Risk early warning method, system and equipment based on LED motorcycle lamp and medium

Abstract

The invention relates to the technical field of risk early warning, in particular to a risk early warning method, system and device based on an LED motorcycle lamp and a medium. The method comprises the following steps: firstly, collecting riding state data including a speed change trend and a vehicle body inclination angle; converting the data into a quantitative risk assessment result by using a preset risk assessment algorithm; and finally, according to the urgency degree of the risk level, triggering LED light early warning and sound prompts with different intensities. The risk degree is visually reflected through the change of the LED lamp, the hysteresis of traditional passive early warning is avoided, and the intelligence and humanization of risk early warning are realized.

Description

Technical Field

[0001] The present application relates to the technical field of risk warning, and in particular to a risk warning method, system, device and medium based on LED motorcycle lights. Background Art

[0002] With the development of urban transportation, motorcycles are widely used as a flexible means of transportation. Due to their strong maneuverability and small size, accidents are more likely to occur under complex road conditions. Especially at night or in bad weather conditions, the driving safety of motorcycles is particularly prominent.

[0003] Currently, the motorcycle LED lighting systems on the market mainly adopt fixed brightness and fixed illumination angle design solutions. These systems detect changes in ambient light through light intensity sensors, automatically adjust the brightness of LED lights, or adjust the illumination angle through steering sensors to achieve basic lighting functions.

[0004] However, the existing LED lighting system can only respond passively to environmental changes. In an emergency, this delayed response mechanism makes it difficult to promptly remind riders to take preventive measures, which can easily lead to accidents. This situation needs to be further improved. Summary of the invention

[0005] In order to solve the problem that the existing LED lighting system is difficult to promptly remind riders to take preventive measures, which easily leads to accidents, this application provides a risk warning method, system, device and medium based on LED motorcycle lights, using the following technical solutions: In a first aspect, the present application provides a risk warning method based on LED motorcycle lights, comprising the following steps: Collect riding speed changes and tilt angles to obtain real-time riding status data; Analyzing and processing the real-time riding status data to obtain a riding risk assessment result; Based on the riding risk assessment result, a warning level is determined, and corresponding LED light warning responses and sound warning prompts are triggered according to the warning level.

[0006] By adopting the above technical solution, in order to improve the safety of motorcycle driving at night, it is necessary to provide timely warnings for potential dangers; this application first collects riding status data, including speed change trends and body inclination angles; then uses a preset risk assessment algorithm to convert these data into quantitative risk assessment results; finally, according to the urgency of the risk level, triggers LED light warnings and sound prompts of different intensities; the risk level is intuitively reflected through changes in LED lights, avoiding the lag of traditional passive warnings and realizing intelligent and humanized risk warnings.

[0007] Optionally, analyzing and processing the real-time riding status data to obtain a riding risk assessment result specifically includes the following steps: Collecting real-time road environment information, and performing multi-source data fusion based on the real-time road environment information and the real-time riding status data to obtain comprehensive status information; Calculating an initial risk assessment value based on the comprehensive status information; Preprocessing the comprehensive status information, and analyzing it based on the preprocessed data using a pretrained neural network model; The riding risk assessment result is calculated based on the model analysis result and the initial risk assessment value.

[0008] By adopting the above technical scheme, since motorcycle riding safety is affected by a combination of factors, it is difficult to accurately assess the degree of risk by relying solely on single speed and tilt angle data; for example, when the road is slippery on rainy days, even a relatively mild riding state may pose a greater risk; and when the road is congested, frequent acceleration and deceleration may lead to misjudgment; the present application first collects road environment information through sensors, performs multi-source fusion with riding status data, forms comprehensive integrated status information, and quickly calculates the initial risk assessment value; then the fused data is standardized and preprocessed, and input into a pre-trained neural network model for analysis; finally, the model analysis results are weighted and integrated with the initial assessment value to obtain a more accurate risk assessment result; this ensures the real-time nature of the assessment, while improving the accuracy of the assessment, and realizes the intelligence and precision of risk assessment.

[0009] Optionally, a pre-trained neural network model is used for analysis, which specifically includes the following steps: Performing target detection on the real-time road environment information to obtain obstacle feature data; Calculating a collision risk probability based on the obstacle characteristic data; The collision risk probability and the initial risk assessment value are weighted and calculated to obtain the riding risk assessment result.

