Method and program product for identifying space-time position of traffic accident by using floating vehicle data

Abstract

The invention discloses a method and a program product for identifying a time-space position of a traffic accident by using floating vehicle data, and the method comprises the steps: (1) obtaining floating vehicle data in a historical analysis period and floating vehicle data in a to-be-identified time period, and calculating a historical average driving speed in the historical analysis period and an actual driving speed in the to-be-identified time period; (2) judging whether each link in each time interval is expected to be influenced by an accident or not according to the historical average driving speed and the actual driving speed; (3) an accident space-time position optimization model is constructed, the model takes whether each link is actually influenced by each accident in each time interval and the space-time of each accident as decision variables, and the minimization of the difference between the actual influence and the expected influence of the accident is taken as a target; (4) adding constraint conditions for the accident space-time position optimization model; and (5) solving the accident space-time position optimization model to obtain an accident space-time position. The method is high in accuracy and robustness.

Description

Technical Field

[0001] The present invention relates to a technology for identifying the time-space position of a traffic accident, and in particular to a method and a program product for identifying the time-space position of a traffic accident by using floating vehicle data. Background Art

[0002] Accurate spatiotemporal localization of traffic accidents, i.e., the location of the time and spatial location of their occurrence, is crucial for a wide range of accident-related analysis and traffic management systems. However, this information is difficult to obtain directly from accident reports due to ambiguous text descriptions and unreported accidents. To address this issue, some existing studies have utilized various data sources, such as social media data, and developed data-driven methods to identify accidents. However, limited data availability and potential low data quality, including data missing and errors, affect the accuracy of these methods in identifying the spatiotemporal locations of network-wide accidents. In addition, the spatiotemporal evolution of accident-induced congestion in urban networks is much more complex than that of linear road segments, resulting in the inability of existing technologies to accurately identify the spatiotemporal locations.

[0003] The patent document with publication number CN 116052418A provides a data analysis method and device for urban road networks, including: determining the spatiotemporal impact range of an emergency event based on the acquired speed data; determining the spatiotemporal propagation law of an emergency event in an urban road network based on the spatiotemporal impact range; expressing the spatiotemporal propagation law as a linear constraint, and estimating the spatiotemporal impact of an emergency event on an urban road network through an optimization model. This technology can predict the spatiotemporal range affected by an accident based on speed data, but it cannot identify the spatiotemporal location of a traffic accident. Summary of the invention

[0004] In view of the problems existing in the prior art, the purpose of the present invention is to provide a method and program product that can identify the spatiotemporal location of a traffic accident using floating vehicle data with high recognition accuracy.

[0005] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0006] A method for identifying the spatiotemporal location of a traffic accident using floating vehicle data comprises the following steps:

[0007] (1) Obtain floating vehicle data during the historical analysis period and floating vehicle data during the time period to be identified, and calculate the historical average driving speed of each link during each time interval during the historical analysis period, and the actual driving speed of each link during each time interval during the time period to be identified;

[0008] (2) Determine whether each link is expected to be affected by the accident in each time interval based on the historical average driving speed and the actual driving speed;

[0009] (3) constructing an accident spatiotemporal location optimization model, wherein the accident spatiotemporal location optimization model uses whether each link is actually affected by each accident in each time interval and the time interval and link where each accident occurs as decision variables, and aims to minimize the difference between the actual and expected impact of the accident on all links in all time intervals;

[0010] (4) adding constraints to the accident spatiotemporal location optimization model, wherein the constraints include source constraints of accident impact, directional propagation constraints of traffic accident impact, continuous propagation constraints of accident impact, additional constraints of road network closure, minimum requirements for accident spatiotemporal location range, and decision variable constraints;

[0011] (5) Solve the accident spatiotemporal location optimization model to obtain the time interval and link of each accident in the time period to be identified, as the accident spatiotemporal location output of the time period to be identified.

