A fleet identification method, device, computer equipment and storage medium

Abstract

The present invention discloses a fleet identification method, device, equipment and storage medium. The method includes: judging whether any two vehicles among a plurality of vehicles belong to the same fleet based on a matching result, a clustering result and a preset condition; if both the matching result and the clustering result meet the preset condition, judging that the two vehicles currently belong to the same fleet, and outputting a first identification result that they belong to the same fleet; if not, judging that the two vehicles currently do not belong to the same fleet, and outputting a second identification result that they do not belong to the same fleet. Since the present invention introduces a preset matching model for matching processing, it can accurately determine the trajectory similarity between vehicles based on the generated matching result; it also introduces a preset secondary clustering model, which can accurately generate clustering results; based on the matching result and the clustering result, it can accurately judge whether any two vehicles among a plurality of vehicles belong to the same fleet, thereby ultimately greatly improving the accuracy of fleet identification.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a fleet identification method, device, computer equipment and storage medium. Background Art

[0002] With the popularity of vehicles, more and more users choose to form different teams to go off-road. Due to the large number of vehicles in the team and different teams have different managers, it is necessary to distinguish different teams and vehicles in different teams.

[0003] Existing fleet identification methods cannot accurately distinguish which fleet a target vehicle belongs to, especially when the target vehicle is at the junction of two fleets. It is even more impossible to accurately determine whether the target vehicle belongs to fleet A or fleet B. Summary of the Invention

[0004] Based on this, it is necessary to provide a fleet identification method, device, computer equipment and storage medium to address the problem in the existing technology that it is difficult to identify whether two or more vehicles belong to the same fleet.

[0005] In a first aspect, an embodiment of the present application provides a fleet identification method, the method comprising:

[0006] Obtain GPS data and point of interest data of multiple vehicles within a preset time period and a preset range;

[0007] Inputting the GPS data of the plurality of vehicles into a preset matching model for matching processing, and generating corresponding matching results for determining the similarity of trajectories between the vehicles;

[0008] Inputting the point of interest data of the plurality of vehicles into a preset secondary clustering model for clustering processing to generate corresponding clustering results;

[0009] Based on the matching result, the clustering result and the preset conditions, it is determined whether any two vehicles among the multiple vehicles belong to the same fleet. If the matching result and the clustering result both meet the preset conditions, it is determined that the two vehicles currently belong to the same fleet, and a first recognition result indicating that they belong to the same fleet is output; if not, it is determined that the two vehicles currently do not belong to the same fleet, and a second recognition result indicating that they do not belong to the same fleet is output.

[0010] In one embodiment, the matching result includes a trajectory matching value between any two vehicles among a plurality of vehicles, and the clustering result includes a starting stop point, a corresponding ending stop point, and a stopping range involved in the corresponding stop point corresponding to any one of the plurality of vehicles; the preset conditions include: the trajectory matching value is greater than a preset first preset value, and the starting stop point, the corresponding ending stop point, and the corresponding stopping range corresponding to any one of the plurality of vehicles are all within a preset range.

[0011] In one embodiment, the clustering rules used by the preset secondary clustering model include a first clustering rule and a second clustering rule, the clustering results include a first clustering result generated based on the first clustering rule and a second clustering result generated based on the second clustering rule, and inputting the point of interest data of the plurality of vehicles into the preset secondary clustering model for clustering processing to generate corresponding clustering results includes:

[0012] Inputting the POI data of the plurality of vehicles into the preset secondary clustering model, performing a first clustering process based on the first clustering rule, and generating a first clustering result, the first clustering result including a clustering area and a plurality of POI types to be searched;

[0013] Determining a corresponding vehicle gathering area based on the cluster area and the multiple types of points of interest;

[0014] A second clustering process is performed based on the second clustering rule and the vehicle gathering area to generate the second clustering result.

