Traffic management methods, devices, equipment and storage media

Abstract

This application discloses a traffic management method, apparatus, equipment, and storage medium, relating to the field of data processing technology, for predicting and timely managing traffic congestion. The method includes: acquiring basic traffic data for multiple roads; determining the throughput of each road based on average vehicle speed and the number of vehicles passing per unit time; dividing the multiple roads into multiple road sets based on the throughput of each road, with different sets corresponding to different throughput ranges; determining the boundaries of roads included in different road sets; acquiring target influencing factors in the road network at each boundary that cause traffic congestion with an impact greater than or equal to a threshold, inputting the target influencing factors into a prediction model, determining the predicted road congestion level corresponding to each target influencing factor, and determining a congestion management strategy corresponding to each target influencing factor based on the predicted road congestion level.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a traffic management method, apparatus, device, and storage medium. Background Technology

[0002] As the scale of the road expands, the number of vehicles on the road increases, leading to frequent traffic congestion and placing considerable pressure on traffic management. Currently, the solution to traffic congestion involves real-time monitoring of road conditions using surveillance cameras and analyzing historical traffic data to identify and implement appropriate measures to manage congested sections.

[0003] The methods described above all rely on monitoring cameras to identify congested areas after traffic congestion has occurred, and then measures are taken to manage the congested sections. This results in a delay in resolving traffic congestion and a lack of timeliness in current traffic congestion management. Summary of the Invention

[0004] This application provides a traffic management method, apparatus, device, and storage medium for predicting and managing traffic congestion in a timely manner.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a traffic management method is provided, comprising: acquiring basic traffic data for multiple roads; the basic traffic data including: average vehicle speed and number of vehicles passing through per unit time; determining the throughput of each road based on the average vehicle speed and number of vehicles passing through per unit time; throughput indicating the number of vehicles passing through a road per unit time; dividing the multiple roads into multiple road sets based on the throughput of each road, with different sets corresponding to different throughput ranges; determining the boundaries of roads included in different road sets; acquiring target influencing factors in the road network at each boundary that cause traffic congestion with an impact greater than or equal to a threshold, inputting the target influencing factors into a prediction model, determining the predicted road congestion level corresponding to each target influencing factor, and determining the congestion management strategy corresponding to each target influencing factor based on the predicted road congestion level.

[0007] In one possible implementation, the target influencing factors causing traffic congestion with an impact greater than or equal to a threshold are obtained in the road network at each intersection. This includes: inputting basic traffic data of the road network at each intersection into a preset flow model to determine the relationship between road capacity and vehicle density corresponding to the road network at each intersection; determining whether traffic congestion exists in the road network at each intersection based on the relationship between road capacity and vehicle density; if at least one intersection is determined to have traffic congestion, obtaining multiple influencing factors causing traffic congestion in the road network at each intersection; determining the association relationship between any two influencing factors among the multiple influencing factors based on an association rule algorithm, and determining the target influencing factor from the multiple influencing factors based on the association relationship. The association relationship is used to indicate the probability that an influencing factor and other influencing factors simultaneously cause traffic congestion. The target influencing factor includes: influencing factors with an impact greater than or equal to a threshold, and influencing factors that are associated with influencing factors with an impact greater than or equal to a threshold.

[0008] In one possible implementation, the method further includes: constructing a target loss function based on the predicted road congestion level and the actual road congestion level corresponding to each target influencing factor; and training the prediction model based on the target loss function until the prediction model converges.

[0009] In one possible implementation, a preset traffic flow model is established based on the basic traffic data of the road network at each intersection; the predicted traffic flow model is used to indicate the relationship between the road capacity and vehicle density corresponding to each intersection road network; based on the relationship between road capacity and vehicle density, it is determined whether there is traffic congestion in the road network at each intersection, including: if the road capacity is greater than the vehicle density, it is determined that there is no traffic congestion in the road network at the intersection; if the road capacity is less than or equal to the vehicle density, it is determined that there is traffic congestion in the road network at the intersection.

[0010] In one possible implementation, the factors leading to traffic congestion in the road network at the intersection include multiple factors. The association rule algorithm is used to determine the association between any at least two of these factors, including: determining the frequency of occurrence of each set of factors in multiple sets of factors based on the multiple factors corresponding to the road network at at least one intersection; determining the support of each set of factors based on the frequency of occurrence of each set of factors, and identifying at least one set of factors from the multiple sets of factors whose support is greater than a preset support; and determining the probability of the simultaneous occurrence of a first set of factors and a second set of factors based on the frequency of occurrence of each set of factors, to determine the association between any two sets of factors, where both the first and second sets of factors are any one of the at least one set of factors, but the first and second sets of factors are different.

[0011] Secondly, a traffic management device is provided, comprising: an acquisition unit and a processing unit; the acquisition unit is used to acquire basic traffic data of multiple roads; the basic traffic data includes: average vehicle speed and number of vehicles passing through per unit time; the processing unit is used to determine the throughput of each of the multiple roads based on the average vehicle speed and the number of vehicles passing through per unit time; the throughput is used to indicate the number of vehicles passing through the road per unit time; the processing unit is further used to divide the multiple roads into multiple road sets based on the throughput of each road, with different sets corresponding to different throughput ranges; the processing unit is further used to determine the boundaries of roads included in different road sets; the acquisition unit is further used to acquire target influencing factors in the road network at each boundary that have an impact on traffic congestion greater than or equal to a threshold; the processing unit is further used to input the target influencing factors into a prediction model, determine the predicted road congestion level corresponding to each target influencing factor, and determine the congestion management strategy corresponding to each target influencing factor based on the predicted road congestion level.