[0012] Furthermore, step (2) specifically includes:

[0013] (2.1) Based on the floating vehicle data and the historical average driving speed during the historical analysis period, calculate the historical speed standard deviation of each link in each time interval during the historical analysis period;

[0014] (2.2) Based on the historical average driving speed, the historical speed standard deviation and the actual driving speed, the expected accident impact indicator variable of each link in each time interval is calculated according to the following formula, wherein the expected accident impact indicator variable is used to indicate whether each link n in each time interval t is expected to be affected by an accident;

[0015]

[0016] In the formula, represents the expected accident impact indicator variable, when When , it means that link n is expected to be affected by the accident within time interval t, otherwise it means that it is not affected, v n,t represents the actual driving speed through link n in time interval t, σ n,t They represent the historical average speed and historical speed standard deviation of link n in time interval t, α represents the scale parameter, N represents the number of links, and T represents the number of time intervals into which the time period to be identified is divided.

[0017] Furthermore, the objective function of the accident spatiotemporal location optimization model is:

[0018]

[0019] In the formula, represents the actual accident impact decision variable, which is used to indicate whether link n is actually affected by accident k in time interval t. When means that link n is actually affected by accident k in time interval t, When t = t, it means that link n is not actually affected by accident k in time interval t. represents the accident spatiotemporal location decision variable, which is used to indicate the time interval t and link n where the accident k occurs. When , it means that the accident k occurs on the link n within the time interval t. t indicates that accident k did not occur on link n within time interval t, and K represents the number of accidents.

[0020] Furthermore, the source constraints of the accident impact are specifically:

[0021]

[0022]

[0023]

[0024]

[0025]

[0026] Where, D n represents the set of downstream links of link n, |D n | represents the number of downstream links of link n, and m represents D n The mth link in is the actual accident impact decision variable used to indicate whether link m is actually affected by accident k within time interval t.

[0027] Furthermore, the directional propagation constraints of the traffic accident impact are specifically:

[0028]

[0029] Where, D n represents the downstream link set of link n, and m represents D n The mth link in is the actual accident impact decision variable used to indicate whether link m is actually affected by accident k within time interval t.

[0030] Furthermore, the continuous propagation constraints of the accident impact are specifically as follows:

[0031]

[0032]

[0033]

[0034] λ1+λ2+λ3≤2

[0035] λ1,λ2,λ3∈{0,1}

[0036] In the formula, n represents the set of downstream links of link n, |D n | represents the number of downstream links of link n, and m represents D n The mth link in is the actual accident impact decision variable used to indicate whether link m is actually affected by accident k in time interval t, and λ1, λ2, λ3 are propagation constraint parameters.

[0037] Furthermore, the additional constraints of the road network closed loop are specifically:

[0038]

[0039] Where Δ represents the set of downstream links of link n, and |Δ| is the number of downstream links of link n.

[0040] Furthermore, the minimum requirements for the accident time and space location range are specifically:

[0041]

[0042] In the formula, is the accident time impact indicator variable. If at least one link is affected by accident k in time interval t, is equal to 1, otherwise it is equal to 0, L t Indicates the preset time threshold, is the accident spatial impact indicator variable. If link n is affected by accident k in at least one time interval, is equal to 1, otherwise it is equal to 0, L n Indicates the preset space threshold.

[0043] Furthermore, the decision variable constraints are specifically:

[0044]

[0045]

[0046]

[0047] A computer program product comprises a computer program / instruction, wherein the computer program / instruction implements the above method when executed by a processor.

[0048] Compared with the prior art, the present invention has the following beneficial effects: the present invention constructs an accident spatiotemporal location optimization model that follows traffic wave propagation by using floating car data (FCD). The model input is the speed of the historical and to-be-identified time periods, which may contain measurement errors and missing data, but are usually available in the entire network. The identification of the spatiotemporal location is achieved by analyzing the origins associated with the spatiotemporal progression of the accident impact. In order to solve the problem of missing and erroneous speed data, the present invention uses accident shock wave propagation as a constraint to describe the impact of the accident on the speed evolution of adjacent links and time intervals, thereby compensating for the limited information in the damaged data. In addition, the impact of complex road network structure on accident shock wave propagation is also considered. The model is verified by numerical experiments, and the results show that the model can achieve satisfactory results under different missing rates and noise intensities, verifying the accuracy and robustness of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of a method for identifying the spatiotemporal location of a traffic accident using floating vehicle data provided by an embodiment of the present invention;

[0050] Figure 2 It is a schematic diagram of a closed loop of roads in the road network;

[0051] Figure 3 is the time deviation of the present invention under different data missing rates;

[0052] Figure 4 It is the position deviation of the present invention under different data missing rates. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0054] Embodiment 1

[0055] In the technical solution of the present invention, several key concepts are involved:

[0056] Floating Car Data: It is a new type of traffic information detection technology. Its core is to use the location and time information collected by floating vehicles with GPS positioning function (such as urban taxis and private cars) to calculate the speed of the vehicle's location point, and correspond this speed information with the electronic map to intuitively describe the traffic flow speed conditions on the road.

