Real-time risk assessment method and system for driving trajectory based on Internet of Vehicles big data

Abstract

The present invention discloses a real-time risk assessment method and system for driving trajectory based on Internet of Vehicles big data, and relates to the technical field of driving trajectory risk assessment. First, the characteristic data of each vehicle collected by monitoring and stored in a cloud server is analyzed to obtain the driving stability characterization index of each vehicle, which is helpful to analyze the stability of the vehicle driving process and identify the safety risks that may exist in the vehicle driving process. Then, the risk assessment associated data of each vehicle is analyzed to obtain the driving risk assessment trigger value threshold of each vehicle, which is helpful to improve the accuracy and pertinence of the driving trajectory risk assessment of each vehicle. Finally, according to the driving stability characterization index and driving risk assessment trigger value threshold of each vehicle, risk warning is carried out, which is helpful to improve the accuracy of driving state assessment, timely discover potential safety hazards, and thus timely issue warnings, reduce the incidence of driving accidents, and improve the safety of vehicle driving.

Description

Technical Field

[0001] The present invention relates to the technical field of driving trajectory risk assessment, and in particular to a real-time driving trajectory risk assessment method and system based on Internet of Vehicles big data. Background Art

[0002] With the continuous development of modern transportation systems, the state of vehicles will change during driving, and nearby vehicles may not be able to respond in time, which may easily lead to traffic accidents. Therefore, real-time risk assessment of driving trajectories has become particularly important. Risk assessment of moving vehicles can analyze the potential safety hazards of vehicles, thereby providing timely early warning prompts and improving the safety of vehicles during driving.

[0003] Prior art, such as the invention patent application with announcement number: CN113159576B, discloses a driving risk calculation method and online evaluation system for an autonomous vehicle, wherein the method calculates the collision damage caused by a hypothetical collision between the vehicle and surrounding traffic participants or static road facilities in a future motion state; the collision damage is reduced in spatial and temporal dimensions, and the maximum value is taken as the driving risk value at the current moment. The system includes a sensor module, a trajectory prediction module, and a risk evaluation module.

[0004] Prior art, such as the invention patent application with publication number: CN115841252A, discloses a highway driving risk assessment method based on predicted trajectories, which includes the following working steps: Step 1: Predict the predicted trajectories of the own vehicle and surrounding vehicles within the prediction interval; Step 2: Integrate the predicted trajectories within the prediction interval obtained in Step 1 into the predicted trajectories of the own vehicle and surrounding vehicles within each look-ahead time tla,m (m=1, 2, ..., T); Step 3: Obtain the quantitative perceived risk posed by the obstacle vehicle to the own vehicle within each look-ahead time; Step 4: Obtain a Bayesian model for quantitative perceived risk level division through the Bayesian posterior probability formula; Step 5: Realize real-time assessment of driving risks.

[0005] Combined with the above scheme, it is found that in the current field of real-time risk assessment technology for driving trajectories, there is a lack of targeted analysis of vehicle driving data, resulting in the inability to timely perceive the vehicle's driving status, unable to timely discover potential risks, and thus unable to reduce the vehicle's driving trajectory risk. In addition, there is little analysis of the vehicle's risk assessment-related data, and the driving trajectory risk assessment results cannot be updated in a timely manner, thereby providing timely warnings and improving the accuracy of vehicle risk assessments. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a real-time risk assessment method and system for driving trajectories based on Internet of Vehicles big data, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a real-time risk assessment method for driving trajectories based on Internet of Vehicles big data, including monitoring and obtaining the precise position of each vehicle, and collecting the characteristic data of each vehicle, and transmitting it to a cloud server.

[0008] The characteristic data of each vehicle in the cloud server is extracted, and the characteristic data of each vehicle is analyzed to obtain the driving stability characterization index of each vehicle.

[0009] The risk assessment associated data of each vehicle is obtained for analysis to obtain the driving risk assessment trigger value threshold of each vehicle.

[0010] Risk warning is issued based on the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle.

[0011] Furthermore, the monitoring obtains the precise position of each vehicle and collects characteristic data of each vehicle. The specific analysis process is: setting a number of monitoring time periods, monitoring and collecting the characteristic data of each vehicle in each monitoring time period, including the yaw rate of each vehicle, the current driving time of each vehicle, and the tilt angle of each vehicle.

[0012] Furthermore, the characteristic data of each vehicle is analyzed to obtain a driving stability characterization index of each vehicle. The specific analysis process is: extracting the yaw rate of each vehicle and the current driving time of each vehicle, and obtaining the yaw angle of each vehicle by integration.

[0013] The tilt angle and the yaw angle of each vehicle are extracted, and the first driving stability characterization index of each vehicle is obtained after processing.