[0012] In one possible implementation, the processing unit is further configured to input basic traffic data of the road network at each intersection into a preset flow model to determine the relationship between road capacity and vehicle density corresponding to the road network at each intersection; the processing unit is further configured to determine whether traffic congestion exists in the road network at each intersection based on the relationship between road capacity and vehicle density; the processing unit is further configured to obtain multiple influencing factors that cause traffic congestion in the road network at each intersection when it is determined that at least one intersection has traffic congestion; the processing unit is further configured to determine the correlation between any two influencing factors among the multiple influencing factors based on an association rule algorithm, and determine the target influencing factor from the multiple influencing factors based on the correlation, wherein the correlation indicates the probability that an influencing factor and other influencing factors simultaneously cause traffic congestion, and the target influencing factor includes: influencing factors with an influence greater than or equal to a threshold, and influencing factors that have a correlation with influencing factors with an influence greater than or equal to the threshold.

[0013] In one possible implementation, the processing unit is further configured to construct a target loss function based on the predicted road congestion level and the actual road congestion level corresponding to each target influencing factor; the processing unit is further configured to train the prediction model based on the target loss function until the prediction model converges.

[0014] In one possible implementation, the processing unit is specifically used to establish a preset flow model based on the basic traffic data of the road network at each intersection; the predicted flow model is used to indicate the relationship between the road capacity and vehicle density corresponding to the road network at each intersection; the processing unit is specifically used to determine that there is no traffic congestion in the road network at the intersection when the road capacity is greater than the vehicle density; the processing unit is specifically used to determine that there is traffic congestion in the road network at the intersection when the road capacity is less than or equal to the vehicle density.

[0015] In one possible implementation, the factors leading to traffic congestion in the road network at the intersection include multiple factors; a processing unit is specifically used to determine the frequency of occurrence of each group of influencing factors in the multiple groups of influencing factors based on the multiple influencing factors corresponding to the road network of each intersection in at least one intersection, wherein a group of influencing factors includes at least one influencing factor among the multiple influencing factors; a processing unit is specifically used to determine the support of each group of influencing factors based on the frequency of occurrence of each group of influencing factors in the multiple groups of influencing factors, and to determine at least one group of influencing factors from the multiple groups of influencing factors whose support is greater than a preset support; a processing unit is specifically used to determine the probability of simultaneous occurrence of a first group of influencing factors and a second group of influencing factors based on the frequency of occurrence of each group of influencing factors in the at least one group of influencing factors, so as to determine the correlation between any two groups of influencing factors, wherein the first group of influencing factors and the second group of influencing factors are both any one of the at least one group of influencing factors, and the first group of influencing factors and the second group of influencing factors are different.

[0016] Thirdly, an electronic device includes: a processor and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer-executable instructions, and when the electronic device is running, the processor executes the computer-executable instructions stored in the memory to cause the electronic device to perform the traffic management method of the first aspect.

[0017] Fourthly, a computer-readable storage medium is provided, including computer instructions that, when executed by a computer, cause the computer to perform the traffic management method of the first aspect.

[0018] This application provides a traffic management method, apparatus, device, and storage medium applied to scenarios involving traffic congestion management. By acquiring basic traffic data, including average vehicle speed and the number of vehicles passing per unit time, for multiple roads, the throughput of each road is determined based on this data. Then, based on different throughput ranges and the throughput of each road, the multiple roads are divided into multiple road sets. Furthermore, the target influencing factors leading to traffic congestion in the road network corresponding to the intersections of roads in different road sets can be obtained. These target influencing factors are input into a prediction model to determine the predicted road congestion level for each target influencing factor, and the corresponding congestion management strategy is determined based on the predicted road congestion level.

[0019] Using the above method, the throughput corresponding to each road can be determined based on the basic traffic data. Since the throughput of each road is different, the road capacity that each road needs to carry during normal traffic operation is different. Therefore, based on the different throughputs, the boundaries where traffic congestion is likely to occur can be predicted and determined. Then, based on the target influencing factors and prediction models that lead to traffic congestion in the road network, the congestion level during traffic congestion can be determined and the corresponding congestion management strategy can be determined. This allows for the prediction and timely management of traffic congestion, improving the efficiency of traffic congestion management. Attached Figure Description

[0020] Figure 1 A schematic diagram of a traffic management system structure provided for an embodiment of this application;

[0021] Figure 2 A schematic flowchart of a traffic management method provided for embodiments of this application. Figure 1 ;

[0022] Figure 3 A schematic flowchart of a traffic management method provided for embodiments of this application. Figure 2 ;

[0023] Figure 4 A schematic flowchart of a traffic management method provided for embodiments of this application. Figure 3 ;

[0024] Figure 5 A schematic flowchart of a traffic management method provided for embodiments of this application. Figure 4 ;

[0025] Figure 6 A schematic flowchart of a traffic management method provided for embodiments of this application. Figure 5 ;

[0026] Figure 7 A schematic diagram of a traffic management device provided for an embodiment of this application;

[0027] Figure 8 This is a schematic diagram of an electronic device structure provided for an embodiment of this application. Detailed Implementation

[0028] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0029] In the description of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" and "multiple" refer to two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0030] As the scale of the industry expands, the number of vehicles on the roads increases, leading to frequent traffic congestion. Current solutions to traffic congestion involve identifying congested areas through surveillance cameras after congestion has occurred, analyzing historical traffic data, and then managing the congested sections. This approach is reactive and cannot address traffic congestion in a timely manner.

[0031] The traffic management method provided in this application embodiment can be applied to traffic management systems. Figure 1 A schematic diagram of one structure of this traffic management system is shown. For example... Figure 1 As shown, the traffic management system 20 includes: a data acquisition module 21, a region division module 22, a traffic analysis module 23, a traffic management module 24, and a database 25.

[0032] Among them, the data acquisition module 21 is used to acquire basic traffic data of multiple roads and to acquire target influencing factors in each intersection road network that cause traffic congestion to have an impact greater than or equal to a threshold.

