Method, device, equipment and storage medium for clustering vehicle stops

Abstract

The present application discloses a method, apparatus, device, and storage medium for clustering vehicle stops. The method comprises: extracting vehicle stop data based on the vehicle's historical trajectory data; clustering the stop data using a density peak clustering algorithm to obtain a plurality of stop clusters; calculating the similarity between grids in each stop cluster based on the vehicle's historical driving trajectory; and performing connectivity segmentation on each stop cluster based on the similarity between grids to obtain segmented stop clusters. The method for clustering vehicle stops provided in the embodiment of the present application, based on density peak clustering of vehicle stops and in combination with actual business scenarios, introduces a grid similarity matrix based on the vehicle stop sequence, further segments the clustering results, and obtains regional boundaries that are closer to the actual situation.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle trajectory data mining, and in particular to a method, device, equipment and storage medium for clustering vehicle stops. Background Art

[0002] Vehicle stop analysis is a crucial component of connected vehicle technology. Accurately analyzing vehicle stop behavior and locations helps understand vehicle driving behavior. Truck stop analysis can identify truck routes and frequently stop locations such as logistics parks, gas stations, repair centers, and businesses. Therefore, truck stop analysis is crucial for logistics transactions and the truck supply chain.

[0003] Existing technologies often use clustering algorithms to group vehicle stops. However, in real-world applications, these algorithms alone cannot separate two adjacent, high-density areas. For example, if two adjacent factories have many truck stops, the algorithms will aggregate them into a single cluster, which is unsatisfactory. They also cannot restore the boundaries of frequent vehicle stops. Summary of the Invention

[0004] The embodiments of the present application provide a method, apparatus, device, and storage medium for clustering vehicle stops. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is provided below. This summary is not intended to be a comprehensive review, identify key or important elements, or delineate the scope of protection for these embodiments. Its sole purpose is to present some concepts in a simplified form, serving as a prelude to the detailed description that follows.

[0005] In a first aspect, an embodiment of the present application provides a method for clustering vehicle stops, comprising:

[0006] Extracting vehicle stop data based on the vehicle's historical trajectory data;

[0007] The stop point data are clustered using the density peak clustering algorithm to obtain multiple stop point clusters;

[0008] Based on the historical driving trajectory of the vehicle, the similarity between the grids in each stop cluster is calculated;

[0009] Connectivity segmentation is performed on each stop point cluster according to the similarity between grids to obtain the segmented stop point clusters.

[0010] In an optional embodiment, before extracting the vehicle's stop point data based on the vehicle's historical trajectory data, the method further includes:

[0011] Get the historical trajectory data of the vehicle within a preset time period.

[0012] In an optional embodiment, after extracting the vehicle's stop point data based on the vehicle's historical trajectory data, the method further includes:

[0013] The vehicle stop point data is gridded using the UberH3 algorithm to obtain gridded stop point data.

[0014] In an optional embodiment, the stop point data is clustered using a density peak clustering algorithm to obtain a plurality of stop point clusters, including:

[0015] Calculate the local density of the stop grid based on a preset cutoff distance;

[0016] Calculate the distance between the stop point grid and the stop point grid with greater density than the local density, and record it as the first distance;

[0017] Calculate the product of the local density and the first distance, and determine multiple cluster centers according to the product;

[0018] The stop point grids are clustered according to the determined multiple cluster centers to obtain multiple stop point clusters.

[0019] In an optional embodiment, the similarity between grids in each stop point cluster is calculated based on the historical driving trajectory of the vehicle, including:

[0020] In each stop point cluster, the distance between the stop point grid and the stop point grid within its preset range is calculated and recorded as the second distance;

[0021] Calculate the number of consecutive stops between the stop grid and the stop grids within the preset range based on the vehicle's historical driving trajectory;

[0022] The similarity between each two stop grids is obtained according to the ratio of the number of times to the second distance.