[0014] Arrange several monitoring time periods, count the time difference between each radar wave and the received reflected wave in the characteristic data of each vehicle in each monitoring time period, extract the speed of electromagnetic wave propagation in the air, and analyze to obtain the distance between each vehicle and the vehicle in front in each monitoring time period.

[0015] The acceleration of each vehicle and the distance between each vehicle and the vehicle in front in each monitoring time period are extracted from the characteristic data of each vehicle, and the second driving stability characterization index of each vehicle is obtained through processing.

[0016] According to the first driving stability characterization index of each vehicle and the second driving stability characterization index of each vehicle, a comprehensive analysis is performed to obtain the driving stability characterization index of each vehicle.

[0017] Furthermore, the driving stability characterization index of each vehicle represents a quantitative result for analyzing the driving state stability of each vehicle obtained by monitoring and analyzing characteristic data of each vehicle.

[0018] Furthermore, the driving risk assessment trigger value threshold of each vehicle is obtained, and the specific analysis process is: extract the risk assessment related data of each vehicle for analysis, including the weight of each vehicle, years of operation, road friction coefficient, and rainfall, which are pre-processed and then imported into the neural network model to analyze and obtain the driving risk assessment trigger value threshold of each vehicle.

[0019] Furthermore, the driving risk assessment trigger value threshold of each vehicle represents a quantitative result for analyzing the risk triggering degree of each vehicle obtained by monitoring and analyzing the risk assessment associated data of each vehicle.

[0020] Furthermore, the risk warning is performed according to the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle. The specific analysis process is: the driving risk assessment trigger value of each vehicle is obtained according to the matching of the driving stability characterization index of each vehicle, and the driving risk assessment trigger value of each vehicle is compared with the driving risk assessment trigger value threshold of each vehicle to obtain the risk warning result. The risk warning result of each vehicle is to execute the risk warning or not to execute the risk warning. If the driving risk assessment trigger value of a vehicle is higher than or equal to the driving risk assessment trigger value threshold of the vehicle, the risk warning is executed. If the driving risk assessment trigger value of a vehicle is lower than the driving risk assessment trigger value threshold of the vehicle, the risk warning is not executed. The risk warning results of each vehicle are thus traversed.

[0021] Furthermore, the driving stability characterization index of each vehicle is specifically analyzed under the following conditions:

[0022] In the formula, α i represents the driving stability characterization index of the i-th vehicle, β i represents the first characterization index of the driving stability of the i-th vehicle, μ 1 Indicates the weight factor corresponding to the set first driving stability characterization index, δ i represents the second characterization index of driving stability of the i-th vehicle, μ 2 It represents the weight factor corresponding to the set second driving stability characterization index, i represents the number of each vehicle, i=1,2,3,…n, n represents the total number of vehicles, and e represents a natural constant.

[0023] Furthermore, the first driving stability characterization index of each vehicle has specific analysis conditions as follows:

[0024] In the formula, β i represents the first characterization index of the driving stability of the i-th vehicle, ε i represents the tilt angle of the i-th vehicle, Δε represents the set limit tilt angle, θ 1 Indicates the influence factor corresponding to the set tilt angle, ρi represents the yaw angle of the i-th vehicle, Δρ represents the set limit yaw angle, θ 2 It represents the influence factor corresponding to the set yaw angle, i represents the number of each vehicle, i=1,2,3,…n, and n represents the total number of vehicles.

[0025] The second aspect of the present invention provides a real-time risk assessment system for driving trajectories based on Internet of Vehicles big data, which is characterized by including: a data acquisition and transmission module for monitoring and obtaining the precise position of each vehicle, and collecting characteristic data of each vehicle, and transmitting it to a cloud server.

[0026] The driving trajectory data analysis module is used to extract the characteristic data of each vehicle in the cloud server, analyze the characteristic data of each vehicle, and obtain the driving stability characterization index of each vehicle.

[0027] The driving risk assessment module is used to obtain the risk assessment related data of each vehicle for analysis and obtain the driving risk assessment trigger value threshold of each vehicle.

[0028] The driving risk warning module is used to issue risk warnings based on the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle.

[0029] The present invention has the following beneficial effects:

[0030] (1) The present invention provides a real-time risk assessment method and system for driving trajectories based on Internet of Vehicles big data. First, the characteristic data of each vehicle is analyzed to obtain the driving stability characterization index of each vehicle, which helps to improve the accuracy of driving behavior assessment and can more accurately perform driving trajectory risk assessment. Then, the risk assessment-related data of each vehicle is analyzed to perform risk warning. The possible safety risks in the vehicle driving process can be identified, so as to provide timely warning.

[0031] (2) The present invention obtains the driving stability characterization index of each vehicle through analysis, which helps to timely discover unstable driving behavior and reduce the occurrence of traffic accidents. It also helps to identify potential traffic hazards and conflicts and evaluate road safety by monitoring and analyzing the stability of each vehicle's driving process and the vehicle's driving conditions on the road.

