A vehicle trip risk safety assessment system

Abstract

This invention discloses a vehicle travel risk safety assessment system, relating to the field of vehicle travel risk assessment technology. It includes a driving data acquisition module, a risk coefficient calculation module, a comprehensive risk analysis module, and a travel risk assessment module. The driving data acquisition module collects vehicle driving data. The risk coefficient calculation module analyzes the risk model of the driving data and analyzes the vehicle's risk coefficient. The comprehensive risk analysis module calculates the vehicle's comprehensive risk index. The travel risk assessment module assesses the vehicle's travel risk. This invention addresses the shortcomings of existing vehicle travel risk assessment technologies, such as insufficient comprehensiveness in analyzing factors affecting vehicle travel safety and the inability to predict vehicle travel risks, which hinders effective assistance to drivers in choosing safe routes and correcting driving habits.

Description

Technical Field

[0001] This invention relates to the field of vehicle travel risk assessment technology, specifically a vehicle travel risk safety assessment system. Background Technology

[0002] Vehicle travel risk assessment technology refers to the technology that uses multi-source data collection, real-time analysis and intelligent algorithms to quantify and predict the level of safety risks that a vehicle may encounter during driving, and to generate proactive intervention strategies. Its purpose is to transform dynamic factors such as environment, vehicles, drivers and traffic flow into quantifiable risk indicators, and to achieve a closed loop of perception-assessment-decision.

[0003] Existing vehicle travel risk assessment technologies typically only assess and respond to risks after they have already occurred, such as activating automatic braking when an impending collision is detected. However, this method cannot predict vehicle travel risks, effectively help drivers choose safe routes, or correct driving habits. Furthermore, existing vehicle travel risk assessment technologies are insufficient in considering factors affecting vehicle travel safety. For instance, Chinese patent application CN118446510A discloses a "Risk Assessment Method for Vehicle Navigation," which assesses the risk of vehicle navigation solely based on traffic flow data and historical accident rate data. Moreover, the indicators and weights given in the subsequent calculation of the road safety risk index are not clearly defined. Existing vehicle travel risk assessment technologies also suffer from insufficient comprehensiveness in analyzing factors affecting vehicle travel safety and the inability to predict vehicle travel risks, resulting in a failure to effectively help drivers choose safe routes and correct driving habits. Summary of the Invention

[0004] This invention aims to at least partially address one of the technical problems in the prior art. It collects vehicle driving data using built-in sensors, analyzes the amplification coefficient of different driving data on traffic accidents based on historical data, analyzes the risk model of the driving data, and then analyzes the vehicle's risk coefficient based on the risk model and driving data. Based on the risk coefficient, it calculates the vehicle's comprehensive risk index, analyzes the risk threshold of historical data, and finally assesses the vehicle's travel risk based on the comprehensive risk index and risk threshold. This addresses the shortcomings of existing vehicle travel risk assessment technologies, such as insufficient comprehensiveness in analyzing factors affecting vehicle travel safety and the inability to predict vehicle travel risks, which prevents effective assistance to drivers in choosing safe routes and correcting driving habits.

[0005] To achieve the above objectives, in a first aspect, this application provides a vehicle travel risk safety assessment system, including a driving data acquisition module, a risk coefficient calculation module, a comprehensive risk analysis module, and a travel risk assessment module; the driving data acquisition module, the risk coefficient calculation module, and the travel risk assessment module are respectively connected to the comprehensive risk analysis module for data transmission.

[0006] The driving data acquisition module is used to collect driving data of the vehicle using the vehicle's built-in sensors;

[0007] The risk coefficient calculation module is used to analyze risk models of different driving data based on historical driving data, and to analyze the risk coefficient of the vehicle based on the risk model and driving data.

[0008] The comprehensive risk analysis module is used to calculate the comprehensive risk index of the vehicle based on the risk coefficient;

[0009] The travel risk assessment module is used to assess the travel risk of a vehicle based on comprehensive risk indicators.

[0010] Furthermore, the driving data acquisition module is configured with a driving data acquisition strategy, which includes:

[0011] Obtain the vehicle's current driving segment and retrieve historical driving data from when traffic accidents occurred on that segment, naming the data as "historical data".

[0012] The driving data includes driving data, environmental data, and traffic data. The driving data includes vehicle speed and following distance. The environmental data includes visibility and road surface friction coefficient. The traffic data includes the regional accident rate within the driving section.

