and accompanied by light rain, it may be set to 1.1.

[0158] S346, calculating a daily driving risk score according to the daily environmental coefficient, the maximum driving speed, the number of emergency brakes, the number of emergency turns, and a preset driving behavior scoring formula.

[0159] The driving behavior scoring formula can be used to calculate the daily driving risk score. The formula generally takes into account multiple driving behavior indicators (such as maximum speed, number of emergency brakes, etc.) and environmental factors.

[0160] The daily driving risk score can be the result calculated according to the above scoring formula, reflecting the driving risk level of the electric vehicle on a specific day. The higher the score, the more dangerous the driving behavior, and vice versa.

[0161] The required parameters in the preset driving behavior scoring formula can be calculated based on the daily environmental coefficient, maximum driving speed, number of sudden brakes, and number of sudden turns, and then substituted into the formula to calculate the daily driving risk score.

[0162] Based on the above technical solution, an optional, preset driving behavior scoring formula is:

[0163]

[0164] Where S is the daily driving risk score; w i The preset weights for the maximum driving speed / sudden braking times / sudden turning times; Fi is the maximum driving speed / number of emergency brakes / number of sharp turns; C is the daily environmental coefficient.

[0165] In this solution, data related to driving behavior can be collected, such as maximum driving speed, number of emergency brakes, number of emergency turns, etc. These behavior indicators are classified as F i , where i = 1, 2, ..., n, represents different behavior indicators. Set the actual value F of each behavior indicator i . Read the weight w set for each driving row in the database i , indicating the relative importance of the behavior to driving risk. For example, the weight of sudden braking may be greater than the maximum driving speed because sudden braking is generally riskier. Then substitute the determined daily environmental factor C into the formula to calculate the daily driving risk score.

[0166] S347, determining safety recommendations based on the daily driving risk score, a preset risk score threshold, and a preset safety standard, and transmitting the safety recommendations to the user's terminal device.

[0167] The preset risk score threshold can be the standard used by the system to determine the driving risk level. According to different thresholds, the system can generate different levels of safety recommendations. For example: T1 = 80: high risk threshold. T2 = 60: medium risk threshold.

[0168] The preset safety standard may refer to the rules by which the system classifies the driving risk score. For example, if the risk score exceeds a certain value, it is judged as high risk and specific safety recommendations need to be generated.

[0169] Safety suggestions can be prompts or reminders to users generated based on the calculated daily driving risk score. Different risk scores correspond to different safety suggestions. For example: high risk (daily driving risk score>T1): "It is recommended to avoid riding during peak hours and ensure safety", medium risk (T2<daily driving risk score≤T1): "Please be vigilant on specific roads and pay attention to driving safety", low risk (daily driving risk score≤T2): "Drive safely, just drive normally".

[0170] The terminal device can refer to the device that the user receives safety advice, such as a mobile phone, smart watch, or in-vehicle smart device. Safety advice will be sent to these devices through wireless communication or Bluetooth, and users can view driving feedback and safety advice in real time.

[0171] The daily driving risk score can be compared with the preset risk score threshold, and the corresponding safety recommendations can be found in the preset safety standards based on the comparison results, and the safety recommendations can be sent to the user's terminal device through wireless communication technology.

[0172] In this embodiment, by collecting driving data and weather data (such as weather and road conditions) every day, the system can accurately assess driving risks. Based on these risk scores, drivers can get safety advice in time, adjust driving behavior, and reduce the probability of accidents.

[0173] The step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this application; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the protection scope of this patent.

[0174] Fourth embodiment

[0175] The fourth embodiment of the present application relates to an electric vehicle intelligent motion prediction and helmet lighting linkage system 400, which is used to implement an electric vehicle intelligent motion prediction and helmet lighting linkage method of the above-mentioned embodiment, such as Figure 5 As shown, the system 400 specifically includes the following:

[0176] The electric vehicle system 401 is equipped with a Bluetooth module for real-time monitoring of the working status of the vehicle and the driving data of the electric vehicle, wherein the working status includes the status of the left and right turn signals, the status of the double flash signal and the brake status, and encapsulating these status information into a Bluetooth broadcast frame;