[0010] By adopting the above technical scheme, due to the complexity and diversity of obstacle types in the road environment, and the significant differences in the risk levels brought by different obstacles, traditional risk assessment methods are difficult to accurately identify and quantify these potential threats; this application first uses a pre-trained neural network model to perform real-time target detection on road environment information, and extracts characteristic data such as the location, type, and movement trend of obstacles; then based on these characteristic data, combined with the relative position and speed relationship between the obstacle and the vehicle, the specific collision risk probability is calculated; finally, the probability value is weighted and fused with the initial risk assessment value to obtain a more comprehensive risk assessment result, which greatly improves the accuracy and reliability of risk assessment.

[0011] Optionally, based on the riding risk assessment result, a warning level is determined, and a corresponding LED light warning response and sound warning prompt are triggered according to the warning level, specifically including the following steps: Determining a color change scheme of the LED light according to the riding risk assessment result; Calculating the dynamic brightness value of the LED light based on the changing trend of the riding risk assessment result; According to the urgency of the riding risk assessment result, the flashing frequency parameter of the LED light is set; According to the color change scheme, dynamic brightness value and flashing frequency parameters, the corresponding LED light warning response and sound warning prompt are triggered.

[0012] By adopting the above technical solution, the present application first selects the corresponding color change scheme according to the risk assessment results, and uses different colors to intuitively express the risk level; then, by analyzing the risk change trend, the brightness of the LED light is dynamically adjusted to match the warning intensity with the risk level; then, based on the urgency of the risk, an appropriate flashing frequency is set to highlight the timeliness of the risk; finally, these parameters are integrated to trigger a warning response, accompanied by corresponding sound prompts; this allows riders to intuitively perceive the risk level, and accurately understand the urgency of the danger, significantly improving the recognizability and timeliness of the warning effect.

[0013] Optionally, triggering a corresponding LED light warning response also includes the following steps: generating an obstacle distribution map based on the obstacle feature data; Calculating a warning lighting area according to the obstacle distribution map and the riding risk assessment result; According to the warning lighting area and the color change scheme, the irradiation direction and lighting range of the LED lamp are adjusted.

[0014] By adopting the above technical solution, this application first constructs a real-time obstacle distribution map based on the detected obstacle feature data to grasp the spatial distribution of various risk targets in the surrounding environment; then, combined with the risk assessment results, calculates the warning area that needs key lighting and determines the priority of lighting; finally, according to the location of the warning area and the color scheme corresponding to the risk level, controls the illumination angle and lighting range of the LED light; it can not only actively guide the rider to focus on the dangerous area, but also intuitively present the degree of risk through differentiated lighting.

[0015] Optionally, the corresponding LED light warning response parameter configuration includes the following steps: Upload the risk assessment results and warning levels of each ride to the cloud server to obtain a historical warning data set; Based on the historical warning data set, extract driving habit features to obtain a personalized warning model; According to the personalized warning model, the configuration of the color change scheme, dynamic brightness value and flicker frequency parameters are dynamically adjusted.

[0016] By adopting the above technical solution, since different riders have significant differences in driving habits and risk perception abilities, it is difficult for a unified warning parameter configuration to meet personalized needs. This application first uploads each risk assessment result and the corresponding warning level to a cloud server in real time to accumulate a personal historical warning data set. Then, the rider's driving habit characteristics are extracted from these historical data, including turning characteristics, braking mode, risk response methods, etc., to build a personalized warning model. Finally, based on the model, the color change scheme, dynamic brightness value and flashing frequency parameters of the LED light are intelligently adjusted to improve the user experience.

[0017] Optionally, the method further comprises the following steps: Collecting operational feedback from the rider in response to the warning; According to the operation feedback, adjusting the triggering condition of the color change scheme; Based on the adjusted trigger condition, the dynamic brightness value and flicker frequency parameters are optimized.

[0018] By adopting the above technical solution, this application first records the rider's actual operational feedback on the warning response, such as ignoring the warning, responding immediately or manually closing it; then based on these feedback data, the trigger threshold and timing of the color change scheme corresponding to different risk levels are intelligently adjusted; finally, based on the optimized trigger conditions, the dynamic brightness value and flashing frequency parameters of the LED light are adjusted accordingly to make the warning effect more in line with user habits.