[0013] Furthermore, the risk coefficient calculation module includes a risk correlation analysis unit, a risk model analysis unit, and a risk coefficient analysis unit;

[0014] The risk correlation analysis unit is used to analyze the amplification coefficient of different driving data on traffic accidents based on historical data;

[0015] The risk model analysis unit is used to analyze the risk model of driving data;

[0016] The risk coefficient analysis unit is used to analyze the risk coefficient of a vehicle based on a risk model and driving data.

[0017] Furthermore, the risk correlation analysis unit is configured with a risk correlation analysis strategy, which includes:

[0018] Collect historical data, calculate the regional accident rate corresponding to different visibility levels, and name it the fog accident rate; calculate the regional accident rate corresponding to different road surface friction coefficients, and name it the wet and slippery accident rate; calculate the regional accident rate when both visibility and road surface friction coefficient are within the normal range, and name it the normal accident rate.

[0019] The normal accident rate, fog accident rate, and wet and slippery accident rate are labeled as NR, FR, and WR, respectively. FR / NR is calculated to obtain the fog increase coefficient, and WR / NR is calculated to obtain the wet and slippery increase coefficient.

[0020] A two-dimensional coordinate system is established with visibility as the X-axis and fog amplification coefficient as the Y-axis, named the Fog Amplification Analysis Chart. The fog amplification coefficient is entered into the Fog Amplification Analysis Chart according to visibility. A two-dimensional coordinate system is established with road friction coefficient as the X-axis and wet slippage amplification coefficient as the Y-axis, named the Wet Slippage Amplification Analysis Chart. The wet slippage amplification coefficient is entered into the Wet Slippage Amplification Analysis Chart according to road friction coefficient.

[0021] Discrete regression analysis was performed on the fog day increase analysis chart and the slippery weather increase analysis chart respectively to obtain the fog day increase equation and the slippery weather increase equation.

[0022] Furthermore, the risk model analysis unit is configured with a risk model analysis strategy, which includes:

[0023] Establish a two-dimensional coordinate system with vehicle speed as the X-axis and following distance as the Y-axis, and name it the vehicle speed and following distance relationship graph. Enter the following distance from historical data into the vehicle speed and following distance relationship graph according to the vehicle speed.

[0024] Based on driving safety rules, the recommended minimum safe following distance at different driving speeds is obtained, and the minimum safe following distance is entered into the speed-distance relationship diagram according to the driving speed.

[0025] The coordinate points obtained from the historical data entry are named accident coordinates, and the coordinate points formed by the minimum safe distance are named safe coordinates.

[0026] Discrete regression analysis was performed on the accident coordinates and the safety coordinates respectively to obtain the speed-distance-accident relationship curve and the speed-distance-safety relationship curve.

[0027] A risk model is constructed, and the speed-distance-accident relationship curve and the speed-distance-safety relationship curve are entered into the risk model.

[0028] Furthermore, the risk coefficient analysis unit is configured with a risk coefficient analysis strategy, which includes:

[0029] Obtain the vehicle's real-time driving speed and following distance, and name them as real-time speed and real-time distance respectively. Enter the real-time speed and real-time distance into the speed-distance relationship graph, and name the obtained coordinate points as dynamic risk points.

[0030] Obtain the distances of dynamic risk points in the vertical direction relative to the vehicle speed-distance-accident curve and the vehicle speed-distance-safety curve, respectively named accident deviation distance and safety deviation distance, and represented by the symbols AD and SD respectively;

[0031] Calculate SD / (AD+SD) and name the result the risk coefficient.

[0032] Furthermore, the comprehensive risk analysis module is configured with a comprehensive risk analysis strategy, which includes:

[0033] The real-time visibility and road friction coefficient of the driving section are obtained and substituted into the fog amplification equation and the wet skid amplification equation respectively. The real-time fog amplification coefficient and wet skid amplification coefficient are obtained and named as the real-time fog amplification coefficient and the real-time wet skid amplification coefficient respectively, and are represented by the symbols RW and WC respectively.

[0034] The risk coefficient is labeled RK, and RK×RW×WC is calculated to obtain the comprehensive risk index of the vehicle on the road segment.

[0035] Furthermore, the travel risk assessment module includes a risk threshold analysis unit and a travel risk assessment unit;

[0036] The risk threshold analysis unit is used to analyze the risk threshold of historical data;

[0037] The travel risk assessment unit is used to assess the travel risk of a vehicle based on comprehensive risk indicators and risk thresholds.

[0038] Furthermore, the risk threshold analysis unit is configured with a risk threshold analysis strategy, which includes:

[0039] Calculate the comprehensive risk index for each historical data point and name it the historical index.

