ETC data accident prediction method and system based on Internet of Things

Abstract

The invention relates to the technical field of data processing of the Internet of Things, and particularly discloses an accident prediction method and system based on ETC data of the Internet of Things, and the method comprises the steps: vehicle historical accident analysis, vehicle driving analysis, predicted driving road and highway state analysis and accident prediction reminding. According to the method, historical risk driving behaviors of vehicles are identified, the driving accident risk of each vehicle is evaluated by acquiring ETC historical data of a first road section of an expressway and driving information of each vehicle in the first road section of the expressway, and the accident risk of the vehicles on a specific road section is predicted by analyzing the driving historical data, environment information and road condition data of the vehicles. Potential dangers can be found and preventive measures can be taken, so that traffic accidents are reduced, the safety of the expressway is improved, a driver can be warned in advance through prediction reminding, the possibility of accidents can be reduced by taking measures in time, and the road traffic safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things data processing, and in particular to an accident prediction method and system based on ETC data of the Internet of Things. Background Art

[0002] At present, with the rapid development of expressways and the continuous growth of traffic volume, traffic accidents on expressways occur frequently. Therefore, expressway traffic management departments urgently need an effective method to predict and prevent the occurrence of traffic accidents. Through the application of this method, traffic management departments can more accurately grasp the occurrence patterns and trends of traffic accidents, so as to take effective preventive measures and reduce the incidence of traffic accidents.

[0003] For example, the invention patent with announcement number CN113704317B announces a method for predicting accident black spots based on analysis of traffic accident characteristics, including: gridding the target area based on GIS; gridding and aggregating the accident data according to the location information of the accident to obtain the distribution data of accident high-incidence points; analyzing the time of the accident, the weather conditions at the time of the accident, and the vehicle speed threshold data in the area during the period of occurrence to form a relationship matrix of the frequency of accidents in a single grid, time period, weather, and vehicle speed threshold; integrating the road network data of vehicle flow and traffic index; determining the most likely accident black spot through analysis of accident high-incidence locations, and determining the most likely time interval for the occurrence of the most likely accident black spot through analysis of accident high-incidence time periods; based on the most likely accident black spot, the most likely time interval, weather, traffic flow, and traffic index, the comprehensive characteristics of accidents at historical accident high-incidence points in different time periods can be integrated and analyzed, thereby realizing the ability to predict possible accident black spots.

[0004] For example, the invention patent with announcement number CN112784121 B announced a traffic accident prediction method based on spatiotemporal graph representation learning. First, the adjacency matrix of the traffic road network is constructed according to the sensor network, and the original traffic data is screened and counted to obtain the speed, capacity and occupancy data of the specific area to construct a feature matrix. Then, a traffic accident prediction model based on the ST-VGAE structure is established. By inputting the adjacency matrix and the feature matrix into ST-VGAE, the traffic state is represented by the spatiotemporal graph convolution module, and it is input into a convolutional neural network to predict the probability of traffic accidents. Finally, the established traffic accident prediction model is trained with the processed data, and the parameters in the model are adjusted to obtain the optimal traffic flow prediction.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] Among the existing traffic accident prediction methods, the main focus is on making predictions based on traffic road areas (such as grid areas, accident black spots, etc.). Regional prediction methods can often only capture the overall trend or pattern of traffic flow and cannot comprehensively map the traffic accident prediction conditions in all scenarios, which directly leads to inaccurate traffic accident prediction results. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention provides an accident prediction method and system based on ETC data of the Internet of Things, which can effectively solve the problems involved in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides an accident prediction method based on ETC data of the Internet of Things, including: S1. Vehicle historical accident analysis: obtain the license plate number of each vehicle traveling on the first section of the expressway, match the license plate number of each vehicle with the historical traffic information corresponding to each license plate number stored in the ETC Internet of Things platform, obtain the historical traffic information of each vehicle, and analyze the historical traffic indicators of each vehicle.

[0009] S2. Vehicle driving analysis: The ETC historical data of the first section of the expressway and the driving information of each vehicle in the first section of the expressway are obtained through the ETC Internet of Things platform. The ETC historical data of the first section of the expressway, the driving information of each vehicle in the first section of the expressway and the historical traffic indicators of each vehicle are comprehensively analyzed to obtain the driving accident risk indicator of each vehicle.

[0010] S3. Analysis of the expected highway status: The estimated environmental information of the second section of the highway and the historical driving conditions of the second section of the highway are obtained through the ETC Internet of Things platform, and a comprehensive analysis is performed to obtain the expected driving accident risk threshold of the vehicle.

[0011] S4. Accident prediction reminder: Compare the driving accident risk index of each vehicle with the vehicle's estimated driving accident risk threshold to obtain a comparison result of each vehicle's driving accident, and determine whether to issue an accident prediction reminder to each vehicle based on the comparison result of each vehicle's driving accident.

[0012] As a further method, the specific analysis process of the historical traffic indicators of each vehicle is as follows:

[0013] The historical total mileage of each vehicle is ratioed to the historical driving time to obtain the historical average driving speed of each vehicle.

[0014] The historical accident rate of each vehicle is obtained by ratioing the historical number of accidents of each vehicle with the historical total mileage.

[0015] The historical violation rate of each vehicle is obtained by performing a ratio processing on the historical number of violations of each vehicle and the historical total mileage.

