Traffic sub-area division method, device, electronic device and storage medium

Abstract

The disclosed embodiments provide a method, device, electronic device and storage medium for dividing traffic sub-areas, and relate to the field of intelligent transportation technology. The method comprises: obtaining the path flow data of the traffic area to be divided; determining the path correlation corresponding to the multiple intersections of the traffic area to be divided based on the path flow data; taking the density modularity as the objective function, hierarchically clustering the multiple intersections to obtain at least one target traffic sub-area that maximizes the objective function. Comprehensively considering the impact of the different number of lanes in the intersection path and whether to turn on the path flow, accurately measure the coordination benefits between intersections, and at the same time, by taking the density modularity as the objective function for hierarchical clustering, it is possible to effectively avoid the defect of the traditional traffic sub-area division model that is easy to fall into the local optimal solution, and improve the accuracy of traffic sub-area division.

Description

Technical Field

[0001] The present disclosure relates to the field of smart transportation, and in particular to a method, device, electronic device and storage medium for dividing traffic sub-zones. Background Art

[0002] In modern urban road networks, there is often a strong correlation between intersections. The adjustment of traffic signals at one intersection often affects the traffic conditions of several adjacent intersections. Therefore, in the field of intelligent transportation, the coordinated control of sub-areas between multiple intersections has received more attention. Since the entire urban road network is large, it is unrealistic to control all intersections as one area. Therefore, it is necessary to divide the urban road network into multiple traffic sub-areas and select different control strategies according to the specific traffic conditions of each traffic sub-area.

[0003] In the traffic sub-area division model of the related art, the granularity of the flow data between the upstream and downstream intersections is relatively coarse, and it is easy to fall into the local optimal solution when dividing the traffic sub-area, resulting in unsatisfactory final traffic sub-area division results. Summary of the invention

[0004] The purpose of the embodiments of the present disclosure is to provide a method, device, electronic device and storage medium for dividing traffic sub-zones.

[0005] To solve the above technical problems, the embodiments of the present disclosure are implemented through the following aspects.

[0006] According to a first aspect of an embodiment of the present disclosure, a method for dividing traffic sub-zones is provided, the method comprising: obtaining path flow data of a traffic area to be divided, the path flow data comprising flow data corresponding to a plurality of lane-level paths at intersections of the traffic area to be divided; determining path associations corresponding to a plurality of intersections of the traffic area to be divided based on the path flow data; taking density modularity as an objective function, hierarchically clustering the plurality of intersections to obtain at least one target traffic sub-zone that maximizes the objective function, the density modularity being determined based on an average path association within the traffic sub-zone, a first ratio, and a second ratio, the first ratio being a ratio of a first sum of path associations within the traffic sub-zone to a second sum of path associations of the traffic area to be divided, the second ratio being a ratio of a cross-path association of the traffic sub-zone to the second sum, the cross-path association being a sum of path associations between the traffic sub-zone and other adjacent traffic sub-zones.

[0007] According to a second aspect of an embodiment of the present disclosure, a device for dividing traffic sub-zones is provided, the device comprising: an acquisition module, used to acquire path flow data of a traffic area to be divided, the path flow data comprising flow data corresponding to a plurality of lane-level paths of intersections of the traffic area to be divided; a determination module, used to determine the path associations corresponding to a plurality of intersections of the traffic area to be divided based on the path flow data; a division module, used to perform hierarchical clustering on the plurality of intersections using density modularity as an objective function to obtain at least one target traffic sub-zone that maximizes the objective function, the density modularity being determined based on an average path association within the traffic sub-zone, a first ratio, and a second ratio, the first ratio being a ratio of a first sum of path associations within the traffic sub-zone to a second sum of path associations of the traffic area to be divided, the second ratio being a ratio of a cross-path association of the traffic sub-zone to the second sum, the cross-path association being a sum of path associations between the traffic sub-zone and other adjacent traffic sub-zones.

[0008] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is used to execute the steps of the method for dividing traffic sub-zones described in the first aspect above.

[0009] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the steps of the method for dividing traffic sub-zones described in the first aspect.

[0010] One of the above technical solutions has the following advantages or beneficial effects. It comprehensively considers the impact of different numbers of lanes in the intersection path and whether to turn on the path flow, accurately measures the coordination benefits between intersections, and at the same time, through hierarchical clustering with density modularity as the objective function, it can effectively avoid the defect of the traditional traffic sub-area division model that is easy to fall into the local optimal solution, and improve the accuracy of traffic sub-area division.