[0040] Obtain the minimum and maximum visibility values, labeled as Vmin and Vmax respectively; obtain the minimum and maximum road friction coefficient values, labeled as Cmin and Cmax respectively.

[0041] Visibility and road friction coefficient in historical data are labeled as HV and HC, respectively.

[0042] Through formula The normalized index for visibility is calculated using the formula. The normalized index for calculating the road friction coefficient is given, where GV is the normalized index for visibility and GC is the normalized index for the road friction coefficient.

[0043] Calculate GV+GC and name the calculation result as the weather impact index. Each historical index corresponds to a weather impact index.

[0044] A two-dimensional coordinate system is established with weather impact indicators as the horizontal axis and historical indicators as the vertical axis, named the Weather Indicator Impact Map. Historical indicators are entered into the Weather Indicator Impact Map according to the weather impact indicators, and the resulting coordinate points are named the Weather Indicator Impact Points.

[0045] Cluster analysis is performed on the weather index image map to obtain different impact clusters. The impact clusters are selected by rectangles to obtain cluster rectangles. When selecting the cluster rectangles, it is necessary to ensure that there is at least one weather index impact point on each side of the cluster rectangle.

[0046] Obtain the geometric center of the cluster rectangle and name it the cluster center. Perform discrete regression analysis on the cluster center to obtain the preliminary equation of the influence of weather indicators. Move the preliminary equation of the influence of weather indicators vertically downward along the opposite direction of the vertical axis until all the points affected by weather indicators are above the preliminary equation of the influence of weather indicators, and obtain the effective equation of the influence of weather indicators.

[0047] Real-time weather impact indicators are calculated based on real-time visibility and road surface friction coefficient, and named as real-time weather impact indicators. These real-time weather impact indicators are then substituted into the effective equation for the impact of weather indicators to obtain the risk threshold.

[0048] Furthermore, the travel risk assessment unit is configured with a travel risk assessment strategy, which includes:

[0049] Determine whether the comprehensive risk index is greater than or equal to the risk threshold. If yes, output a driving risk signal; otherwise, output a driving safety signal.

[0050] If a driving risk signal is output, it indicates that the vehicle poses a travel risk within the road segment; if a driving safety signal is output, it indicates that the vehicle does not pose a travel risk within the road segment.

[0051] The beneficial effects of this invention are as follows: This invention collects vehicle driving data using built-in sensors, then analyzes the amplification coefficient of different driving data on traffic accidents based on historical data, further analyzes the risk model of driving data, and then analyzes the vehicle's risk coefficient based on the risk model and driving data. Based on the risk coefficient, a comprehensive risk index of the vehicle is calculated. The advantage is that different driving speeds correspond to different safe following distances. By analyzing the driver's following distance, it is possible to determine whether there is a collision risk. In addition to the collision risk, visibility and road friction coefficient will further increase this collision risk. Therefore, the comprehensive risk index of the vehicle is calculated based on driving data analysis to reflect the safety of the vehicle in the driving segment, thereby improving the accuracy and rationality of vehicle travel risk assessment.

[0052] This invention analyzes risk thresholds from historical data and then assesses vehicle travel risks based on comprehensive risk indicators and risk thresholds. The advantage is that while comprehensive risk indicators reflect vehicle safety within a road segment, there is no established standard for their judgment. Therefore, by analyzing historical data to obtain risk thresholds, a basis for judging comprehensive risk indicators can be derived. This allows for predictive risk assessment of vehicle safety within a road segment, improving the accuracy and effectiveness of vehicle travel risk assessment. Attached Figure Description

[0053] Figure 1 This is a schematic diagram of the system of the present invention;

[0054] Figure 2 This is a foggy weather amplification analysis chart of the present invention;

[0055] Figure 3 This is a diagram showing the relationship between vehicle speed and distance in this invention;

[0056] Figure 4 This is a schematic diagram of the dynamic risk points of the present invention;

[0057] Figure 5 This is a weather index impact diagram of the present invention;

[0058] Figure 6 This is a schematic diagram illustrating the impact of the present invention on clustering;

[0059] Figure 7 This is a schematic diagram of the clustering rectangle of the present invention;

[0060] Figure 8 This is a schematic diagram of the clustering centers of the present invention;

[0061] Figure 9 This is a schematic diagram of the curve corresponding to the preliminary equation for the influence of weather indicators in this invention. Detailed Implementation

[0062] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0063] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0064] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0065] Example 1, please refer to Figure 1 As shown, this application provides a vehicle travel risk safety assessment system, including a driving data acquisition module, a risk coefficient calculation module, a comprehensive risk analysis module, and a travel risk assessment module; the driving data acquisition module, the risk coefficient calculation module, and the travel risk assessment module are respectively connected to the comprehensive risk analysis module for data transmission.