[0032] (3) The present invention obtains the driving risk assessment trigger value threshold of each vehicle through analysis, and performs targeted analysis on different vehicles to obtain the corresponding driving risk assessment trigger value threshold, which helps to more accurately reflect the risk warning situation of each vehicle, thereby providing more accurate warning prompts.

[0033] (4) The present invention provides risk warning through analysis, which helps to timely discover potential dangerous conditions and reduce the possibility of accidents. It can also provide personalized safety protection for each vehicle and improve driving safety. Timely risk warning can improve the safety of vehicle driving and reduce driving trajectory risks.

[0034] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0036] Figure 2 It is a schematic diagram of system module connection of the present invention.

[0037] Figure 3 This is an example image of the driving stability characterization value of a vehicle. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] See also Figure 1 As shown, the first aspect of the present invention provides a technical solution: a real-time risk assessment method for driving trajectories based on Internet of Vehicles big data, including monitoring and obtaining the precise position of each vehicle, and collecting characteristic data of each vehicle, and transmitting it to a cloud server.

[0040] The characteristic data of each vehicle in the cloud server is extracted, and the characteristic data of each vehicle is analyzed to obtain the driving stability characterization index of each vehicle.

[0041] The risk assessment associated data of each vehicle is obtained for analysis to obtain the driving risk assessment trigger value threshold of each vehicle.

[0042] Risk warning is issued based on the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle.

[0043] Specifically, the precise position of each vehicle is monitored and the characteristic data of each vehicle is collected. The specific analysis process is: several monitoring time periods are set, and the characteristic data of each vehicle is monitored and collected in each monitoring time period, including the yaw rate of each vehicle, the current driving time of each vehicle, and the tilt angle of each vehicle.

[0044] Specifically, the characteristic data of each vehicle is analyzed to obtain the driving stability characterization index of each vehicle. The specific analysis process is: extracting the yaw rate of each vehicle and the current driving time of each vehicle, and obtaining the yaw angle of each vehicle by integration.

[0045] It should be noted that the yaw angle of each vehicle is obtained by performing data analysis on the yaw rate of each vehicle and the current driving time of each vehicle, and is used to analyze the quantified result of the driving stability of each vehicle, and is used as the analysis basis of the first characterization index of the driving stability of each vehicle. It can be obtained by the following analysis method, and the specific analysis conditions are as follows:

[0046]

[0047] In the formula, ρ i represents the yaw angle of the i-th vehicle, represents the yaw rate of the i-th vehicle at time t, T i represents the current travel time of the i-th vehicle, i represents the number of each vehicle, i=1,2,3,…n, n represents the total number of vehicles, e represents a natural constant, t i ∈[0,T i ].

[0048] In an embodiment, the environmental information around the vehicle can also be captured by the on-board camera, and the posture of the vehicle can be estimated and tracked using computer vision technology. The position, direction and movement of the vehicle in the image can be analyzed to obtain the yaw angle of each vehicle.

[0049] It should be noted that analyzing the vehicle's yaw angle helps to understand changes in the vehicle's driving direction, detect abnormal vehicle behavior in a timely manner, and predict changes in the vehicle's driving trajectory, thereby improving the safety of vehicle driving and providing more accurate data support for real-time risk assessment of driving trajectories.

[0050] It should be noted that the yaw rate of a vehicle refers to the rotation rate of the vehicle around the vertical axis. The yaw rate of the vehicle is directly read by the inertial measurement unit equipped with the vehicle. For example, assuming that the yaw rate of a vehicle measured by the inertial measurement unit of a vehicle is 10 (rad / s), then the yaw rate of the vehicle is 10 (rad / s).

[0051] It should be noted that the current driving time of a vehicle refers to the length of time from the time the vehicle is started to the current moment, which can be measured by a timer. For example, assuming that the timer time for starting a vehicle is 0.01h and the timer time at the current moment is 1.01h, then the current driving time of the vehicle is 1h.

[0052] It should be explained that in this embodiment, the yaw rate of the vehicle and the current driving time of the vehicle are analyzed, so that the current driving direction and trend of the vehicle can be analyzed and the steering action of the vehicle can be perceived in time. According to the analysis method of this embodiment, a smaller yaw rate and a longer current driving time indicate that the stability of the vehicle's driving process is higher, which can reduce the risk of the vehicle's driving trajectory.

[0053] In this implementation, analyzing the vehicle's yaw rate helps monitor the vehicle's steering stability, analyzing the vehicle's current driving time helps determine whether the driver is in a fatigued state, and analyzing the yaw angle of each vehicle can timely discover potential safety hazards during vehicle driving, which helps improve vehicle driving safety.