[0011] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0012] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 A schematic diagram showing a flow chart of a method for dividing traffic sub-areas provided in an embodiment of the present disclosure;

[0015] Figure 2 A schematic diagram showing traffic data of a lane-level path in the method for dividing a traffic sub-zone provided in an embodiment of the present disclosure;

[0016] Figure 3 Another schematic diagram showing a flow chart of a method for dividing traffic sub-areas provided in an embodiment of the present disclosure;

[0017] Figure 4 Another schematic diagram showing a flow chart of a method for dividing traffic sub-areas provided in an embodiment of the present disclosure;

[0018] Figure 5 A schematic diagram showing the division result of the traffic sub-areas provided by the embodiment of the present disclosure;

[0019] Figure 6 Another schematic diagram showing a flow chart of a method for dividing traffic sub-areas provided in an embodiment of the present disclosure;

[0020] Figure 7 Another schematic diagram showing a flow chart of a method for dividing traffic sub-areas provided in an embodiment of the present disclosure;

[0021] Figure 8 A block diagram showing a device for dividing traffic sub-areas provided in an embodiment of the present application is shown;

[0022] Fig. 9 A block diagram showing another device for dividing traffic sub-areas provided in an embodiment of the present application;

[0023] Fig.10 A schematic diagram of the hardware structure of an electronic device for executing the method for dividing traffic sub-zones provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the technical solutions in the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present disclosure.

[0025] Figure 1 A flow chart of a method for dividing traffic sub-areas provided by an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the method may include the following steps:

[0026] In step S101, the path flow data of the traffic area to be divided is obtained.

[0027] The path flow data includes flow data corresponding to a plurality of lane-level paths at the intersection of the traffic area to be divided.

[0028] Traffic flow data records the data of the entrance lanes and exit lanes of the intersections through which vehicles pass in chronological order.

[0029] Since the traffic data of adjacent intersections have a certain correlation, the signal control scheme of several adjacent intersections can be optimized as a whole to achieve regional coordination, which is called a traffic sub-zone or a traffic micro-sub-zone.

[0030] The Whitson model can be used to measure the correlation between two intersections. In the Whitson model, the lane flow between intersection j and intersection k is used as the corresponding flow data, that is, the overall lane flow in a certain direction of two adjacent intersections.

[0031] In this embodiment, path flow data may also be obtained, and the lane flow between intersection j and intersection k may be further subdivided into flow data corresponding to different lane-level paths.

[0032] Figure 2 A schematic diagram of traffic data of a lane-level path in the method for dividing a traffic sub-zone provided by an embodiment of the present disclosure is shown as follows: Figure 2 As shown, intersection j and intersection k are adjacent, and the intersection j to intersection k includes two upstream lanes, namely upstream lane 1 and upstream lane 2 (the figure does not show the upstream lane that turns right through intersection j to intersection k), and the corresponding lane-level path includes upstream lane 1 to lane 1, upstream lane 1 to lane 2, upstream lane 2 to lane 1, and upstream lane 2 to lane 2, a total of four lane-level paths, and the corresponding path flow data may include the path flow data corresponding to these four lane-level paths respectively .

[0033] It is understandable that the path flow data corresponding to the lane-level paths from intersection k to intersection j are different from the path flow data corresponding to the lane-level paths from intersection j to intersection k. When dividing traffic sub-areas, it is necessary to obtain the corresponding flow data of multiple lane-level paths of all adjacent intersections between the traffic sub-areas to be divided. By comprehensively considering the impact of different numbers of lanes in the intersection path and whether to turn on the path flow, the path flow data can accurately reflect the ability of spatiotemporal heterogeneity of flow, thereby accurately measuring the coordination benefits between intersections.

[0034] In step S102, the path association degrees respectively corresponding to the plurality of intersections in the traffic area to be divided are determined based on the path flow data.

[0035] In the embodiment of the present application, the correlation is used to measure the coordination efficiency between two intersections. The correlation is related to the distance between the intersections, the traffic volume, etc. There is a greater need to merge two adjacent intersections with a greater correlation into the same traffic sub-area.

[0036] The path correlation degree is the correlation degree between intersections determined according to the flow data corresponding to the lane-level paths between the above-mentioned intersections, and is used to more accurately measure the coordination benefit between the two intersections.

[0037] In step S103, the density modularity is used as the objective function to perform hierarchical clustering on multiple intersections to obtain at least one target traffic sub-area that maximizes the objective function.

[0038] Clustering algorithms are based on similarity, which makes the samples in a cluster have more similarities and the differences between different cluster families are larger. Hierarchical clustering is a type of clustering algorithm, which is a top-down splitting or bottom-up merging clustering algorithm.

[0039] Among them, the density modularity is determined based on the average path correlation, the first ratio and the second ratio in the traffic sub-area. The first ratio is the ratio of the first sum of the path correlations in the traffic sub-area to the second sum of the path correlations of the traffic area to be divided. The second ratio is the ratio of the cross-path correlation of the traffic sub-area to the second sum. The cross-path correlation is the sum of the path correlations between the traffic sub-area and other adjacent traffic sub-areas.

