Crowdsourcing data segmentation method, system, electronic device and storage medium

Abstract

The present invention provides a crowdsourcing data segmentation method, system, electronic device and storage medium, the method comprising: constructing a vehicle track segment connectivity index and a zebra crossing connectivity index respectively; constructing a zebra crossing connectivity graph and a track connectivity graph based on NetworkX; adding the first and last nodes of each group of edges as task indexes to a segmentation index set, searching for a node set containing the first and last nodes in the track connectivity graph according to the task index, searching for a connected path corresponding to the node set in the track connectivity graph, obtaining all corresponding track data according to the nodes in the connected path, and traversing the segmentation index set to obtain the data after crowdsourcing data segmentation. Thus, data segmentation efficiency can be improved, labor and time consumption can be reduced, and segmentation accuracy can be guaranteed.

Description

Technical Field

[0001] The present invention belongs to the field of high-precision map production, and in particular relates to a crowdsourcing data segmentation method, system, electronic device and storage medium. Background Art

[0002] In the field of autonomous driving, accurate control of vehicle driving often requires the drawing of high-precision maps. By widely deploying low-cost crowdsourcing collection vehicles, high-quality data can be collected at a high frequency to increase the update frequency of high-precision maps. The amount of data collected by crowdsourcing is usually very large, requiring data segmentation and multi-node distributed processing.

[0003] However, the current segmentation of crowdsourcing trajectory data often requires manual participation. When segmenting trajectory data based on zebra crossings, it is necessary to manually mark the zebra crossing positions and then automatically segment them. At the same time, there will be errors and duplications in the segmented data, which also require manual screening. Due to the large amount of crowdsourcing data, the efficiency of segmentation using this method is low. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a crowdsourcing data segmentation method, system, electronic device and storage medium, which are used to solve the problem of low efficiency of existing segmentation methods.

[0005] In a first aspect of an embodiment of the present invention, a crowdsourcing data segmentation method is provided, comprising:

[0006] Based on the vehicle trajectory data collected by crowdsourcing, a vehicle trajectory segment connectivity index is constructed;

[0007] According to the zebra crossing information passed by each trajectory in the trajectory segment connectivity index, a zebra crossing connectivity index is constructed;

[0008] Create a first empty graph based on networkx, add the zebra crossings in the zebra crossing connectivity index set as nodes to the first empty graph, and add edges and edge attributes to adjacent nodes to obtain a zebra crossing connectivity graph;

[0009] Create a second empty graph based on networkx, add the trajectory points of the zebra crossing observed as nodes to the second empty graph, and add node attributes and edges to obtain a trajectory connectivity graph;

[0010] After filtering the edges in the zebra crossing connectivity graph, add the first and last nodes of each group of edges as task indexes to the split index set;

[0011] According to the task index, the node set containing the first and last nodes in the trajectory connectivity graph is searched, and the connected path corresponding to the node set is searched in the trajectory connectivity graph. According to the nodes in the connected path, all corresponding trajectory data are obtained, and the segmentation index set is traversed to obtain the data after the crowdsourcing data is segmented.

[0012] In a second aspect of an embodiment of the present invention, a crowdsourcing data segmentation system is provided, including:

[0013] The first construction module is used to construct a vehicle trajectory segment connectivity index based on the vehicle trajectory data collected by crowdsourcing;

[0014] The second construction module is used to construct a zebra crossing connectivity index according to the zebra crossing information passed by each trajectory segment in the trajectory segment connectivity index;

[0015] A zebra crossing connectivity graph construction module is used to create a first empty graph based on networkx, add zebra crossings in the zebra crossing connectivity index set as nodes to the first empty graph, and add edges and edge attributes to adjacent nodes to obtain a zebra crossing connectivity graph;

[0016] A trajectory connectivity graph construction module is used to create a second empty graph based on networkx, add the trajectory points observed at the zebra crossing as nodes to the second empty graph, and add node attributes and edges to obtain a trajectory connectivity graph;

[0017] Construct a split index module to filter the edges in the zebra crossing connectivity graph and add the first and last nodes of each group of edges as task indexes to the split index set;

[0018] The traversal and segmentation module is used to search for the node set containing the head and tail nodes in the trajectory connectivity graph according to the task index, and to search for the connected path corresponding to the node set in the trajectory connectivity graph. According to the nodes in the connected path, all corresponding trajectory data are obtained, and the segmentation index set is traversed to obtain the data after the crowdsourcing data is segmented.