[0015] In one embodiment, the method further comprises:

[0016] Reading the first clustering rule, the first clustering rule comprising: when a plurality of first vehicles to be clustered stop at a preset stop point for a duration less than or equal to a preset stop duration, performing a first clustering process according to a preset clustering method, a configured first parameter distance, and a first neighborhood;

[0017] Read the second clustering rule, which includes: when the number of stop points of multiple second vehicles to be clustered parked in the vehicle gathering area is greater than a preset percentile, and the number of multiple second vehicles to be clustered is greater than a second preset value, perform a second clustering process according to the configured second parameter distance and second neighborhood.

[0018] In one embodiment, the method further comprises:

[0019] When it is determined that any two vehicles among the plurality of vehicles belong to the same fleet, the corresponding two vehicles are both configured with the same fleet tag.

[0020] In one embodiment, the method further comprises:

[0021] The GPS data of any one of the multiple vehicles is preprocessed to obtain preprocessed GPS data of the corresponding vehicle.

[0022] In one embodiment, the pre-processing of the GPS data of any one of the plurality of vehicles includes:

[0023] performing grid processing on the GPS data of any one of the plurality of vehicles; and / or,

[0024] performing time window processing on the GPS data of any one of the plurality of vehicles; and / or,

[0025] performing deduplication processing on the GPS data of any one of the multiple vehicles; and / or,

[0026] performing cropping processing on the GPS data of any one of the plurality of vehicles; and / or,

[0027] The GPS data of any one of the plurality of vehicles is filtered.

[0028] In a second aspect, an embodiment of the present application provides a fleet identification device, the device comprising:

[0029] An acquisition module is used to acquire GPS data of multiple vehicles and point of interest data of multiple vehicles within a preset time period and a preset range;

[0030] a matching module, configured to input the GPS data of the plurality of vehicles acquired by the acquisition module into a preset matching model for matching processing, and generate corresponding matching results for determining the similarity of trajectories between the vehicles;

[0031] a clustering module, configured to input the POI data of the plurality of vehicles acquired by the acquisition module into a preset secondary clustering model for clustering processing, and generate corresponding clustering results;

[0032] a judgment module, configured to judge whether any two vehicles among the plurality of vehicles belong to the same fleet based on the matching result generated by the matching module, the clustering result generated by the clustering module, and a preset condition; if both the matching result and the clustering result satisfy the preset condition, then the two vehicles are judged to belong to the same fleet; if not, then the two vehicles are judged not to belong to the same fleet;

[0033] The output module is used to output the first recognition result obtained by the judgment module, which indicates that the vehicles belong to the same vehicle fleet; or to output the second recognition result obtained by the judgment module, which indicates that the vehicles do not belong to the same vehicle fleet.

[0034] In a third aspect, an embodiment of the present application provides a computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the above-mentioned method steps.

[0035] In a fourth aspect, an embodiment of the present application provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, causes the one or more processors to perform the above-mentioned method steps.

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

[0037] In an embodiment of the present application, GPS data and point-of-interest data of multiple vehicles within a preset time period and a preset range are obtained; the GPS data of the multiple vehicles are input into a preset matching model for matching processing, generating corresponding matching results for determining the similarity of trajectories between the vehicles; the point-of-interest data of the multiple vehicles are input into a preset secondary clustering model for clustering processing, generating corresponding clustering results; and based on the matching results, clustering results, and preset conditions, it is determined whether any two of the multiple vehicles belong to the same fleet. If the matching results and clustering results both meet the preset conditions, it is determined that the two vehicles currently belong to the same fleet and a first recognition result of belonging to the same fleet is output; if not, it is determined that the two vehicles currently do not belong to the same fleet and a second recognition result of not belonging to the same fleet is output. Therefore, using the embodiment of the present application, due to the introduction of the preset matching model for matching processing, the trajectory similarity between the vehicles can be accurately determined based on the generated matching results; the preset secondary clustering model is also introduced to accurately generate clustering results; based on the matching results and clustering results, it is possible to accurately determine whether any two of the multiple vehicles belong to the same fleet, thereby ultimately greatly improving the accuracy of fleet identification. 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

[0038] 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.