[0023] In an optional embodiment, connectivity segmentation is performed on each stop point cluster according to the similarity between grids to obtain segmented stop point clusters, including:

[0024] Determine the connectivity threshold based on the calculated similarity between grids;

[0025] The two grids whose similarity is less than the connectivity threshold are segmented to obtain the segmented stop point clusters.

[0026] In an optional embodiment, after obtaining the segmented stop point clusters, the method further includes:

[0027] Get the boundary information and POI information of the segmented stop point cluster;

[0028] Automatically mark the boundaries of POIs based on boundary information.

[0029] In a second aspect, an embodiment of the present application provides a device for clustering vehicle stops, including:

[0030] A stop point extraction module is used to extract the vehicle's stop point data based on the vehicle's historical trajectory data;

[0031] A first clustering module is used to cluster the stop point data using a density peak clustering algorithm to obtain multiple stop point clusters;

[0032] A similarity calculation module is used to calculate the similarity between grids in each stop point cluster based on the historical driving trajectory of the vehicle;

[0033] The second clustering module is used to perform connectivity segmentation on each stop point cluster according to the similarity between grids to obtain segmented stop point clusters.

[0034] In a third aspect, an embodiment of the present application provides a device for clustering vehicle stops, including a processor and a memory storing program instructions. The processor is configured to execute the method for clustering vehicle stops provided in the above embodiment when executing the program instructions.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable medium having computer-readable instructions stored thereon, and the computer-readable instructions are executed by a processor to implement a method for clustering vehicle stops provided in the above embodiment.

[0036] The technical solutions provided by the embodiments of the present application may have the following beneficial effects:

[0037] The method for clustering vehicle stop points provided in the embodiment of the present application mainly performs stop identification on the trajectory points reported by the vehicle history, and then performs density peak clustering on the stop points of all vehicles. Based on the density peak clustering and combined with actual business scenarios, the similarity between grids is calculated for each connected area through the vehicle stop sequence. The clustering results are further segmented based on the similarity between grids to obtain regional boundaries that are closer to the actual situation. This eliminates the need for a large amount of complex work such as surveying and manually marking POI (Point of Interest) boundaries, which is of great significance for identifying trucks entering and exiting fences and truck loading and unloading.

[0038] 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 invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0040] Figure 1This is a flow chart of a method for clustering vehicle stop points according to an exemplary embodiment;

[0041] Figure 2 is a flow chart of another method for clustering vehicle stops according to an exemplary embodiment;

[0042] Figure 3 is a schematic diagram showing a gridding of stop points according to an exemplary embodiment;

[0043] Figure 4 is a schematic diagram showing a method of selecting a cluster center according to an exemplary embodiment;

[0044] Figure 5 is a schematic diagram showing a segmented stop point cluster according to an exemplary embodiment;

[0045] Figure 6 is a schematic diagram showing another segmented stop point cluster according to an exemplary embodiment;

[0046] Figure 7 is a schematic diagram showing the structure of a device for clustering vehicle stops according to an exemplary embodiment;

[0047] Figure 8 is a schematic diagram of a device structure for clustering vehicle stop points according to an exemplary embodiment;

[0048] Figure 9 It is a schematic diagram of a computer storage medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0049] The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

[0050] It should be understood that the embodiments described are only a portion 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 persons of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0051] In the following description, unless otherwise indicated, identical numbers in different figures represent identical or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of systems and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0052] Clustering algorithms are often used to group vehicle stops. However, in real-world applications, these algorithms alone cannot separate two adjacent, high-density areas. For example, if two factories are adjacent and both have a high number of truck stops, the algorithm will result in a single cluster, which is insufficient for practical applications. They also fail to reconstruct the areas and boundaries where vehicles frequently stop. For example, a vehicle may be 100 meters from a factory, but it's unclear whether it's inside or outside the factory.

[0053] Based on this, an embodiment of the present application provides a method for clustering vehicle stops, which mainly distinguishes the stops of the vehicle's historically reported trajectory points, and then spatially clusters the stops of all vehicles. Due to the large amount of stop point data, the UberH3 grid is used to count the stops, and then density peak clustering is performed based on the grid. Then, connectivity segmentation is performed on the density peak center, and the similarity between grids is calculated for each connected area through the vehicle's stop sequence. The cluster area is again connected based on the similarity between grids to obtain a regional boundary that is closer to the actual situation. This eliminates a lot of complex work of surveying and manually marking POI boundaries, which is of great significance for distinguishing trucks entering and exiting fences and truck loading and unloading.