[0019] In a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect of the embodiment of the present invention when executing the computer program.

[0020] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiment of the present invention are implemented.

[0021] In an embodiment of the present invention, by constructing a trajectory segment connectivity index and a zebra crossing connectivity index respectively, the data is converted into a corresponding connectivity graph, and a retrieval calculation is performed based on the connectivity graph to find connectivity paths, nodes and corresponding trajectory data. Crowdsourcing data segmentation is achieved through segmentation indexes, which can effectively improve data segmentation efficiency, ensure segmentation accuracy, reduce manpower and time consumption, and reduce segmentation calculation amount. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic diagram of a flow chart of a crowdsourcing data segmentation method provided by an embodiment of the present invention;

[0024] Figure 2 A schematic diagram of the structure of a crowdsourcing data segmentation system provided by one embodiment of the present invention;

[0025] Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be understood that the term "including" and other similar expressions in the specification or claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, such as a process, method, system, or device including a series of steps or units is not limited to the listed steps or units. In addition, "first" and "second" are used to distinguish different objects, not to describe a specific order.

[0028] See also Figure 1 , a flow chart of a crowdsourcing data segmentation method provided by an embodiment of the present invention includes:

[0029] S101, constructing a vehicle trajectory segment connectivity index based on the vehicle trajectory data collected by crowdsourcing;

[0030] The trajectory data is collected by crowdsourcing vehicles, and each vehicle uploads the collected data once at a certain interval. The uploaded data contains information such as timestamp and vehicle number. The vehicle trajectory data generally includes the trajectory points of the vehicle and the corresponding road test data. In this embodiment, the connectivity index of the trajectory segment is constructed according to the driving trajectory of each vehicle.

[0031] Specifically, the trajectory data of the crowdsourced vehicle is sorted by collection time, and the trajectory segments in which the collection time difference between the starting trajectory point and the ending trajectory point is greater than a predetermined threshold are split to obtain the trajectory segment connectivity index of the crowdsourced vehicle.

[0032] For example, ① When a crowdsourcing car collects data, it packages and uploads the data collected within a certain time interval. Each packaged data uses the vehicle number and the timestamp converted when the package was made. The two are added together to form a new number to mark the batch of data, which is referred to as the collection number N;

[0033] ② Take all the collected trajectory point data of a vehicle and sort them in chronological order to form multiple time-sequenced trajectory segments;

[0034] ③ Calculate N in sequence a The timestamp of the last track point and N a-1 The difference Δt of the timestamp of the first trajectory point. b With N b-1 If Δt is greater than a certain threshold, Split into and If there is still a Δt greater than the threshold, Continue to split into And so on;

[0035] ④ Process the trajectory point data of each vehicle according to the above process, and when the vehicle is replaced and re-executed, The value of a is the last segment of the trajectory obtained by the last split in ③. The b value of the vehicle is increased by one, that is, a = b + 1. After all vehicles are processed, the trajectory segment connection index set of all vehicles is obtained.

[0036] S102, constructing a zebra crossing connectivity index according to the zebra crossing information passed by each trajectory segment in the trajectory segment connectivity index;

[0037] The crowdsourced vehicle driving trajectory can be segmented based on zebra crossings. By obtaining the trajectory points passing through the zebra crossings, a data set of zebra crossing information is formed, and then a connectivity index of multiple zebra crossings is constructed.

[0038] Specifically, based on the trajectory points in the trajectory segment connectivity index, a data set of all zebra crossings is obtained; the zebra crossing data set is sorted according to the zebra crossing collection observation time to obtain a connected sequence set of zebra crossing data, and the zebra crossing information is replaced with the zebra crossing number with the same name to obtain a zebra crossing connectivity index set.

[0039] For example, (1) take T According to the collection number N, all zebra crossing information data sets P after the same name information is identified are taken out, that is, all zebra crossing collection data corresponding to the same zebra crossing in the real world are marked with a unified same name number. Each zebra crossing in the real world has a unique same name number, recorded as PS, and each collected zebra crossing collection data corresponds to the observation collection time obs_time;

[0040] (2) Sort all the data in P according to the order of obs_time to obtain the connected sequence set C = {P1, P2, P3...P n}, each P corresponds to a PS value, namely P n :PS, replace the data P in C with the corresponding PS value, and then get the connected index set CS of the zebra crossing with the same name = {PS1, PS2, PS3...PS n}, there may be repeated PS values ​​in CS, and the subscripts 1, 2, 3...n have no increasing relationship.