[0039] Figure 1 A diagram illustrating an implementation environment of a fleet identification method provided in one embodiment;

[0040] Figure 2 is a block diagram of the internal structure of a computer device in one embodiment;

[0041] Figure 3 This is a flow chart of a fleet identification method provided by an embodiment of the present disclosure;

[0042] Figure 4 This is a schematic diagram of parking areas corresponding to multiple vehicles in a specific application scenario provided by an embodiment of the present disclosure;

[0043] Figure 5 This is a flow chart of a fleet identification method in a specific application scenario provided by an embodiment of the present disclosure;

[0044] Figure 6 This is a schematic diagram of a vehicle fleet trajectory identified based on a vehicle fleet identification method in a specific application scenario provided by an embodiment of the present disclosure;

[0045] Figure 7 It is a structural diagram of a vehicle fleet identification device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

[0047] 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.

[0048] Optional embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0049] Figure 1 FIG. 1 is a diagram illustrating an implementation environment of a fleet identification method provided in an embodiment. Figure 1 As shown, in this implementation environment, a computer device 110 and a terminal 120 are included.

[0050] It should be noted that the terminal 120 and the computer device 110 may be, but are not limited to, a smartphone, a tablet computer, a laptop computer, a desktop computer, etc. The computer device 110 and the terminal 110 may be connected via Bluetooth, USB (Universal Serial Bus), or other communication connection methods, and the present invention does not impose any limitation thereto.

[0051] Figure 2 FIG. 1 is a schematic diagram of the internal structure of a computer device in one embodiment. Figure 2As shown, the computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected via a system bus. The non-volatile storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement a fleet identification method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may implement a fleet identification method. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0052] like Figure 3 As shown, the embodiment of the present disclosure provides a fleet identification method, which specifically includes the following method steps:

[0053] S302: Obtain GPS data of multiple vehicles and point of interest data of multiple vehicles within a preset time period and a preset range.

[0054] In the embodiment of the present application, there is no specific limitation on the preset time period, which may be GPS data within one month, and the preset range may be nationwide, for example, point of interest data of multiple vehicles across the country.

[0055] In the embodiment of the present application, if the GPS data of the multiple vehicles obtained are historical GPS data within a month, the stop points can be calculated based on the historical GPS data within the month. The method used to calculate the stop points is a conventional method and will not be repeated here.

[0056] The final stop information includes the vehicle stop start time, stop end time, and stop center point.

[0057] Figure 4 This is a schematic diagram of parking areas corresponding to multiple vehicles in a specific application scenario provided by an embodiment of the present disclosure.

[0058] like Figure 4 As shown, the parking areas corresponding to cars A, B, and C can be clearly identified.

[0059] In a possible implementation, the identification method provided in the embodiment of the present disclosure further includes the following steps:

[0060] The GPS data of any one of the multiple vehicles is preprocessed to obtain preprocessed GPS data of the corresponding vehicle; thus, after the preprocessing, the obtained preprocessed GPS data of the vehicle is more accurate.

[0061] In one possible implementation, preprocessing the GPS data of any one of the multiple vehicles includes the following steps:

[0062] Grid processing is performed on GPS data of any one of the multiple vehicles.

[0063] In one possible implementation, preprocessing the GPS data of any one of the multiple vehicles includes the following steps:

[0064] Time windowing is performed on GPS data of any one vehicle among GPS data of a plurality of vehicles.

[0065] In actual application scenarios, the gridding and time windowing processing of the GPS data of any one of multiple vehicles are often combined, as described below:

[0066] All vehicle GPS data are gridded and time-windowed. Gridding and time-windowing are key matching steps, with a grid size of k kilometers and a time window of t minutes.

[0067] In one possible implementation, preprocessing the GPS data of any one of the multiple vehicles includes the following steps:

[0068] Deduplication processing is performed on GPS data of any one vehicle among GPS data of multiple vehicles.