[0016] The historical average speed, historical accident rate and historical violation rate of each vehicle are comprehensively analyzed to obtain the historical traffic indicators of each vehicle.

[0017] As a further method, the specific analysis process of the driving accident risk index of each vehicle is as follows:

[0018] The maximum travel speed of each vehicle in the first section of the expressway is analyzed by ratio with the highest historical travel speed of the first section of the expressway to obtain the speed utilization rate of each vehicle in the first section of the expressway.

[0019] The number of historical traffic accidents in the first section of the expressway, the speed utilization rate of each vehicle in the first section of the expressway, the number of lane changes and the historical traffic indicators of each vehicle are comprehensively analyzed to obtain the driving accident risk index of each vehicle.

[0020] As a further method, the vehicle is expected to have an accident risk threshold, and the specific analysis method is as follows:

[0021]

[0022] Where ρ is the predicted accident risk threshold of the vehicle, e is a natural constant, js is the precipitation in the second section of the expressway, Δjs is the precipitation threshold preset in the traffic management database, kj is the visibility in the second section of the expressway, Δkj is the reference visibility preset in the traffic management database, sc is the number of historical traffic accidents in the second section of the expressway, z1 is the risk impact index corresponding to the unit value of the number of historical traffic accidents preset in the traffic management database, yd is the number of historical vehicles passing through the second section of the expressway, and Δyd is the reference number of vehicles passing through preset in the traffic management database.

[0023] As a further method, the specific process of determining whether to perform accident prediction reminder for each vehicle based on the comparison results of the driving accidents of each vehicle is as follows:

[0024] The comparison results of the vehicle driving accidents are specifically as follows:

[0025] If the driving accident risk index of a vehicle is greater than the vehicle's estimated driving accident risk threshold, the driving accident comparison result of the vehicle is the first comparison result.

[0026] If the comparison result of a vehicle driving accident is the first comparison result, an accident prediction reminder is issued to the vehicle.

[0027] If the driving accident risk index of a vehicle is less than or equal to the vehicle predicted driving accident risk threshold, the driving accident comparison result of the vehicle is the second comparison result.

[0028] If the driving accident comparison result of a certain vehicle is the second comparison result, there is no need to provide an accident prediction reminder for the vehicle.

[0029] The second aspect of the present invention provides an accident prediction system based on ETC data of the Internet of Things, including: a vehicle historical accident analysis module, used to obtain the license plate number of each vehicle traveling on the first section of the expressway, match the license plate number of each vehicle with the historical traffic information corresponding to each license plate number stored in the ETC Internet of Things platform, obtain the historical traffic information of each vehicle, and analyze the historical traffic indicators of each vehicle.

[0030] The vehicle driving analysis module is used to obtain the ETC historical data of the first section of the expressway and the driving information of each vehicle in the first section of the expressway through the ETC Internet of Things platform, and comprehensively analyze the ETC historical data of the first section of the expressway, the driving information of each vehicle in the first section of the expressway and the historical traffic indicators of each vehicle to obtain the driving accident risk indicator of each vehicle.

[0031] The estimated driving road highway status analysis module is used to obtain the estimated environmental information of the second section of the highway and the historical driving road condition information of the second section of the highway through the ETC Internet of Things platform, and conduct a comprehensive analysis to obtain the vehicle's estimated driving accident risk threshold.

[0032] The accident prediction and reminder module is used to compare the driving accident risk index of each vehicle with the vehicle's expected driving accident risk threshold, obtain the comparison results of each vehicle's driving accidents, and determine whether to issue accident prediction reminders to each vehicle based on the comparison results of each vehicle's driving accidents.

[0033] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0034] (1) The present invention obtains historical traffic indicators of each vehicle by analyzing the historical traffic information of each vehicle, and can identify the risks and dangerous driving behaviors of the vehicle's historical driving. For example, some vehicles may be prone to accidents due to frequent violations of traffic rules (such as speeding, sudden braking, etc.).

[0035] (2) The present invention obtains the ETC historical data of the first section of the expressway and the driving information of each vehicle in the first section of the expressway, and comprehensively analyzes the ETC historical data of the area to which the first section of the expressway belongs, the driving information of each vehicle in the first section of the expressway, and the historical traffic indicators of each vehicle to obtain the driving accident risk indicator of each vehicle. The driving accident risk of each vehicle can be accurately assessed. The combination of historical data and real-time driving information provides a comprehensive basis for accident risk prediction, and can more accurately identify potential accident risk factors, such as driving habits, traffic conditions, and historical accident records of vehicles, thereby achieving more efficient accident warning.

[0036] (3) The present invention obtains the estimated environmental information of the second section of the expressway and the historical driving road condition information of the second section of the expressway, and performs comprehensive analysis to obtain the estimated driving accident risk threshold of the vehicle. By analyzing the vehicle's driving history data, environmental information and road condition data, the accident risk of the vehicle on a specific section can be accurately predicted, which helps to discover potential dangers early and take preventive measures, thereby reducing the occurrence of traffic accidents and improving the safety of the expressway.