[0019] In a second aspect, the present application provides a risk warning system based on LED motorcycle lights, comprising: A real-time riding status data collection module is used to collect riding speed changes and tilt angles to obtain real-time riding status data; A riding risk assessment result analysis module is used to analyze and process the real-time riding status data to obtain a riding risk assessment result; The risk warning module is used to determine the warning level based on the riding risk assessment result, and trigger the corresponding LED light warning response and sound warning prompt according to the warning level.

[0020] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned risk warning method based on LED motorcycle lights when executing the computer program.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned risk warning method based on LED motorcycle lights are implemented.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application first collects riding status data, including speed change trends and body tilt angles; then uses a preset risk assessment algorithm to convert these data into quantitative risk assessment results; finally, according to the urgency of the risk level, triggers LED light warnings and sound prompts of different intensities; the change of LED lights intuitively reflects the risk level, avoids the lag of traditional passive warnings, and realizes the intelligence and humanization of risk warnings; 2. Since motorcycle riding safety is affected by a variety of factors, it is difficult to accurately assess the degree of risk by relying solely on single speed and tilt angle data. For example, when the road is slippery on rainy days, even a relatively mild riding state may pose a greater risk. When the road is congested, frequent acceleration and deceleration may lead to misjudgment. This application first collects road environment information through sensors, and performs multi-source fusion with riding state data to form comprehensive comprehensive state information, and quickly calculates the initial risk assessment value. The fused data is then standardized and preprocessed, and input into a pre-trained neural network model for analysis. Finally, the model analysis results are weighted and integrated with the initial assessment value to obtain a more accurate risk assessment result. This ensures the real-time nature of the assessment, improves the accuracy of the assessment, and realizes the intelligence and precision of risk assessment. 3. Since the types of obstacles in the road environment are complex and diverse, and the risk levels brought by different obstacles vary significantly, traditional risk assessment methods are difficult to accurately identify and quantify these potential threats; this application first uses a pre-trained neural network model to perform real-time target detection on road environment information, and extracts characteristic data such as the location, type, and movement trend of obstacles; then based on these characteristic data, combined with the relative position and speed relationship between the obstacle and the vehicle, the specific collision risk probability is calculated; finally, the probability value is weighted and fused with the initial risk assessment value to obtain a more comprehensive risk assessment result, which greatly improves the accuracy and reliability of the risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a risk warning method based on LED motorcycle lights according to an embodiment of the present application; Figure 2 It is a flowchart of step S120 in a risk warning method based on LED motorcycle lights according to an embodiment of the present application; Figure 3It is a flowchart of step S230 in a risk warning method based on LED motorcycle lights according to an embodiment of the present application; Figure 4 It is a flowchart of step S130 in a risk warning method based on LED motorcycle lights according to an embodiment of the present application; Figure 5 It is a schematic diagram of a process of generating an obstacle distribution map in a risk warning method based on LED motorcycle lights in an embodiment of the present application; Figure 6 It is a flow chart of LED light warning parameter configuration in a risk warning method based on LED motorcycle lights in an embodiment of the present application; Figure 7 It is a flow chart of trigger condition adjustment in a risk warning method based on LED motorcycle lights in an embodiment of the present application; Figure 8 This is a module schematic diagram of a risk warning system based on LED motorcycle lights in an embodiment of the present application; Fig. 9 It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0025] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0026] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0027] In the first aspect, the present application provides a risk warning method based on LED motorcycle lights, referring to Figure 1 , including the following steps: S110: Collect riding speed changes and tilt angles to obtain real-time riding status data.

[0028] Among them, real-time riding status data refers to the key parameter information reflecting the current motion status of the motorcycle, mainly including speed change data and body tilt angle data. Speed ​​change data includes not only real-time speed value, but also acceleration change; tilt angle includes lateral tilt angle and longitudinal pitch angle, which are used to characterize the posture change of the motorcycle.

[0029] Specifically, these data are collected through the sensor system installed on the motorcycle. The speed sensor is used to collect wheel speed information, and the real-time speed is obtained by converting the wheel circumference; the acceleration sensor and gyroscope are used to collect the acceleration and angular velocity information of the vehicle body in three directions, and the accurate tilt angle value is obtained through attitude solution.