[0040] The hierarchical clustering algorithm attempts to divide the data set at different levels to form a tree-like clustering structure. The data set can be divided by a bottom-up merging strategy or a top-down splitting strategy. Taking the hierarchical clustering algorithm with a bottom-up merging strategy as an example, each intersection in the traffic area to be divided is first taken as an initial first traffic sub-area, and then in each step, two adjacent traffic sub-areas that can maximize the value of density modularity are found and merged, and this is repeated until the traffic area to be divided is merged into a preset number (for example, one) of traffic sub-areas, and at least one traffic sub-area corresponding to the traffic sub-area division scenario when the value of density modularity in the merged path is the largest is taken as at least one target traffic sub-area.

[0041] By adopting the above technical solution, the impact of different numbers of lanes in the intersection path and whether to turn on the path flow is comprehensively considered, and the coordination benefit between intersections is accurately measured. At the same time, by using density modularity as the objective function for hierarchical clustering, the defect of the traditional traffic sub-area division model that it is easy to fall into the local optimal solution can be effectively avoided, and the accuracy of traffic sub-area division can be improved.

[0042] Figure 3 Another flow chart of the method for dividing traffic sub-areas provided by the embodiment of the present disclosure is shown as follows: Figure 3 As shown, step S103 may include the following steps.

[0043] In step S1031, each intersection is taken as an initial first traffic sub-area.

[0044] In step S1032, two adjacent first traffic sub-areas that maximize the function value of the objective function after merging are determined, and the two adjacent first traffic sub-areas are merged into one second traffic sub-area.

[0045] In some embodiments, the function value of the objective function can be determined by the following formula 1.

[0046] (Formula 1)

[0047] Where DM is the density modularity, is the average path correlation within the ith traffic sub-area, is the first ratio corresponding to the i-th traffic sub-area (i.e., the ratio of the first sum of the path associations in the traffic sub-area to the second sum of the path associations in the traffic area to be divided), representing the coordination benefit of the traffic sub-area i, is the second ratio corresponding to the ith traffic sub-area (the ratio of the cross-path correlation of the traffic sub-area to the second sum, where the cross-path correlation is the sum of the path correlations between the traffic sub-area and other adjacent traffic sub-areas), p and q are the numbers of the intersections, respectively, and N is the set of all intersections, i.e., the set includes N intersections. is the path association between intersection p and intersection q, is the number of intersections in the i-th traffic sub-area.

[0048] In some possible implementations, M1 adjacent intersection combinations (not ), calculate M1 density modularities according to formula 1 respectively, determine the intersection combination corresponding to the largest density modularity from the M1 density modularities, and merge two adjacent intersections in the intersection combination into a second traffic sub-area.

[0049] In step S1033, the second traffic sub-area and the remaining first traffic sub-areas are taken as new first traffic sub-areas, and the steps of determining two adjacent first traffic sub-areas that maximize the objective function after merging are repeated, and merging the two adjacent first traffic sub-areas into one second traffic sub-area are repeated until the traffic areas to be divided are merged into one traffic sub-area.

[0050] In some possible implementations, one second traffic sub-area and the remaining N-2 first traffic sub-areas are used as new N-1 first traffic sub-areas, M2 adjacent intersection combinations are determined from the N-1 new first traffic sub-areas, M2 density modularities are calculated respectively, the intersection combination corresponding to the largest density modularity is determined from the M2 density modularities, and two adjacent intersections corresponding to the intersection combination are merged into a second traffic sub-area to obtain a new N-2 traffic sub-area. This process is repeated until the traffic areas to be divided are merged into one traffic sub-area.

[0051] In step S1034, at least one traffic sub-area corresponding to the traffic sub-area division scenario when the function value of the objective function in the clustering process is the maximum is used as at least one target traffic sub-area.

[0052] Assuming that step S1032 and step S1033 include K merging steps in total, they may include K density modularity function values ​​corresponding to each merging step, and each density modularity function value is the density modularity function value after the corresponding merging step is executed. The maximum function value may be determined from the K density modularity function values, and at least one traffic sub-area corresponding to the traffic sub-area division scenario when the density modularity has the maximum function value in the clustering process is used as at least one target traffic sub-area.

[0053] It is understandable that a top-down splitting strategy may also be adopted for hierarchical clustering, and this application does not impose any limitation on this. The specific steps are similar to the above steps and will not be elaborated on.

[0054] By adopting the above technical solution, the impact of different numbers of lanes in the intersection path and whether to turn on the path flow is comprehensively considered, and the coordination benefit between intersections is accurately measured. At the same time, by using density modularity as the objective function for hierarchical clustering, the defect of the traditional traffic sub-area division model that it is easy to fall into the local optimal solution can be effectively avoided, and the accuracy of traffic sub-area division can be improved.