[0057] Road network: Different from highways or urban expressways, urban road networks have unique topological structures, such as upstream and downstream relationships between links, and some road closed-loop situations.

[0058] Traffic wave propagation: Traffic wave propagation refers to the phenomenon of traffic flow propagating on the road, similar to the wave in the fluid. By establishing a mathematical programming model, the temporal and spatial impact range of traffic accidents can be estimated, and the output of the model can meet the propagation law of traffic waves.

[0059] The embodiment of the present invention provides a method for identifying the spatiotemporal location of a traffic accident using floating vehicle data, such as Figure 1 As shown, the following steps are included:

[0060] (1) Obtain floating vehicle data during the historical analysis period and floating vehicle data during the time period to be identified, and calculate the historical average driving speed through each link in each time interval during the historical analysis period, and the actual driving speed through each link in each time interval during the time period to be identified.

[0061] The historical analysis period can be specifically the floating vehicle data before the time period to be identified. The historical analysis period is divided into T time intervals. Based on the floating vehicle data, the driving speed of the vehicle passing through link n in time interval t during the historical analysis period can be calculated, and then the average calculation is performed to obtain the historical average driving speed Similarly, the actual driving speed v through link n in the time interval t of the time period to be identified can be calculated n,t , 1≤n≤N,1≤t≤T, N is the number of links.

[0062] (2) Based on the historical average driving speed and the actual driving speed, determine whether each link in each time interval is expected to be affected by the accident.

[0063] This step specifically includes:

[0064] (2.1) Based on the floating vehicle data and the historical average driving speed during the historical analysis period, calculate the historical speed standard deviation σ of each link in each time interval during the historical analysis period n,t ;

[0065] (2.2) When an accident indexed by k occurs on a link, it disrupts the smooth flow of traffic and causes a reduction in travel speed. The impact caused by the accident will propagate to upstream links over time, causing regional congestion in both spatial and temporal dimensions. Therefore, the speed caused by the accident is usually lower than the average speed. In order to measure this disruption and capture the potential impact of an accident on link n during time interval t, an expected accident impact indicator variable is defined by comparing the vehicle speed during the identified time period with the average vehicle speed during the historical analysis period. Indicates whether each link n is expected to be affected by the accident in each time interval t. The specific calculation formula is:

[0066]

[0067] In the formula, when When , it means that link n is expected to be affected by the accident within time interval t, otherwise it means that it is not affected, v n,t represents the actual driving speed through link n in time interval t, σ n,t They represent the historical average speed and historical speed standard deviation of link n in time interval t, and α represents the proportional parameter.

[0068] (3) Construct an accident spatiotemporal location optimization model, wherein the accident spatiotemporal location optimization model uses whether each link is actually affected by each accident in each time interval and the time interval and link where each accident occurs as decision variables, and aims to minimize the difference between the actual and expected impact of accidents on all links in all time intervals.

[0069] Due to missing or incorrect data, the observed accident impact directly derived from the velocity data may not conform to the propagation law of the accident shock wave. In order to restore the actual accident impact, the goal of this invention is to minimize the difference between the actual and expected accident impacts. The specific formula is:

[0070]

[0071] In the formula, the decision variables of the accident spatiotemporal location optimization model include the actual accident impact decision variables and the accident spatiotemporal location decision variables It is used to indicate whether link n is actually affected by accident k in time interval t. When means that link n is actually affected by accident k in time interval t, When t = t, it means that link n is not actually affected by accident k in time interval t. It is used to indicate the time interval t and link n where the accident k occurs. When , it means that the accident k occurs on the link n within the time interval t. t indicates that accident k did not occur on link n within time interval t, and K represents the number of accidents.

[0072] (4) Adding constraints to the accident spatiotemporal location optimization model, wherein the constraints include source constraints of accident impacts, directional propagation constraints of traffic accident impacts, continuous propagation constraints of accident impacts, additional constraints of road network closure, minimum requirements for the accident spatiotemporal location range, and decision variable constraints.

