A method for tracing traffic flow indicators before an accident based on accident data

Abstract

The present invention is applicable to the technical field of traffic accident analysis and prevention, and provides a method for tracing traffic flow indicators before an accident occurs based on accident data, the method comprising: obtaining traffic flow data before the accident occurs, and preprocessing the data; and calculating traffic flow indicators before the accident occurs based on the preprocessed data. Based on highway ETC data and historical accident data, the present invention efficiently collects and processes accident-related information in an automated manner, constructs a data set covering multi-dimensional traffic flow indicators, comprehensively reflects the travel behavior characteristics of vehicles before the accident, and ensures the accuracy and reliability of data analysis. Calculation methods for a number of key traffic flow indicators are proposed, including travel frequency on weekdays and weekends, cumulative travel distance and standard deviation, travel characteristics in different time periods, etc. Through refined indicator analysis, the historical driving characteristics of accident vehicles are more comprehensively captured.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic accident analysis and prevention, and in particular relates to a method for tracing back traffic flow indicators before an accident occurs based on accident data. Background Art

[0002] In the existing highway traffic safety management technology, identifying potential accident black spots by analyzing traffic flow data before an accident occurs is an important research topic. However, the existing technology still has many shortcomings in practical applications.

[0003] First, the efficiency of data acquisition and preprocessing is low. Most current methods rely on manual or semi-automatic means to extract accident-related information from historical accident data and retrospectively obtain traffic flow data at the time of the accident. This method is not only time-consuming and laborious, but also prone to data omissions or processing errors when faced with large-scale data, which affects the accuracy of the analysis results.

[0004] Secondly, existing technologies are often limited to simple statistical analysis when calculating traffic flow indicators, and fail to fully tap into more detailed traffic flow characteristics. For example, for the travel patterns of accident vehicles, the current analysis method lacks detailed analysis of travel frequency and duration in different time periods (such as morning peak, evening peak, off-peak and night), resulting in certain limitations in predicting and preventing accidents.

[0005] In addition, existing technologies lack multi-dimensional assessment of the driving behavior of accident vehicles. For example, existing methods usually only focus on basic indicators such as vehicle speed and distance, but fail to fully consider more complex behavioral characteristics such as the stability of the starting and ending points of the trip and the stability of the toll stations passed through, which may lead to some potential risk factors not being identified in time. Summary of the invention

[0006] The purpose of the present invention is to provide a method for tracing traffic flow indicators before an accident occurs based on accident data, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0007] The present invention is implemented as follows: a method for tracing traffic flow indicators before an accident based on accident data, the method comprising:

[0008] Obtain traffic flow data before the accident and pre-process the data;

[0009] Collect historical highway accident data and extract accident-related information, including the time of the accident, the accident pile number, the accident license plate, and the upstream and downstream gantry numbers;

[0010] The traffic flow data of the accident was extracted from the ETC toll station flow database of the expressway, and the accident indicators were extracted, including the time of entering and exiting the toll station, the traffic sign and the toll mileage;

[0011] Based on the preprocessed data, the traffic flow indicators before the accident are calculated.

[0012] As a further solution of the present invention, the traffic flow index calculated before the accident occurs includes a travel frequency index, a travel distance index, a travel duration index, a travel speed index and a stability index.

[0013] As a further solution of the present invention, the travel frequency index includes:

[0014] Weekday trip frequency of each accident vehicle F weekday :

[0015] ;

[0016] Where: O i Represents the vehicle i Travel records on weekdays;

[0017] Weekend trip frequency per accident vehicle F weekend :

[0018] ;

[0019] Where: O i Represents the vehicle’s trip record for the i-th time on the weekend;

[0020] The frequency of morning peak trips for each accident vehicle F m.peak :

[0021] ;

[0022] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are in the time period of 7:00~9:00. nRepresents the travel frequency of the vehicle;

[0023] Frequency of evening peak trips per accident vehicle F e.peak :

[0024] ;

[0025] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 17:00~19:00. n Represents the travel frequency of the vehicle;

[0026] The frequency of off-peak trips for each accident vehicle F off-peak :

[0027] ;

[0028] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i They are not in the time period of 7:00~9:00 and 17:00~19:00, n represents the travel frequency of the vehicle;

[0029] Night trip frequency of each accident vehicle F e :

[0030] ;

[0031] Where: i Representative i Pass ID, T 2i Representative iThe exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 19:00~24:00. n Represents the travel frequency of the vehicle.