[0041] (3) All data in T are processed according to the above steps to obtain the connected index set CW of multi-car multi-zebra crossing information = {CS1, CS2, CS3...CS n}

[0042] S103, creating a first empty graph based on networkx, adding the zebra crossing in the zebra crossing connectivity index set as a node to the first empty graph, and adding edges and edge attributes to adjacent nodes to obtain a zebra crossing connectivity graph;

[0043] Networkx is a software package written in Python that can be used to create, manipulate and learn complex network structures. Based on networkx, you can store networks in standardized and non-standardized data formats, generate a variety of random networks and classical networks, analyze network structures, build network models, design new network algorithms, and draw networks.

[0044] Based on the zebra crossing connectivity index, a zebra crossing connectivity graph is constructed to facilitate segmentation of candidate pair trajectories. In the zebra crossing connectivity graph, nodes are represented by zebra crossings, and edges represent connectivity relationships between nodes.

[0045] Specifically, the zebra crossings in the zebra crossing connectivity index set are added as node points to the first empty graph, and duplicate nodes are automatically merged based on networkx; edges that do not belong to the added edge set are added to the first empty graph; the Euclidean distance of the average value coordinates of the zebra crossing point coordinates of adjacent nodes on the edge is marked, and the Euclidean distance is used as the edge attribute.

[0046] For example, (1) use networkx to initialize an empty graph G, and denote PHE as the set of edges that have been added, PHE = {};

[0047] (2) Take CS in CW = {PS1, PS2, PS3...PS n}Data set. According to the arrangement order of PS in CS, traverse each PS, record the subscript of the currently selected PS as m, and perform the following operations in sequence:

[0048] a1. Add node PS to G m , networkx will automatically merge duplicate nodes;

[0049] a2. If m>1, and (PS m-1 ,PS m ) edge is not in PHE, then G adds an edge (PS m-1 ,PS m ), add edge in PHE (PS m-1 ,PS m );

[0050] a3. If the edge is added successfully, calculate all edges marked as PS m-1 The average coordinates of the zebra line points and all the coordinates are marked as Pm m The mean value of the coordinates of the zebra line point is the Euclidean distance D m , add the corresponding edge attribute d=D in the graph m ;

[0051] (3) After performing the above operations on all CSs in the CW set, the graph G obtained is the connected graph of all zebra crossings with the same name.

[0052] S104, creating a second empty graph based on networkx, adding the trajectory points observed at the zebra crossing as nodes to the second empty graph, and adding node attributes and edges to obtain a trajectory connected graph;

[0053] It can be understood that the first empty graph and the second empty graph are only used to distinguish different graphs created based on networkx. The second empty graph is used to construct a trajectory connectivity graph.

[0054] In the trajectory connectivity graph, the nodes are the trajectory points where zebra crossings are observed, the node attributes are the zebra crossing numbers, and the edges represent the connectivity relationships between nodes.

[0055] For example, (1) use networkx to initialize an empty graph Q, and let THE be the set of edges that have been added, THE = {};

[0056] (2) Take T Data collection. The order of N in the traversal, traverse each N, and record the subscript of the currently selected N as v:

[0057] a1. Add node N to Q v , N v All observed zebra crossing numbers with the same name are recorded as set ID, and the node attribute id = ID is added. If ID is an empty set, id = [];

[0058] a2. If v>1, and (N v-1 ,N v ) edge is not in THE, then Q adds an edge (N v-1 ,N v ), add edge (N v-1 ,N v );

[0059] (3) For all The graph Q obtained after the above operation is the trajectory connection graph of all zebra crossings with the same name.

[0060] S105, after filtering the edges in the zebra crossing connectivity graph, add the first and last nodes of each group of edges as task indexes to the segmentation index set;

[0061] Specifically, all edges and edge attributes in the zebra crossing connectivity graph are obtained, edges whose edge attribute values ​​are less than a predetermined value are deleted, and the remaining edges are sorted according to the attribute values; the sorted edges are traversed, and the first and last nodes of each group of edges are used as a group of task indexes.

[0062] For example, (1) take all the edges in G, filter them according to the edge attribute d, remove the edges whose d is less than 90, and sort the remaining edges according to d from small to large;

[0063] (2) The segmentation index set is recorded as IDX, IDX = {}, and the sorted edges are traversed. The first and last nodes of each set of edges are recorded as a set of task indexes (SI, EI), that is, (start index, end index), and added to IDX.