[0069] In an actual application scenario, deduplication processing is performed on the GPS data of any one of multiple vehicles, as follows:

[0070] The first method keeps the gridding unchanged while changing the time axis. The second method changes both the gridding and the time axis, and removes duplicates within the same time span within the gridding.

[0071] In one possible implementation, preprocessing the GPS data of any one of the multiple vehicles includes the following steps:

[0072] The GPS data of any one vehicle among the GPS data of a plurality of vehicles is cropped.

[0073] In the embodiment of the present application, there is no specific limitation on the cutting method used in the above-mentioned cutting process.

[0074] In one possible implementation, preprocessing the GPS data of any one of the multiple vehicles includes the following steps:

[0075] Filtering processing is performed on GPS data of any one vehicle among GPS data of a plurality of vehicles.

[0076] In specific application scenarios, corresponding filtering rules can be configured for the above filtering processing. For example, the configured filtering rules can be: the total mileage is greater than N kilometers, where N is a natural number greater than or equal to 1. The specific value of N can be limited according to different application scenarios.

[0077] S304: Inputting the GPS data of the plurality of vehicles into a preset matching model for matching processing, and generating corresponding matching results for determining the similarity of trajectories between the vehicles.

[0078] In the embodiment of the present application, the preset matching degree model can be configured based on different preset matching degree algorithms.

[0079] In a specific application scenario, the formula used by the preset matching algorithm corresponding to the preset matching model is:

[0080] Matching rate a = number of paired grids and time windows b / total number of grids and time windows for vehicles c; thus, the similarity of trajectories between vehicles can be accurately determined based on the above matching rate calculation formula.

[0081] In actual application scenarios, the larger the value of the matching rate a is, the higher the trajectory similarity between vehicles is, and the greater the probability that the vehicles belong to the same fleet.

[0082] The above are merely examples. The preset matching algorithm can be optimized according to different application scenarios, and will not be elaborated here.

[0083] S306: Inputting the POI data of the plurality of vehicles into a preset secondary clustering model for clustering processing to generate corresponding clustering results.

[0084] In one possible implementation, the clustering rules used by the preset secondary clustering model include a first clustering rule and a second clustering rule, and the clustering results include a first clustering result generated based on the first clustering rule and a second clustering result generated based on the second clustering rule. Point of interest data of multiple vehicles are input into the preset secondary clustering model for clustering processing to generate corresponding clustering results, including the following steps:

[0085] Inputting the point of interest data of multiple vehicles into a preset secondary clustering model, performing a first clustering process based on a first clustering rule, and generating a first clustering result, the first clustering result including a clustering area and multiple types of points of interest to be searched;

[0086] Based on the clustering area and multiple points of interest types, the corresponding vehicle gathering area is determined;

[0087] A second clustering process is performed based on the second clustering rule and the vehicle cluster area to generate a second clustering result.

[0088] In an embodiment of the present application, the first clustering rule includes: when the stop time of multiple first vehicles to be clustered at a preset stop point is less than or equal to the preset stop time, a first clustering process is performed according to the preset clustering method, the configured first parameter distance and the first neighborhood.

[0089] The second clustering rule includes: when the number of stop points of multiple second vehicles to be clustered parked in the vehicle gathering area is greater than a preset percentile, and the number of multiple second vehicles to be clustered is greater than a second preset value, a second clustering process is performed according to the configured second parameter distance and second neighborhood.

[0090] There is no specific restriction on the specific values corresponding to the above-mentioned preset docking time, preset clustering method (which can be dbscan clustering method), first parameter distance, first neighborhood, preset percentile, second preset value, second parameter distance and second neighborhood, and they can be adjusted according to the needs of different application scenarios.

[0091] In a possible implementation, the fleet identification method provided in the embodiment of the present disclosure further includes the following steps:

[0092] The first clustering rule is read, and the first clustering rule includes: when the parking time of multiple first vehicles to be clustered at a preset parking point is less than or equal to the preset parking time, a first clustering process is performed according to a preset clustering method, a configured first parameter distance and a first neighborhood.