[0030] S120: Analyze and process the real-time riding status data to obtain a riding risk assessment result.

[0031] Among them, analysis and processing refers to feature extraction and risk calculation of the collected riding status data. The system divides the continuous speed change and tilt angle data into segments according to the time window, extracts the statistical characteristics and change trend characteristics of each segment of data, and conducts risk assessment based on the preset safety threshold.

[0032] Specifically, the speed change threshold is set to 5 km / h per second, and the tilt angle threshold is set to 35 degrees relative to the vertical direction. When it is detected that the speed change exceeds the threshold or the tilt angle is close to the critical value, the system will calculate the risk level according to the degree of excess. For example, the risk assessment results can be divided into a numerical range of 0-100, where 0-30 indicates safety, 31-60 indicates attention, 61-80 indicates warning, and 81-100 indicates danger.

[0033] S130: Determine a warning level based on the riding risk assessment result, and trigger corresponding LED light warning response and sound warning prompt according to the warning level.

[0034] Among them, the warning level is a hierarchical warning mechanism determined based on the risk assessment results. Different warning levels correspond to different LED light display effects and sound prompts. The warning level is usually divided into four levels: reminder, attention, warning and danger, and each level adopts a different warning strategy.

[0035] Specifically, when the system determines the warning level, it will trigger the corresponding warning response. For example, at the reminder level, the LED light may display a steady yellow light and emit a light warning sound; at the warning level, the LED light may flash red and emit a rapid alarm sound. The intensity and frequency of the warning response will increase with the increase of the risk level to attract the rider's attention. The system can also automatically adjust the brightness of the LED light according to the ambient brightness to ensure that the warning effect can be clearly seen under different lighting conditions.

[0036] In one embodiment, referring to Figure 2 In step S120, the real-time riding status data is analyzed and processed to obtain a riding risk assessment result, which specifically includes the following steps: S210: Collect real-time road environment information, and perform multi-source data fusion based on the real-time road environment information and real-time riding status data to obtain comprehensive status information.

[0037] Among them, real-time road environment information refers to the surrounding environment data collected by various sensors, including but not limited to road conditions, light conditions, weather conditions and other environmental factors. Multi-source data fusion is the process of aligning these environmental information with riding status data in time and space and integrating their features.

[0038] Specifically, the camera can be used to collect images of the road ahead, the light sensor can be used to detect the ambient brightness, and the temperature and humidity sensor can be used to collect weather data. For example, when fusion is performed, the ambient data of every 100ms is paired with the riding status data of the corresponding time period to form a state vector containing multi-dimensional features.

[0039] S220. Calculate an initial risk assessment value based on the comprehensive status information.

[0040] Among them, the initial risk assessment value is based on the traditional rule calculation method to conduct preliminary risk quantification of the comprehensive status information.

[0041] Specifically, weight coefficients are set for different state characteristics, such as speed change weight 0.3, tilt angle weight 0.3, road condition weight 0.2, and visibility weight 0.2. The initial risk assessment value in the range of 0-100 is obtained by weighted summation. When multiple factors are close to the danger threshold at the same time, the system will increase the overall risk assessment level.

[0042] S230, preprocessing the comprehensive status information, and analyzing it using a pre-trained neural network model based on the preprocessed data.

[0043] Preprocessing refers to standardizing, denoising, and extracting features from comprehensive state information to make the data more suitable for processing by the neural network model. The pretrained neural network model is a deep learning model trained with a large amount of historical data.

[0044] S240: Calculate a riding risk assessment result based on the model analysis result and the initial risk assessment value.

[0045] Among them, the final risk assessment result is a comprehensive assessment value obtained by fusing the output result of the neural network model with the initial risk assessment value.

[0046] Specifically, the two assessment results are combined by weighted average, for example, the initial assessment value is given a weight of 0.4 and the model analysis result is given a weight of 0.6. The final risk assessment result is also mapped to a range of 0-100, and the weight ratio of different assessment methods can be adjusted according to actual needs.

[0047] In one embodiment, referring to Figure 3 In step S230, the pre-trained neural network model is used for analysis, which specifically includes the following steps: S231. Perform target detection on the real-time road environment information to obtain obstacle feature data.