[0054] The tilt angle and the yaw angle of each vehicle are extracted, and the first driving stability characterization index of each vehicle is obtained after processing.

[0055] It should be noted that the first driving stability characterization index of each vehicle represents a quantitative result obtained by performing data analysis and processing on the tilt angle and yaw angle of each vehicle, which is used to analyze the degree of change of the trajectory of each vehicle during the driving process, and serves as the analysis basis for the driving stability characterization index of each vehicle.

[0056] Arrange several monitoring time periods, count the time difference between each radar wave and the received reflected wave in the characteristic data of each vehicle in each monitoring time period, extract the speed of electromagnetic wave propagation in the air, and analyze to obtain the distance between each vehicle and the vehicle in front in each monitoring time period.

[0057] The acceleration of each vehicle and the distance between each vehicle and the vehicle in front in each monitoring time period are extracted from the characteristic data of each vehicle, and the second driving stability characterization index of each vehicle is obtained through processing.

[0058] It should be noted that the second driving stability characterization index of each vehicle represents a quantitative result obtained by performing data analysis and processing on the acceleration of each vehicle and the distance between each vehicle and the vehicle in front in each monitoring time period for analyzing the driving safety of each vehicle, and serves as an analysis basis for the driving stability characterization index of each vehicle. It can be obtained by the following analysis method, and the specific analysis conditions are as follows:

[0059]

[0060] In the formula, δ i represents the second characterization index of driving stability of the i-th vehicle, b i represents the acceleration of the i-th vehicle, Δb represents the set limit acceleration, θ 3 Indicates the influence factor corresponding to the set acceleration, c i→jrepresents the distance between the i-th vehicle and the vehicle ahead in the j-th monitoring period, Δc represents the set limit distance, θ 4 It represents the impact factor corresponding to the set distance, j represents the number of each monitoring time period, j=1,2,3,…m, and m represents the total number of monitoring time periods.

[0061] In the embodiment, the second driving stability characterization index of each vehicle may also be obtained by analyzing the corner speed of the vehicle.

[0062] It should be noted that the defined acceleration of a vehicle refers to the maximum acceleration allowed by the vehicle during driving, obtained through statistical analysis of historical data. For example, assuming that the defined acceleration of a vehicle obtained through statistical analysis is 40 (m / s 2 ), then the defined acceleration of the vehicle is 40 (m / s 2 ).

[0063] It should be noted that the vehicle's defined distance refers to the minimum distance allowed between the vehicle and the vehicle in front during driving, which is obtained through statistical analysis of historical data. For example, assuming that the defined distance of a vehicle obtained through statistical analysis is 0.5m, then the defined distance of the vehicle is 0.5m. If it is lower than this range, traffic accidents may occur because the vehicles are too close and the driver does not have enough distance to react when encountering emergencies.

[0064] It should be noted that the influence factors corresponding to the acceleration of the vehicle and the influence factors corresponding to the distance are obtained through historical data analysis. Specifically, the acceleration of a certain vehicle is 30 (m / s 2 ), the distance between the vehicle and the vehicle in front is 1m. At the same time, through statistical analysis, it is found that when the acceleration of the vehicle reaches 40 (m / s 2 ), the vehicle speed may be too high, which may cause traffic hazards. In addition, when the distance between the vehicle and the vehicle in front is 0.5m, it is easy to fail to react in time due to the close distance, which may increase the possibility of traffic accidents. Therefore, when the acceleration of the vehicle exceeds 30 (m / s 2 ), the impact factor corresponding to the vehicle's acceleration can be set to 0.6. When the vehicle's acceleration reaches 40 (m / s 2 ), the impact factor corresponding to the vehicle's acceleration should be set to a maximum value of 1.3. When the distance between the vehicle and the vehicle in front is less than 1m, the impact factor corresponding to the distance can be set to 0.7. When the distance between the vehicle and the vehicle in front is 0.5m, the impact factor corresponding to the distance should be set to a maximum value of 1.4.

[0065] It should be noted that analyzing the second driving stability characterization index of each vehicle is helpful to understand the impact of driving behavior on vehicle stability, improve the accuracy of driving status assessment, and promptly discover potential safety hazards, thereby providing timely warnings.

[0066] It should be noted that the acceleration of a vehicle refers to the rate of change of the vehicle's speed per unit time. The acceleration of the vehicle is obtained by monitoring and analyzing the engine output and braking system status of the vehicle. For example, assuming that the acceleration of a vehicle is 20 (m / s 2 ), then the acceleration of the vehicle is 20 (m / s 2 ).

[0067] It should be noted that the distance between a vehicle and the vehicle in front refers to the space between each vehicle and the vehicle in front of it during the monitoring period. For example, assuming that the time difference between each radar wave and the received reflected wave in the characteristic data of a vehicle during a monitoring period is 0.01 μs, and the speed of electromagnetic wave propagation in the air is 3×10 8 m / s, then the distance between the vehicle and the vehicle ahead during this monitoring period is 0.01μs×3×10 8 m / s=3m.