[0093] In a specific application scenario, the vehicle stops are clustered S0 (first clustering), as follows:

[0094] Stops with a duration greater than t0 are filtered out, and then DBSCAN clustering is performed with parameters d = d0 meters and n = m neighborhoods. Clustering regions are sorted in reverse order by the number of stops. DBSCAN-based clustering is a conventional method and will not be described here.

[0095] The specific values corresponding to the above-mentioned time duration t0, parameter distance d=d0 meters, and neighborhood n=m can be configured according to different application scenarios, and the specific values are not specifically limited here.

[0096] In a possible implementation, the fleet identification method provided in the embodiment of the present disclosure further includes the following steps:

[0097] Read the second clustering rule, the second clustering rule includes: when the number of stop points of multiple second vehicles to be clustered parked in the vehicle gathering area is greater than a preset percentile, and the number of multiple second vehicles to be clustered is greater than a second preset value, perform a second clustering process according to the configured second parameter distance and second neighborhood.

[0098] In a specific application scenario, clustering S1 (second clustering) is performed based on POIs (points of interest), as follows:

[0099] We searched for POIs within an N-meter radius around the clustering area. We then performed a secondary DBScan clustering on vehicle clusters within these areas, specifically those with strong correlations to POI types such as ports, railway stations, airport freight, logistics parks, industrial parks, outdoor parking lots, farmers' markets, and furniture and building materials markets. The clustering rule is: the number of stops in the clustered area must be greater than the c percentile, and the number of vehicles must be greater than d. We selected the distance parameter d = d1 meters and the neighborhood n = m1. DBScan-based clustering is a conventional method and will not be further elaborated here.

[0100] The specific values corresponding to the above-mentioned c percentile, number of vehicles d, parameter distance d=d1 meters, and neighborhood n=m1 can be configured according to different application scenarios, and the specific values are not specifically limited here.

[0101] S308: Based on the matching result, clustering result and preset conditions, determine whether any two vehicles among the multiple vehicles belong to the same fleet. If the matching result and the clustering result both meet the preset conditions, determine that the two vehicles currently belong to the same fleet, and output a first recognition result indicating that they belong to the same fleet; if not, determine that the two vehicles currently do not belong to the same fleet, and output a second recognition result indicating that they do not belong to the same fleet.

[0102] In the embodiment of the present application, the matching result includes the trajectory matching value between any two vehicles among the multiple vehicles, and the clustering result includes the starting stop point, the ending stop point, and the stop range involved in the corresponding stop point corresponding to any one of the multiple vehicles;

[0103] Preconditions include:

[0104] The trajectory matching value is greater than a preset first preset value, and the starting stop point, the corresponding end stop point, and the corresponding stop range of any one of the multiple vehicles are all within the preset range.

[0105] In the embodiments of the present application, the first preset value is not specifically limited. The formula for calculating the trajectory matching value can be: matching rate a = number of paired grids and time windows b / total number of grids and time windows for vehicles c; thus, the trajectory similarity between vehicles can be accurately determined based on the above matching rate calculation formula.

[0106] There is no specific restriction on the preset range, and the corresponding preset range can be adjusted according to the needs of different application scenarios.

[0107] In a possible implementation, the identification method provided in the embodiment of the present disclosure further includes the following steps:

[0108] When it is determined that any two vehicles among the plurality of vehicles belong to the same fleet, the corresponding two vehicles are both configured with the same fleet tag.

[0109] like Figure 5 This is a flow chart of a fleet identification method in a specific application scenario provided by an embodiment of the present disclosure; Figure 5 For the fleet identification process, see the above Figure 3 The description of the same or similar parts will not be repeated here.

[0110] like Figure 6 As shown in FIG, it is a schematic diagram of a fleet trajectory identified based on a fleet identification method in a specific application scenario provided by an embodiment of the present disclosure. Figure 6 As shown, Figure 6 The coarse and continuous GPS track in is the GPS track of vehicle A, and Figure 6 The intermittent GPS track in is the GPS track of vehicle B.