[0037] (4) The present invention compares the driving accident risk index of each vehicle with the vehicle's expected driving accident risk threshold, and finally determines whether to issue an accident prediction reminder for each vehicle based on the comparison result. It can identify vehicles or driving behaviors that may pose high risks in advance. Through prediction reminders, drivers can receive advance warnings and take timely measures to reduce the possibility of accidents, thereby effectively improving road traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0039] Figure 1 The figure is a schematic flow chart of the method steps of the present invention.

[0040] Figure 2 It is a schematic diagram of system module connection of the present invention. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0042] Reference Figure 1 As shown, the first aspect of the present invention provides an accident prediction method based on ETC data of the Internet of Things, including: S1. Vehicle historical accident analysis: obtaining the license plate number of each vehicle traveling on the first section of the expressway, matching the license plate number of each vehicle with the historical traffic information corresponding to each license plate number stored in the ETC Internet of Things platform, obtaining the historical traffic information of each vehicle, and analyzing the historical traffic indicators of each vehicle.

[0043] It needs to be explained that the license plate numbers of the above-mentioned vehicles are obtained through surveillance cameras installed in the current highways. The surveillance cameras can capture images of driving vehicles, and the license plate numbers can be extracted from these images through license plate recognition technology. The ETC Internet of Things platform is a comprehensive service platform built based on ETC technology and integrating the characteristics of the Internet of Things. By reading the information in the ETC equipment installed on the vehicle (such as OBU, i.e., on-board unit), it can accurately identify the vehicle's license plate number information. The license plate number is the basis for subsequent traffic information matching and historical traffic analysis. A large amount of vehicle travel records and historical traffic information will be stored in the ETC Internet of Things platform, including vehicle travel time, speed, mileage, etc. This information is very important for analyzing vehicle The driving conditions of the ETC Internet of Things platform are crucial. The ETC Internet of Things platform not only exchanges information with the ETC toll stations, but also shares data with the traffic management department to achieve more extensive information interconnection and traffic management. The license plate number is the unique identifier of the vehicle. It is unique on the ETC Internet of Things platform and the license plate number of the currently traveling vehicle. The license plate number of each vehicle is matched with the historical traffic information corresponding to each license plate number stored in the ETC Internet of Things platform. The database query is used to compare the license plate number of the currently traveling vehicle with the historical traffic information in the ETC Internet of Things platform. For each currently traveling vehicle, the historical traffic information that matches its license plate number is searched in the ETC Internet of Things platform, and this information is extracted for subsequent analysis and comparison.

[0044] S2. Vehicle driving analysis: The ETC historical data of the first section of the expressway and the driving information of each vehicle in the first section of the expressway are obtained through the ETC Internet of Things platform. The ETC historical data of the first section of the expressway, the driving information of each vehicle in the first section of the expressway and the historical traffic indicators of each vehicle are comprehensively analyzed to obtain the driving accident risk indicator of each vehicle.

[0045] S3. Analysis of the expected highway status: The estimated environmental information of the second section of the highway and the historical driving conditions of the second section of the highway are obtained through the ETC Internet of Things platform, and a comprehensive analysis is performed to obtain the expected driving accident risk threshold of the vehicle.

[0046] In this embodiment, the first section of the highway refers to the starting section for vehicles to conduct historical accident analysis and driving analysis, and is the data collection area of ​​the accident prediction system, which is used to obtain and analyze the vehicle's driving data and historical traffic information. The second section of the highway is the section where the vehicle continues to travel after the first section, and is also the main area for the accident prediction system to predict the vehicle's future driving accident risks. The first section of the highway and the second section of the highway are set according to actual conditions. The first section of the highway needs to be long enough to collect enough vehicle driving data to conduct accurate historical accident analysis and driving analysis, and the second section of the highway should be set according to prediction needs to ensure that it can cover the main areas where the vehicle is expected to travel.

[0047] S4. Accident prediction reminder: Compare the driving accident risk index of each vehicle with the vehicle's estimated driving accident risk threshold to obtain a comparison result of each vehicle's driving accident, and determine whether to issue an accident prediction reminder to each vehicle based on the comparison result of each vehicle's driving accident.

[0048] Specifically, the historical traffic information of each vehicle includes the historical driving time, historical total mileage, historical accident number and historical violation number of each vehicle.

[0049] It should be explained that the historical driving time and total mileage of the above-mentioned vehicles are obtained through the vehicle driving recorder. The historical number of accidents and the historical number of violations can be directly queried by the traffic management department (such as the vehicle management office or the traffic police team). In this embodiment, the vehicle's accidents include but are not limited to collisions or contacts with other vehicles, road facilities, etc. when the vehicle is driving on the road, resulting in traffic interruptions; the vehicle's violations specifically include but are not limited to speeding, illegal lane changes, driving in the opposite direction, drunk driving or fatigue driving, overloading or overcrowding, etc.

[0050] In this embodiment, the longer the historical driving time of the vehicle is, the greater its total historical mileage will be. The increase in the total historical mileage of the vehicle means that the frequency of use and the degree of wear of the vehicle are also increasing, which will lead to aging, damage or failure of vehicle components, thereby increasing the risk of accidents. There is a certain positive correlation between the number of historical accidents and the number of historical violations. Violations often increase the risk of accidents because the violations themselves may violate traffic rules or driving safety principles. Therefore, there is a complex mutual influence relationship between the parameters in the historical traffic information of each vehicle.