[0032] As a further solution of the present invention, the travel distance index includes:

[0033] The cumulative travel distance of each accident vehicle S sum :

[0034] ;

[0035] Where: i Representative i Pass ID, S i Represents the vehicle i The charging mileage n Represents the travel frequency of the vehicle;

[0036] Average travel distance per accident vehicle :

[0037] ;

[0038] Where: i Representative i Pass ID, S i Represents the vehicle i The charging mileage n Represents the travel frequency of the vehicle;

[0039] Standard deviation of travel distance for each accident vehicle :

[0040] ;

[0041] Where: i Representative i Pass ID, S i Represents the vehicle i The charging mileage n Represents the travel frequency of the vehicle.

[0042] The travel time indicators include:

[0043] Total travel time of each accident vehicle T :

[0044] ;

[0045] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, n Represents the travel frequency of the vehicle.

[0046] Average travel time per accident vehicle :

[0047] ;

[0048] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i represents the entry transaction time of the i-th pass ID, and n represents the travel frequency of the vehicle;

[0049] Standard deviation of travel time for each accident vehicle :

[0050] ;

[0051] Where: T i Represents the vehicle i Duration of each trip, represents the average travel time of the vehicle, n Represents the travel frequency of the vehicle;

[0052] Morning peak travel time for each accident vehicle T m.peak :

[0053] ;

[0054] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID,T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i They are all in the time period of 7:00~9:00, and n represents the travel frequency of the vehicle;

[0055] Average morning peak travel time for each accident vehicle :

[0056] ;

[0057] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are in the time period of 7:00~9:00. n Represents the travel frequency of the vehicle;

[0058] Evening peak travel time for each accident vehicle T e.peak :

[0059] ;

[0060] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 17:00~19:00. n Represents the travel frequency of the vehicle;

[0061] Average evening peak travel time for each accident vehicle :

[0062] ;

[0063] Where: i represents the ith pass ID, T2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 17:00~19:00. n Represents the travel frequency of the vehicle;

[0064] Off-peak travel time of each accident vehicle T off-peak :

[0065] ;

[0066] Where: i Representative i Pass ID, T2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i They are not in the time period of 7:00~9:00 and 17:00~19:00, n represents the travel frequency of the vehicle;

[0067] Average off-peak travel time for each accident vehicle :

[0068] ;

[0069] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i They are not in the time periods of 7:00~9:00 and 17:00~19:00. nRepresents the travel frequency of the vehicle;

[0070] Night travel time of each accident vehicle T e :

[0071] ;

[0072] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 19:00~24:00. n Represents the travel frequency of the vehicle;

[0073] Average night travel time per accident vehicle :

[0074] ;

[0075] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 19:00~24:00. n Represents the travel frequency of the vehicle.

[0076] The travel speed indicators include:

[0077] The average travel speed of each accident vehicle :

[0078] ;

[0079] In the formula ：i Representative i Pass ID, S i Representativei The toll mileage of the pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, n Represents the travel frequency of the vehicle;

[0080] Standard deviation of travel speed for each accident vehicle :

[0081] ;

[0082] Where: V i Represents the vehicle i The travel speed, represents the average travel speed of the vehicle, n Represents the travel frequency of the vehicle;

[0083] The cumulative speeding frequency of each accident vehicle :

[0084] ;

[0085] Where: O i Represents the vehicle i Speeding record, V i Represents the vehicle i The travel speed, m Indicates that the vehicle has m Speeding record.

[0086] As a further solution of the present invention, the stability index includes:

[0087] Stability of the starting and ending points of each accident vehicle H OD :

[0088] ;

[0089] ;

[0090] ;

[0091] ;

[0092] Where: e i ,xi ) represents i Entrance toll booths with pass ID records e i and exit toll booths x i , C ( e,x ) represents the entrance e To the exit x The number of times the route appears, N represents the total number of all routes. P(e,x) represents the probability of each route;

[0093] The stability of toll booths passed by each accident vehicle H station :

[0094] ;

[0095] ;

[0096] ;

[0097] ;

[0098] Where: S i Representative i Toll booths with pass ID records, including entrance toll booths e i and exit toll booths x i , C ( S ) represents a toll booth S The number of occurrences, M represents the total number of all toll booths, P ( S ) represents the probability of each toll booth.