[0033] The region division module 22 is used to divide multiple roads into multiple road sets based on the throughput of each road, with different sets corresponding to different throughput ranges, and to determine the boundaries of roads included in different road sets.

[0034] The traffic flow analysis module 23 is used to determine the throughput of each of the multiple roads based on the average vehicle speed and the number of vehicles passing through per unit time.

[0035] The traffic management module 24 is used to input the target influencing factors into the prediction model, determine the predicted road congestion level corresponding to each target influencing factor, and determine the congestion management strategy corresponding to each target influencing factor based on the predicted road congestion level.

[0036] Database 25 is used to store data information generated in data acquisition module 21, area division module 22, traffic analysis module 23 and traffic management module 24.

[0037] Optionally, the data acquisition module 21 may include: a vehicle flow information acquisition unit, a road capacity information acquisition unit, and an influencing factor acquisition unit; the vehicle flow information acquisition unit is used to collect the flow information of vehicles on the road at different time periods, the road capacity information acquisition unit is used to collect the road's traffic capacity, and the influencing factor acquisition unit is used to collect several influencing factors that affect road flow.

[0038] Optionally, the region division module 22 may include: a throughput calculation unit and a region designation unit; the throughput calculation unit is used to calculate the throughput of each road; the region designation unit is used to group roads with the same throughput range into different sets based on the road throughput as the standard.

[0039] Optionally, the traffic flow analysis module 23 may include: an influencing factor analysis unit and a traffic congestion analysis unit; the influencing factor analysis unit is used to mine factors that affect the normal operation of traffic using the association rule (apriori) algorithm, and the traffic congestion analysis unit is used to analyze the relationship between road capacity and vehicle density.

[0040] Optionally, the traffic management module 24 may include: a neural network analysis unit and a management strategy unit; the neural network analysis unit is used to analyze the congestion level of the road network based on the influencing factors, and the management strategy unit is used to generate corresponding management methods based on the congestion level.

[0041] Optionally, the database 25 may include: a data storage unit and a data retrieval unit; the data storage unit is used to store road traffic flow, road capacity, and influencing factors; the data retrieval unit is used to retrieve information for data analysis.

[0042] The following description, in conjunction with the accompanying drawings, describes a traffic management method provided by an embodiment of this application.

[0043] like Figure 2 As shown in the embodiment of this application, a traffic management method includes steps S201-S205:

[0044] S201, Obtain basic traffic data for multiple roads.

[0045] The basic traffic data includes: average vehicle speed and the number of vehicles passing through per unit time.

[0046] Optionally, the average speed of vehicles traveling on multiple roads can be obtained from the navigation system; or information such as the number of vehicles passing through multiple roads per unit time, road capacity, and vehicle density can be obtained from surveillance cameras; and traffic data and vehicle information corresponding to multiple roads can be obtained from traffic management departments.

[0047] S202. Based on the average vehicle speed and the number of vehicles passing through per unit time, determine the throughput of each of the multiple roads.

[0048] Throughput is used to indicate the number of vehicles passing through a road per unit of time.

[0049] Alternatively, the throughput can be calculated based on the following formula:

[0050] Formula 1: Q = V × N

[0051] Where Q represents throughput, V represents average vehicle speed, and N represents the number of vehicles passing through per unit time.

[0052] S203. Based on the throughput of each road, multiple roads are divided into multiple road sets, with different sets corresponding to different throughput ranges.

[0053] Optionally, multiple throughput ranges can be predetermined, and based on the throughput corresponding to each road, the throughput range to which the throughput of each road belongs can be determined, so that roads belonging to the same throughput range can be identified as a set, thereby dividing multiple roads into multiple sets.

[0054] S204. Determine the boundaries of roads included in different road sets among multiple road sets.

[0055] Optionally, based on the throughput corresponding to each road, multiple roads are divided into multiple road sets. Since the throughput corresponding to each road is different, the road capacity that each road needs to carry during normal traffic operation is different. Therefore, the difference in throughput will affect the normal operation of traffic and will also lead to different capacity of different road sets. As a result, traffic congestion will occur at the intersection of roads included in different road sets.

[0056] As can be understood, a road network refers to a network of interconnected roads within a certain area. In cities, the road network consists of various arterial roads and regional roads with different functions within the town's jurisdiction.

[0057] S205. Obtain the target influencing factors in the road network at each intersection that cause traffic congestion with an impact greater than or equal to a threshold, input the target influencing factors into the prediction model, determine the predicted road congestion level corresponding to each target influencing factor, and determine the congestion management strategy corresponding to each target influencing factor based on the predicted road congestion level.

[0058] Optionally, the target influencing factors that cause traffic congestion in the road network at each intersection can be obtained by collecting multiple factors affecting traffic operation from surveillance cameras and / or driver feedback on each road segment.

[0059] Specifically, factors that contribute to traffic congestion may include: weather, traffic accidents, public holidays, speed limits, and road length.

[0060] Optionally, the prediction model can be a Graph Convolutional Network (GCN) model, which can be implemented using the following formula:

[0061]

[0062] Among them, H (l) W represents the feature matrix of the l-th layer node. (l) This represents the weight matrix of the l-th layer. Let σ represent the adjacency matrix plus the self-loop matrix, σ represent the activation function, and Z represent the eigenvectors of the entire graph, which are the sum of the eigenvectors of all nodes.

[0063] For example, information such as speed limits, segment lengths, and congestion levels at each intersection can be transformed into a feature vector, which can then be used as input to the GCN model.