[0054] The following is a detailed description of the vehicle stop point clustering method provided by the embodiment of the present application in conjunction with the accompanying drawings. Figure 1 , the method specifically includes the following steps.

[0055] S101 extracts the vehicle's stop point data based on the vehicle's historical trajectory data.

[0056] In one possible implementation, the historical trajectory data of the vehicle within a preset time period is first obtained, for example, the GPS trajectory data of the vehicle within the past month is obtained. Among them, the GPS trajectory point is the vehicle position data reported in real time by the GPS (Global Positioning System) device deployed on the vehicle. Usually, when the GPS device reports in real time, the reporting time interval can be set according to the actual situation. The preferred time interval of this application is 10S. It should be noted that in addition to using the vehicle-mounted GPS device to report the vehicle's trajectory data in real time, this application can also use the Beidou device to locate the vehicle trajectory and report it.

[0057] After acquiring the trajectory point data, the process also includes extracting abnormal data from the trajectory point data. This abnormal data includes information errors such as speed errors, latitude and longitude errors, disconnected data, and unlocated data. The abnormal data is deleted to obtain preprocessed trajectory data.

[0058] Extract the vehicle's stop point data from the preprocessed vehicle trajectory data.

[0059] Specifically, points with a speed of 0 are obtained from the trajectory information and merged according to the time interval threshold and the offset threshold. For example, multiple stops within 10 minutes are merged, and multiple stops within 50 meters are merged to obtain stops represented by the centroid. Through this step, small stops can be aggregated within a certain range, and then the stop time is calculated, and stops with a speed greater than the preset stop threshold are screened out to determine whether the vehicle has stopped. In this application, the preferred stop threshold is 5 minutes, and those skilled in the art can set it according to actual conditions.

[0060] According to this step, the historical trajectory data of the vehicle can be used to perform a stop judgment to obtain the historical stop data of the vehicle.

[0061] S102 clusters the stop point data using a density peak clustering algorithm to obtain multiple stop point clusters.

[0062] In one possible implementation, due to the large amount of stop point data, before clustering the stop points using the density peak clustering algorithm, the vehicle stop point data is gridded using the UberH3 algorithm to obtain the gridded stop point data.

[0063] UberH3 is a geospatial indexing system that uses a hexagonal grid. Stops are gridded using UberH3. In one possible implementation, the grid level is set to 9. The number of stopped vehicles within each grid is calculated as the density of the grid, and the latitude and longitude of all stops within the grid are calculated as the latitude and longitude of the grid.

[0064] Figure 3 is a schematic diagram showing a gridded docking point according to an exemplary embodiment. Figure 3 As shown in the figure, the left half is the stop point data before gridding, which has a large amount of data and is relatively dense. The right half is the stop point data after gridding, which is clearer and convenient for further analysis of the stop data.

[0065] Furthermore, the stop point data are clustered using the density peak clustering algorithm to obtain multiple stop point clusters.

[0066] The full name of the density peak clustering algorithm is clustering by fast search and find of density peaks (DPC). This algorithm can automatically find cluster centers and achieve efficient clustering of data of any shape. The algorithm is based on two basic assumptions: (1) the local density of the cluster center (density peak point) is greater than the local density of its surrounding neighbors; (2) the distances between different cluster centers are relatively far. In order to find cluster centers that meet both of these conditions, the algorithm introduces the definition of local density.

[0067] First, the local density of the stop grid is calculated based on a preset cutoff distance.

[0068] Specifically, calculate the stop grid x i and the stop grid x j The distance d ij Then, get the preset cutoff distance d c The cutoff distance can be determined according to the actual business scenario. i The number of stop grids whose distance is less than the cutoff distance is the stop grid x i The local density ρ i .