[0048] Among them, target detection refers to the use of pre-trained deep learning models to analyze road environment images in real time to identify and locate possible obstacles. Obstacle feature data includes information such as obstacle type, location, size, and motion status.

[0049] Specifically, a deep learning-based target detection network is used for real-time detection. For example, the system processes one frame of image every 50ms, and the detection range covers the area within 30 meters in front of the motorcycle. The detection results include information such as the obstacle's bounding box coordinates, category probability, and motion trajectory. For dynamic obstacles, their movement direction and speed estimation are also recorded.

[0050] S232. Calculate the collision risk probability based on the obstacle feature data.

[0051] Among them, the collision risk probability is a risk indicator calculated based on obstacle feature data and current riding status through spatiotemporal trajectory prediction and collision detection algorithm.

[0052] Specifically, the system first predicts the possible trajectory of the obstacle in the next few seconds based on its motion characteristics, and predicts its own motion trajectory based on the speed and direction of the motorcycle. By calculating the intersection probability of these trajectories, the collision risk probability is obtained.

[0053] S233. Perform weighted calculation on the collision risk probability and the initial risk assessment value to obtain a riding risk assessment result.

[0054] Among them, weighted calculation is to combine the collision risk probability with the initial risk assessment value to obtain a more comprehensive risk assessment result.

[0055] Specifically, a dynamic weight calculation method is adopted to increase the weight of the collision risk probability when a high-risk obstacle is detected. For example, under normal circumstances, the weight of the collision risk probability is 0.5, and the weight of the initial risk assessment value is 0.5; when an emergency is detected, the weight of the collision risk probability can be increased to 0.7 or higher. The final risk assessment result is still mapped to the range of 0-100 for subsequent early warning responses. The system will also calculate the accuracy of early warnings in different scenarios based on historical data, and dynamically adjust the weight parameters to optimize the evaluation effect.

[0056] In one embodiment, referring to Figure 4 In step S130, based on the riding risk assessment result, the warning level is determined, and the corresponding LED light warning response and sound warning prompt are triggered according to the warning level, which specifically includes the following steps: S131. Determine a color change scheme of the LED light according to the riding risk assessment result.

[0057] The color change scheme refers to selecting the corresponding LED light display color or color combination according to different risk assessment results. The system establishes a corresponding relationship between the risk level and a specific color scheme, and intuitively expresses the risk level through color changes.

[0058] Specifically, set the color schemes corresponding to different risk intervals, for example, assessment results 0-30 correspond to green (safety), 31-60 correspond to yellow (caution), 61-80 correspond to orange (warning), and 81-100 correspond to red (danger). In the color transition interval, the system can achieve a gradual effect, such as a smooth transition from yellow to orange, making the warning more natural. Linear interpolation calculation of RGB color values ​​can be used for color transformation.

[0059] S132. Calculate the dynamic brightness value of the LED light based on the changing trend of the riding risk assessment result.

[0060] The dynamic brightness value is a parameter of LED light brightness that is dynamically adjusted according to the changing trend of risk assessment results. The system will consider the rate of change of risk level and adjust the display brightness of LED light to highlight the urgency of risk change.

[0061] Specifically, the basic brightness is set in the range of 20%-60%. When the risk assessment result rises rapidly, the brightness value is increased accordingly. For example, if the risk value rises by more than 20 points within 10 seconds, the brightness is increased to the range of 80%-100%. The system will also adaptively adjust the basic brightness based on the data of the ambient light sensor to ensure that the warning signal can be clearly identified under different lighting conditions.

[0062] S133: setting the flashing frequency parameters of the LED light in combination with the urgency of the riding risk assessment result.

[0063] Among them, the flashing frequency parameter is the LED light flashing control parameter set based on the urgency of the risk. The change of flashing frequency can effectively convey the urgency of the risk, and high-frequency flashing indicates an emergency situation that requires immediate attention.

[0064] Specifically, different flashing modes are set according to the risk assessment results. For example, the light remains on in low-risk conditions, flashes slowly at 0.5 Hz in medium-risk conditions, flashes quickly at 2 Hz in high-risk conditions, and flashes rapidly at 4 Hz in emergency conditions. The flashing duty cycle can also be adjusted dynamically, such as increasing the proportion of light on time when the risk is high to improve the visual impact.