[0068] It should be explained that in this embodiment, the acceleration of each vehicle and the distance between each vehicle and the vehicle in front in each monitoring time period are analyzed, which can improve the accuracy of driving status assessment. The analysis method of this embodiment, the smaller vehicle acceleration and the larger vehicle distance from the vehicle in front indicate that the vehicle speed changes less and the distance between vehicles is smaller during driving, which helps to reduce traffic accidents caused by excessive vehicle speed.

[0069] In this implementation scheme, analyzing the acceleration of the vehicle helps to evaluate the stability of the vehicle's driving process, and can also evaluate and measure abnormal driving behavior, so as to promptly discover potential dangers. Analyzing the distance between the vehicle and the vehicle in front helps to evaluate the vehicle's collision risk. Analyzing the second driving stability characterization index of each vehicle can improve the reliability of vehicle risk assessment. If the vehicle's acceleration is too large and the following distance is too small, the vehicle collision risk may increase, which may be ignored when analyzing each factor separately.

[0070] According to the first driving stability characterization index of each vehicle and the second driving stability characterization index of each vehicle, a comprehensive analysis is performed to obtain the driving stability characterization index of each vehicle.

[0071] In this implementation scheme, the driving stability characterization index of each vehicle comprehensively considers a variety of driving stability factors, improves the accuracy of driving behavior assessment, increases the comprehensiveness of vehicle status monitoring, and can more accurately assess driving trajectory risks, thereby providing timely warnings and reducing the incidence of traffic accidents.

[0072] Specifically, the driving stability characterization index of each vehicle represents a quantitative result for analyzing the driving state stability of each vehicle obtained by monitoring and analyzing the characteristic data of each vehicle.

[0073] Specifically, the driving risk assessment trigger value threshold of each vehicle is obtained. The specific analysis process is: extract the risk assessment related data of each vehicle for analysis, including the weight of each vehicle, years of operation, road friction coefficient, and rainfall, which are pre-processed and imported into the neural network model to analyze and obtain the driving risk assessment trigger value threshold of each vehicle.

[0074] It should be noted that the data is imported into the neural network model and analyzed to obtain the driving risk assessment trigger value threshold of each vehicle. The specific analysis process is as follows: first, according to the data characteristics, the number of nodes in the input layer is determined. The weight, years of operation, road friction coefficient, and rainfall of each vehicle correspond to 4 nodes respectively. The number of nodes in the output layer is 1. The data characteristics of the output layer are the driving risk assessment trigger value thresholds of each vehicle. The historical data is input into the recurrent neural network model to train the model, and the model parameters are continuously adjusted to avoid overfitting or underfitting. The trained recurrent neural network model is used to analyze the data in the input layer to obtain the driving risk assessment trigger value thresholds of each vehicle.

[0075] In this implementation, a neural network model is used to analyze and derive the driving risk assessment trigger value threshold for each vehicle, which helps to improve the accuracy and pertinence of driving trajectory risk assessment. It can be combined with actual data for monitoring and feedback, and the driving risk assessment results can be updated in a timely manner, thereby providing timely warnings and improving vehicle driving safety.

[0076] Specifically, the driving risk assessment trigger value threshold of each vehicle represents a quantitative result for analyzing the risk triggering degree of each vehicle obtained by monitoring and analyzing the risk assessment associated data of each vehicle.

[0077] Specifically, risk warning is performed according to the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle. The specific analysis process is: the driving risk assessment trigger value of each vehicle is obtained according to the matching of the driving stability characterization index of each vehicle, and the driving risk assessment trigger value of each vehicle is compared with the driving risk assessment trigger value threshold of each vehicle to obtain the risk warning result. The risk warning result of each vehicle is to execute risk warning or not to execute risk warning. If the driving risk assessment trigger value of a vehicle is higher than or equal to the driving risk assessment trigger value threshold of the vehicle, the risk warning is executed. If the driving risk assessment trigger value of a vehicle is lower than the driving risk assessment trigger value threshold of the vehicle, the risk warning is not executed. The risk warning results of each vehicle are thus traversed.

[0078] In this implementation scheme, the driving stability characterization index of each vehicle is extracted and compared with the driving risk assessment trigger value of each vehicle corresponding to the set driving stability characterization index interval of each vehicle, and the driving risk assessment trigger value of each vehicle is matched.