[0073] Among them, the source constraints of accident impact are specifically:

[0074]

[0075]

[0076]

[0077]

[0078]

[0079] Where, D n represents the set of downstream links of link n, |D n | represents the number of downstream links of link n, and m represents D n The mth link in is the actual accident impact decision variable used to indicate whether link m is actually affected by accident k within time interval t.

[0080] There are five constraints related to the source of accident impact. The first constraint is used to ensure that when accident k occurs on link n within time interval t, link n will be affected by accident k at time t. The second and third constraints are used to ensure that when accident k occurs on link n within time interval t, link n at the previous moment and all downstream links of link n at time t will not be affected by accident k. n | represents the number of downstream links of link n; the fourth constraint is used to ensure that when link n at the current moment and all downstream links of link n at time t are not affected by accident k, accident k occurs on link n within time interval t; the fifth constraint is used to ensure that when accident k occurs on link n within time interval t, then this moment t and link n are unique.

[0081] The directional propagation constraints of the traffic accident impact are specifically:

[0082]

[0083] There is one constraint related to the directional propagation constraint of traffic accident impact. This constraint is used to ensure that when link n is affected by accident k in time interval t, and accident k does not occur on link n in time interval t, then this impact must spread from the downstream link of link n at time t, or from the moment before time t of link n, or both. It is worth noting that when When the value of is 1, this constraint always holds.

[0084] The specific constraints on the continuous propagation of the accident impact are:

[0085]

[0086]

[0087]

[0088] λ1+λ2+λ3≤2

[0089] λ1,λ2,λ3∈{0,1}

[0090] Where λ1, λ2, λ3 are propagation constraint parameters.

[0091] There are five constraints related to the continuous propagation of the accident impact. These five constraints together ensure the uninterrupted propagation of the accident impact. That is, for a certain link, if the previous moment and the downstream link were affected by the accident, then the link at this moment will definitely be affected by the accident.

[0092] Among them, the road network closed-loop constraints are specifically:

[0093]

[0094] Where Δ represents the set of downstream links of link n, and |Δ| is the number of downstream links of link n.

[0095] There is one additional constraint related to the closed loop of the road network. This constraint is used to avoid the discontinuous propagation of accident shock waves caused by isolated closed loops. Unlike the direct sequential structure of highway segments, the links in the road network can form complex closed loops. In such a loop, a link can be both the upstream link and the downstream link of another link at the same time. This structure may form isolated impact areas (see configuration Figure 2 ). An isolated closed loop always satisfies the above constraints, making it independent of other affected areas. Therefore, this independence leads to discontinuous propagation of accident shock waves, a result that contradicts the real-world traffic dynamics and will further mislead the identification of the incident origin.

[0096] The minimum requirements for the accident time and space location range are as follows:

[0097]

[0098] In the formula, is the accident time impact indicator variable. If at least one link is affected by accident k in time interval t, is equal to 1, otherwise it is equal to 0, L t Indicates the preset time threshold, is the accident spatial impact indicator variable. If link n is affected by accident k in at least one time interval, is equal to 1, otherwise it is equal to 0, Ln Indicates the preset space threshold.

[0099] There are 8 constraints related to the minimum requirements for the spatial and temporal scope of accidents. In the process of traffic accident identification, those accidents with less impact can be filtered out. Therefore, the minimum event duration and the minimum number of affected links are set, that is, L t and L n , as the preset time and space thresholds.

[0100] The decision variable constraints are specifically:

[0101]

[0102] There are five constraints related to decision variables. The last two constraints ensure that the values ​​of the two decision variables outside the boundary are both 0.

[0103] (5) Solve the accident spatiotemporal location optimization model to obtain the time interval and link of each accident in the time period to be identified, as the accident spatiotemporal location output of the time period to be identified.

[0104] Through the above objective function and the constraints of the subsequent steps, the optimization model can use the information provided by the input velocity data, input the unobserved accident shock according to the spatiotemporal propagation of the accident shock wave, and correct the erroneous accident shock. This optimization model can be effectively solved by the standard branch and bound algorithm.

[0105] Solve for the decision variables of the accident time and space location After that, obtain the variable with value 1, and then extract the index number k, n, t to obtain the time interval t (time position) and link n (spatial position) where the accident k occurred.