[0066] The driving data acquisition module is used to collect vehicle driving data using the vehicle's built-in sensors;

[0067] The vehicle data acquisition module is configured with a vehicle data acquisition strategy, which includes:

[0068] Obtain the vehicle's current driving segment and retrieve historical driving data from when traffic accidents occurred on that segment, naming the data as "historical data".

[0069] Driving data includes driving data, environmental data, and traffic data. Driving data includes vehicle speed and following distance, environmental data includes visibility and road surface friction coefficient, and traffic data includes the regional accident rate within the driving segment.

[0070] In practical applications, when collecting driving data, vehicle speed, following distance, and road friction coefficient can be obtained through the vehicle's built-in sensors. Visibility can be obtained through weather forecasts, and regional accident rates can be obtained through traffic management departments. The regional accident rates are the same for most driving sections, but there are a few sections where the regional accident rate is higher than other driving sections due to design issues. Therefore, it is necessary to conduct independent analysis on driving sections with higher regional accident rates than other driving sections.

[0071] The risk coefficient calculation module is used to analyze risk models of different driving data based on historical driving data, and to analyze the risk coefficient of the vehicle based on the risk model and driving data. The risk coefficient calculation module includes a risk correlation analysis unit, a risk model analysis unit, and a risk coefficient analysis unit.

[0072] The risk correlation analysis unit is used to analyze the amplification coefficient of different driving data on traffic accidents based on historical data;

[0073] The risk correlation analysis unit is configured with risk correlation analysis strategies, which include:

[0074] Collect historical data, calculate the regional accident rate corresponding to different visibility levels, and name it the fog accident rate; calculate the regional accident rate corresponding to different road surface friction coefficients, and name it the wet and slippery accident rate; calculate the regional accident rate when both visibility and road surface friction coefficient are within the normal range, and name it the normal accident rate.

[0075] The normal accident rate, fog accident rate, and wet and slippery accident rate are labeled as NR, FR, and WR, respectively. FR / NR is calculated to obtain the fog increase coefficient, and WR / NR is calculated to obtain the wet and slippery increase coefficient.

[0076] Please see Figure 2 As shown, a two-dimensional coordinate system is established with visibility as the X-axis and fog amplification coefficient as the Y-axis, named the Fog Amplification Analysis Chart. The fog amplification coefficient is entered into the Fog Amplification Analysis Chart according to visibility. A two-dimensional coordinate system is established with road friction coefficient as the X-axis and wet slippery coefficient as the Y-axis, named the Wet Slippery Amplification Analysis Chart. The wet slippery coefficient is entered into the Wet Slippery Amplification Analysis Chart according to road friction coefficient.

[0077] Discrete regression analysis was performed on the fog day increase analysis chart and the slippery weather increase analysis chart to obtain the fog day increase equation and the slippery weather increase equation, respectively.

[0078] In practical applications, the accident rates in foggy and slippery conditions can be obtained from traffic management departments. For example, when visibility is 50m, the foggy accident rate is 16.26 accidents per million vehicle-kilometers. The normal accident rate is the regional accident rate when visibility and road surface friction coefficient are both within the normal range. This is essentially the accident rate under clear weather conditions with no fog and no water, snow, or ice on the roads. The normal accident rate is 0.41 accidents per million vehicle-kilometers. The fog amplification coefficient at 50m visibility is calculated to be 39.66. The result is rounded to two decimal places, and the fog amplification analysis chart is constructed as follows. Figure 2 As shown, the equation for the increase in foggy weather, obtained through discrete regression analysis, is YV = 3986.2 × XV. -1.139 Where YV is the fog amplification factor and XV is the visibility, the slippery weather amplification equation is obtained by similar analysis as YR=0.4388×XR -1.976 Where YR is the wet slip amplification coefficient and XR is the road surface friction coefficient.

[0079] The risk model analysis unit is used to analyze risk models in driving data;

[0080] The risk model analysis unit is configured with risk model analysis strategies, which include:

[0081] Please see Figure 3 As shown, a two-dimensional coordinate system is established with the vehicle speed as the X-axis and the following distance as the Y-axis, named the vehicle speed and following distance relationship graph. The following distances from historical data are entered into the vehicle speed and following distance relationship graph according to the vehicle speed.