[0079] Specifically, the driving stability characterization index of each vehicle can be obtained not only by pattern recognition and analysis using historical data, but also by the following calculation method. The specific analysis conditions are:

[0080]

[0081] In the formula, α i represents the driving stability characterization index of the i-th vehicle, β i represents the first characterization index of the driving stability of the i-th vehicle, μ 1 Indicates the weight factor corresponding to the set first driving stability characterization index, δ i represents the second characterization index of driving stability of the i-th vehicle, μ 2 It represents the weight factor corresponding to the set second driving stability characterization index, i represents the number of each vehicle, i=1,2,3,…n, n represents the total number of vehicles, and e represents a natural constant.

[0082] It should be noted that Figure 3 This is an example image of a vehicle's driving stability characterization index.

[0083] It should be noted that Figure 3 The vehicle's driving stability characterization index increases with the increase of the vehicle's first driving stability characterization index. In the figure, the horizontal axis is the vehicle's driving stability characterization index, and the vertical axis is the vehicle's driving stability characterization index. a, b, and c respectively represent the curves of the vehicle's driving stability characterization index changing with the increase of the vehicle's first driving stability characterization index when the vehicle's second driving stability characterization index is 0.2, 0.5, and 0.8. When the vehicle's first driving stability characterization index increases, the vehicle's driving stability characterization index increases accordingly, and the vehicle's first driving stability characterization index has a greater impact on the vehicle's driving stability characterization index.

[0084] It should be noted that the weight factors corresponding to the first driving stability characterization index and the weight factors corresponding to the second driving stability characterization index are obtained through historical data analysis, and the weight factors can be adjusted according to the importance of different indicators. For example, if the driving stability characterization index of a vehicle is greatly affected by the change in the direction of the vehicle, then the first driving stability characterization index of the vehicle may be assigned a higher weight factor, because a large change in the direction of the vehicle will reduce the driving stability of the vehicle and affect the accuracy of the driving trajectory risk assessment. Similarly, if the driving stability characterization index of a vehicle is greatly affected by the acceleration of the vehicle, then the second driving stability characterization index of the vehicle may be assigned a higher weight factor, because a large change in acceleration will affect the driving stability of the vehicle.

[0085] It should be noted that analyzing the driving stability characterization index of each vehicle can help to promptly detect abnormal conditions of the vehicle, provide timely warnings, and reduce the possibility of accidents.

[0086] It should be explained that in this embodiment, the first driving stability characterization index and the second driving stability characterization index of each vehicle are analyzed to predict potential safety risks. The analysis method of this embodiment, a larger first driving stability characterization index of a vehicle and a larger second driving stability characterization index of a vehicle indicate that the vehicle has higher stability during driving, which helps to improve the safety of vehicle driving.

[0087] In this implementation, analyzing the vehicle's driving stability characterization index can analyze the vehicle's driving stability, which helps to identify possible safety risks during the vehicle's driving process, thereby providing timely warnings.

[0088] Specifically, the first driving stability characterization index of each vehicle can be obtained not only by pattern recognition and analysis using historical data, but also by the following calculation method. The specific analysis conditions are:

[0089]

[0090] In the formula, β i represents the first characterization index of the driving stability of the i-th vehicle, ε i represents the tilt angle of the i-th vehicle, Δε represents the set limit tilt angle, θ 1 Indicates the influence factor corresponding to the set tilt angle, ρ i represents the yaw angle of the i-th vehicle, Δρ represents the set limit yaw angle, θ 2 It represents the influence factor corresponding to the set yaw angle, i represents the number of each vehicle, i=1,2,3,…n, and n represents the total number of vehicles.

[0091] It should be noted that Table 1 shows the first driving stability characterization values ​​corresponding to different tilt angles and yaw angles of the same vehicle.

[0092] Table 1 The first characterization value of driving stability corresponding to different tilt angles and yaw angles of the same vehicle

[0093]

[0094]

[0095] It should be noted that, in Table 1, as the tilt angle and yaw angle of the vehicle increase, the data of the first characterization value of the vehicle's driving stability becomes smaller, and the tilt angle and yaw angle of the vehicle have a more obvious impact on the risk assessment of the vehicle. The first characterization index of driving stability of each vehicle in Table 1 is analyzed by combining the tilt angle and yaw angle of the vehicle, and the values ​​of three different tilt angles and yaw angles of the same vehicle are listed. The first characterization index of driving stability of the vehicle is obtained by the formula. The values ​​of the first characterization index of driving stability of these vehicles provide the stability of the vehicle under different conditions. When the yaw angle of the vehicle is the same and the tilt angle increases, the first characterization index of driving stability indicates that the first characterization value of driving stability of the vehicle decreases with the increase of the tilt angle of the vehicle. Similarly, the first characterization value of driving stability of the vehicle also decreases with the increase of the yaw angle of the vehicle. Obtaining these values ​​helps the vehicle driver to better understand the driving status of the vehicle under specific conditions, so as to make timely adjustments.