[0106] The following numerical experiments are conducted on the embodiment of the present invention, which mainly include the following steps:

[0107] Step 1: Experimental Setup

[0108] The numerical experiments were conducted on a road network. The simulation network used reproduced the area around the Beijing National Stadium at a 1:1 scale, including 28 major intersections and 95 major roads. All boundary nodes can be used as origins and destinations. Vehicles enter the network at four points: the flow demand at the upper left corner and the lower right corner is 3500pcu / h, and the flow demand at the lower left corner and the lower right corner is 3250pcu / h. The saturation flow of each channel on the link is configured as 1800pcu / h / lane. The road is divided into sections of equal length, set to 50 meters, and the time is discretized into equal time intervals of 2 minutes. In the simulation, the loop detector is located at the midpoint of each section (i.e., link) to record the speed of the vehicle passing through the section. Therefore, VISSIM can record the speed and position of all vehicles. The average driving speed of vehicles passing through each section in a given time interval can be further calculated.

[0109] Step 2: Experimental results of noise-free data

[0110] Based on the average performance of all 30 accidents, it can be found that the proposed model can accurately identify the occurrence link and propagation direction of the accident. The average deviation of the time and location of these accidents is 0.6 minutes and 27.87 meters respectively. Overall, these results show that the model has high accuracy in identifying the spatiotemporal location of traffic accidents when the input data is complete and clean.

[0111] Step 3: Random Missing Data Experiment Results

[0112] Considering that the network-wide speed data obtained from the floating car data may be intermittently unavailable on certain links and time intervals, experiments are conducted to evaluate the performance of the proposed model under data missing conditions, specifically, by randomly ignoring the observed speed data in the spatial and temporal dimensions with the missing rate set to [10%, 20%, 30%, 40%, 50%, 60%, 70%]. Figure 3 and Figure 4 As shown, the experimental results show that as the missing rate increases, the deviations in distance and time also increase, which is due to the fact that there is less and less information related to the observed impact accidents. It is worth noting that when the missing rate is lower than 50%, the model of the present invention can produce satisfactory results for all accidents. Beyond this threshold, some accidents show obvious deviations in distance or time. In addition, it can be seen that the median deviations of distance and time remain within an acceptable range for all missing rates. This shows that the model has the ability to adapt and perform reliably even in the case of large amounts of missing data. Overall, these findings demonstrate the robustness and reliability of the model proposed in the present invention, even in the case of large amounts of missing data.

[0113] Step 4: Noise data experimental results

[0114] Another important issue in determining network-wide accidents is measurement errors and random speed fluctuations, which can lead to erroneous data and hinder accurate observation of accident impacts. This will further lead to bias in determining the spatiotemporal location of accidents. The proposed model addresses this challenge by minimizing the difference between the expected and observed spatiotemporal propagation of accident impacts. This experiment evaluates the performance of the proposed model at different percentages and magnitudes. Specifically, Gaussian white noise is introduced into the speed data with sizes and percentages of [1, 2, 3]σ and [5%, 10%, 15%, 20%, 25%, 30%], where σ represents the standard deviation of the speed data. The results show that as the error percentage increases, the distance and time deviations also increase. Similar results can be observed with the increase of noise. In addition, for lower noise magnitudes (e.g., 1σ and 2σ), the deviation increases slowly with the increase of noise percentage. However, at higher noise magnitudes (e.g., 3σ), the deviation increases more sharply, especially when the noise percentage exceeds 20%. In general, it is found that the performance of the proposed model is still satisfactory even in the presence of erroneous data.

[0115] Embodiment 2

[0116] The embodiment of the present invention also provides a computer program product, such as an app on a mobile phone, a tablet, an installation program on a computer, etc., which includes a computer program / instruction, and the computer program / instruction is executed by a processor to implement the method described in Example 1. The code of the computer executable program for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming language includes an object-oriented programming language, such as Java, Smalltalk, C++, and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0117] It should be understood that the above embodiments and descriptions only describe the principles, main features and advantages of the present invention. Without departing from the spirit and scope of the present invention, the present invention may be subject to various changes and improvements, and these changes and improvements all fall within the scope of protection of the present invention.