[0051] Specifically, the specific analysis process of the historical traffic indicators of each vehicle is as follows:

[0052] The historical total mileage of each vehicle is ratioed to the historical driving time to obtain the historical average driving speed of each vehicle.

[0053] The historical accident rate of each vehicle is obtained by ratioing the historical number of accidents of each vehicle with the historical total mileage.

[0054] The historical violation rate of each vehicle is obtained by performing a ratio processing on the historical number of violations of each vehicle and the historical total mileage.

[0055] The historical average speed, historical accident rate and historical violation rate of each vehicle are comprehensively analyzed to obtain the historical traffic index of each vehicle. The specific analysis method is as follows:

[0056]

[0057] In the formula, γ a is the ath vehicle historical traffic index, a is the number of each vehicle, a=1, 2, 3...b, b is the total number of vehicles.

[0058] st a is the historical average driving speed of the ath vehicle, which refers to the ratio of the vehicle's historical total mileage to its historical driving time.

[0059] Δst is the driving reference speed preset in the traffic management database, which refers to the standard driving speed value formulated by the traffic management database to ensure the safety of road traffic.

[0060] sg a is the historical accident rate of the a-th vehicle, which refers to the ratio of the number of historical accidents of the vehicle to the total historical mileage.

[0061] h1 is the traffic impact index corresponding to the unit value of the historical accident rate preset in the traffic management database. The traffic impact index corresponding to the unit value of the historical accident rate can be directly obtained from the traffic management database, and the corresponding relationship can be a preset mapping relationship. For example, a mapping set is formed according to the historical accident rate and the traffic impact index corresponding to the unit value of the historical accident rate, and the real-time historical accident rate is input into the mapping set to obtain the traffic impact index corresponding to the unit value of the historical accident rate. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0062] sw a is the historical violation rate of the a-th vehicle, which refers to the ratio of the vehicle’s historical violation times to its historical total mileage.

[0063] h2 is the traffic impact index corresponding to the unit value of the historical violation rate preset in the traffic management database. The traffic impact index corresponding to the unit value of the historical violation rate can be directly obtained from the traffic management database, and the corresponding relationship can be a preset mapping relationship. For example, a mapping set is formed according to the historical violation rate and the traffic impact index corresponding to the unit value of the historical violation rate, and the real-time violation rate is input into the mapping set to obtain the traffic impact index corresponding to the unit value of the historical violation rate. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0064] In this embodiment, if the historical average driving speed of the vehicle deviates greatly from the preset driving reference speed, it will disrupt the stability of the entire traffic flow and reduce the road traffic efficiency, especially on the highway. Too fast speed will cause the vehicle to lose control, while too slow speed will hinder traffic flow and cause rear-end collisions. A higher vehicle historical violation rate will lead to a higher vehicle historical accident rate, which means that the vehicle is more likely to have an accident during driving, which directly leads to an increase in the vehicle's historical traffic indicators. Therefore, through a detailed analysis of each parameter in the vehicle's historical traffic indicators, the vehicle's driving safety can be more comprehensively evaluated, which can more truly reflect the actual performance of the vehicle and the driver in the traffic environment, and discover the potential risks of the vehicle and the driver in traffic safety.

[0065] Furthermore, the ETC historical data of the first section of the expressway specifically includes the historical maximum speed and the number of historical traffic accidents of the first section of the expressway.

[0066] It should be explained that the historical maximum speed of the first section of the above-mentioned expressway is the speed of historical vehicles passing through the first section of the expressway recorded by the ETC on the expressway, and the maximum value analysis is performed on these data to obtain the historical maximum speed of the first section of the expressway. The number of historical traffic accidents is the historical traffic accident situations recorded by the expressway management department of the first section of the expressway, and the number of historical traffic accidents is obtained by statistics.

[0067] The driving information of each vehicle in the first section of the expressway specifically includes the maximum driving speed and the number of lane changes of each vehicle in the first section of the expressway.

[0068] It should be explained that the maximum speed of the above-mentioned vehicles in the first section of the expressway is obtained by the highway management department, which usually installs traffic monitoring equipment in key sections, such as radar speed meters, cameras, etc. These devices can monitor and record the vehicle's driving speed in real time, so as to obtain the maximum speed of each vehicle in the first section of the expressway. The number of lane changes of each vehicle in the first section of the expressway is obtained by the highway management department through analyzing the vehicle's lane changing behavior through traffic monitoring video of the driving in the first section of the expressway. Through video processing technology, the vehicle's lane changing action can be automatically identified and the number of lane changes can be counted, so as to obtain the number of lane changes of each vehicle in the first section of the expressway.

[0069] Specifically, the specific analysis process of the driving accident risk index of each vehicle is as follows:

[0070] The maximum travel speed of each vehicle in the first section of the expressway is analyzed by ratio with the highest historical travel speed of the first section of the expressway to obtain the speed utilization rate of each vehicle in the first section of the expressway.

[0071] The number of historical traffic accidents in the first section of the expressway, the speed utilization rate of each vehicle in the first section of the expressway, the number of lane changes and the historical traffic indicators of each vehicle are comprehensively analyzed to obtain the driving accident risk index of each vehicle.