[0069]

[0070] in,

[0071] Calculate the distance between the stop grid and the stop grid with greater density than the local density, and record it as the first distance δ i .

[0072]

[0073] Calculate the product of local density and the first distance γ i , according to the product γ i Multiple cluster centers are determined.

[0074] γ i =ρ i *δ i

[0075] In one possible implementation, the point with the largest local density and the largest first distance is the cluster center. Therefore, the cluster center can be determined based on the product of the local density and the first distance. The products of the local density and the first distance are sorted from high to low, and the point with the largest product is the cluster center.

[0076] Figure 4 FIG. 1 is a schematic diagram showing a method of selecting a cluster center according to an exemplary embodiment. Figure 4 As shown, the γ values ​​are sorted from high to low, and the segmentation point of the cluster center is determined by the γ descending graph, which is called the singular point. The point before the singular point is the cluster center. The singular point is determined by finding the min(∠AB i C)) is obtained. Among them, the points with low local density but large first distance are noise points.

[0077] After obtaining multiple cluster centers, each remaining point is assigned to the cluster where its nearest neighbor and the cluster center with a local density greater than that of the nearest neighbor are located, and multiple stop point clusters are obtained after clustering.

[0078] S103 calculates the similarity between the grids in each stop point cluster based on the historical driving trajectory of the vehicle.

[0079] After clustering using the above method, cluster centers can be automatically discovered, enabling efficient clustering of data of any shape. However, in real-world applications, simply using density peak clustering cannot separate two adjacent high-density areas. For example, if two adjacent factory areas have many truck stops, the DPC will form a single cluster, which does not meet practical requirements. Therefore, further segmentation is performed on the clusters after clustering.

[0080] Specifically, in each stop point cluster, the distance between the stop point grid and the stop point grids within the preset range is calculated and recorded as the second distance. In one possible implementation, since the distance between the two grids is far, there is no need to perform connectivity analysis, and only the second distance D between a stop point grid and the grids within the three outer circles is calculated. ij .

[0081] Then obtain the vehicle's driving trajectory and calculate the number of consecutive stops C between the stop grid and the stop grids within the preset range. ij . C ij It represents the number of times the vehicle stops at grid i and then at grid j. If the vehicle stops continuously between grid i and grid j without passing through other grids in between, it means that the connectivity between the two grids is large and they may be located in the same factory area.

[0082] The similarity between each two stop grids is obtained based on the ratio of the number of times to the second distance. In one possible implementation, the similarity between two grids is calculated according to the following formula:

[0083] W ij =C ij / D ij

[0084] Among them, W ij represents the similarity between the stop grids, C ij represents the number of consecutive stops between grid i and grid j, D ij Represents the distance between grid i and grid j.

[0085] According to this step, the connectivity between grids can be analyzed based on the parking sequence of vehicles.

[0086] S104 performs connectivity segmentation on each stop point cluster according to the similarity between grids to obtain segmented stop point clusters.

[0087] A connectivity threshold is determined based on the calculated similarity between the grids. For example, the octillion of the calculated similarity is used as the connectivity threshold. This embodiment of the application does not impose any specific restrictions on the value of the threshold, and it can be set according to actual circumstances. Two grids with similarities less than the connectivity threshold are segmented to obtain segmented stop point clusters.

[0088] Figure 5 and Figure 6 is a schematic diagram of the stop point cluster after segmentation, as shown in Figure 5 and Figure 6 As shown in the figure, even if the stops are dense, the stop clusters that conform to the actual situation can be segmented based on the connectivity of the grid.

[0089] According to this step, based on the traditional DPC clustering and combined with actual business scenarios, the grid similarity based on vehicle stop sequence is introduced to further divide the clustering results and obtain regional boundaries that are closer to the actual situation.

[0090] Typically, a POI on a map contains a name, category, and longitude and latitude information. For example, schools, restaurants, and businesses are all considered POIs. POIs play an important role in daily life. However, because a POI is just a point, it can only determine proximity, not entry or exit. For example, a car may be 100 meters from a factory, but it's impossible to determine whether it's inside or outside. Manual annotation of the POI boundaries is required to determine whether the vehicle has entered or exited the fence.