[0082] Based on driving safety rules, the recommended minimum safe following distance at different driving speeds is obtained, and the minimum safe following distance is entered into the speed-distance relationship diagram according to the driving speed.

[0083] The coordinate points obtained from the historical data entry are named accident coordinates, and the coordinate points formed by the minimum safe distance are named safe coordinates.

[0084] Discrete regression analysis was performed on the accident coordinates and the safety coordinates respectively to obtain the speed-distance-accident relationship curve and the speed-distance-safety relationship curve.

[0085] Construct a risk model and input the speed-distance-accident relationship curve and the speed-distance-safety relationship curve into the risk model;

[0086] In practical applications, the vehicle speed and distance relationship diagram is constructed as follows: Figure 3 As shown, Figure 3 The diagram already shows the speed-distance-accident relationship curve and the speed-distance-safety relationship curve. The speed-distance-safety relationship curve represents the officially recommended minimum safe distance at different speeds, which can be found online or in traffic regulations. The required distance varies depending on the speed. Rear-end collisions account for the largest proportion of traffic accidents, usually caused by failure to maintain a safe distance. The speed-distance-accident relationship curve reflects the relationship between speed and distance in historical traffic accidents. The closer a vehicle is to the speed-distance-accident relationship curve, the higher the probability of a traffic accident; conversely, the closer it is to the speed-distance-safety relationship curve, the lower the probability of a traffic accident.

[0087] The risk coefficient analysis unit is used to analyze the risk coefficient of a vehicle based on a risk model and driving data.

[0088] The risk coefficient analysis unit is configured with risk coefficient analysis strategies, which include:

[0089] Please see Figure 4 As shown, the real-time driving speed and following distance of the vehicle are obtained and named as real-time speed and real-time distance respectively. The real-time speed and real-time distance are entered into the speed-distance relationship graph, and the obtained coordinate points are named as dynamic risk points.

[0090] Obtain the distances of dynamic risk points in the vertical direction relative to the vehicle speed-distance-accident curve and the vehicle speed-distance-safety curve, respectively named accident deviation distance and safety deviation distance, and represented by the symbols AD and SD respectively;

[0091] Calculate SD / (AD+SD), and name the result the risk coefficient;

[0092] In practical applications, the location of dynamically identified risk points is entered as follows: Figure 4 As shown, the AD was 19.68 and the SD was 6.92. The calculated risk coefficient was 0.26. This risk coefficient is only the risk coefficient under normal conditions, that is, the risk coefficient when visibility and road friction coefficient are normal.

[0093] The comprehensive risk analysis module is used to calculate the comprehensive risk index of a vehicle based on risk coefficients;

[0094] The comprehensive risk analysis module is configured with comprehensive risk analysis strategies, which include:

[0095] The real-time visibility and road friction coefficient of the driving section are obtained and substituted into the fog amplification equation and the wet skid amplification equation respectively. The real-time fog amplification coefficient and wet skid amplification coefficient are obtained and named as the real-time fog amplification coefficient and the real-time wet skid amplification coefficient respectively, and are represented by the symbols RW and WC respectively.

[0096] The risk coefficient is labeled as RK, and RK×RW×WC is calculated to obtain the comprehensive risk index of the vehicle on the road segment.

[0097] In practical applications, the real-time visibility and road friction coefficient of the driving section are obtained as 5000m and 0.5, respectively. Since visibility greater than 1km has virtually no impact on driving, and the highest visibility obtained in this embodiment is 1500m, it is assumed to be 1500m when the visibility exceeds 1500m. That is, the real-time fog amplification coefficient RW is assumed to be 1. Substituting the road friction coefficient into the solution, the real-time wet and slippery amplification coefficient WC is obtained as 1.73. The calculation result is rounded to two decimal places. Further calculation yields a comprehensive risk index of 0.45 for the vehicle in the driving section. The calculation result is rounded to two decimal places.

[0098] The travel risk assessment module is used to assess the travel risk of vehicles based on comprehensive risk indicators; the travel risk assessment module includes a risk threshold analysis unit and a travel risk assessment unit.

[0099] The risk threshold analysis unit is used to analyze risk thresholds in historical data;

[0100] The risk threshold analysis unit is configured with a risk threshold analysis strategy, which includes:

[0101] Calculate the comprehensive risk index for each historical data point and name it the historical index.

[0102] Obtain the minimum and maximum visibility values, labeled as Vmin and Vmax respectively; obtain the minimum and maximum road friction coefficient values, labeled as Cmin and Cmax respectively.