[0065] S134. According to the color change scheme, dynamic brightness value and flashing frequency parameters, trigger corresponding LED light warning response and sound warning prompt.

[0066] Among them, the early warning response is the comprehensive application of parameters such as color, brightness and flashing, combined with corresponding sound prompts to form a complete early warning effect.

[0067] Specifically, the system triggers a warning response based on a combination of pre-set parameters. For example, when a dangerous situation is detected, the LED light flashes red, 100% brightness, and 4Hz frequency, and a rapid alarm sound is emitted at the same time. The volume and rhythm of the sound prompt will also be adjusted accordingly with the risk level, forming a three-dimensional warning effect of sound and light synchronization. The system can also automatically adjust the warning parameters according to the vehicle speed, and appropriately increase the warning intensity when driving at high speed to ensure the warning effect.

[0068] In one embodiment, referring to Figure 5 , triggering the corresponding LED light warning response, and also includes the following steps: S510: Generate an obstacle distribution map based on obstacle feature data.

[0069] Among them, the obstacle distribution map is a two-dimensional plane schematic diagram generated based on the target detection results, which is used to represent the spatial distribution of obstacles around the vehicle.

[0070] Specifically, a polar coordinate system centered on the motorcycle is established to map the detected obstacle information onto a two-dimensional plane with a radius of 30 meters. For example, different types of obstacles are represented by different markers in the distribution map, static obstacles are represented by solid points, and moving obstacles are represented by markers with directional arrows. The system updates the distribution map every 100ms to reflect changes in the surrounding environment in real time.

[0071] S520: Calculate the warning lighting area according to the obstacle distribution map and the riding risk assessment result.

[0072] Among them, the early warning lighting area is the spatial range that requires key lighting calculated based on the obstacle distribution and risk assessment results.

[0073] Specifically, the system combines the location information of obstacles with the risk assessment results to determine the areas that need key lighting. For example, when a high-risk obstacle is detected 10 meters ahead, the system will set that area as the key lighting area, and the lighting range will cover the area 2 meters around the obstacle. For moving obstacles, the system will appropriately expand the lighting range based on its motion trajectory prediction.

[0074] S530: Adjust the irradiation direction and illumination range of the LED lamp according to the warning illumination area and the color change scheme.

[0075] In one embodiment, referring to Figure 6 , the corresponding LED light warning response parameter configuration includes the following steps: S610, uploading each riding risk assessment result and warning level to the cloud server to obtain a historical warning data set.

[0076] S620: Based on the historical warning data set, extract driving habit features to obtain a personalized warning model.

[0077] Among them, driving habit characteristics are key indicators that can characterize the driver's personal characteristics by deeply mining historical data. These characteristics reflect the driver's sensitivity and reaction pattern to different warning signals.

[0078] Specifically, the machine learning algorithm is used to analyze the driver's behavior patterns in different scenarios. For example, the driver's reaction time to warnings of different colors is statistically analyzed, the warning effectiveness under different flashing frequencies is calculated, and the difference in brightness sensitivity between nighttime and daytime driving is extracted. The system will establish a feature vector of the driver, which includes habit indicators in multiple dimensions, such as risk perception threshold, visual preference, reaction speed, etc.

[0079] S630: Dynamically adjust the configuration of the color change scheme, dynamic brightness value, and flicker frequency parameters according to the personalized warning model.

[0080] Dynamic adjustment is a process of optimizing warning parameters in real time based on a personalized warning model. This adjustment mechanism can make the warning effect better adapt to the individual characteristics of the driver.

[0081] Specifically, the system adjusts the threshold and change rules of the warning parameters according to the personalized model. For example, for drivers who are not sensitive to red, the red warning can be used at a lower risk level; for drivers who are sensitive to high-frequency flickering, the maximum flickering frequency can be reduced to 2Hz; for drivers with poor night vision, the basic brightness of the night warning can be increased.

[0082] In one embodiment, referring to Figure 7 , the method further comprises the following steps: S710: Collect the rider's operational feedback on the warning response.

[0083] Among them, operational feedback refers to the system collecting and recording the specific operational behaviors of the rider in response to the warning signal. These feedback data include but are not limited to deceleration, steering, braking and other operations, as well as the time characteristics and force characteristics of the operation.