[0091] In this embodiment, after obtaining the segmented stop point clusters, the boundary information and POI information of the segmented stop point clusters are also obtained. Based on the longitude and latitude information of the boundary grids in the stop point clusters, the POI boundaries can be automatically annotated. This eliminates the complex work of extensive surveying and manual annotation of POI boundaries, which is of great significance for determining truck entry and exit fences and truck loading and unloading.

[0092] In order to facilitate understanding of the method for clustering vehicle stops provided in the embodiment of the present application, the following Figure 2 For explanation. Figure 2 As shown, the method includes the following steps.

[0093] First, the original trajectory point data of the vehicle is obtained, and then the stop point recognition is performed, and the vehicle stop point data is extracted according to the vehicle trajectory data.

[0094] Furthermore, due to the large amount of stop point data, the stop point data is gridded using the UberH3 algorithm to obtain gridded stop point data.

[0095] The density peak clustering algorithm is used to cluster the stop point grid to obtain multiple cluster centers. Connectivity segmentation is performed based on the cluster centers to obtain multiple clustered stop point clusters.

[0096] According to the historical stop sequence of the vehicle, the similarity between the grids in each stop cluster is calculated, and the connectivity segmentation is performed again based on the similarity between the grids to obtain the segmented stop cluster.

[0097] The method for clustering vehicle stop points provided in the embodiments of the present application mainly performs stop identification on the vehicle's historically reported trajectory points, and then performs density peak clustering on the stop points of all vehicles. Based on the density peak clustering and in combination with actual business scenarios, the similarity between grids is calculated for each connected area based on the vehicle's stop sequence. The clustering results are further segmented based on the similarity between grids to obtain regional boundaries that are closer to the actual situation. This eliminates the need for a large amount of complex work such as surveying and manually marking POI boundaries, which is of great significance for identifying trucks entering and exiting fences and truck loading and unloading.

[0098] The embodiment of the present application also provides a device for clustering vehicle stops, which is used to execute the method for clustering vehicle stops in the above embodiment, such as Figure 7 As shown, the device includes:

[0099] The stop point extraction module 701 is used to extract the vehicle's stop point data based on the vehicle's historical trajectory data;

[0100] A first clustering module 702 is configured to cluster the stop point data using a density peak clustering algorithm to obtain a plurality of stop point clusters;

[0101] A similarity calculation module 703 is used to calculate the similarity between the grids in each stop point cluster based on the historical driving trajectory of the vehicle;

[0102] The second clustering module 704 is configured to perform connectivity segmentation on each stop point cluster according to the similarity between grids to obtain segmented stop point clusters.

[0103] It should be noted that the apparatus for clustering vehicle stops provided in the above embodiment, when executing the method for clustering vehicle stops, only uses the division of the above-mentioned functional modules as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus for clustering vehicle stops provided in the above embodiment and the method embodiment for clustering vehicle stops are based on the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0104] An embodiment of the present application further provides an electronic device corresponding to the vehicle stop point clustering method provided in the aforementioned embodiment, so as to execute the aforementioned vehicle stop point clustering method.

[0105] Please refer to Figure 8 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 8 As shown, the electronic device includes: a processor 800, a memory 801, a bus 802 and a communication interface 803, and the processor 800, the communication interface 803 and the memory 801 are connected via the bus 802; the memory 801 stores a computer program that can be run on the processor 800, and when the processor 800 runs the computer program, it executes the method for clustering vehicle stops provided in any of the aforementioned embodiments of the present application.

[0106] The memory 801 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface 803 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0107] Bus 802 may be an ISA bus, a PCI bus, or an EISA bus. Buses may be classified as address buses, data buses, and control buses. Memory 801 is used to store programs, and processor 800 executes the programs upon receiving execution instructions. The vehicle stop clustering method disclosed in any of the aforementioned embodiments of the present application may be applied to or implemented by processor 800.