[0064] S106, searching for a node set including the first and last nodes in the trajectory connectivity graph according to the task index, and searching for a connected path corresponding to the node set in the trajectory connectivity graph, obtaining all corresponding trajectory data according to the nodes in the connected path, and traversing the segmentation index set to obtain the data after the crowdsourcing data is segmented.

[0065] Based on the connection relationship of the nodes in the zebra crossing connectivity graph, the corresponding connectivity paths, nodes and corresponding trajectory data can be obtained in the trajectory connectivity graph, so that the trajectory data can be divided based on the zebra crossing.

[0066] Specifically, the first node of the task index is searched in the trajectory connectivity graph to obtain the first set, and the tail node of the task index is searched in the trajectory connectivity graph to obtain the second set; all connected paths from the first set to the second set are searched in the trajectory connectivity graph, and the paths whose node attributes in the connected paths do not contain the attribute values ​​of the first set and the second set are deleted; the nodes in the remaining paths are obtained, and all data corresponding to the nodes are obtained.

[0067] For example, (1) for each task (SI, EI), find all nodes whose ids contain SI in Q and record them as set SQ, and find all nodes whose ids contain EI and record them as set EQ;

[0068] (2) Find all the connected paths from SQ to EQ nodes in Q, check all the paths, and if there is a path with a node id attribute that does not contain SQ and EQ, delete the path;

[0069] (3) After the deletion is complete, take out the node N in all remaining paths, and then take out all the data corresponding to N, which is the result data of a single split task;

[0070] (4) Traverse IDX and perform the above operations on all tasks to obtain the crowdsourcing data segmentation data of all independent tasks.

[0071] In this embodiment, the graph index function is used to convert data into a graph, and the search calculation of the graph is used to quickly obtain the index result, and then the index is converted back to data. This can improve the efficiency of data segmentation, reduce the amount of calculation, and reduce the time and labor consumption.

[0072] It should be understood that the sequence numbers of the steps in the above embodiments do not imply a sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0073] Figure 2 A schematic diagram of the structure of a crowdsourcing data segmentation system provided by an embodiment of the present invention, the system comprising:

[0074] A first construction module 210 is used to construct a vehicle trajectory segment connectivity index based on the vehicle trajectory data collected by crowdsourcing;

[0075] The trajectory data of the crowdsourced vehicle are sorted by collection time, and the trajectory segments in which the collection time difference between the starting trajectory point and the ending trajectory point is greater than a predetermined threshold are split to obtain the trajectory segment connectivity index of the crowdsourced vehicle.

[0076] The second construction module 220 is used to construct a zebra crossing connectivity index according to the zebra crossing information passed by each trajectory segment in the trajectory segment connectivity index;

[0077] Among them, based on the trajectory points in the trajectory segment connectivity index, a data set of all zebra crossings is obtained; the zebra crossing data set is sorted according to the zebra crossing collection observation time to obtain a connected order set of zebra crossing data, and the zebra crossing information is replaced with the zebra crossing number with the same name to obtain a zebra crossing connectivity index set.

[0078] A zebra crossing connectivity graph construction module 230 is used to create a first empty graph based on networkx, add zebra crossings in the zebra crossing connectivity index set as nodes to the first empty graph, and add edges and edge attributes to adjacent nodes to obtain a zebra crossing connectivity graph;

[0079] Among them, the zebra crossing in the zebra crossing connectivity index set is added as a node point to the first empty graph, and duplicate nodes are automatically merged based on networkx; edges that do not belong to the added edge set are added to the first empty graph; the Euclidean distance of the average value coordinates of the zebra crossing point coordinates corresponding to the adjacent nodes on the edge is marked, and the Euclidean distance is used as the edge attribute.

[0080] A trajectory connection graph construction module 240 is used to create a second empty graph based on networkx, add the trajectory points observed at the zebra crossing as nodes to the second empty graph, and add node attributes and edges to obtain a trajectory connection graph;

[0081] Constructing a segmentation index module 250, which is used to filter the edges in the zebra crossing connectivity graph and add the first and last nodes of each group of edges as task indexes to the segmentation index set;

[0082] Among them, all edges and edge attributes in the zebra crossing connectivity graph are obtained, edges with edge attribute values ​​less than a predetermined value are deleted, and the remaining edges are sorted according to the attribute values; the sorted edges are traversed, and the first and last nodes of each group of edges are used as a group of task indexes.