[0072] In this embodiment, there is a complex relationship between the number of historical traffic accidents in the first section of the expressway, the speed utilization rate of each vehicle in the first section of the expressway, the number of lane changes, and the historical traffic indicators of each vehicle. The number of historical traffic accidents in the first section of the expressway is relatively large, indicating that there may be more safety hazards or traffic bottlenecks in the section, thereby increasing the risk of future traffic accidents. A higher speed utilization rate on the expressway usually means that the driver is close to or exceeds the speed limit, which increases the risk of accidents. Especially when the traffic volume is large or the road conditions are complex, an excessively high speed utilization rate may lead to slow reaction and then cause an accident. At a higher speed, the lane change operation of the vehicle is more dangerous, especially when a quick lane change is required, which is easy to cause rear-end collisions, scratches and other accidents. Therefore, there is a certain positive correlation between the speed utilization rate of the vehicle in the first section of the expressway and the number of lane changes. The influence of historical traffic indicators usually reflects the standardization and safety of historical driving behavior. If there are more accident records in history, or the vehicle has a bad traffic violation record, it means that the vehicle is more likely to have an accident when driving on the first section of the expressway.

[0073] The specific analysis method for obtaining the driving accident risk index of each vehicle is as follows:

[0074]

[0075] In the formula, F a is the accident risk index of the ath vehicle, e is a natural constant, a is the number of each vehicle, a=1, 2, 3...b, b is the total number of vehicles, γ a is the historical traffic index of the ath vehicle.

[0076] lc is the number of historical traffic accidents on the first section of the expressway, which refers to the total number of traffic accidents that occurred on the first section of the expressway.

[0077] k1 is the risk impact index corresponding to the unit value of the historical number of traffic accidents preset in the traffic management database. The risk impact index corresponding to the unit value of the historical number of traffic accidents can be directly obtained from the traffic management database, and the corresponding relationship can be a pre-set mapping relationship. For example, a mapping set is formed according to the number of historical traffic accidents and the risk impact index corresponding to the unit value of the historical number of traffic accidents, and the real-time number of traffic accidents is input into the mapping set to obtain the risk impact index corresponding to the unit value of the historical number of traffic accidents. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0078] ly a It is the speed utilization rate of the ath vehicle in the first section of the expressway, which refers to the ratio of the average driving speed of the vehicles in the first section of the expressway to the historical highest speed of the first section of the expressway.

[0079] k2 is the driving impact index corresponding to the speed utilization unit value preset in the traffic management database. The driving impact index corresponding to the speed utilization unit value can be directly obtained from the traffic management database. The corresponding relationship can be a preset mapping relationship. For example, a mapping set is formed according to the historical speed utilization and the driving impact index corresponding to the speed utilization unit value, and the real-time speed utilization is input into the mapping set to obtain the driving impact index corresponding to the speed utilization unit value. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0080] bc a The number of lane changes made by the a-th vehicle in the first section of the expressway refers to the total number of lane changes made by the vehicle on the section.

[0081] k3 is the driving impact index corresponding to the unit value of the number of lane changes preset in the traffic management database. The driving impact index corresponding to the unit value of the number of lane changes can be directly obtained from the traffic management database, and the corresponding relationship can be a preset mapping relationship. For example, a mapping set is formed according to the historical number of lane changes and the driving impact index corresponding to the unit value of the number of lane changes, and the real-time number of lane changes is input into the mapping set to obtain the driving impact index corresponding to the unit value of the number of lane changes. The mapping relationship can be one-to-one or many-to-one. At the same time, its value range in this example is [0, 1].

[0082] k4 is the driving impact index corresponding to the vehicle historical traffic index preset in the traffic management database. The driving impact index corresponding to the vehicle historical traffic index can be directly obtained from the traffic management database. The corresponding relationship can be a preset mapping relationship. For example, a mapping set is formed according to the historical vehicle historical traffic indicators and the driving impact index corresponding to the vehicle historical traffic indicators, and the real-time vehicle historical traffic indicators are input into the mapping set to obtain the driving impact index corresponding to the vehicle historical traffic indicators. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0083] In this embodiment, the first section of the expressway has a large number of historical traffic accidents, which means that there are major safety hazards or irregular driving behavior problems in this section. In this case, the risk of an accident occurring when the vehicle is traveling on this section will increase. The higher the speed utilization rate of the vehicle in the first section of the expressway, the longer the driver's reaction time and braking distance will be when the vehicle encounters an emergency, thereby increasing the risk of an accident. The vehicle changes lanes a large number of times in the first section of the expressway. During the lane change process, the vehicle needs to interact with vehicles in other lanes, which increases the risk of a collision. Therefore, the risk of a driving accident for a vehicle that changes lanes a large number of times will also increase accordingly. If the vehicle has a high historical traffic index, then the risk of the vehicle occurring in the future may also be high. Through a detailed analysis of the parameters in the vehicle's driving accident risk index, the potential risks in the vehicle's driving process can be more comprehensively evaluated. Based on the vehicle's driving data, the vehicle's driving accident risk can be accurately evaluated, providing accurate risk warning information for accident prediction.

[0084] Specifically, the estimated environmental information of the second section of the expressway includes precipitation and visibility of the second section of the expressway.

[0085] It should be explained that the precipitation and visibility of the second section of the above-mentioned expressway can be obtained through querying the meteorological data released by the meteorological monitoring station.

[0086] The historical driving traffic condition information of the second section of the expressway specifically includes the historical number of traffic accidents and the historical number of vehicles passing through the second section of the expressway.