[0108] The processor 800 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor 800 or by software instructions. The above processor 800 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or 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 random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 801 , and the processor 800 reads the information in the memory 801 and completes the steps of the above method in combination with its hardware.

[0109] The electronic device provided in the embodiment of the present application and the method for clustering vehicle stops provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0110] The present application also provides a computer-readable storage medium corresponding to the vehicle stop point clustering method provided in the above embodiment. Figure 9 The computer-readable storage medium shown is a CD 900 on which a computer program (ie, a program product) is stored. When the computer program is executed by a processor, the method for clustering vehicle stops provided in any of the aforementioned embodiments is executed.

[0111] It should be noted that examples of computer-readable storage media may also 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 optical or magnetic storage media, which are not listed here one by one.

[0112] The computer-readable storage medium provided in the above-mentioned embodiment of the present application and the method for clustering vehicle stops provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0113] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for clustering vehicle stops, characterized in that: include: Extracting vehicle stop data based on the vehicle's historical trajectory data; Clustering the stop point data using a density peak clustering algorithm to obtain a plurality of stop point clusters; In each stop point cluster, the distance between the stop point grid and the stop point grids within the preset range is calculated and recorded as the second distance; based on the vehicle's historical driving trajectory, the number of consecutive stops of the vehicle between the stop point grid and the stop point grids within the preset range is calculated; Obtaining the similarity between each two stop point grids according to a ratio of the number of times to the second distance; Connectivity segmentation is performed on each stop point cluster according to the similarity between grids to obtain the segmented stop point clusters.

2. The method according to claim 1, characterized in that Before extracting the vehicle's stop point data based on the vehicle's historical trajectory data, it also includes: Get the historical trajectory data of the vehicle within a preset time period.

3. The method according to claim 1, characterized in that After extracting the vehicle's stop data based on the vehicle's historical trajectory data, it also includes: The vehicle stop point data is gridded using the UberH3 algorithm to obtain gridded stop point data.

4. The method according to claim 3, characterized in that The stop point data is clustered using a density peak clustering algorithm to obtain multiple stop point clusters, including: Calculate the local density of the stop grid based on a preset cutoff distance; Calculate the distance between the stop point grid and the stop point grid with greater density than the local density, and record it as the first distance; Calculating the product of the local density and the first distance, and determining a plurality of cluster centers according to the product; The stop point grids are clustered according to the determined multiple cluster centers to obtain multiple stop point clusters.

5. The method according to claim 1, wherein Connectivity segmentation is performed on each stop point cluster based on the similarity between grids, and the segmented stop point clusters are obtained, including: Determine the connectivity threshold based on the calculated similarity between grids; The two grids whose similarity is less than the connectivity threshold are segmented to obtain the segmented stop point clusters.

6. The method according to claim 1, characterized in that After obtaining the segmented stop point cluster, it also includes: Get the boundary information and POI information of the segmented stop point cluster; The boundary of the POI is automatically marked according to the boundary information.

7. A device for clustering vehicle stops, characterized in that: include: A stop point extraction module is used to extract the vehicle's stop point data based on the vehicle's historical trajectory data; A first clustering module is used to cluster the stop point data using a density peak clustering algorithm to obtain a plurality of stop point clusters; The similarity calculation module is used to calculate the distance between the stop point grid and the stop point grids within the preset range in each stop point cluster, which is recorded as the second distance; and calculate the number of consecutive stops of the vehicle between the stop point grid and the stop point grids within the preset range based on the historical driving trajectory of the vehicle; Obtaining the similarity between each two stop point grids according to a ratio of the number of times to the second distance; The second clustering module is used to perform connectivity segmentation on each stop point cluster according to the similarity between grids to obtain segmented stop point clusters.

8. A device for clustering vehicle stops, characterized in that: The system comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the method for clustering vehicle stops according to any one of claims 1 to 6 when executing the program instructions.

9. A computer-readable medium, characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions are executed by a processor to implement the method for clustering vehicle stops according to any one of claims 1 to 6.

Images