[0055] In actual scenarios, path flow data may be lost due to various reasons, such as the reason for the collection of flow data by the flow data device, or the vehicle may enter a parking lot, a community, or park for a long time on the road between intersection j and intersection k, resulting in the vehicle not being detected in the upstream lane of intersection k within a preset time, thereby causing the path flow data to be missing. The missing path flow data will have a certain impact on the accuracy of the traffic sub-area division. In order to solve the above technical problems, in some embodiments, different methods for determining the path correlation can be flexibly adopted based on the path flow missing rate.

[0056] Figure 4 Another flow chart of the method for dividing traffic sub-areas provided by the embodiment of the present disclosure is shown as follows: Figure 4 As shown, step S102 may include the following steps:

[0057] In step S1021 , a path flow missing rate between the first intersection and the second intersection is determined according to the path flow data.

[0058] The first intersection and the second intersection are any two adjacent intersections among the multiple intersections.

[0059] The path flow missing rate between the first intersection and the second intersection may be determined using the path flow data corresponding to the first intersection and the second intersection, respectively.

[0060] In step S1022 , when the path flow missing rate is greater than or equal to a preset missing rate threshold, the path association between the first intersection and the second intersection is determined by using the Whitson model.

[0061] In some possible implementations, the path association between the first intersection and the second intersection may be determined by the Whitson model using the following formula 2.

[0062] (Formula 2)

[0063] in, is the association degree determined by the Whitson model from intersection j to intersection k, is the lane flow from intersection j to intersection k, M is the number of lanes on the road section from intersection j to intersection k, L is the path length between intersection j and intersection k, is the path association between intersection j and intersection k, .

[0064] In step S1023, when the path flow missing rate is less than a preset missing rate threshold, the path association between the first intersection and the second intersection is determined based on the path flow of the lane-level path between the first intersection and the second intersection, and the path length between the first intersection and the second intersection.

[0065] In some embodiments, the path relevance may be determined specifically through the following steps.

[0066] In step 10, the first path association is determined according to the first path flow and path length from the first intersection to the second intersection, and the first path flow is the maximum flow data among the flow data corresponding to multiple lane-level paths from the first intersection to the second intersection.

[0067] In some possible implementations, the first path relevance may be determined by the following formula three.

[0068] (Formula 3)

[0069] in, is the path flow set from intersection j to intersection k, is the path flow corresponding to the lane-level path from the upstream lane s to the target lane d, S is the set of upstream lanes from intersection j to intersection k, and D is the set of lanes from intersection j to intersection k. Figure 2 middle, Right now L is the path length between intersection j and intersection k.

[0070] In step 11, the second path association is determined according to the second path flow and path length from the second intersection to the first intersection, and the second path flow is the maximum flow data among the flow data corresponding to multiple lane-level paths from the second intersection to the first intersection.

[0071] The method for determining the second path relevance is similar to the method for determining the first path relevance, and will not be described in detail.

[0072] In step 12, the larger one of the first path association degree and the second path association degree is used as the path association degree between the first intersection and the second intersection.

[0073] In some possible implementations, the path relevance may be determined by the following formula 4.

[0074] (Formula 4)

[0075] in, is the path association between intersection j and intersection k, .

[0076] By adopting the above technical solution, different methods for determining the path correlation can be flexibly adopted according to the path flow missing rate. When measuring the coordination benefits between intersections, the adverse effects of path flow missing can be reduced or eliminated, thereby further improving the accuracy of traffic sub-area division.

[0077] The characteristics of the path flow data in different time periods may be significantly different. For example, the characteristics of the path flow data during the morning peak, off-peak and evening peak may be quite different. In addition, the characteristics of the path flow data during the week and weekends may also be quite different.

[0078] In some embodiments, according to the target time period of the traffic sub-area to be divided, the path flow data of the traffic area to be divided corresponding to the target time period is obtained.

[0079] The method of dividing the target time period can be flexibly set based on needs. For example, the path flow data of the traffic area to be divided corresponding to the target time period can be obtained based on the target time periods during the morning peak, off-peak and evening peak. The target time period can also be determined based on weekdays and holidays to obtain the path flow data of the traffic area to be divided corresponding to weekdays and holidays. The target time period can also be determined based on the combination of weekdays and holidays, as well as the peak and off-peak periods within a day, to obtain the path flow data of the traffic area to be divided within the corresponding target time period.

[0080] The target time periods corresponding to different traffic areas to be divided may be the same or different, and the final division results of traffic sub-areas in different target time periods may be the same or different.