[0087] It should be explained that the historical number of traffic accidents and the historical number of vehicles passing through the second section of the above-mentioned expressway can be obtained by accessing the traffic accident data and vehicle traffic data recorded by the traffic management department.

[0088] Furthermore, the vehicle is expected to have an accident risk threshold, and the specific analysis process is as follows:

[0089] A comprehensive analysis is conducted on the precipitation, visibility, number of historical traffic accidents and number of historical vehicles passing through the second section of the expressway to obtain the expected vehicle accident risk threshold.

[0090] In this embodiment, there is a complex data relationship between the precipitation, visibility, historical traffic accident number and historical vehicle passing number of the second section of the above-mentioned expressway. An increase in precipitation usually causes the road surface to be slippery, and raindrops will obstruct the driver's line of sight and reduce visibility. The greater the precipitation, the more slippery the road surface and the lower the visibility, and the greater the driver's control difficulty and the possibility of misjudgment, which will lead to an increase in the number of historical accidents. The historical vehicle passing number reflects the traffic flow of the section. The greater the traffic flow, the greater the interaction and interference between vehicles, thereby increasing the possibility of traffic accidents.

[0091] Specifically, the vehicle predicted driving accident risk threshold is analyzed by the following specific method:

[0092]

[0093] Where ρ is the vehicle's estimated accident risk threshold, and e is a natural constant.

[0094] js is the precipitation on the second section of the expressway, which refers to the total amount of rainfall or snowfall when the vehicle reaches the second section of the expressway.

[0095] Δjs is the precipitation threshold preset in the traffic management database, which refers to a precipitation warning value set based on historical data and experience.

[0096] kj is the visibility of the second section of the expressway, which refers to the distance at which the driver can clearly see the road ahead when the vehicle reaches the second section of the expressway.

[0097] Δkj is the reference visibility preset in the traffic management database, which refers to a visibility standard set according to the weather.

[0098] sc is the number of historical traffic accidents on the second section of the expressway, which refers to the total number of traffic accidents that occurred on the second section of the expressway.

[0099] z1 is the risk impact index corresponding to the unit value of the historical number of traffic accidents preset in the traffic management database. The risk impact index corresponding to the unit value of the historical number of accidents can be directly obtained from the traffic management database, and the corresponding relationship can be a pre-set mapping relationship. For example, a mapping set is formed according to the number of historical accidents and the risk impact index corresponding to the unit value of the historical number of accidents, and the real-time number of accidents is input into the mapping set to obtain the risk impact index corresponding to the unit value of the historical number of accidents. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0100] yd is the historical vehicle traffic volume of the second section of the expressway, which refers to the total number of vehicles passing through the second section of the expressway.

[0101] Δyd is the reference number of vehicles passing preset in the traffic management database, which refers to a vehicle passing standard set based on historical data and traffic flow forecasts.

[0102] In this embodiment, when the precipitation on the second section of the highway is relatively high, even more than the preset precipitation threshold, the road surface will become slippery, and the friction between the tires and the ground will decrease, resulting in an increase in the braking distance of the vehicle and a decrease in maneuverability. At the same time, rain may also affect the driver's line of sight, reduce visibility, and increase the possibility of accidents. Therefore, excessive precipitation will significantly increase the vehicle's expected driving accident risk threshold; lower visibility on the second section of the highway, even lower than the preset reference visibility, will lead to limited driver's line of sight and reduced judgment of the road conditions and obstacles ahead, resulting in the driver's inability to promptly detect and respond to potential dangerous situations, thereby increasing the probability of accidents. Therefore, insufficient visibility will also increase the vehicle's expected driving accident risk threshold. A large number of historical accidents on the second section of the highway The number of occurrences indicates that there are more safety hazards or unfavorable factors in this section of road. These hazards or factors may cause drivers to face higher risks during driving. Therefore, the increase in the number of historical accidents will directly lead to an increase in the vehicle's expected driving accident risk threshold. A larger number of historical vehicles passing through the second section of the highway, or even more than the preset reference number of vehicles passing, will significantly increase the traffic flow on the section. The increase in traffic flow will lead to increased interaction and interference between vehicles. Drivers need to adjust their speed and lanes more frequently, which increases the difficulty of control and the possibility of misjudgment. Therefore, through a detailed analysis of the parameters in the vehicle's expected driving accident risk threshold, the potential risks of vehicles driving on the second section of the highway can be more comprehensively evaluated, thereby improving the accuracy of accident prediction.

[0103] Specifically, the process of determining whether to perform accident prediction reminder for each vehicle based on the comparison results of the driving accidents of each vehicle is as follows:

[0104] The comparison results of the vehicle driving accidents are specifically as follows:

[0105] If the driving accident risk index of a vehicle is greater than the vehicle's estimated driving accident risk threshold, the driving accident comparison result of the vehicle is the first comparison result.

[0106] If the comparison result of a vehicle driving accident is the first comparison result, an accident prediction reminder is issued to the vehicle.