[0103] Visibility and road friction coefficient in historical data are labeled as HV and HC, respectively.

[0104] Through formula The normalized index for visibility is calculated using the formula. The normalized index for calculating the road friction coefficient is given, where GV is the normalized index for visibility and GC is the normalized index for the road friction coefficient.

[0105] Calculate GV+GC and name the calculation result as the weather impact index. Each historical index corresponds to a weather impact index.

[0106] In practical applications, Vmin and Vmax are obtained as 20m and 1500m respectively, and Cmin and Cmax are 0.1 and 0.7 respectively. According to the aforementioned rules, when the visibility HV exceeds 1500m, it is calculated as 1500m. For example, in a certain historical data, HV is 5000m, which is regarded as 1500m, and the final calculated GV is 1. The weather impact index affects driving safety. The smaller the weather impact index, the greater the impact of weather on driving safety. Visibility and road friction coefficient can be added after normalization to assess the degree of impact on driving safety under the combined effect of the two. For example, in a certain driving, GV is 0.6 and GC is 1, and the final weather impact index is 1.6. In another driving, GV is 0.8 and GC is 0.8, and the final weather impact index is also 1.6. Although the visibility is higher than the previous data, the road surface is more slippery, which will also affect driving safety. Therefore, the weather impact index is the same in the calculation of the latter two driving.

[0107] Please see Figure 5 As shown, a two-dimensional coordinate system is established with weather impact indicators as the horizontal axis and historical indicators as the vertical axis, named the Weather Indicator Impact Map. Historical indicators are entered into the Weather Indicator Impact Map according to the weather impact indicators, and the resulting coordinate points are named the Weather Indicator Impact Points.

[0108] In practical applications, the resulting weather index impact map is as follows: Figure 5As shown, the historical data represents driving data at the time of the traffic accident. The weather index impact map reflects the approximate distribution of the comprehensive risk index of traffic accidents under different weather impact indices in the historical data, thereby identifying the risk threshold. Since different weather impact indices amplify the risk coefficient, the applicable risk thresholds differ between normal and poor weather conditions. Therefore, further analysis is needed to adapt to different weather impact indices. At the same time, there are a few isolated weather index impact points in the historical data. These historical indices are usually low-probability events and account for a small proportion in the analysis, having too little impact on the analysis results. However, safety is paramount, and we need to consider all situations. Therefore, after cluster analysis, different impacts are clustered as a whole, which can improve the impact of low-probability events on the analysis results.

[0109] Please see Figures 6 to 7 As shown, cluster analysis is performed on the weather index image map to obtain different impact clusters. The impact clusters are selected by rectangles to obtain cluster rectangles. When selecting the cluster rectangles, it is necessary to ensure that there is at least one weather index impact point on each side of the cluster rectangle.

[0110] Please see Figures 8 to 9 As shown, the geometric center of the cluster rectangle is obtained and named the cluster center. Discrete regression analysis is performed on the cluster center to obtain the preliminary equation of the influence of weather indicators. The preliminary equation of the influence of weather indicators is moved vertically downward along the opposite direction of the vertical axis until all the influence points of weather indicators are above the preliminary equation of the influence of weather indicators, and the effective equation of the influence of weather indicators is obtained.

[0111] Real-time weather impact indicators are calculated based on real-time visibility and road surface friction coefficient, and named as real-time weather impact indicators. The real-time weather impact indicators are then substituted into the effective equation of weather indicator impact to obtain the risk threshold.

[0112] In practical applications, the factors affecting clustering are analyzed, such as... Figure 6 As shown, Figure 6 Each hollow circle represents an influence cluster; selecting these circles yields cluster rectangles, as shown below. Figure 7 As shown, the extracted cluster centers are as follows: Figure 8 As shown, the curves corresponding to the preliminary equations of the influence of weather indicators are obtained through discrete regression analysis, as shown in the figure. Figure 9As shown, the preliminary equation for the influence of weather indicators reflects the historical trends of these indicators as weather influences them. However, safety is a critical factor that requires careful consideration. Since some weather indicator influence points are located below the preliminary equation, it needs to be calibrated by shifting the equation downwards so that all influence points are above it. This will encompass all historical driving conditions corresponding to these indicators and align with the historical trends of these indicators as weather influences them. The final effective equation for the influence of weather indicators is then obtained as YT = 3.92 × X. 2 -21.75×X+24.46, for example, the real-time weather impact index calculated during this trip is 1.5, and the risk threshold calculated by substituting it into the calculation is 0.655;

[0113] The travel risk assessment unit is used to assess the travel risk of vehicles based on comprehensive risk indicators and risk thresholds;

[0114] The travel risk assessment unit is equipped with travel risk assessment strategies, which include:

[0115] Determine whether the comprehensive risk index is greater than or equal to the risk threshold. If yes, output a driving risk signal; otherwise, output a driving safety signal.