[0081] Figure 5 A schematic diagram showing the division result of the traffic sub-area provided by the embodiment of the present disclosure (the division result is not completely circled), as shown in FIG. Figure 5 As shown, in different target time periods, the traffic sub-area division method provided in this embodiment can obtain different division results, thereby being able to adapt to the characteristics of path flow data in different target time periods.

[0082] By adopting the above technical solution, the path flow data within different target time periods can be obtained according to different target time periods, and then the division results of traffic sub-areas corresponding to different target time periods can be obtained, further improving the applicability of the traffic sub-area division method.

[0083] Figure 6 Another flow chart of the method for dividing traffic sub-areas provided by the embodiment of the present disclosure is shown as follows: Figure 6 As shown, the method may further include the following steps.

[0084] In step S104, a sub-interval correlation matrix and an intra-sub-region correlation matrix are constructed according to the adjacent relationships and path correlations among the plurality of intersections.

[0085] The sub-interval correlation matrix can characterize whether any two intersections are adjacent intersections between different sub-intervals, and the corresponding path correlation. The intra-sub-interval correlation matrix can characterize whether any two intersections are adjacent intersections within the same sub-interval, and the corresponding path correlation. After constructing the sub-interval correlation matrix and the intra-sub-interval correlation matrix, the value of the objective function can be determined according to the sub-interval correlation matrix and the intra-sub-interval correlation matrix in the subsequent step S103, which can greatly reduce the amount of calculation of the value of the objective function. The specific steps of calculating according to the sub-interval correlation matrix and the intra-sub-interval correlation matrix can refer to the knowledge of matrix operations, and will not be elaborated.

[0086] Among them, the dimensions of the sub-interval correlation matrix and the intra-sub-region correlation matrix are , N is the number of intersections. When the sub-intervals are adjacent, the values ​​of the elements of the sub-interval association matrix for intersections of adjacent sections of the sub-interval are the path associations between the intersections of adjacent sections, and the values ​​of the elements of the sub-interval association matrix for other intersections (i.e., intersections that are not adjacent sections of the sub-interval, and non-adjacent intersections) are the first preset values. When the adjacent intersections belong to the same sub-area, the values ​​of the elements of the association matrix within the sub-area are the path associations between the adjacent intersections within the sub-area, and the values ​​of the elements of the association matrix for other intersections (i.e., intersections of adjacent sections of the sub-interval, and non-adjacent intersections) within the sub-area are the second preset values.

[0087] Preferably, the first preset value and the second preset value may be 0.

[0088] By adopting the above technical solution, the accuracy of traffic sub-area division can be improved, the calculation amount of traffic sub-network division can be further reduced through matrix operation, and the efficiency of traffic sub-network division can be further improved.

[0089] Figure 7Another flow chart of the method for dividing traffic sub-areas provided by the embodiment of the present disclosure is shown as follows: Figure 7 As shown, the method may further include the following steps.

[0090] In step S105, an inter-subarea adjacency matrix and an intra-subarea adjacency matrix are constructed according to the adjacency relations between the plurality of intersections.

[0091] The sub-interval adjacency matrix can characterize whether any two intersections are adjacent intersections of adjacent traffic sub-intervals, and the intra-sub-area adjacency matrix can characterize whether any two intersections are adjacent intersections in the same traffic sub-area. After constructing the sub-interval correlation matrix, the intra-sub-area correlation matrix, and the sub-interval correlation matrix and the intra-sub-area correlation matrix, the value of the objective function can be determined in the subsequent step S103 according to the sub-interval correlation matrix, the intra-sub-area correlation matrix, and the sub-interval correlation matrix and the intra-sub-area correlation matrix, which can greatly reduce the amount of calculation of the value of the objective function. The specific steps of calculating according to the sub-interval correlation matrix and the intra-sub-area correlation matrix can refer to the knowledge of matrix operations, and will not be elaborated.

[0092] The dimensions of the sub-interval adjacency matrix and the intra-sub-region adjacency matrix are In the case where the sub-intervals are adjacent, the values ​​of the elements of the sub-interval adjacency matrix at the intersections of the adjacent sections of the sub-interval are the third preset values, and the values ​​of the elements of the sub-interval adjacency matrix at other intersections (i.e., intersections that are not adjacent sections of the sub-interval and non-adjacent intersections) are the fourth preset values; in the case where adjacent intersections belong to the same sub-area, the values ​​of the elements of the adjacency matrix within the sub-area are the fifth preset values, and the values ​​of the elements of the adjacency matrix at other intersections (i.e., intersections of adjacent sections of the sub-interval and non-adjacent intersections) are the sixth preset values.

[0093] Preferably, the third preset value and the fifth preset value may be 1, and the fourth preset value and the sixth preset value may be 0.