[0099] The beneficial effects of the present invention are:

[0100] 1. Based on highway ETC data and historical accident data, the present invention efficiently collects and processes accident-related information in an automated manner, constructs a data set covering multi-dimensional traffic flow indicators, comprehensively reflects the travel behavior characteristics of vehicles before the accident, and ensures the accuracy and reliability of data analysis.

[0101] 2. The present invention proposes a calculation method for multiple key traffic flow indicators, including travel frequency on weekdays and weekends, cumulative travel distance and standard deviation, travel characteristics in different time periods, etc. Through refined indicator analysis, the historical driving characteristics of accident vehicles are captured more comprehensively.

[0102] 3. The present invention introduces the evaluation of complex behavioral characteristics such as the stability of travel starting and ending points and the stability of toll stations along the way. Through a multi-dimensional analysis method, it breaks through the limitations of single indicator analysis in the prior art and effectively identifies potential accident risk factors.

[0103] 4. Through comprehensive analysis of multi-dimensional data, the present invention can identify accident black spots and potential risk sections earlier and more accurately, providing reliable technical support for traffic management departments to formulate targeted accident prevention measures.

[0104] 5. The present invention significantly improves the efficiency and depth of pre-accident traffic flow data analysis, assesses accident risks in a more scientific and comprehensive manner, reduces the accident rate, and improves the overall safety level of highways. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] Picture 1 A schematic flow chart of a method for tracing back traffic flow indicators before an accident based on accident data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0106] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0107] The present invention proposes a more systematic and comprehensive method for tracing traffic flow indicators before an accident based on accident data. This method not only improves the efficiency of data acquisition and processing, but also provides strong data support for the accurate identification and prevention of accident black spots by calculating multiple key traffic flow indicators, such as travel frequency on weekdays and weekends, travel distance and its standard deviation, cumulative speeding frequency, travel characteristics in different time periods, etc. At the same time, through multi-dimensional behavioral feature evaluation, the present invention can better capture the potential risks of accident vehicles and effectively improve the overall level of highway traffic safety management.

[0108] Specifically, Picture 1 As shown, a method for tracing back traffic flow indicators before an accident based on accident data includes:

[0109] Obtain traffic flow data before the accident and pre-process the data;

[0110] Collect historical highway accident data and extract accident-related information, including the time of the accident, the accident pile number, the accident license plate, and the upstream and downstream gantry numbers. The data sample is shown in Table 1.

[0111] Table 1 Accident data sample

[0112]

[0113] According to the collected accident data, such as the time of occurrence, accident license plate, and upstream and downstream gantries, the traffic flow data of the accident was back-extracted from the highway ETC toll station flow database, and various indicators were extracted, including the time of entering and exiting the toll station, the pass sign, and the toll mileage, as shown in Table 2;

[0114] Table 2 Main fields of ETC flow data

[0115]

[0116] Based on the preprocessed data, the traffic flow indicators before the accident are calculated.

[0117] Specifically, the traffic flow indicators calculated before the accident occur include a travel frequency indicator, a travel distance indicator, a travel time indicator, a travel speed indicator and a stability indicator.

[0118] In the present invention, the travel frequency index includes:

[0119] Weekday trip frequency of each accident vehicle F weekday :

[0120] ;

[0121] Where: O i Represents the vehicle i Travel records on weekdays;

[0122] Weekend trip frequency per accident vehicle F weekend :

[0123] ;

[0124] Where: O i Represents the vehicle’s trip record for the i-th time on the weekend;

[0125] The frequency of morning peak trips for each accident vehicle F m.peak :

[0126] ;

[0127] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are in the time period of 7:00~9:00. n Represents the travel frequency of the vehicle;

[0128] Frequency of evening peak trips per accident vehicle F e.peak :

[0129] ;

[0130] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 17:00~19:00. n Represents the travel frequency of the vehicle;

[0131] The frequency of off-peak trips for each accident vehicle F off-peak :

[0132] ;

[0133] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i They are not in the time period of 7:00~9:00 and 17:00~19:00, n represents the travel frequency of the vehicle;

[0134] Night trip frequency of each accident vehicle F e :

[0135] ;

[0136] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 19:00~24:00. n Represents the travel frequency of the vehicle.