[0064] It should be noted that each row of the input to the GCN model represents a feature vector of a boundary. For example, the feature vector of the first row is [20,1000,2,30,800,3], which means that the two road segments at the first boundary correspond to a speed limit of 20, a road segment length of 1000, a congestion level of 2, a speed limit of 30, a road segment length of 800, and a congestion level of 3, respectively. Then, all feature values ​​are normalized to be between 0 and 1.

[0065] Suppose we use a neural network model with two layers of GCNs, where the output feature vector of the first GCN layer has a length of 4 and the output feature vector of the second GCN layer has a length of 2. In each layer, a linear rectification function (ReLU) is used as the activation function for nonlinear transformation.

[0066] The first-layer GCN model can be represented by the following formula:

[0067]

[0068] Among them, H (1) W represents the input feature vector matrix. (0) This represents the weight matrix of the first-layer GCN. Let σ represent the adjacency matrix plus the self-loop matrix, σ represent the activation function, and max represent ReLU.

[0069] Furthermore, the first-layer GCN model can be calculated, with each row representing a boundary GCN feature vector. For example, the feature vector [0.16, 0.32, 0.25, 0.03] in the first row represents the first boundary GCN feature vector after processing by the first-layer GCN.

[0070] The second-layer GCN network model can be represented by the following formula:

[0071]

[0072] Among them, H (2) W represents the output feature matrix of the first-layer GCN network model. (1) This represents the weight matrix of the second-layer GCN network model. Let σ represent the adjacency matrix plus the self-loop matrix, σ represent the activation function, and max represent ReLU.

[0073] Therefore, the second-layer GCN model can be calculated, with each row representing a boundary GCN feature vector. For example, the feature vector [0.10, 0.13] in the first row represents the first boundary GCN feature vector after processing by the second-layer GCN.

[0074] Based on the comparison of road congestion levels y, the average error of the predicted road congestion level across the entire intersection is calculated. Assume the actual road congestion levels are: y = [2, 3, 1, 4, 5], corresponding to the actual road congestion levels across all intersections. The second value in the output vector obtained from the GCN model (i.e., the predicted road congestion level) can be used as the predicted value, and the loss can be calculated according to the defined loss function.

[0075] Optionally, based on the road congestion level predicted by the prediction model, corresponding strategies can be provided for management.

[0076] For example, at intersections with low traffic congestion levels, shorter real-time red light durations can be set to allow vehicles to pass through the intersection quickly. For instance, in key commercial areas, if the traffic congestion level is below the predicted average, the red-green light ratio can be adjusted to 1:3. At intersections with high traffic congestion levels, some traffic control measures can be implemented. For example, at major intersections of important arterial roads, if the traffic congestion level exceeds the predicted average, traffic control measures can be activated to limit private vehicle traffic and encourage the use of public transportation or walking.

[0077] In a design, such as Figure 3 As shown in the embodiment of this application, a traffic management method is provided. Step S205 in the above method may specifically include S301-S304:

[0078] S301. Input the basic traffic data of the road network at each intersection into the preset flow model to determine the relationship between the road capacity and vehicle density corresponding to each intersection.

[0079] Optionally, the preset traffic model can be represented by the following formula five:

[0080]

[0081] Among them, f ij Let C be the road traffic flow from the i-th intersection to the j-th intersection. ij Let V(f) be the road capacity from intersection i to intersection j, V(f) be the feasible flow rate, A be the arc set of the road network, and K be the flow rate. n Let be the coefficient of traffic flow, e be the base of the natural logarithm, α be the average driver reaction time, and ρ be the vehicle density.

[0082] It should be noted that the following parameters in the preset traffic flow model are predetermined constant values: road traffic flow, feasible flow flow, arc set of the road network, traffic flow coefficient, base of the natural logarithm, and average driver reaction time.

[0083] It is understandable that, based on a road network with multiple intersections and a pre-set traffic flow model, we can further understand the traffic situation between multiple sets, making it easier to identify the location of traffic congestion.

[0084] For example, the preset traffic flow model takes as constants the road traffic flow, feasible flow flow, arc set of the road network, traffic flow coefficient, base of the natural logarithm, and average driver reaction time as inputs to determine the relationship between road capacity and vehicle density at each intersection of the road network. Furthermore, based on the relationship between road capacity and vehicle density at each intersection of the road network, it can determine congested areas, high-traffic sections, bottlenecks, and congested time periods, and provide a data foundation for subsequent modeling.

[0085] S302. Based on the relationship between road capacity and vehicle density, determine whether there is traffic congestion at each intersection of the road network.

[0086] It should be noted that the relationship between road capacity and vehicle density at each intersection (e.g., the difference between road capacity and vehicle density) can indicate whether the intersection is congested, the degree of congestion, and the traffic volume of the road segment.

[0087] S303. If it is determined that there is traffic congestion in at least one intersection of the road network, obtain multiple influencing factors that cause traffic congestion in the road network at each intersection.

[0088] Optionally, by collecting data from surveillance cameras and / or driver feedback on factors affecting traffic flow at each road segment, multiple influencing factors leading to traffic congestion at each intersection of the road network can be obtained, and all influencing factors can be organized into a set K = (K1, K2, ..., K...). n ), where K n This represents the nth influencing factor affecting traffic flow.

[0089] S304. Determine the association relationship between any two influencing factors among multiple influencing factors based on the association rule algorithm, and determine the target influencing factor from multiple influencing factors based on the association relationship.

[0090] The correlation is used to indicate the probability that an influencing factor and other influencing factors will simultaneously cause traffic congestion. The target influencing factors include: influencing factors with an influence greater than or equal to a threshold, and influencing factors that are correlated with influencing factors with an influence greater than or equal to a threshold.

[0091] Optionally, in a set of multiple influencing factors, i.e., K = (K1, K2, ..., K... n In this context, factors with the same influencing factors (i.e., those causing traffic congestion with the same cause, such as heavy rain and heavy snow, are grouped together and their frequency in that set is calculated. The minimum support and minimum confidence are then determined to derive the frequent 1-itemsets, and the support for each group of influencing factors is calculated, as shown in Formula 6.