[0096] It should be noted that the first driving stability characterization index of each vehicle comprehensively considers the vehicle's tilt angle and yaw angle, which helps to identify potential risks of the vehicle, such as rollover when turning and vehicle loss of control, and improve driving safety.

[0097] It should be noted that the tilt angle of a vehicle refers to the degree of inclination of the vehicle relative to the horizontal plane, which can be measured by on-board sensors. For example, assuming that the on-board sensor of a vehicle measures that the degree of inclination of the vehicle relative to the horizontal plane is 30°, then the tilt angle of the vehicle is 30°.

[0098] It should be noted that the vehicle's defined tilt angle represents the maximum tilt angle allowed for the vehicle during driving, obtained through statistical analysis of historical data. For example, assuming that the defined tilt angle of a vehicle obtained through statistical analysis is 50°, then the defined tilt angle of the vehicle is 50°.

[0099] It should be noted that the defined yaw angle of a vehicle refers to the yaw angle allowed for the vehicle during driving, which is obtained through statistical analysis of historical data. For example, assuming that the defined yaw angle of a vehicle is 70° after statistical analysis, then the defined yaw angle of the vehicle is 70°. If the yaw angle is higher than this range, the vehicle may turn too much, and traffic accidents such as rollover may occur during driving.

[0100] It should be noted that, through historical data analysis, the influencing factors corresponding to the vehicle's tilt angle and the influencing factors corresponding to the yaw angle are obtained, specifically: after statistical analysis, it is found that the tilt angle of a certain vehicle is 30°, and the yaw angle of the vehicle is 50°. At the same time, after statistical analysis, it is found that when the tilt angle of the vehicle reaches 50°, the vehicle will turn too much and it is easy to roll over. In addition, when the yaw angle of the vehicle reaches 70°, it is easy to cause traffic accidents. Therefore, when the tilt angle of the vehicle exceeds 30°, the influencing factor corresponding to the tilt angle of the vehicle increases and can be set to 0.5. When the tilt angle of the vehicle reaches 50°, the influencing factor corresponding to the tilt angle of the vehicle should be set to a maximum value of 1.2. When the yaw angle of the vehicle exceeds 50°, the influencing factor corresponding to the yaw angle of the vehicle increases and can be set to 0.3. When the yaw angle of the vehicle reaches 70°, the influencing factor corresponding to the yaw angle of the vehicle should be set to a maximum value of 1.1.

[0101] It should be explained that the analysis of the vehicle's tilt angle and yaw angle in this embodiment can predict potential safety risks. The analysis method of this embodiment, a larger vehicle tilt angle and a larger vehicle yaw angle indicate that the vehicle may change direction during driving, which helps to issue early warnings in time, prompting the driver to take corresponding measures to reduce the possibility of accidents.

[0102] In this implementation, by monitoring and analyzing the tilt angle and yaw angle of the vehicle and analyzing and obtaining the first characterization index of the vehicle's driving stability, dynamic monitoring of the vehicle's driving state can be achieved, thereby improving the accuracy of driving trajectory risk assessment.

[0103] The second aspect of the present invention provides a real-time risk assessment system for driving trajectories based on Internet of Vehicles big data, including: a data acquisition and transmission module, which is used to monitor and obtain the precise position of each vehicle, and collect the characteristic data of each vehicle, and transmit it to a cloud server.

[0104] The driving trajectory data analysis module is used to extract the characteristic data of each vehicle in the cloud server, analyze the characteristic data of each vehicle, and obtain the driving stability characterization index of each vehicle.

[0105] The driving risk assessment module is used to obtain the risk assessment related data of each vehicle for analysis and obtain the driving risk assessment trigger value threshold of each vehicle.

[0106] The driving risk warning module is used to issue risk warnings based on the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle.

[0107] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0108] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A real-time risk assessment method for vehicle trajectories based on Internet of Vehicles big data, characterized in that: include: Monitor and obtain the precise location of each vehicle, collect characteristic data of each vehicle, and transmit it to the cloud server; Extracting characteristic data of each vehicle in the cloud server, analyzing the characteristic data of each vehicle, and obtaining a driving stability characterization index of each vehicle; Obtain risk assessment related data of each vehicle for analysis to obtain driving risk assessment trigger value thresholds of each vehicle; Provide risk warning based on the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle; The monitoring obtains the precise location of each vehicle and collects the characteristic data of each vehicle. The specific analysis process is as follows: Setting a number of monitoring time periods, monitoring and collecting characteristic data of each vehicle in each monitoring time period, including the yaw rate of each vehicle, the current driving time of each vehicle, and the tilt angle of each vehicle; The characteristic data of each vehicle is analyzed to obtain the driving stability characterization index of each vehicle. The specific analysis process is as follows: Extract the yaw rate of each vehicle and the current driving time of each vehicle, and obtain the yaw angle of each vehicle by integration; Extracting the tilt angle and the yaw angle of each vehicle, and obtaining the first driving stability characterization index of each vehicle after processing; Arrange several monitoring time periods, count the time difference between each radar wave and the received reflected wave in the characteristic data of each vehicle in each monitoring time period, extract the speed of electromagnetic wave propagation in the air, and analyze and obtain the distance between each vehicle and the vehicle in front in each monitoring time period; Extracting the acceleration of each vehicle and the distance between each vehicle and the vehicle ahead in each monitoring time period from the characteristic data of each vehicle, and obtaining the second driving stability characterization index of each vehicle after processing; According to the first driving stability characterization index of each vehicle and the second driving stability characterization index of each vehicle, a comprehensive analysis is performed to obtain the driving stability characterization index of each vehicle.