Claims

1. A method for identifying the spatiotemporal location of a traffic accident using floating vehicle data, characterized in that: The steps include: (1) Obtain floating vehicle data during the historical analysis period and floating vehicle data during the time period to be identified, and calculate the historical average driving speed of each link during each time interval during the historical analysis period, and the actual driving speed of each link during each time interval during the time period to be identified; (2) Determine whether each link is expected to be affected by the accident in each time interval based on the historical average driving speed and the actual driving speed; (3) constructing an accident spatiotemporal location optimization model, wherein the accident spatiotemporal location optimization model uses whether each link is actually affected by each accident in each time interval and the time interval and link where each accident occurs as decision variables, and aims to minimize the difference between the actual and expected impact of the accident on all links in all time intervals; (4) adding constraints to the accident spatiotemporal location optimization model, wherein the constraints include source constraints of accident impact, directional propagation constraints of traffic accident impact, continuous propagation constraints of accident impact, additional constraints of road network closure, minimum requirements for accident spatiotemporal location range, and decision variable constraints; (5) Solve the accident spatiotemporal location optimization model to obtain the time interval and link of each accident in the time period to be identified, as the accident spatiotemporal location output of the time period to be identified.

2. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 1, characterized in that: Step (2) specifically includes: (2.1) Based on the floating vehicle data and the historical average driving speed during the historical analysis period, calculate the historical speed standard deviation of each link in each time interval during the historical analysis period; (2.2) Based on the historical average driving speed, the historical speed standard deviation and the actual driving speed, the expected accident impact indicator variable of each link in each time interval is calculated according to the following formula, wherein the expected accident impact indicator variable is used to indicate whether each link n in each time interval t is expected to be affected by an accident; In the formula, represents the expected accident impact indicator variable, when When , it means that link n is expected to be affected by the accident within time interval t, otherwise it means that it is not affected, v n,t represents the actual driving speed through link n in time interval t, σ n,t They represent the historical average speed and historical speed standard deviation of link n in time interval t, α represents the scale parameter, N represents the number of links, and T represents the number of time intervals into which the time period to be identified is divided.

3. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 2, characterized in that: The objective function of the accident spatiotemporal location optimization model is: In the formula, represents the actual accident impact decision variable, which is used to indicate whether link n is actually affected by accident k in time interval t. When means that link n is actually affected by accident k in time interval t, When t = t, it means that link n is not actually affected by accident k in time interval t. represents the accident spatiotemporal location decision variable, which is used to indicate the time interval t and link n where the accident k occurs. When , it means that the accident k occurs on the link n within the time interval t. t indicates that accident k did not occur on link n within time interval t, and K represents the number of accidents.

4. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 3, characterized in that: The source constraints of the accident impact are specifically: Where, D n represents the set of downstream links of link n, |D n | represents the number of downstream links of link n, and m represents D n The mth link in is the actual accident impact decision variable used to indicate whether link m is actually affected by accident k within time interval t.

5. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 3, characterized in that: The directional propagation constraints of the traffic accident impact are specifically: Where, D n represents the downstream link set of link n, and m represents D n The mth link in is the actual accident impact decision variable used to indicate whether link m is actually affected by accident k within time interval t.

6. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 3, characterized in that: The specific constraints for the continuous propagation of the accident impact are: λ1+λ2+λ3≤2 λ1,λ2,λ3∈{0,1} Where D n represents the set of downstream links of link n, |D n | represents the number of downstream links of link n, and m represents D n The mth link in is the actual accident impact decision variable used to indicate whether link m is actually affected by accident k in time interval t, and λ1, λ2, λ3 are propagation constraint parameters.

7. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 3, characterized in that: The additional constraints of the road network closed loop are specifically: Where Δ represents the set of downstream links of link n, and |Δ| is the number of downstream links of link n.

8. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 3, characterized in that: The minimum requirements for the accident time and space location range are as follows: In the formula, is the accident time impact indicator variable. If at least one link is affected by accident k in time interval t, is equal to 1, otherwise it is equal to 0, L t Indicates the preset time threshold, is the accident spatial impact indicator variable. If link n is affected by accident k in at least one time interval, is equal to 1, otherwise it is equal to 0, L n Indicates the preset space threshold.

9. The method for identifying the spatiotemporal location of a traffic accident using floating vehicle data according to claim 3, characterized in that: The decision variable constraints are specifically:

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images