[0092]

[0093] Where Sup represents support, num(all example) represents the number of multiple influencing factors, and num represents the number of influencing factors in a certain group that needs to be calculated.

[0094] Further, identify the largest frequent set (i.e., the set containing the target influencing factors) and derive the confidence score for each set of influencing factors, as shown in Formula 7:

[0095]

[0096] Where Con represents the confidence level, P(X|Y) refers to the probability of the occurrence of the influencing factor X given that the influencing factor Y has occurred, P(XY) refers to the probability that the influencing factors X and Y occur simultaneously, and P(Y) refers to the probability of the occurrence of the influencing factor Y.

[0097] In a design, such as Figure 4 As shown in the embodiment of this application, a traffic management method is provided, which may further include steps S401-S402:

[0098] S401. Construct a target loss function based on the predicted road congestion level and the actual road congestion level corresponding to each target influencing factor.

[0099] Optionally, the target loss function can be expressed by the following formula:

[0100]

[0101] Among them, y i This represents the actual road congestion level corresponding to the i-th road segment. This represents the predicted road congestion level corresponding to the i-th road segment.

[0102] S402. Based on the objective loss function, train the prediction model until the prediction model converges.

[0103] It is understandable that, based on the established loss function, the prediction model can be further trained to optimize its accuracy and improve the efficiency of traffic congestion management.

[0104] In one design, a pre-defined traffic flow model is established based on the basic traffic data of the road network at each intersection; the predicted traffic flow model is used to indicate the relationship between the road capacity and vehicle density corresponding to each intersection's road network; such as... Figure 5 As shown in the embodiment of this application, a traffic management method is provided. Step S302 in the above method may specifically include S501-S502:

[0105] S501. When the road capacity is greater than the vehicle density, it is determined that there is no traffic congestion in the road network at the intersection.

[0106] S502. When the road capacity is less than or equal to the vehicle density, it is determined that there is traffic congestion in the road network at the intersection.

[0107] Optionally, combining Formula 5, the road flow rate, feasible flow rate, arc set of the road network, traffic flow coefficient, base of the natural logarithm, and average driver reaction time, which are constants in the preset flow model, are input to determine the relationship between the road capacity and vehicle density corresponding to each intersection of the road network. It can be determined that when C... ij When ρ > 0, the road capacity C can be determined. ij When C is greater than the vehicle density ρ, vehicles can pass through the road without obstruction; when C... ij When ≤ρ, the road capacity C ij If the vehicle density ρ is less than or equal to the vehicle density ρ, the road flow will reach saturation, leading to traffic congestion.

[0108] In one design, several factors contribute to traffic congestion in the intersecting road network; such as... Figure 6 As shown in the embodiment of this application, a traffic management method is provided. Step S304 in the above method may specifically include S601-S603:

[0109] S601. Based on the multiple influencing factors corresponding to the road network of each intersection in at least one intersection, determine the frequency of occurrence of each group of influencing factors in the multiple groups of influencing factors, wherein a group of influencing factors includes at least one of the multiple influencing factors.

[0110] S602. Based on the frequency of occurrence of each group of influencing factors in multiple groups of influencing factors, determine the support level of each group of influencing factors, and identify at least one group of influencing factors from multiple groups of influencing factors whose support level is greater than the preset support level.

[0111] S603. Based on the number of times each group of influencing factors appears in at least one group of influencing factors, determine the probability that the first group of influencing factors and the second group of influencing factors appear simultaneously, so as to determine the correlation between any two groups of influencing factors.

[0112] Among them, the first group of influencing factors and the second group of influencing factors are both any one of at least one group of influencing factors, and the first group of influencing factors and the second group of influencing factors are different.

[0113] For example, as shown in Table 1, the five letters a, b, c, d, and e are used to represent influencing factors. The four road segments are numbered 1, 2, 3, and 4 respectively. Furthermore, each road segment corresponds to multiple influencing factors, and minSup = 50% and minCon = 50% are set.

[0114] Table 1

[0115] Road section number Influencing factors 1 acd 2 bce 3 abce 4 be

[0116] The first scan scans the database (i.e., Table 1) to obtain the frequency of each influencing factor, thus obtaining the frequent 1-itemset, as shown in Table 2 below:

[0117] Table 2

[0118] Influencing factors frequency a 2 b 3 c 3 d 1 e 3

[0119] Since the preset minSup=50% and the road segment numbers collected are 4, the number of occurrences of each influencing factor should be greater than or equal to 4×50%=2.

[0120] Therefore, based on frequent 1-itemsets, the influencing factors that satisfy the minimum support can be obtained as shown in Table 3:

[0121] Table 3

[0122] Influencing factors frequency a 2 b 3 c 3 e 3

[0123] Furthermore, through a second scan, the database (i.e., Table 1) is scanned to obtain the number of times each pair of influencing factors occurs simultaneously (i.e., at least two influencing factors jointly cause traffic congestion), thus obtaining frequent 2-itemsets, as shown in Table 4 below:

[0124] Table 4

[0125] Influencing factors frequency ab 1 ac 2 ae 1 bc 2 be 3 ce 2

[0126] Therefore, based on frequent 2-itemsets, the influencing factors that satisfy the minimum support can be obtained as shown in Table 5:

[0127] Table 5

[0128] Influencing factors frequency ac 2 bc 2 be 3 ce 2

[0129] Furthermore, through a third scan, the database (i.e., Table 1) is scanned to obtain the frequency of each of the three influencing factors occurring simultaneously (i.e., at least three influencing factors jointly causing traffic congestion), thus obtaining the frequent 3-itemsets, as shown in Table 6 below:

[0130] Table 6

[0131] Influencing factors frequency abc 1 abe 1 ace 1 bce 2

[0132] Therefore, based on frequent 3-itemsets, the influencing factors that satisfy the minimum support can be obtained as shown in Table 7:

[0133] Table 7

[0134] Influencing factors frequency bce 2

[0135] Since minCon = 50%, the association rules between the factors that satisfy the minimum confidence level can be obtained as follows:

[0136] (1) When influencing factor b occurs, the probability that influencing factors c and e occur simultaneously is 66.7%. The specific calculation method is shown in Formula 9 below.