[0107] It needs to be explained that when the driving accident risk index of a certain vehicle is greater than the vehicle's expected driving accident risk threshold, it means that the probability of the vehicle having an accident while driving on the second section of the highway has increased significantly, and the vehicle has a higher driving risk, which will cause the probability of the vehicle having an accident on the second section of the highway to increase significantly. Therefore, it is necessary to issue an accident prediction reminder for the vehicle. The specific warning prompt can be a voice prompt issued by the traffic management department through the on-board system configured for the vehicle, such as "Pay attention to driving safety, the current driving risk is high, please reduce speed and keep a safe distance."

[0108] If the driving accident risk index of a vehicle is less than or equal to the vehicle predicted driving accident risk threshold, the driving accident comparison result of the vehicle is the second comparison result.

[0109] If the driving accident comparison result of a certain vehicle is the second comparison result, there is no need to provide an accident prediction reminder for the vehicle.

[0110] It needs to be explained that when the above-mentioned driving accident risk index of a vehicle is less than or equal to the vehicle's expected driving accident risk threshold, this means that the vehicle is relatively safe when driving on the second section of the highway, and the probability of an accident is low. The driver can continue driving with relative confidence, but still needs to remain vigilant and be ready to respond to possible emergencies at any time. The traffic management department can consider that it is safe for the vehicle to drive on the second section of the highway and no additional intervention measures are needed.

[0111] Reference Figure 2 As shown, the second aspect of the present invention provides a system for an accident prediction method based on ETC data of the Internet of Things, including: a vehicle history accident analysis module, a vehicle driving analysis module, an expected driving road and highway status analysis module, an accident prediction reminder module and a traffic management database.

[0112] The vehicle history accident analysis module is connected to the vehicle driving analysis module, the target vehicle basic information acquisition analysis module is connected to the target vehicle usage data monitoring and analysis module, the vehicle driving analysis module is connected to the expected driving road highway status analysis module, the expected driving road highway status analysis module is connected to the accident prediction reminder module, and the vehicle history accident analysis module, the vehicle driving analysis module and the expected driving road highway status analysis module are all connected to the traffic management database.

[0113] The vehicle historical accident analysis module is used to obtain the license plate number of each vehicle traveling on the first section of the expressway, match the license plate number of each vehicle with the historical traffic information corresponding to each license plate number stored in the ETC Internet of Things platform, obtain the historical traffic information of each vehicle, and analyze the historical traffic indicators of each vehicle;

[0114] The vehicle driving analysis module is used to obtain the ETC historical data of the first section of the expressway and the driving information of each vehicle in the first section of the expressway through the ETC Internet of Things platform, and comprehensively analyze the ETC historical data of the first section of the expressway, the driving information of each vehicle in the first section of the expressway, and the historical traffic indicators of each vehicle to obtain the driving accident risk indicator of each vehicle.

[0115] The predicted driving highway status analysis module is used to obtain the estimated environmental information of the second section of the highway and the historical driving road condition information of the second section of the highway through the ETC Internet of Things platform, and conduct a comprehensive analysis to obtain the predicted driving accident risk threshold of the vehicle.

[0116] The accident prediction and reminder module is used to compare the driving accident risk index of each vehicle with the vehicle's expected driving accident risk threshold, obtain the driving accident comparison result of each vehicle, and determine whether to perform accident prediction reminder for each vehicle based on the driving accident comparison result of each vehicle.

[0117] The traffic management database is used to store a preset driving reference speed, a traffic impact index corresponding to a preset unit value of a historical accident rate, a traffic impact index corresponding to a preset unit value of a historical violation rate, a risk impact index corresponding to a preset unit value of the number of historical traffic accidents, a driving impact index corresponding to a preset unit value of a speed utilization rate, a driving impact index corresponding to a preset unit value of the number of lane changes, a driving impact index corresponding to a preset historical vehicle traffic index, a preset precipitation threshold, a preset reference visibility, a risk impact index corresponding to a preset unit value of the number of historical traffic accidents, and a preset reference number of vehicle passages.

[0118] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. An accident prediction method based on ETC data of the Internet of Things, characterized in that: include: S1. Vehicle historical accident analysis: obtain the license plate number of each vehicle traveling on the first section of the expressway, match the license plate number of each vehicle with the historical traffic information corresponding to each license plate number stored on the ETC IoT platform, obtain the historical traffic information of each vehicle, and analyze the historical traffic indicators of each vehicle; S2. Vehicle driving analysis: Obtain the ETC historical data of the first section of the expressway and the driving information of each vehicle in the first section of the expressway through the ETC Internet of Things platform, conduct a comprehensive analysis of the ETC historical data of the first section of the expressway, the driving information of each vehicle in the first section of the expressway, and the historical traffic indicators of each vehicle to obtain the driving accident risk indicator of each vehicle; S3. Analysis of the expected state of the highway: The estimated environmental information of the second section of the highway and the historical driving conditions of the second section of the highway are obtained through the ETC IoT platform, and a comprehensive analysis is performed to obtain the estimated driving accident risk threshold of the vehicle; S4. Accident prediction reminder: Compare the driving accident risk index of each vehicle with the vehicle's estimated driving accident risk threshold to obtain a comparison result of each vehicle's driving accident, and determine whether to issue an accident prediction reminder to each vehicle based on the comparison result of each vehicle's driving accident.

2. The accident prediction method based on ETC data of the Internet of Things according to claim 1 is characterized in that: The historical traffic information of each vehicle specifically includes the historical driving time, historical total mileage, historical accident number and historical violation number of each vehicle.