[0137] The travel distance indicators include:

[0138] The cumulative travel distance of each accident vehicle S sum :

[0139] ;

[0140] Where: i Representative i Pass ID, S i Represents the vehicle i The charging mileage n Represents the travel frequency of the vehicle;

[0141] Average travel distance per accident vehicle :

[0142] ;

[0143] Where: i Representative i Pass ID, S i Represents the vehicle i The charging mileage n Represents the travel frequency of the vehicle;

[0144] Standard deviation of travel distance for each accident vehicle :

[0145] ;

[0146] Where: i Representative i Pass ID, S i Represents the vehiclei The charging mileage n Represents the travel frequency of the vehicle.

[0147] The travel time indicators include:

[0148] Total travel time of each accident vehicle T :

[0149] ;

[0150] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, n Represents the travel frequency of the vehicle.

[0151] Average travel time per accident vehicle :

[0152] ;

[0153] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i represents the entry transaction time of the i-th pass ID, and n represents the travel frequency of the vehicle;

[0154] Standard deviation of travel time for each accident vehicle :

[0155] ;

[0156] Where: T i Represents the vehicle i Duration of each trip, represents the average travel time of the vehicle, n Represents the travel frequency of the vehicle;

[0157] Morning peak travel time for each accident vehicle T m.peak :

[0158] ;

[0159] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i They are all in the time period of 7:00~9:00, and n represents the travel frequency of the vehicle;

[0160] Average morning peak travel time for each accident vehicle :

[0161] ;

[0162] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are in the time period of 7:00~9:00. n Represents the travel frequency of the vehicle;

[0163] Evening peak travel time for each accident vehicle T e.peak :

[0164] ;

[0165] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 17:00~19:00. nRepresents the travel frequency of the vehicle;

[0166] Average evening peak travel time for each accident vehicle :

[0167] ;

[0168] Where: i represents the ith pass ID, T2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 17:00~19:00. n Represents the travel frequency of the vehicle;

[0169] Off-peak travel time of each accident vehicle T off-peak :

[0170] ;

[0171] Where: i Representative i Pass ID, T2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i They are not in the time period of 7:00~9:00 and 17:00~19:00, n represents the travel frequency of the vehicle;

[0172] Average off-peak travel time for each accident vehicle :

[0173] ;

[0174] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative iThe time when the entry transaction of the pass ID occurs, T 2i and T 1i They are not in the time periods of 7:00~9:00 and 17:00~19:00. n Represents the travel frequency of the vehicle;

[0175] Night travel time of each accident vehicle T e :

[0176] ;

[0177] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 19:00~24:00. n Represents the travel frequency of the vehicle;

[0178] Average night travel time per accident vehicle :

[0179] ;

[0180] Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 19:00~24:00. n Represents the travel frequency of the vehicle.

[0181] The travel speed indicators include:

[0182] The average travel speed of each accident vehicle :

[0183] ;

[0184] In the formula ：i Representative i Pass ID, S i Representative i The toll mileage of the pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, n Represents the travel frequency of the vehicle;

[0185] Standard deviation of travel speed for each accident vehicle :

[0186] ;

[0187] Where: V i Represents the vehicle i The travel speed, represents the average travel speed of the vehicle, n Represents the travel frequency of the vehicle;

[0188] The cumulative speeding frequency of each accident vehicle :

[0189] ;

[0190] Where: O i Represents the vehicle i Speeding record, V i Represents the vehicle i The travel speed, m Indicates that the vehicle has m Speeding record.

[0191] The stability indicators include:

[0192] Stability of the starting and ending points of each accident vehicle H OD :

[0193] ;

[0194] ;

[0195] ;

[0196] ;

[0197] Where: e i ,x i ) represents i Entrance toll booths with pass ID records e i and exit toll booths x i , C ( e,x ) represents the entrance e To the exit x The number of times the route appears, N represents the total number of all routes. P(e,x) represents the probability of each route;

[0198] The stability of toll booths passed by each accident vehicle H station :

[0199] ;

[0200] ;

[0201] ;

[0202] ;

[0203] Where: S i Representative i Toll booths with pass ID records, including entrance toll booths e i and exit toll booths x i , C ( S ) represents a toll booth S The number of occurrences, M represents the total number of all toll booths, P ( S ) represents the probability of each toll booth.