[0083] The traversal and segmentation module 260 is used to search for a node set including the head and tail nodes in the trajectory connectivity graph according to the task index, and to search for a connected path corresponding to the node set in the trajectory connectivity graph, and to obtain all corresponding trajectory data according to the nodes in the connected path, and to traverse the segmentation index set to obtain the data after the crowdsourcing data is segmented.

[0084] Among them, the first node of the task index is found in the trajectory connectivity graph to obtain the first set, and the tail node of the task index is found in the trajectory connectivity graph to obtain the second set; all connected paths from the first set to the second set are found in the trajectory connectivity graph, and the paths whose node attributes in the connected paths do not contain the attribute values ​​of the first set and the second set are deleted; the nodes in the remaining paths are obtained, and all data corresponding to the nodes are obtained.

[0085] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described system and module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0086] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is used to quickly segment crowdsourcing data. Figure 3 As shown, the electronic device 3 of this embodiment includes: a memory 310, a processor 320 and a system bus 330, wherein the memory 310 includes an executable program 3101 stored thereon, and those skilled in the art can understand that Figure 3 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0087] Combine the following Figure 3 A detailed introduction to the various components of electronic equipment:

[0088] The memory 310 can be used to store software programs and modules, and the processor 320 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 310. The memory 310 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cache data), etc. In addition, the memory 310 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0089] The memory 310 contains an executable program 3101 of the signboard extraction method, which can be divided into one or more modules / units, which are stored in the memory 310 and executed by the processor 320 to achieve crowdsourcing data segmentation, etc. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 3101 in the electronic device 3. For example, the computer program 3101 can be divided into an acquisition module, a fusion module, a thinning module, a detection module, and an extraction module.

[0090] The processor 320 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 310, and calling data stored in the memory 310, it performs various functions of the electronic device and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 320 may include one or more processing units; preferably, the processor 320 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 320.

[0091] The system bus 330 is used to connect the various functional components inside the computer, and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, VESA bus, etc. The instructions of the processor 320 are transmitted to the memory 310 through the bus, and the memory 310 feeds back data to the processor 320. The system bus 330 is responsible for the data and instruction exchange between the processor 320 and the memory 310. Of course, the system bus 330 can also be connected to other devices, such as network interfaces, display devices, etc.

[0092] In the embodiment of the present invention, the executable program executed by the processor 320 included in the electronic device includes:

[0093] Based on the vehicle trajectory data collected by crowdsourcing, a vehicle trajectory segment connectivity index is constructed;

[0094] According to the zebra crossing information passed by each trajectory in the trajectory segment connectivity index, a zebra crossing connectivity index is constructed;

[0095] Create a first empty graph based on networkx, add the zebra crossings in the zebra crossing connectivity index set as nodes to the first empty graph, and add edges and edge attributes to adjacent nodes to obtain a zebra crossing connectivity graph;

[0096] Create a second empty graph based on networkx, add the trajectory points of the zebra crossing observed as nodes to the second empty graph, and add node attributes and edges to obtain a trajectory connectivity graph;

[0097] After filtering the edges in the zebra crossing connectivity graph, add the first and last nodes of each group of edges as task indexes to the split index set;

[0098] According to the task index, the node set containing the first and last nodes in the trajectory connectivity graph is searched, and the connected path corresponding to the node set is searched in the trajectory connectivity graph. According to the nodes in the connected path, all corresponding trajectory data are obtained, and the segmentation index set is traversed to obtain the data after the crowdsourcing data is segmented.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0100] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A crowdsourcing data segmentation method, characterized in that: include: Based on the vehicle trajectory data collected by crowdsourcing, a vehicle trajectory segment connectivity index is constructed; According to the zebra crossing information passed by each trajectory in the trajectory segment connectivity index, a zebra crossing connectivity index is constructed; Create a first empty graph based on networkx, add the zebra crossings in the zebra crossing connectivity index set as nodes to the first empty graph, and add edges and edge attributes to adjacent nodes to obtain a zebra crossing connectivity graph; Create a second empty graph based on networkx, add the trajectory points of the zebra crossing observed as nodes to the second empty graph, and add node attributes and edges to obtain a trajectory connectivity graph; After filtering the edges in the zebra crossing connectivity graph, add the first and last nodes of each group of edges as task indexes to the split index set; According to the task index, the node set containing the first and last nodes in the trajectory connectivity graph is searched, and the connected path corresponding to the node set is searched in the trajectory connectivity graph. According to the nodes in the connected path, all corresponding trajectory data are obtained, and the segmentation index set is traversed to obtain the data after the crowdsourcing data is segmented.