[0116] If a driving risk signal is output, it indicates that the vehicle poses a travel risk within the driving segment; if a driving safety signal is output, it indicates that the vehicle does not pose a travel risk within the driving segment.

[0117] In practical applications, the calculated comprehensive risk index of the vehicle within the driving segment is 0.45, which is less than the risk index. Therefore, a driving safety signal is output, indicating that the vehicle does not pose a travel risk within the driving segment.

[0118] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

Claims

1. A vehicle travel risk safety assessment system, characterized in that, It includes a driving data acquisition module, a risk coefficient calculation module, a comprehensive risk analysis module, and a travel risk assessment module; the driving data acquisition module, the risk coefficient calculation module, and the travel risk assessment module are respectively connected to the comprehensive risk analysis module. The driving data acquisition module is used to collect driving data of the vehicle using the vehicle's built-in sensors; The risk coefficient calculation module is used to analyze risk models of different driving data based on historical driving data, and to analyze the risk coefficient of the vehicle based on the risk model and driving data. The comprehensive risk analysis module is used to calculate the comprehensive risk index of the vehicle based on the risk coefficient; The travel risk assessment module is used to assess the travel risk of the vehicle based on comprehensive risk indicators. The travel risk assessment module includes a risk threshold analysis unit and a travel risk assessment unit; The risk threshold analysis unit is used to analyze the risk threshold of historical data; The risk threshold analysis unit is configured with a risk threshold analysis strategy, which includes: Calculate the comprehensive risk index for each historical data point and name it the historical index. Obtain the minimum and maximum visibility values, labeled as Vmin and Vmax respectively; obtain the minimum and maximum road friction coefficient values, labeled as Cmin and Cmax respectively. Visibility and road friction coefficient in historical data are labeled as HV and HC, respectively. Through formula The normalized index for visibility is calculated using the formula. The normalized index for calculating the road friction coefficient is given, where GV is the normalized index for visibility and GC is the normalized index for the road friction coefficient. Calculate GV+GC and name the calculation result as the weather impact index. Each historical index corresponds to a weather impact index. A two-dimensional coordinate system is established with weather impact indicators as the horizontal axis and historical indicators as the vertical axis, named the Weather Indicator Impact Map. Historical indicators are entered into the Weather Indicator Impact Map according to the weather impact indicators, and the resulting coordinate points are named the Weather Indicator Impact Points. Cluster analysis is performed on the weather index image map to obtain different impact clusters. The impact clusters are selected by rectangles to obtain cluster rectangles. When selecting the cluster rectangles, it is necessary to ensure that there is at least one weather index impact point on each side of the cluster rectangle. Obtain the geometric center of the cluster rectangle and name it the cluster center. Perform discrete regression analysis on the cluster center to obtain the preliminary equation of the influence of weather indicators. Move the preliminary equation of the influence of weather indicators vertically downward along the opposite direction of the vertical axis until all the points affected by weather indicators are above the preliminary equation of the influence of weather indicators, and obtain the effective equation of the influence of weather indicators. Real-time weather impact indicators are calculated based on real-time visibility and road surface friction coefficient, and named as real-time weather impact indicators. These real-time weather impact indicators are then substituted into the effective equation for the impact of weather indicators to obtain the risk threshold.

2. The vehicle travel risk safety assessment system according to claim 1, characterized in that, The vehicle data acquisition module is configured with a vehicle data acquisition strategy, which includes: Obtain the vehicle's current driving segment and retrieve historical driving data from when traffic accidents occurred on that segment, naming the data as "historical data". The driving data includes driving data, environmental data, and traffic data. The driving data includes vehicle speed and following distance. The environmental data includes visibility and road surface friction coefficient. The traffic data includes the regional accident rate within the driving section.

3. The vehicle travel risk safety assessment system according to claim 1, characterized in that, The risk coefficient calculation module includes a risk correlation analysis unit, a risk model analysis unit, and a risk coefficient analysis unit. The risk correlation analysis unit is used to analyze the amplification coefficient of different driving data on traffic accidents based on historical data; The risk model analysis unit is used to analyze the risk model of driving data; The risk coefficient analysis unit is used to analyze the risk coefficient of a vehicle based on a risk model and driving data.