[0094] By adopting the above technical solution, the accuracy of traffic sub-area division can be improved, the calculation amount of traffic sub-network division can be further reduced through matrix operation, and the efficiency of traffic sub-network division can be further improved.

[0095] Figure 8 A block diagram of a traffic sub-area division device provided in an embodiment of the present application is shown. Figure 8 As shown, the traffic sub-area division device 100 includes:

[0096] An acquisition module 110 is used to acquire path flow data of the traffic area to be divided, wherein the path flow data includes flow data corresponding to a plurality of lane-level paths at the intersection of the traffic area to be divided;

[0097] A determination module 120, configured to determine the path associations respectively corresponding to the plurality of intersections in the traffic area to be divided based on the path flow data;

[0098] The division module 130 is used to perform hierarchical clustering on the multiple intersections with density modularity as the objective function to obtain at least one target traffic sub-area that maximizes the objective function, wherein the density modularity is determined based on the average path association within the traffic sub-area, a first ratio, and a second ratio, wherein the first ratio is the ratio of a first sum of path associations within the traffic sub-area to a second sum of path associations of the traffic area to be divided, and the second ratio is the ratio of a cross-path association of the traffic sub-area to the second sum, wherein the cross-path association is the sum of path associations between the traffic sub-area and other adjacent traffic sub-areas.

[0099] Optionally, the division module 130 is further configured to:

[0100] Take each intersection as the initial first traffic sub-area;

[0101] Determine two adjacent first traffic sub-areas that maximize the function value of the objective function after merging, and merge the two adjacent first traffic sub-areas into one second traffic sub-area;

[0102] The second traffic sub-area and the remaining first traffic sub-areas are used as new first traffic sub-areas, and the steps of determining two adjacent first traffic sub-areas that maximize the objective function after merging are repeated, and merging the two adjacent first traffic sub-areas into one second traffic sub-area are repeated until the traffic area to be divided is merged into one sub-area;

[0103] At least one traffic sub-area corresponding to the traffic sub-area division scenario when the function value of the objective function is the maximum in the clustering process is used as at least one target traffic sub-area.

[0104] Optionally, the determination module 120 is further configured to:

[0105] Determine a path flow missing rate between a first intersection and a second intersection according to the path flow data, where the first intersection and the second intersection are any two adjacent intersections among the plurality of intersections;

[0106] When the path flow missing rate is greater than or equal to a preset missing rate threshold, the path association between the first intersection and the second intersection is determined by the Whitson model; or,

[0107] When the path flow missing rate is less than a preset missing rate threshold, the path association between the first intersection and the second intersection is determined according to the path flow of the lane-level path between the first intersection and the second intersection and the path length between the first intersection and the second intersection.

[0108] Optionally, the determination module 120 is further configured to:

[0109] Determine a first path association degree according to a first path flow and a path length from the first intersection to the second intersection, wherein the first path flow is the largest flow data among flow data corresponding to a plurality of lane-level paths from the first intersection to the second intersection;

[0110] Determine the second path association degree according to the second path flow and path length from the second intersection to the first intersection, the second path flow is the maximum flow data among the flow data corresponding to the multiple lane-level paths from the second intersection to the first intersection;

[0111] The larger one of the first path association degree and the second path association degree is used as the path association degree between the first intersection and the second intersection.

[0112] Optionally, the acquisition module 110 is further configured to:

[0113] According to the target time period of the traffic sub-area to be divided, the path flow data of the traffic area to be divided corresponding to the target time period is obtained.

[0114] The device 100 provided in the embodiment of the present application can execute each method in the foregoing method embodiment and realize the functions and beneficial effects of each method in the foregoing method embodiment, which will not be described in detail here.

[0115] Fig. 9 A block diagram of another traffic sub-area division device provided in an embodiment of the present application is shown. Fig. 9 As shown, the traffic sub-area division device 100 further includes a construction module 140 for:

[0116] According to the adjacent relationship and path correlation between multiple intersections, a sub-interval correlation matrix and an intra-sub-area correlation matrix are constructed;

[0117] Among them, the dimensions of the sub-interval correlation matrix and the intra-sub-region correlation matrix are , N is the number of intersections. When the sub-intervals are adjacent, the values ​​of the elements of the sub-interval association matrix of the intersections of adjacent sections of the sub-interval are the path associations between the intersections of the adjacent sections, and the values ​​of the elements of the sub-interval association matrix of other intersections are the first preset values. When the adjacent intersections belong to the same sub-area, the values ​​of the elements of the association matrix within the sub-area are the path associations between the adjacent intersections within the sub-area, and the values ​​of the elements of the association matrix of other intersections within the sub-area are the second preset values.