2. The method for real-time risk assessment of driving trajectories based on Internet of Vehicles big data according to claim 1 is characterized by: The driving stability characterization index of each vehicle represents a quantitative result for analyzing the driving state stability of each vehicle obtained by monitoring and analyzing the characteristic data of each vehicle.

3. The method for real-time risk assessment of driving trajectories based on Internet of Vehicles big data according to claim 1 is characterized by: The driving risk assessment trigger value threshold of each vehicle is obtained, and the specific analysis process is as follows: The risk assessment related data of each vehicle is extracted for analysis, including the weight of each vehicle, years of operation, road friction coefficient, and rainfall, which are pre-processed and then imported into the neural network model to analyze and obtain the driving risk assessment trigger value threshold of each vehicle.

4. The method for real-time risk assessment of driving trajectories based on Internet of Vehicles big data according to claim 3 is characterized by: The driving risk assessment trigger value threshold of each vehicle represents a quantitative result for analyzing the risk triggering degree of each vehicle obtained by monitoring and analyzing the risk assessment associated data of each vehicle.

5. The method for real-time risk assessment of driving trajectories based on Internet of Vehicles big data according to claim 1 is characterized by: The risk warning is performed according to the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle. The specific analysis process is as follows: The driving risk assessment trigger value of each vehicle is obtained by matching the driving stability characterization index of each vehicle, and the driving risk assessment trigger value of each vehicle is compared with the driving risk assessment trigger value threshold of each vehicle to obtain the risk warning result. The risk warning result of each vehicle is to execute the risk warning or not to execute the risk warning. If the driving risk assessment trigger value of a vehicle is higher than or equal to the driving risk assessment trigger value threshold of the vehicle, the risk warning is executed. If the driving risk assessment trigger value of a vehicle is lower than the driving risk assessment trigger value threshold of the vehicle, the risk warning is not executed. The risk warning results of each vehicle are obtained by traversing.

6. The method for real-time risk assessment of driving trajectories based on Internet of Vehicles big data according to claim 2 is characterized by: The driving stability characterization index of each vehicle is specifically analyzed under the following conditions: In the formula, α i represents the driving stability characterization index of the i-th vehicle, β i represents the first driving stability characterization index of the i-th vehicle, μ1 represents the weight factor corresponding to the set first driving stability characterization index, δ i represents the second characterization index of driving stability of the i-th vehicle, μ2 represents the weight factor corresponding to the set second characterization index of driving stability, i represents the number of each vehicle, i=1,2,3,…n, n represents the total number of vehicles, and e represents a natural constant.

7. The method for real-time risk assessment of driving trajectories based on Internet of Vehicles big data according to claim 1 is characterized by: The first driving stability characterization index of each vehicle is specifically analyzed under the following conditions: In the formula, β i represents the first characterization index of the driving stability of the i-th vehicle, ε i represents the tilt angle of the i-th vehicle, Δε represents the set limit tilt angle, θ1 represents the influence factor corresponding to the set tilt angle, ρ i represents the yaw angle of the i-th vehicle, Δρ represents the set limit yaw angle, θ2 represents the influence factor corresponding to the set yaw angle, i represents the number of each vehicle, i=1,2,3,…n, n represents the total number of vehicles.

8. A real-time risk assessment system for vehicle trajectories based on Internet of Vehicles big data according to any one of claims 1 to 7, characterized in that: include: The data acquisition and transmission module is used to monitor and obtain the precise location of each vehicle, collect the characteristic data of each vehicle, and transmit it to the cloud server; The driving trajectory data analysis module is used to extract the characteristic data of each vehicle in the cloud server, analyze the characteristic data of each vehicle, and obtain the driving stability characterization index of each vehicle; The driving risk assessment module is used to obtain the risk assessment related data of each vehicle for analysis and obtain the driving risk assessment trigger value threshold of each vehicle; The driving risk warning module is used to issue risk warnings based on the driving stability characterization index of each vehicle and the driving risk assessment trigger value threshold of each vehicle.

Images