[0137]

[0138] (2) When influencing factor c occurs, the probability that influencing factors b and e occur simultaneously is 66.7%. The specific calculation method is as follows: Formula 10.

[0139]

[0140] (3) When influencing factor e occurs, the probability that influencing factors b and influencing factor c occur simultaneously is 66.7%. The specific calculation method is shown in Formula 11 below.

[0141]

[0142] (4) When influencing factors b and c occur simultaneously, the probability of influencing factor e occurring is 100%. The specific calculation method is shown in Formula XII below.

[0143]

[0144] (5) When influencing factors b and e occur simultaneously, the probability of influencing factor c occurring is 66.7%. The specific calculation method is shown in Formula XIII below.

[0145]

[0146] (6) When influencing factor c and influencing factor e occur simultaneously, the probability of influencing factor b occurring is 100%. The specific calculation method is as follows: Formula XIV.

[0147]

[0148] This application provides a traffic management method that acquires basic traffic data, including average vehicle speed and the number of vehicles passing through per unit time, for multiple roads. Based on this basic traffic data, the throughput of each road is determined. Then, based on different throughput ranges, the multiple roads are divided into multiple road sets. Furthermore, the target influencing factors leading to traffic congestion in the road network corresponding to the intersections of roads in different road sets are obtained. These target influencing factors are input into a prediction model to determine the predicted road congestion level for each target influencing factor. Based on the predicted road congestion level, a corresponding congestion management strategy is determined. Through this method, the throughput corresponding to each road can be determined based on the basic traffic data. Since the throughput of each road is different, the road capacity required for each road during normal traffic operation is different. Therefore, based on the different throughputs, the boundaries prone to traffic congestion are predicted and determined. Then, based on the target influencing factors leading to traffic congestion in the road network and the prediction model, the congestion level during traffic congestion is determined, and a corresponding congestion management strategy is determined. This allows for the prediction and timely management of traffic congestion, improving the efficiency of traffic congestion management.

[0149] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0150] This application embodiment can divide a traffic management device into functional modules based on the above method example. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0151] Figure 7 This is a schematic diagram of a traffic management device provided in an embodiment of this application. Figure 7 As shown, a traffic management device 100 is used to predict and manage traffic congestion in a timely manner, for example, for performing... Figure 2 A traffic management method is shown. The traffic management device 100 includes: an acquisition unit 1001 and a processing unit 1002;

[0152] The acquisition unit 1001 is used to acquire basic traffic data for multiple roads; the basic traffic data includes: average vehicle speed and number of vehicles passing through per unit time;

[0153] The processing unit 1002 is used to determine the throughput of each of the multiple roads based on the average vehicle speed and the number of vehicles passing through per unit time; the throughput is used to indicate the number of vehicles passing through the road per unit time.

[0154] The processing unit 1002 is also used to divide multiple roads into multiple road sets based on the throughput of each road, with different sets corresponding to different throughput ranges;

[0155] The processing unit 1002 is also used to determine the boundaries of roads included in different road sets among multiple road sets;

[0156] Unit 1001 acquires the target influencing factors in each intersection of the road network that cause traffic congestion with an impact greater than or equal to a threshold.

[0157] The processing unit 1002 is also used to input the target influencing factors into the prediction model, determine the predicted road congestion level corresponding to each target influencing factor, and determine the congestion management strategy corresponding to each target influencing factor based on the predicted road congestion level.

[0158] In one possible implementation, in a traffic management device 100 provided in this application embodiment, the processing unit 1002 is further configured to input the basic traffic data of the road network at each intersection into a preset flow model, and determine the relationship between the road capacity and vehicle density corresponding to the road network at each intersection.

[0159] The processing unit 1002 is also used to determine whether there is traffic congestion at each intersection of the road network based on the relationship between road capacity and vehicle density;

[0160] The processing unit 1002 is also configured to, when it is determined that there is traffic congestion in at least one intersection of the road network, acquire multiple influencing factors in the road network at each intersection that cause traffic congestion.

[0161] The processing unit 1002 is further configured to determine the association relationship between any two influencing factors among multiple influencing factors based on the association rule algorithm, and to determine the target influencing factor from multiple influencing factors based on the association relationship. The association relationship is used to indicate the probability that an influencing factor and other influencing factors will simultaneously cause traffic congestion. The target influencing factor includes: influencing factors with an influence degree greater than or equal to a threshold, and influencing factors that have an association relationship with influencing factors with an influence degree greater than or equal to the threshold.

[0162] In one possible implementation, in a traffic management device 100 provided in this application embodiment, the processing unit 1002 is further configured to construct a target loss function based on the predicted road congestion level and the actual road congestion level corresponding to each target influencing factor.

[0163] The processing unit 1002 is also used to train the prediction model based on the target loss function until the prediction model converges.

[0164] In one possible implementation, the processing unit 1002 is specifically used to establish a preset flow model based on the basic traffic data of the road network at each intersection; the predicted flow model is used to indicate the relationship between the road capacity and vehicle density corresponding to the road network at each intersection.

[0165] The processing unit 1002 is specifically used to determine that there is no traffic congestion in the road network at the intersection when the road capacity is greater than the vehicle density.