[0118] Optionally, the construction module 140 is further configured to:

[0119] According to the adjacency relationship between multiple intersections, a sub-area adjacency matrix and an intra-sub-area adjacency matrix are constructed;

[0120] The dimensions of the sub-interval adjacency matrix and the intra-sub-region adjacency matrix are When the sub-intervals are adjacent, the values ​​of the elements of the sub-interval adjacency matrix at the intersections of the adjacent road sections of the sub-interval are the third preset values, and the values ​​of the elements of the sub-interval adjacency matrix at other intersections are the fourth preset values; when the adjacent intersections belong to the same sub-area, the values ​​of the elements of the adjacency matrix within the sub-area are the fifth preset values, and the values ​​of the elements of the adjacency matrix at other intersections within the sub-area are the sixth preset values.

[0121] The device 100 provided in the embodiment of the present application can execute each method in the foregoing method embodiment and realize the functions and beneficial effects of each method in the foregoing method embodiment, which will not be described in detail here.

[0122] Fig.10 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present disclosure is shown. Fig.10 As shown, at the hardware level, the electronic device includes at least one processor, and optionally includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0123] The processor, network interface and memory can be interconnected through an internal bus, which can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0124] The memory stores the program. Specifically, the program may include a program code, and the program code includes at least one computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0125] At least one processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for locating the target user at the logical level. At least one processor executes the program stored in the memory and specifically performs: the method disclosed in the embodiment shown in the first aspect and realizes the functions and beneficial effects of each method described in the method embodiment above, which will not be repeated here.

[0126] The method disclosed in the embodiment shown in the first aspect of the present disclosure can be applied to at least one processor or implemented by at least one processor. The processor may have the ability to process signals. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware or software instructions in at least one processor. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0127] The electronic device can also execute the methods described in the foregoing method embodiments, and realize the functions and beneficial effects of the methods described in the foregoing method embodiments, which will not be repeated here.

[0128] Of course, in addition to software implementation, the electronic device disclosed in the present invention does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0129] The embodiments of the present disclosure also propose a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by at least one processor, they implement the method disclosed in the embodiment shown in the first aspect and realize the functions and beneficial effects of the various methods described in the previous method embodiments, which will not be repeated here.

[0130] The computer-readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0131] Furthermore, the embodiments of the present disclosure also provide a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the following process is implemented: the method disclosed in the embodiment shown in the first aspect and the functions and beneficial effects of the various methods described in the previous method embodiments are implemented, which will not be repeated here.

[0132] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the various processes of the method disclosed in the embodiment shown in the first aspect and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0133] In short, the above is only a preferred embodiment of the present disclosure and does not limit the protection scope of the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

[0134] The systems, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0135] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0136] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0137] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

Claims

1. A method for dividing traffic sub-areas, characterized in that: The method comprises: Acquire path flow data of the traffic area to be divided, wherein the path flow data includes flow data corresponding to a plurality of lane-level paths at the intersection of the traffic area to be divided; Determine the path association degrees respectively corresponding to the plurality of intersections in the traffic area to be divided based on the path flow data; Taking density modularity as an objective function, hierarchical clustering is performed on the multiple intersections to obtain at least one target traffic sub-area that maximizes the objective function, wherein the density modularity is determined according to an average path association within the traffic sub-area, a first ratio, and a second ratio, wherein the first ratio is a ratio of a first sum of path associations within the traffic sub-area to a second sum of path associations of the traffic area to be divided, and the second ratio is a ratio of a cross-path association of the traffic sub-area to the second sum, wherein the cross-path association is a sum of path associations between the traffic sub-area and other adjacent traffic sub-areas; The determining, based on the path flow data, the path associations respectively corresponding to the plurality of intersections in the traffic area to be divided comprises: Determine a first path association degree according to a first path flow from a first intersection to a second intersection and the path length, wherein the first path flow is the maximum flow data among the flow data corresponding to a plurality of lane-level paths from the first intersection to the second intersection, and the first intersection and the second intersection are any two adjacent intersections among the plurality of intersections; Determine a second path association degree according to a second path flow from the second intersection to the first intersection and the path length, wherein the second path flow is the largest flow data among the flow data corresponding to a plurality of lane-level paths from the second intersection to the first intersection; The larger one of the first path association degree and the second path association degree is used as the path association degree between the first intersection and the second intersection.

2. The method according to claim 1, characterized in that The method of performing hierarchical clustering on the plurality of intersections using density modularity as an objective function to obtain at least one target traffic sub-area that maximizes the objective function includes: Take each intersection as the initial first traffic sub-area; determining two adjacent first traffic sub-areas that maximize the function value of the objective function after merging, and merging the two adjacent first traffic sub-areas into one second traffic sub-area; The second traffic sub-area and the remaining first traffic sub-areas are used as new first traffic sub-areas, and the steps of repeatedly determining two adjacent first traffic sub-areas that maximize the objective function after merging, and merging the two adjacent first traffic sub-areas into one second traffic sub-area are repeated until the traffic area to be divided is merged into one traffic sub-area; At least one traffic sub-area corresponding to the traffic sub-area division scenario when the function value of the objective function is the maximum during the clustering process is used as the at least one target traffic sub-area.