[0084] Specifically, the system collects the rider's operation data through multiple sensors. For example, the speed sensor records the deceleration curve after the warning, the direction sensor records the steering angle change, and the pressure sensor records the braking force. The operation data within 5 seconds after each warning is triggered will be recorded, including the time of occurrence, duration and change trend of the operation. The system will also record the time interval from the issuance of the warning signal to the rider's first response to evaluate the effectiveness of the warning.

[0085] S720: Adjust the triggering condition of the color change scheme according to the operation feedback.

[0086] The trigger condition adjustment is based on the operational feedback data to optimize the trigger threshold and timing of different color warning signals. This adjustment ensures that the warning signal can be triggered at the most appropriate time, neither disturbing the rider too early nor too late to lose the warning effect.

[0087] Specifically, the system analyzes the correspondence between warning signals and operational feedback to determine the optimal triggering time. For example, if it is found that yellow warnings are often ignored, the system will appropriately lower the trigger threshold of yellow warnings so that they start to prompt when the risk is lower; if it is found that red warnings often cause overreactions, the trigger threshold will be appropriately increased. The system will set different trigger conditions for different driving speeds. Warning signals will be triggered earlier when driving at high speeds, leaving more sufficient reaction time.

[0088] S730: Optimize dynamic brightness value and flicker frequency parameters based on the adjusted trigger condition.

[0089] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0090] In the second aspect, the present application provides a risk warning system based on LED motorcycle lights. The risk warning system based on LED motorcycle lights of the present application is described below in combination with the above-mentioned risk warning method based on LED motorcycle lights.

[0091] Reference Figure 8 , a risk warning system based on LED motorcycle lights, including: The real-time riding status data collection module is used to collect the riding speed change and tilt angle to obtain the real-time riding status data; The cycling risk assessment result analysis module is used to analyze and process the real-time cycling status data to obtain the cycling risk assessment result; The risk warning module is used to determine the warning level based on the riding risk assessment results, and trigger the corresponding LED light warning response and sound warning prompt according to the warning level.

[0092] In one embodiment, the riding risk assessment result analysis module includes: A real-time environment information collection unit is used to collect real-time road environment information, and to perform multi-source data fusion based on the real-time road environment information and real-time riding status data to obtain comprehensive status information; An initial risk calculation unit, used to calculate an initial risk assessment value based on the comprehensive status information; A data preprocessing unit, used for preprocessing the comprehensive status information; A neural network analysis unit, used for performing analysis based on the preprocessed data using a pretrained neural network model; The risk assessment unit is used to calculate the riding risk assessment result based on the model analysis result and the initial risk assessment value.

[0093] In one embodiment, the neural network analysis unit comprises: The obstacle detection module is used to detect targets based on real-time road environment information and obtain obstacle feature data; A collision risk calculation module, used to calculate the collision risk probability based on obstacle feature data; The risk weighted calculation module is used to perform weighted calculation on the collision risk probability and the initial risk assessment value to obtain a riding risk assessment result.

[0094] In one embodiment, the risk warning module includes: A color change control unit, used to determine a color change scheme of the LED light according to a riding risk assessment result; A brightness calculation unit, used to calculate the dynamic brightness value of the LED light based on the changing trend of the riding risk assessment result; A frequency setting unit, used to set the flashing frequency parameters of the LED light in combination with the urgency of the riding risk assessment result; The warning trigger unit is used to trigger the corresponding LED light warning response and sound warning prompt according to the color change scheme, dynamic brightness value and flashing frequency parameters.

[0095] In one embodiment, the early warning triggering unit further includes: An obstacle distribution generation module, used to generate an obstacle distribution map based on obstacle feature data; A lighting area calculation module is used to calculate the warning lighting area based on the obstacle distribution map and the riding risk assessment results; The lighting adjustment module is used to adjust the irradiation direction and lighting range of the LED light according to the warning lighting area and color change scheme.

[0096] In one embodiment, a parameter configuration module is further included, and the parameter configuration module includes: A data uploading unit is used to upload the risk assessment results and warning levels of each ride to the cloud server to obtain a historical warning data set; A model building unit, used to extract driving habit features based on historical warning data sets to obtain a personalized warning model; The parameter adjustment unit is used to dynamically adjust the configuration of color change scheme, dynamic brightness value and flicker frequency parameters according to the personalized warning model.