[0166] The processing unit 1002 is specifically used to determine that there is traffic congestion in the road network at the intersection when the road capacity is less than or equal to the vehicle density.

[0167] In one possible implementation, the factors that cause traffic congestion in the road network at the intersection include multiple factors. In a traffic management device 100 provided in this application embodiment, the processing unit 1002 is specifically used to determine the number of times each set of influencing factors occurs based on multiple influencing factors corresponding to the road network of each intersection in at least one intersection. A set of influencing factors includes at least one influencing factor among multiple influencing factors.

[0168] The processing unit 1002 is specifically used to determine the support of each group of influencing factors based on the number of times each group of influencing factors appears in multiple groups of influencing factors, and to determine at least one group of influencing factors whose support is greater than the preset support from multiple groups of influencing factors.

[0169] The processing unit 1002 is specifically used to determine the probability of the first group of influencing factors and the second group of influencing factors occurring simultaneously based on the number of times each group of influencing factors appears in at least one group of influencing factors, so as to determine the correlation between any two groups of influencing factors. The first group of influencing factors and the second group of influencing factors are both any group of influencing factors in at least one group of influencing factors, and the first group of influencing factors and the second group of influencing factors are different.

[0170] In the case of implementing the functions of the integrated modules described above in hardware, this application provides another possible structural diagram of the electronic device involved in the above embodiments. For example... Figure 8 As shown, an electronic device 90 is used to predict and manage traffic congestion in a timely manner, for example, for performing... Figure 2 The diagram illustrates a traffic management method. The electronic device 90 includes a processor 901, a memory 902, and a bus 903. The processor 901 and the memory 902 are connected via the bus 903.

[0171] Processor 901 is the control center of the communication device. It can be a single processor or a collective term for multiple processing elements. For example, processor 901 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0172] As one embodiment, processor 901 may include one or more CPUs, for example Figure 8 CPU 0 and CPU 1 are shown in the diagram.

[0173] The memory 902 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0174] As one possible implementation, the memory 902 can exist independently of the processor 901. The memory 902 can be connected to the processor 901 via a bus 903 and is used to store instructions or program code. When the processor 901 calls and executes the instructions or program code stored in the memory 902, it can implement the traffic management method provided in this application embodiment.

[0175] In another possible implementation, the memory 902 can also be integrated with the processor 901.

[0176] Bus 903 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0177] It should be pointed out that, Figure 8 The structure shown does not constitute a limitation on the electronic device 90. Except... Figure 8 In addition to the components shown, the electronic device 90 may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0178] As an example, combined Figure 7 The functions implemented by the acquisition unit 1001 and the processing unit 1002 in the electronic device are the same as Figure 8 The processor 901 in it has the same function.

[0179] Optional, such as Figure 8 As shown, the electronic device 90 provided in this application embodiment may further include a communication interface 904.

[0180] Communication interface 904 is used to connect with other devices via a communication network. This communication network can be Ethernet, a wireless access network, a wireless local area network (WLAN), etc. Communication interface 904 may include a receiving unit for receiving data and a transmitting unit for transmitting data.

[0181] In one design, the communication interface in the electronic device provided in this application embodiment can also be integrated into the processor.

[0182] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0183] This application also provides a computer-readable storage medium storing instructions. When a computer executes these instructions, the computer performs each step of the method flow shown in the above-described method embodiments.

[0184] Embodiments of this application provide a computer program product containing instructions that, when executed on a computer, cause the computer to perform a traffic management method as described in the above method embodiments.

[0185] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing, or any other form of computer-readable storage medium in the art.

[0186] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside within an application-specific integrated circuit (ASIC).

[0187] In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0188] Since the electronic devices, computer-readable storage media, and computer program products in the embodiments of this application can be applied to the above methods, the technical effects they can achieve can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0189] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A traffic management method characterized by, The method comprises: obtaining basic traffic data of a plurality of roads; the basic traffic data comprises: vehicle average speed, number of vehicles passing per unit time; determining the throughput of each road in the plurality of roads based on the vehicle average speed and the number of vehicles passing per unit time; the throughput is used to indicate the number of vehicles passing per unit time in the road; based on the throughput of each road, the plurality of roads are divided into a plurality of road sets, and different sets correspond to different throughput intervals; determining the intersection of the roads included in different road sets in the plurality of road sets; obtaining a target influence factor in the road network of each intersection, which causes the influence degree of traffic congestion to be greater than or equal to a threshold value, and inputting the target influence factor into a prediction model to determine a predicted road congestion level corresponding to each target influence factor, and determining a congestion management strategy corresponding to each target influence factor based on the predicted road congestion level; the obtaining of the target influence factor in the road network of each intersection, which causes the influence degree of traffic congestion to be greater than or equal to a threshold value, comprises: inputting the basic traffic data of the road network of each intersection into a preset flow model to determine the size relationship between the road capacity and the vehicle density corresponding to the road network of each intersection; based on the size relationship between the road capacity and the vehicle density, determining whether the road network of each intersection has a traffic congestion condition; in the case where it is determined that the road network of at least one intersection has a traffic congestion condition, obtaining a plurality of influence factors in the road network of each intersection that cause the traffic congestion state; based on an association rule algorithm, determining the association relationship between any at least two influence factors in the plurality of influence factors, and based on the association relationship, determining the target influence factor from the plurality of influence factors, the association relationship is used to indicate the probability that one influence factor and other influence factors simultaneously cause the traffic congestion state, and the target influence factor comprises: an influence factor with an influence degree greater than or equal to a threshold value, and an influence factor having an association relationship with an influence factor with an influence degree greater than or equal to a threshold value.

2. The method of claim 1, wherein, The method further comprises: based on the predicted road congestion level and the actual road congestion level corresponding to each target influence factor, constructing a target loss function; based on the target loss function, training the prediction model until the prediction model converges.