3. The accident prediction method based on ETC data of the Internet of Things according to claim 2 is characterized in that: The specific analysis process of the historical traffic indicators of each vehicle is as follows: The historical total mileage of each vehicle is compared with the historical driving time to obtain the historical average driving speed of each vehicle; The historical accident rate of each vehicle is obtained by performing a ratio processing on the number of historical accidents of each vehicle and the historical total mileage. The historical violation rate of each vehicle is obtained by performing a ratio processing on the historical number of violations of each vehicle and the historical total mileage. The historical average speed, historical accident rate and historical violation rate of each vehicle are comprehensively analyzed to obtain the historical traffic indicators of each vehicle.

4. The accident prediction method based on ETC data of the Internet of Things according to claim 1 is characterized in that: The ETC historical data of the first section of the expressway specifically includes the historical maximum speed and the number of historical traffic accidents of the first section of the expressway; The driving information of each vehicle in the first section of the expressway specifically includes the maximum driving speed and the number of lane changes of each vehicle in the first section of the expressway.

5. The accident prediction method based on ETC data of the Internet of Things according to claim 4 is characterized in that: The specific analysis process of the driving accident risk index of each vehicle is as follows: Perform a ratio analysis of the maximum speed of each vehicle in the first section of the expressway and the highest historical speed of the first section of the expressway to obtain the speed utilization rate of each vehicle in the first section of the expressway; The number of historical traffic accidents in the first section of the expressway, the speed utilization rate of each vehicle in the first section of the expressway, the number of lane changes and the historical traffic indicators of each vehicle are comprehensively analyzed to obtain the driving accident risk index of each vehicle.

6. The accident prediction method based on ETC data of the Internet of Things according to claim 1 is characterized in that: The estimated environmental information of the second section of the expressway specifically includes precipitation and visibility of the second section of the expressway; The historical driving traffic condition information of the second section of the expressway specifically includes the historical number of traffic accidents and the historical number of vehicles passing through the second section of the expressway.

7. The accident prediction method based on ETC data of the Internet of Things according to claim 6 is characterized by: The specific analysis process of the vehicle predicted driving accident risk threshold is as follows: A comprehensive analysis is conducted on the precipitation, visibility, number of historical traffic accidents and number of historical vehicles passing through the second section of the expressway to obtain the expected vehicle accident risk threshold.

8. The accident prediction method based on ETC data of the Internet of Things according to claim 7 is characterized by: The specific analysis method of the vehicle predicted driving accident risk threshold is as follows: Where ρ is the predicted accident risk threshold of the vehicle, e is a natural constant, js is the precipitation in the second section of the expressway, Δjs is the precipitation threshold preset in the traffic management database, kj is the visibility in the second section of the expressway, Δkj is the reference visibility preset in the traffic management database, sc is the number of historical traffic accidents in the second section of the expressway, z1 is the risk impact index corresponding to the unit value of the number of historical traffic accidents preset in the traffic management database, yd is the number of historical vehicles passing through the second section of the expressway, and Δyd is the reference number of vehicles passing through preset in the traffic management database.

9. The accident prediction method based on ETC data of the Internet of Things according to claim 1 is characterized in that: The specific process of determining whether to perform accident prediction reminder for each vehicle based on the comparison results of each vehicle's driving accident is as follows: The comparison results of the vehicle driving accidents are specifically as follows: If the driving accident risk index of a certain vehicle is greater than the vehicle estimated driving accident risk threshold, the driving accident comparison result of the vehicle is the first comparison result; If the comparison result of a vehicle driving accident is the first comparison result, an accident prediction reminder is issued to the vehicle; If the driving accident risk index of a certain vehicle is less than or equal to the vehicle predicted driving accident risk threshold, the driving accident comparison result of the vehicle is the second comparison result; If the driving accident comparison result of a certain vehicle is the second comparison result, there is no need to provide an accident prediction reminder for the vehicle.

10. A system using the accident prediction method based on ETC data of the Internet of Things as claimed in any one of claims 1 to 9, characterized in that: include: The vehicle historical accident analysis module is used to obtain the license plate number of each vehicle traveling on the first section of the expressway, match the license plate number of each vehicle with the historical traffic information corresponding to each license plate number stored in the ETC Internet of Things platform, obtain the historical traffic information of each vehicle, and analyze the historical traffic indicators of each vehicle; The vehicle driving analysis module is used to obtain the ETC historical data of the first section of the expressway and the driving information of each vehicle in the first section of the expressway through the ETC Internet of Things platform, and comprehensively analyze the ETC historical data of the first section of the expressway, the driving information of each vehicle in the first section of the expressway, and the historical traffic indicators of each vehicle to obtain the driving accident risk indicator of each vehicle; The estimated driving highway status analysis module is used to obtain the estimated environmental information of the second section of the highway and the historical driving road condition information of the second section of the highway through the ETC Internet of Things platform, and conduct a comprehensive analysis to obtain the estimated driving accident risk threshold of the vehicle; The accident prediction and reminder module is used to compare the driving accident risk index of each vehicle with the vehicle's expected driving accident risk threshold, obtain the comparison results of each vehicle's driving accidents, and determine whether to issue accident prediction reminders to each vehicle based on the comparison results of each vehicle's driving accidents.

Images