3. The method according to claim 1, characterized in that The determining, based on the path flow data, the path associations respectively corresponding to the plurality of intersections in the traffic area to be divided comprises: Determining a path flow missing rate between a first intersection and a second intersection according to the path flow data; In the case where the path flow loss rate is greater than or equal to a preset loss rate threshold, determining the path association between the first intersection and the second intersection by using a Whitson model; or, When the path flow loss rate is less than a preset loss rate threshold, a first path association is determined according to the first path flow and the path length from the first intersection to the second intersection; a second path association is determined according to the second path flow and the path length from the second intersection to the first intersection; and the larger of the first path association and the second path association is used as the path association between the first intersection and the second intersection.

4. The method according to claim 1, characterized in that: The step of obtaining the path flow data of the traffic area to be divided includes: According to the target time period of the traffic sub-area to be divided, the path flow data of the traffic area to be divided corresponding to the target time period is obtained.

5. The method according to any one of claims 1 to 4, characterized in that After determining the path associations respectively corresponding to the plurality of intersections in the traffic area to be divided based on the path flow data, the method further includes: Constructing a sub-area correlation matrix and an intra-sub-area correlation matrix according to the adjacent relationships between the plurality of intersections and the path correlation; The dimensions of the sub-interval correlation matrix and the intra-sub-region correlation matrix are , N is the number of intersections. When the sub-intervals are adjacent, the values ​​of the elements of the sub-interval association matrix for intersections of adjacent sections of the sub-interval are the path associations between the intersections of the adjacent sections, and the values ​​of the elements of the sub-interval association matrix for other intersections are the first preset values. When the adjacent intersections belong to the same sub-area, the values ​​of the elements of the association matrix within the sub-area are the path associations between the adjacent intersections within the sub-area, and the values ​​of the elements of the association matrix for other intersections within the sub-area are the second preset values.

6. The method according to claim 5, characterized in that The method further comprises: Constructing an inter-subarea adjacency matrix and an intra-subarea adjacency matrix according to the adjacency relations between the plurality of intersections; The dimensions of the sub-interval adjacency matrix and the intra-sub-region adjacency matrix are both When the sub-intervals are adjacent, the values ​​of the elements of the adjacency matrix of the intersections of the adjacent road sections of the sub-intervals are the third preset values, and the values ​​of the elements of the adjacency matrix of the other intersections are the fourth preset values; when the adjacent intersections belong to the same sub-area, the values ​​of the elements of the adjacency matrix in the sub-area are the fifth preset values, and the values ​​of the elements of the adjacency matrix of the other intersections in the sub-area are the sixth preset values.

7. A device for dividing traffic sub-areas, characterized in that: The device comprises: An acquisition module, used to acquire path flow data of the traffic area to be divided, wherein the path flow data includes flow data corresponding to a plurality of lane-level paths at the intersection of the traffic area to be divided; A determination module, used for determining the path association degrees respectively corresponding to the plurality of intersections in the traffic area to be divided based on the path flow data; A partitioning module, for performing hierarchical clustering on the plurality of intersections with density modularity as an objective function to obtain at least one target traffic sub-area that maximizes the objective function, wherein the density modularity is determined based on an average path association within the traffic sub-area, a first ratio, and a second ratio, wherein the first ratio is a ratio of a first sum of path associations within the traffic sub-area to a second sum of path associations of the traffic area to be partitioned, and the second ratio is a ratio of a cross-path association of the traffic sub-area to the second sum, wherein the cross-path association is a sum of path associations between the traffic sub-area and other adjacent traffic sub-areas; The determining module is further used for: Determine a first path association degree according to a first path flow from a first intersection to a second intersection and the path length, wherein the first path flow is the maximum flow data among the flow data corresponding to a plurality of lane-level paths from the first intersection to the second intersection, and the first intersection and the second intersection are any two adjacent intersections among the plurality of intersections; Determine a second path association degree according to a second path flow from the second intersection to the first intersection and the path length, wherein the second path flow is the largest flow data among the flow data corresponding to a plurality of lane-level paths from the second intersection to the first intersection; The larger one of the first path association degree and the second path association degree is used as the path association degree between the first intersection and the second intersection.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method for dividing traffic sub-zones according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for dividing traffic sub-zones according to any one of claims 1 to 6 is implemented.

Images