3. The method of claim 1, wherein, The method further comprises: based on the basic traffic data of the road network of each intersection, establishing the preset flow model; the preset flow model is used to indicate the size relationship between the road capacity and the vehicle density corresponding to the road network of each intersection; based on the size relationship between the road capacity and the vehicle density, determining whether the road network of each intersection has a traffic congestion condition, comprises: in the case where the road capacity is greater than the vehicle density, it is determined that the road network of the intersection does not have a traffic congestion condition; in the case where the road capacity is less than or equal to the vehicle density, it is determined that the road network of the intersection has a traffic congestion condition.

4. The method of claim 1, wherein, The influence factors causing the traffic congestion state in the road network of the junction include a plurality of influence factors; The association relationship between any two of the plurality of influence factors is determined based on the association rule algorithm, including: Based on the plurality of influence factors corresponding to the road network of each of the at least one junction, the number of occurrences of each group of influence factors in a plurality of groups of influence factors is determined, and a group of influence factors includes at least one influence factor in the plurality of influence factors; Based on the number of occurrences of each group of influence factors in the plurality of groups of influence factors, the support degree of each group of influence factors is determined, and at least one group of influence factors with a support degree greater than a preset support degree is determined from the plurality of groups of influence factors; Based on the number of occurrences of each group of influence factors in the at least one group of influence factors, the probability of the simultaneous occurrence of a first group of influence factors and a second group of influence factors is determined to determine the association relationship between any two groups of influence factors, the first group of influence factors and the second group of influence factors are any group of influence factors in the at least one group of influence factors, and the first group of influence factors and the second group of influence factors are different.

5. A traffic management device, characterized by The traffic management device includes an acquisition unit and a processing unit; The acquisition unit is configured to acquire basic traffic data of a plurality of roads; the basic traffic data includes vehicle average speed and vehicle number passing per unit time; The processing unit is configured to determine the throughput of each road in the plurality of roads based on the vehicle average speed and the vehicle number passing per unit time; the throughput is used to indicate the number of vehicles passing per unit time in the road; The processing unit is further configured to divide the plurality of roads into a plurality of road sets based on the throughput of each road, and different sets correspond to different throughput intervals; The processing unit is further configured to determine the junction of roads included in different road sets in the plurality of road sets; The acquisition unit is further configured to acquire target influence factors in the road network of each junction, the influence degree of which causing traffic congestion is greater than or equal to a threshold value; The processing unit is further configured to input the target influence factors into a prediction model to determine a corresponding predicted road congestion level of each target influence factor, and determine a congestion management strategy corresponding to each target influence factor based on the predicted road congestion level; The processing unit is further configured to input the basic traffic data of the road network of each junction into a preset flow model to determine the size relationship between the road capacity and the vehicle density corresponding to the road network of each junction; The processing unit is further configured to determine whether there is a traffic congestion condition in the road network of each junction based on the size relationship between the road capacity and the vehicle density; The processing unit is further configured to acquire a plurality of influence factors causing a traffic congestion state in the road network of each junction in a case where it is determined that there is a traffic congestion condition in the road network of at least one junction. The processing unit is further configured to determine an association relationship between any at least two of the plurality of influence factors based on an association rule algorithm, and determine the target influence factor from the plurality of influence factors based on the association relationship, the association relationship being used to indicate a probability that one influence factor and other influence factors simultaneously cause the traffic congestion state, and the target influence factor including: an influence factor with an influence degree greater than or equal to a threshold value, and an influence factor having an association relationship with the influence factor with the influence degree greater than or equal to the threshold value.

6. The traffic management apparatus according to claim 5, wherein The processing unit is further configured to construct a target loss function based on the predicted road congestion level and the actual road congestion level corresponding to each target influence factor. The processing unit is further configured to train the prediction model based on the target loss function until the prediction model converges.

7. The traffic management apparatus according to claim 5, wherein The processing unit is specifically configured to establish the preset traffic flow model based on the basic traffic data of each of the road networks at the junctions; and the preset traffic flow model is used to indicate a size relationship between the road traffic capacity and the vehicle density corresponding to each of the road networks at the junctions. The processing unit is specifically configured to determine that the road network at the junction does not have the traffic congestion state in a case where the road traffic capacity is greater than the vehicle density. The processing unit is specifically configured to determine that the road network at the junction has the traffic congestion state in a case where the road traffic capacity is less than or equal to the vehicle density.

8. The traffic management apparatus according to claim 5, characterized by The influence factors causing the traffic congestion state in the road network at the junction include a plurality of influence factors. The processing unit is specifically configured to determine, based on the plurality of influence factors corresponding to each of the road networks at the junctions in the at least one junction, a number of times that each of a plurality of groups of influence factors appears, each group of influence factors including at least one of the plurality of influence factors. The processing unit is specifically configured to determine, based on the number of times that each of the plurality of groups of influence factors appears, a support degree of each of the groups of influence factors, and determine at least one group of influence factors with a support degree greater than a preset support degree from the plurality of groups of influence factors. The processing unit is specifically configured to determine, based on the number of times that each of the at least one group of influence factors appears, a probability that a first group of influence factors and a second group of influence factors appear simultaneously, to determine an association relationship between any two groups of influence factors, the first group of influence factors and the second group of influence factors being any of the at least one group of influence factors, and the first group of influence factors and the second group of influence factors being different.

9. An electronic device, comprising: The electronic device includes a processor and a memory; the memory is configured to store one or more programs including computer execution instructions; when the electronic device is running, the processor executes the computer execution instructions stored in the memory, so that the electronic device executes the traffic management method in any one of claims 1-4. The computer instructions, when executed by a computer, cause the computer to execute the traffic management method in any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, ​

Images