2. The method according to claim 1, characterized in that The vehicle trajectory data collected based on crowdsourcing is used to construct a vehicle trajectory segment connectivity index, which includes: The trajectory data of the crowdsourced vehicle are sorted by the collection time, and the trajectory segments in which the collection time difference between the starting trajectory point and the ending trajectory point is greater than a predetermined threshold are split to obtain the trajectory segment connectivity index of the crowdsourced vehicle.

3. The method according to claim 1, characterized in that The step of constructing a zebra crossing connectivity index according to the zebra crossing information passed by each track segment in the track segment connectivity index comprises: Based on the trajectory points in the trajectory segment connectivity index, obtain the dataset of all the pedestrian crossings. The zebra crossing data set is sorted according to the zebra crossing collection observation time to obtain the connected order set of zebra crossing data, and the zebra crossing information is replaced with the zebra crossing number with the same name to obtain the zebra crossing connected index set.

4. The method according to claim 1, characterized in that: The method of creating a first empty graph based on NetworkX, adding the zebra crossing in the zebra crossing connectivity index set as a node to the first empty graph, and adding edges and edge attributes to adjacent nodes includes: Add the zebra crossings in the zebra crossing connectivity index set as nodes to the first empty graph, and automatically merge duplicate nodes based on networkx; Add edges that do not belong to the set of added edges to the first empty graph; The Euclidean distance of the average value coordinates of the zebra crossing point coordinates of the adjacent nodes on the marked edge is used as the edge attribute.

5. The method according to claim 1, characterized in that After filtering the edges in the zebra crossing connectivity graph, adding the first and last nodes of each group of edges as task indexes to the segmentation index set includes: Get all the edges and edge attributes in the zebra crossing connectivity graph, delete the edges whose edge attribute values ​​are less than a predetermined value, and sort the remaining edges by attribute value; Traverse the sorted edges and use the first and last nodes of each group of edges as a set of task indexes.

6. The method according to claim 1, characterized in that The step of searching for a node set including the first and last nodes in the trajectory connectivity graph according to the task index, searching for a connected path corresponding to the node set in the trajectory connectivity graph, and obtaining all corresponding trajectory data according to the nodes in the connected path includes: Find the first node of the task index in the trajectory connection graph to obtain a first set, and find the tail node of the task index in the trajectory connection graph to obtain a second set; Find all connected paths from the first set to the second set in the trajectory connectivity graph, and delete paths in the connectivity paths whose node attributes do not contain attribute values ​​of the first set and the second set; Get the nodes in the remaining path and get all the data corresponding to the nodes.

7. A crowdsourcing data segmentation system, characterized in that: include: The first construction module is used to construct a vehicle trajectory segment connectivity index based on the vehicle trajectory data collected by crowdsourcing; The second construction module is used to construct a zebra crossing connectivity index according to the zebra crossing information passed by each trajectory segment in the trajectory segment connectivity index; A zebra crossing connectivity graph construction module is used to create a first empty graph based on networkx, add zebra crossings in the zebra crossing connectivity index set as nodes to the first empty graph, and add edges and edge attributes to adjacent nodes to obtain a zebra crossing connectivity graph; A trajectory connectivity graph construction module is used to create a second empty graph based on networkx, add the trajectory points observed at the zebra crossing as nodes to the second empty graph, and add node attributes and edges to obtain a trajectory connectivity graph; Construct a split index module to filter the edges in the zebra crossing connectivity graph and add the first and last nodes of each group of edges as task indexes to the split index set; The traversal and segmentation module is used to search for the node set containing the head and tail nodes in the trajectory connectivity graph according to the task index, and to search for the connected path corresponding to the node set in the trajectory connectivity graph. According to the nodes in the connected path, all corresponding trajectory data are obtained, and the segmentation index set is traversed to obtain the data after the crowdsourcing data is segmented.

8. The system according to claim 7, characterized in that The vehicle trajectory data collected based on crowdsourcing is used to construct a vehicle trajectory segment connectivity index, which includes: The trajectory data of the crowdsourced vehicle are sorted by the collection time, and the trajectory segments in which the collection time difference between the starting trajectory point and the ending trajectory point is greater than a predetermined threshold are split to obtain the trajectory segment connectivity index of the crowdsourced vehicle.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a crowdsourcing data segmentation method as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the steps of a crowdsourcing data segmentation method as described in any one of claims 1 to 6 are implemented.

Images