4. The vehicle travel risk safety assessment system according to claim 3, characterized in that, The risk correlation analysis unit is configured with a risk correlation analysis strategy, which includes: Collect historical data, calculate the regional accident rate corresponding to different visibility levels, and name it the fog accident rate; calculate the regional accident rate corresponding to different road surface friction coefficients, and name it the wet and slippery accident rate; calculate the regional accident rate when both visibility and road surface friction coefficient are within the normal range, and name it the normal accident rate. The normal accident rate, fog accident rate, and wet and slippery accident rate are labeled as NR, FR, and WR, respectively. FR / NR is calculated to obtain the fog increase coefficient, and WR / NR is calculated to obtain the wet and slippery increase coefficient. A two-dimensional coordinate system is established with visibility as the X-axis and fog amplification coefficient as the Y-axis, named the Fog Amplification Analysis Chart. The fog amplification coefficient is entered into the Fog Amplification Analysis Chart according to visibility. A two-dimensional coordinate system is established with road friction coefficient as the X-axis and wet slippage amplification coefficient as the Y-axis, named the Wet Slippage Amplification Analysis Chart. The wet slippage amplification coefficient is entered into the Wet Slippage Amplification Analysis Chart according to road friction coefficient. Discrete regression analysis was performed on the fog day increase analysis chart and the slippery weather increase analysis chart respectively to obtain the fog day increase equation and the slippery weather increase equation.

5. The vehicle travel risk safety assessment system according to claim 4, characterized in that, The risk model analysis unit is configured with a risk model analysis strategy, which includes: Establish a two-dimensional coordinate system with vehicle speed as the X-axis and following distance as the Y-axis, and name it the vehicle speed and following distance relationship graph. Enter the following distance from historical data into the vehicle speed and following distance relationship graph according to the vehicle speed. Based on driving safety rules, the recommended minimum safe following distance at different driving speeds is obtained, and the minimum safe following distance is entered into the speed-distance relationship diagram according to the driving speed. The coordinate points obtained from the historical data entry are named accident coordinates, and the coordinate points formed by the minimum safe distance are named safe coordinates. Discrete regression analysis was performed on the accident coordinates and the safety coordinates respectively to obtain the speed-distance-accident relationship curve and the speed-distance-safety relationship curve. A risk model is constructed, and the speed-distance-accident relationship curve and the speed-distance-safety relationship curve are entered into the risk model.

6. The vehicle travel risk safety assessment system according to claim 5, characterized in that, The risk coefficient analysis unit is configured with a risk coefficient analysis strategy, which includes: Obtain the vehicle's real-time driving speed and following distance, and name them as real-time speed and real-time distance respectively. Enter the real-time speed and real-time distance into the speed-distance relationship graph, and name the obtained coordinate points as dynamic risk points. Obtain the distances of dynamic risk points in the vertical direction relative to the vehicle speed-distance-accident curve and the vehicle speed-distance-safety curve, respectively named accident deviation distance and safety deviation distance, and represented by the symbols AD and SD respectively; Calculate SD / (AD+SD) and name the result the risk coefficient.

7. A vehicle travel risk safety assessment system according to claim 6, characterized in that, The comprehensive risk analysis module is configured with a comprehensive risk analysis strategy, which includes: The real-time visibility and road friction coefficient of the driving section are obtained and substituted into the fog amplification equation and the wet skid amplification equation respectively. The real-time fog amplification coefficient and wet skid amplification coefficient are obtained and named as the real-time fog amplification coefficient and the real-time wet skid amplification coefficient respectively, and are represented by the symbols RW and WC respectively. The risk coefficient is labeled RK, and RK×RW×WC is calculated to obtain the comprehensive risk index of the vehicle on the road segment.

8. The vehicle travel risk safety assessment system according to claim 7, characterized in that, The travel risk assessment module also includes a travel risk assessment unit; The travel risk assessment unit is used to assess the travel risk of a vehicle based on comprehensive risk indicators and risk thresholds.

9. A vehicle travel risk safety assessment system according to claim 8, characterized in that, The travel risk assessment unit is configured with a travel risk assessment strategy, which includes: Determine whether the comprehensive risk index is greater than or equal to the risk threshold. If yes, output a driving risk signal; otherwise, output a driving safety signal. If a driving risk signal is output, it indicates that the vehicle poses a travel risk within the road segment; if a driving safety signal is output, it indicates that the vehicle does not pose a travel risk within the road segment.

Images