[0111] In an embodiment of the present disclosure, GPS data and point-of-interest data of multiple vehicles within a preset time period and a preset range are obtained; the GPS data of the multiple vehicles are input into a preset matching model for matching processing to generate corresponding matching results for determining the similarity of trajectories between the vehicles; the point-of-interest data of the multiple vehicles are input into a preset secondary clustering model for clustering processing to generate corresponding clustering results; and based on the matching results, clustering results, and preset conditions, it is determined whether any two of the multiple vehicles belong to the same fleet. If the matching results and clustering results both meet the preset conditions, it is determined that the two vehicles currently belong to the same fleet and a first recognition result of belonging to the same fleet is output; if not, it is determined that the two vehicles currently do not belong to the same fleet and a second recognition result of not belonging to the same fleet is output. Therefore, using the embodiment of the present application, due to the introduction of the preset matching model for matching processing, the trajectory similarity between the vehicles can be accurately determined based on the generated matching results; the preset secondary clustering model is also introduced to accurately generate clustering results; based on the matching results and clustering results, it is possible to accurately determine whether any two of the multiple vehicles belong to the same fleet, thereby ultimately greatly improving the accuracy of fleet identification.

[0112] The following is an embodiment of the vehicle fleet identification device of the present invention, which can be used to implement the embodiment of the vehicle fleet identification method of the present invention. For details not disclosed in the embodiment of the vehicle fleet identification device of the present invention, please refer to the embodiment of the vehicle fleet identification method of the present invention.

[0113] See Figure 7 , which shows a schematic diagram of the structure of a fleet identification device provided by an exemplary embodiment of the present invention. The fleet identification device can be implemented as all or part of a terminal through software, hardware, or a combination of both. The fleet identification device includes an acquisition module 701, a matching module 702, a clustering module 703, a determination module 704, and an output module 705.

[0114] Specifically, the acquisition module 701 is used to acquire GPS data of multiple vehicles and point of interest data of multiple vehicles within a preset time period and a preset range;

[0115] Matching module 702, for inputting the GPS data of multiple vehicles acquired by acquisition module 701 into a preset matching model for matching processing, and generating corresponding matching results for determining the similarity of trajectories between vehicles;

[0116] The clustering module 703 is used to input the POI data of multiple vehicles acquired by the acquisition module 701 into a preset secondary clustering model for clustering processing to generate corresponding clustering results;

[0117] The judgment module 704 is configured to judge whether any two vehicles among the plurality of vehicles belong to the same fleet based on the matching result generated by the matching module 702, the clustering result generated by the clustering module 703, and a preset condition. If both the matching result and the clustering result meet the preset condition, the two vehicles are judged to belong to the same fleet; if not, the two vehicles are judged not to belong to the same fleet.

[0118] The output module 705 is used to output the first recognition result obtained by the judgment module 704, which indicates that the vehicles belong to the same vehicle group; or to output the second recognition result obtained by the judgment module 704, which indicates that the vehicles do not belong to the same vehicle group.

[0119] Optionally, the matching result includes a trajectory matching value between any two vehicles among the multiple vehicles, and the clustering result includes a starting stop point, a corresponding ending stop point, and a stopping range involved in the corresponding stop point corresponding to any one of the multiple vehicles; the preset conditions include: the trajectory matching value is greater than a preset first preset value, and the starting stop point, the corresponding ending stop point, and the corresponding stopping range corresponding to any one of the multiple vehicles are all within a preset range.

[0120] Optionally, the output module 705 is configured to output the first recognition result obtained by the judgment module 704 as belonging to the same vehicle fleet.