[0177] The helmet 402 with integrated Bluetooth device is used to continuously monitor the Bluetooth broadcast information from the electric vehicle and parse the status information in the broadcast frame when receiving it; according to the parsed status information, the LED lights on the helmet are controlled to display accordingly, including but not limited to left and right turn indication, double flash indication and brake indication;

[0178] The intelligent monitoring module 403 is used to predict the movement of the electric vehicle and monitor the blind spot based on the driving data of the electric vehicle, and to control the earphones on the helmet to emit corresponding prompt sounds according to the prediction results and monitoring results, and automatically trigger the warning light effect to remind the driver of the following vehicle;

[0179] The Bluetooth headset 404 is integrated into the helmet 401 and has a voice control function. The user can answer calls, start or stop navigation, and send messages through voice commands.

[0180] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0181] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0182] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0183] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A method for intelligent motion prediction of electric vehicles and linkage with helmet lighting, characterized in that: The method comprises: The vehicle computer system of the electric vehicle monitors the working status of the vehicle and the driving data of the electric vehicle in real time, wherein the working status includes the status of the left and right turn signals, the status of the double flash signal and the brake status, and encapsulates these status information into the Bluetooth broadcast frame; The helmet Bluetooth device continuously monitors the Bluetooth broadcast information from the electric vehicle and parses the status information in the broadcast frame when it receives it; Control the LED lights on the helmet to display accordingly according to the parsed status information, including but not limited to left and right turn indications, double flash indications, and brake indications; Based on the driving data of the electric vehicle, the electric vehicle action prediction and blind spot monitoring are performed, and according to the prediction results and the monitoring results, the earphones on the helmet are controlled to emit corresponding prompt sounds, and the warning light effect is automatically triggered to remind the driver of the following vehicle; The helmet is integrated with a Bluetooth headset with voice control function, and users can answer calls, start or close navigation, and send messages through voice commands.

2. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 1, characterized in that: in, The electric vehicle movement prediction and blind spot monitoring are performed based on the electric vehicle driving data, and the earphones on the helmet are controlled to emit corresponding prompt sounds according to the prediction results and the monitoring results, and the warning light effect is automatically triggered to remind the driver of the following vehicle, including: Inputting the electric vehicle driving data into a preset prediction model to obtain an electric vehicle action prediction result; wherein the electric vehicle driving data includes a vehicle driving speed and a vehicle steering angle; and the electric vehicle action prediction result includes at least one predicted action; Acquire environmental information in real time through radar and camera, and determine distance data between the electric vehicle and other traffic participants according to the environmental information; If the distance data is higher than a preset distance threshold, encapsulating the electric vehicle action prediction result into a first Bluetooth broadcast frame; Acquire the actual motion data of the electric vehicle in real time. If the electric vehicle motion prediction result is consistent with the actual motion data of the electric vehicle, send the first Bluetooth broadcast frame to the helmet Bluetooth module, so that the helmet Bluetooth module can parse the first Bluetooth broadcast frame, obtain the electric vehicle motion prediction result, and control the lighting corresponding to the helmet to display according to the electric vehicle motion prediction result; If the electric vehicle motion prediction result is inconsistent with the actual motion data of the electric vehicle, the actual motion data of the electric vehicle is encapsulated into a second Bluetooth broadcast frame; the second Bluetooth broadcast frame is sent to the helmet Bluetooth module, so that the helmet Bluetooth module parses the second Bluetooth broadcast frame to obtain the actual motion data of the electric vehicle, and controls the corresponding lighting of the helmet for display according to the actual motion data of the electric vehicle.

3. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 1, characterized in that: The training process of the preset prediction model includes: Acquire historical action execution records, and determine historical actions, historical vehicle driving speeds, and historical vehicle steering angles according to the historical action execution records; Marking the vehicle speed label of the historical action according to the historical vehicle speed, and marking the vehicle steering angle label of the historical action according to the historical vehicle steering angle; Creating an action dataset based on the historical actions, the vehicle speed label, and the vehicle steering angle label; Construct a prediction model and train the prediction model according to the action data set until the prediction model reaches a preset prediction model training standard.

4. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 2, characterized in that: After sending the second Bluetooth broadcast frame to the helmet Bluetooth module, the method further includes: Acquire an actual vehicle driving speed and an actual vehicle steering angle corresponding to the actual motion data, label the actual motion data with a vehicle driving speed label according to the actual vehicle driving speed, and label the actual motion data with a vehicle steering angle label according to the actual vehicle steering angle; The actual action data, the corresponding vehicle speed label and the corresponding vehicle steering angle label are added to the action data set, and the prediction model is retrained according to the action data set until the prediction model reaches a preset prediction model training standard.

5. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 1, characterized in that: After obtaining environmental information and determining distance data between the electric vehicle and other traffic participants according to the environmental information, the method further includes: If the distance data is lower than a preset distance threshold, determining the traffic participant whose distance data is lower than the preset distance threshold as a target traffic participant; Acquiring location information of a target traffic participant, and determining a relative direction between the target traffic participant and the electric vehicle according to the location information; If the relative direction is the left rear / right rear, determining the movement direction of the target traffic participant, and determining the vehicle movement direction of the electric vehicle according to the electric vehicle action prediction result; Whether there is a collision risk is determined based on the movement direction of the target traffic participant and the movement direction of the electric vehicle. If there is no collision risk, the electric vehicle action prediction result is encapsulated as a first Bluetooth broadcast frame.

6. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 5, characterized in that: After determining whether there is a collision risk according to the moving direction of the target traffic participant and the moving direction of the electric vehicle, the method further includes: If there is a risk of collision, a collision warning message is generated according to the direction of movement of the vehicle, and the collision warning message is sent to a helmet voice device, so that the helmet voice device plays the collision warning message to the rider to avoid the risk of collision.

7. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 5, characterized in that: After obtaining the position information of the target traffic participant and determining the relative direction between the target traffic participant and the electric vehicle according to the position information, the method further includes: If the relative direction is directly behind, rear-end collision warning information is generated according to the relative direction, and the rear-end collision warning information is sent to the helmet voice device, so that the helmet voice device plays the rear-end collision warning information to the rider to avoid the risk of rear-end collision.

8. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 1, characterized in that: After sending the first Bluetooth broadcast frame to the helmet Bluetooth module, the method further includes: Acquire the maximum speed, number of sudden brakes, number of sudden turns and weather data of the electric vehicle at a preset collection time point each day, and determine the daily environmental coefficient according to the weather data and a preset environmental coefficient determination standard; Calculate the daily driving risk score based on the daily environmental coefficient, the maximum driving speed, the number of emergency brakes, the number of emergency turns, and a preset driving behavior scoring formula; A safety recommendation is determined based on the daily driving risk score, a preset risk score threshold, and a preset safety standard, and the safety recommendation is transmitted to a terminal device of the user.

9. The method for intelligent motion prediction of electric vehicles and linkage with helmet lighting according to claim 8, characterized in that: The preset driving behavior scoring formula is: Where S is the daily driving risk score; w i The preset weights for the maximum driving speed / sudden braking times / sudden turning times; F i is the maximum driving speed / number of emergency brakes / number of sharp turns; C is the daily environmental coefficient.

10. An electric vehicle intelligent motion prediction and helmet lighting linkage system, used to implement the method according to any one of claims 1 to 9, characterized in that: The system comprises: The electric vehicle system is equipped with a Bluetooth module for real-time monitoring of the vehicle's working status and electric vehicle driving data, including the left and right turn signal status, double flash signal status, and brake status, and encapsulating these status information into Bluetooth broadcast frames; A helmet with an integrated Bluetooth device is used to continuously monitor Bluetooth broadcast information from electric vehicles and parse the status information in the broadcast frame when it is received; according to the parsed status information, the LED lights on the helmet are controlled to display accordingly, including but not limited to left and right turn indications, double flash indications, and brake indications; An intelligent monitoring module, used to predict the movement of the electric vehicle and monitor the blind spot based on the driving data of the electric vehicle, and to control the earphones on the helmet to emit corresponding prompt sounds according to the prediction results and monitoring results, and to automatically trigger the warning light effect to remind the driver of the following vehicle; The Bluetooth headset is integrated into the helmet and has a voice control function. Users can answer calls, start or close navigation, and send messages through voice commands.

Images