[0097] In one embodiment, a feedback optimization module is further included, and the feedback optimization module includes: A feedback collection unit, used to collect the rider's operational feedback on the warning response; A trigger condition adjustment unit, used to adjust the trigger condition of the color change scheme according to the operation feedback; The parameter optimization unit is used to optimize the dynamic brightness value and the flicker frequency parameters based on the adjusted trigger condition.

[0098] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a risk warning method based on LED motorcycle lights is implemented.

[0099] Those skilled in the art will understand that Fig. 9The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0100] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0101] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0102] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A risk warning method based on LED motorcycle lights, characterized in that: The steps include: Collect riding speed changes and tilt angles to obtain real-time riding status data; Analyzing and processing the real-time riding status data to obtain a riding risk assessment result; Based on the riding risk assessment result, a warning level is determined, and corresponding LED light warning responses and sound warning prompts are triggered according to the warning level.

2. The risk warning method based on LED motorcycle lights according to claim 1 is characterized in that: Analyzing and processing the real-time riding status data to obtain a riding risk assessment result specifically includes the following steps: Collecting real-time road environment information, and performing multi-source data fusion based on the real-time road environment information and the real-time riding status data to obtain comprehensive status information; Calculating an initial risk assessment value based on the comprehensive status information; Preprocessing the comprehensive status information, and analyzing it based on the preprocessed data using a pretrained neural network model; The riding risk assessment result is calculated based on the model analysis result and the initial risk assessment value.

3. The risk warning method based on LED motorcycle lights according to claim 2 is characterized in that: The analysis is performed using a pre-trained neural network model, which includes the following steps: Performing target detection on the real-time road environment information to obtain obstacle feature data; Calculating a collision risk probability based on the obstacle characteristic data; The collision risk probability and the initial risk assessment value are weighted and calculated to obtain the riding risk assessment result.

4. The risk warning method based on LED motorcycle lights according to claim 3 is characterized in that: Based on the riding risk assessment result, a warning level is determined, and a corresponding LED light warning response and sound warning prompt are triggered according to the warning level, specifically including the following steps: Determining a color change scheme of the LED light according to the riding risk assessment result; Calculating the dynamic brightness value of the LED light based on the changing trend of the riding risk assessment result; According to the urgency of the riding risk assessment result, the flashing frequency parameter of the LED light is set; According to the color change scheme, dynamic brightness value and flashing frequency parameters, the corresponding LED light warning response and sound warning prompt are triggered.

5. The risk warning method based on LED motorcycle lights according to claim 4 is characterized in that: Triggering the corresponding LED light warning response also includes the following steps: generating an obstacle distribution map based on the obstacle feature data; Calculating a warning lighting area according to the obstacle distribution map and the riding risk assessment result; According to the warning lighting area and the color change scheme, the irradiation direction and lighting range of the LED lamp are adjusted.

6. The risk warning method based on LED motorcycle lights according to claim 4 is characterized in that: The corresponding LED light warning response parameter configuration includes the following steps: Upload the risk assessment results and warning levels of each ride to the cloud server to obtain a historical warning data set; Based on the historical warning data set, extract driving habit features to obtain a personalized warning model; According to the personalized warning model, the configuration of the color change scheme, dynamic brightness value and flicker frequency parameters are dynamically adjusted.

7. The risk warning method based on LED motorcycle lights according to claim 6 is characterized in that: The method further comprises the steps of: Collecting operational feedback from the rider in response to the warning; According to the operation feedback, adjusting the triggering condition of the color change scheme; Based on the adjusted trigger condition, the dynamic brightness value and flicker frequency parameters are optimized.

8. A risk warning system based on LED motorcycle lights, characterized in that: include: The real-time riding status data collection module is used to collect the riding speed change and tilt angle to obtain the real-time riding status data; A riding risk assessment result analysis module is used to analyze and process the real-time riding status data to obtain a riding risk assessment result; The risk warning module is used to determine the warning level based on the riding risk assessment result, and trigger the corresponding LED light warning response and sound warning prompt according to the warning level.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the risk warning method based on an LED motorcycle light according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the risk warning method based on LED motorcycle lights described in any one of claims 1 to 7 are implemented.

Images