[0204] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have strict order restrictions, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0205] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0206] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0207] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for tracing traffic flow indicators before an accident based on accident data, characterized in that: The method comprises: Obtain traffic flow data before the accident and pre-process the data; Collect historical highway accident data and extract accident-related information, including the time of the accident, the accident pile number, the accident license plate, and the upstream and downstream gantry numbers; The traffic flow data of the accident was extracted from the ETC toll station flow database of the expressway, and the accident indicators were extracted, including the time of entering and exiting the toll station, the traffic sign and the toll mileage; Based on the preprocessed data, calculate the traffic flow index before the accident; The traffic flow indexes calculated before the accident occurred include travel frequency index, travel distance index, travel time index, travel speed index and stability index; The travel frequency indicators include: Weekday trip frequency of each accident vehicle F weekday : ； Where: O j Represents the vehicle j Travel records on weekdays; Weekend trip frequency per accident vehicle F weekend : ； Where: O j Represents the vehicle j Travel records on weekends; The frequency of morning peak trips for each accident vehicle F m.peak : ； Where: i Representative i Pass ID, T 2i Representative i The exit charging time of the pass ID, T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are in the time period of 7:00~9:

00. n Represents the travel frequency of the vehicle; Frequency of evening peak trips per accident vehicle F e.peak : ； Where: T 1i Representative i The time when the entry transaction of the pass ID occurs, T 2i and T 1i All are within the time period of 17:00~19:00; The frequency of off-peak trips for each accident vehicle F off-peak : ； Where: T 2i and T 1i They are not in the time periods of 7:00~9:00 and 17:00~19:00; Night trip frequency of each accident vehicle F e : ； Where: T 2i and T 1i All are within the time period of 19:00~24:00; The stability indicators include: Stability of the starting and ending points of each accident vehicle H OD : ； ； ； ； Where: e i ,x i ) represents i Entrance toll booths with pass ID records e i and exit toll booths x i , C ( e,x ) represents the entrance e To the exit x The number of times the route appears, N represents the total number of all routes, and P(e,x) represents the probability of each route; The stability of each accident vehicle passing through the toll booth H station : ； ； ； ； Where: G i Representative i Toll booths with pass ID records, including entrance toll booths e i and exit toll booths x i , C ( G ) represents a toll booth G The number of occurrences, M represents the total number of all toll booths, P ( G ) represents the probability of each toll booth.

2. The method according to claim 1, characterized in that: The travel distance indicators include: The cumulative travel distance of each accident vehicle S sum : ； Average travel distance per accident vehicle : ； Standard deviation of travel distance for each accident vehicle : ； Where: S i Represents the vehicle i The chargeable mileage.

3. The method according to claim 1, characterized in that The travel time indicators include: Total travel time of each accident vehicle T : ； Average travel time per accident vehicle : ； Standard deviation of travel time for each accident vehicle : ； Where: T i Represents the vehicle i Duration of each trip, Represents the average travel time of the vehicle; Morning peak travel time for each accident vehicle T m.peak : ； Where: T 2i and T 1i All are within the time period of 7:00~9:00; Average morning peak travel time for each accident vehicle : ； Where: T 2i and T 1i All are within the time period of 7:00~9:00; Evening peak travel time for each accident vehicle T e.peak : ； Where: T 2i and T 1i All are within the time period of 17:00~19:00; Average evening peak travel time for each accident vehicle : ； Where: T 2i and T 1i All are within the time period of 17:00~19:00; Off-peak travel time of each accident vehicle T off-peak : ； Where: T 2i and T 1i They are not in the time periods of 7:00~9:00 and 17:00~19:00; Average off-peak travel time for each accident vehicle : ； Where: T 2i and T 1i They are not in the time periods of 7:00~9:00 and 17:00~19:00; Night travel time of each accident vehicle T e : ； Where: T 2i and T 1i All are within the time period of 19:00~24:00; Average night travel time per accident vehicle : ； Where: T 2i and T 1i All are within the time period of 19:00~24:

00.

4. The method according to claim 1, characterized in that: The travel speed indicators include: The average travel speed of each accident vehicle : ； In the formula ：S i Representative i The toll mileage of each pass ID; Standard deviation of travel speed for each accident vehicle : ； Where: V i Represents the vehicle i The travel speed, Represents the average travel speed of the vehicle; The cumulative speeding frequency of each accident vehicle : ； Where: O i Represents the vehicle i Speeding record, m Indicates that the vehicle has m Speeding record.

Images