[0121] Optionally, the clustering rules used by the preset secondary clustering model include a first clustering rule and a second clustering rule, and the clustering results include a first clustering result generated based on the first clustering rule and a second clustering result generated based on the second clustering rule. The clustering module 703 is specifically configured to:

[0122] Inputting the point of interest data of multiple vehicles into a preset secondary clustering model, performing a first clustering process based on a first clustering rule, and generating a first clustering result, the first clustering result including a clustering area and multiple types of points of interest to be searched;

[0123] Based on the clustering area and multiple points of interest types, the corresponding vehicle gathering area is determined;

[0124] A second clustering process is performed based on the second clustering rule and the vehicle cluster area to generate a second clustering result.

[0125] Optionally, the device further includes:

[0126] A reading module is used to read a first clustering rule, wherein the first clustering rule read by the reading module includes: when a plurality of first vehicles to be clustered stop at a preset stop point for a duration less than or equal to a preset stop duration, performing a first clustering process according to a preset clustering method, a configured first parameter distance, and a first neighborhood; and

[0127] Used to read the second clustering rule, the second clustering rule read by the reading module includes: when the number of stop points of multiple second vehicles to be clustered parked in the vehicle gathering area is greater than a preset percentile, and the number of multiple second vehicles to be clustered is greater than a second preset value, a second clustering processing is performed according to the configured second parameter distance and second neighborhood.

[0128] Optionally, the device further includes:

[0129] The configuration module is configured to configure the corresponding two vehicles with the same fleet label identifier when the judgment module 704 determines that any two vehicles among the multiple vehicles belong to the same fleet.

[0130] Optionally, the device further includes:

[0131] The preprocessing module is used to preprocess the GPS data of any one of the multiple vehicles to obtain the preprocessed GPS data of the corresponding vehicle.

[0132] Optionally, the preprocessing module is specifically used to:

[0133] Performing grid processing on GPS data of any one of the multiple vehicles; and / or, performing time window processing on GPS data of any one of the multiple vehicles; and / or,

[0134] Deduplication processing is performed on the GPS data of any one of the multiple vehicles; and / or, cropping processing is performed on the GPS data of any one of the multiple vehicles; and / or, filtering processing is performed on the GPS data of any one of the multiple vehicles.

[0135] It should be noted that the fleet identification device provided in the above embodiment, when executing the fleet identification method, is merely illustrated by the division of the aforementioned functional modules. In actual applications, the aforementioned functions can be assigned to different functional modules as needed, i.e., the internal structure of the device can be divided into different functional modules to perform all or part of the functions described above. Furthermore, the fleet identification device provided in the above embodiment and the fleet identification method embodiment are based on the same concept. The implementation process is detailed in the fleet identification method embodiment and will not be further described here.

[0136] In the embodiment of the present disclosure, the judgment module is used to judge whether any two vehicles among a plurality of vehicles belong to the same fleet based on the matching result generated by the matching module, the clustering result generated by the clustering module, and the preset conditions. If both the matching result and the clustering result meet the preset conditions, it is judged that the two current vehicles belong to the same fleet; if not, it is judged that the two current vehicles do not belong to the same fleet; and the output module is used to output the first recognition result obtained by the judgment module, indicating that they belong to the same fleet; or, to output the second recognition result obtained by the judgment module, indicating that they do not belong to the same fleet. Therefore, by adopting the embodiment of the present application, since a preset matching model is introduced for matching processing, the trajectory similarity between vehicles can be accurately determined based on the generated matching result; a preset secondary clustering model is also introduced, which can accurately generate clustering results; based on the matching result and the clustering result, it can accurately judge whether any two vehicles among a plurality of vehicles belong to the same fleet, thereby ultimately greatly improving the accuracy of fleet identification.

[0137] In one embodiment, a computer device is proposed, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: obtaining GPS data of multiple vehicles and point-of-interest data of multiple vehicles within a preset time period and a preset range; inputting the GPS data of the multiple vehicles into a preset matching model for matching processing, and generating corresponding matching results for determining the similarity of trajectories between the vehicles; inputting the point-of-interest data of the multiple vehicles into a preset secondary clustering model for clustering processing, and generating corresponding clustering results; and judging whether any two vehicles among the multiple vehicles belong to the same fleet based on the matching results, the clustering results, and preset conditions. If both the matching results and the clustering results meet the preset conditions, judging that the two vehicles currently belong to the same fleet, and outputting a first recognition result that they belong to the same fleet; if not, judging that the two vehicles currently do not belong to the same fleet, and outputting a second recognition result that they do not belong to the same fleet.

[0138] In one embodiment, a storage medium storing computer-readable instructions is proposed. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps: obtaining GPS data of multiple vehicles and point-of-interest data of multiple vehicles within a preset time period and a preset range; inputting the GPS data of the multiple vehicles into a preset matching model for matching processing, and generating corresponding matching results for determining the similarity of trajectories between the vehicles; inputting the point-of-interest data of the multiple vehicles into a preset secondary clustering model for clustering processing, and generating corresponding clustering results; and judging whether any two vehicles among the multiple vehicles belong to the same fleet based on the matching results, the clustering results and preset conditions. If both the matching results and the clustering results meet the preset conditions, it is judged that the two vehicles currently belong to the same fleet, and a first identification result that they belong to the same fleet is output; if not, it is judged that the two vehicles currently do not belong to the same fleet, and a second identification result that they do not belong to the same fleet is output.

[0139] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0140] 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.

[0141] 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 fleet identification method, characterized in that: The method comprises: Obtain GPS data and point of interest data of multiple vehicles within a preset time period and a preset range; Inputting the GPS data of the plurality of vehicles into a preset matching model for matching processing, and generating corresponding matching results for determining the similarity of trajectories between the vehicles; Inputting the point of interest data of the plurality of vehicles into a preset secondary clustering model for clustering processing to generate corresponding clustering results; Determining whether any two vehicles among the plurality of vehicles belong to the same fleet based on the matching result, the clustering result, and a preset condition; if both the matching result and the clustering result satisfy the preset condition, determining that the two vehicles currently belong to the same fleet and outputting a first recognition result indicating that the two vehicles currently belong to the same fleet; if not, determining that the two vehicles currently do not belong to the same fleet and outputting a second recognition result indicating that the two vehicles currently do not belong to the same fleet; The clustering rules adopted by the preset secondary clustering model include a first clustering rule and a second clustering rule, the clustering results include a first clustering result generated based on the first clustering rule and a second clustering result generated based on the second clustering rule, and the inputting of the point of interest data of the plurality of vehicles into the preset secondary clustering model for clustering processing to generate corresponding clustering results includes: Inputting the POI data of the plurality of vehicles into the preset secondary clustering model, performing a first clustering process based on the first clustering rule, and generating a first clustering result, the first clustering result including a clustering area and a plurality of POI types to be searched; Determining a corresponding vehicle gathering area based on the cluster area and the multiple types of points of interest; Performing a second clustering process based on the second clustering rule and the vehicle gathering area to generate a second clustering result; The method further comprises: Reading the first clustering rule, the first clustering rule comprising: when a plurality of first vehicles to be clustered stop at a preset stop point for a duration less than or equal to a preset stop duration, performing a first clustering process according to a preset clustering method, a configured first parameter distance, and a first neighborhood; Read the second clustering rule, which includes: when the number of stop points of multiple second vehicles to be clustered parked in the vehicle gathering area is greater than a preset percentile, and the number of multiple second vehicles to be clustered is greater than a second preset value, perform a second clustering process according to the configured second parameter distance and second neighborhood.

2. The method according to claim 1, characterized in that The matching result includes a trajectory matching value between any two vehicles among the multiple vehicles, and the clustering result includes a starting stop point, a corresponding end stop point, and a stop range involved in the corresponding stop point corresponding to any one of the multiple vehicles; The preset conditions include: The trajectory matching degree value is greater than a preset first preset value, and the starting stop point, the corresponding end stop point, and the corresponding stop range of any one of the multiple vehicles are all within the preset range.

3. The method according to claim 1, characterized in that The method further comprises: When it is determined that any two vehicles among the plurality of vehicles belong to the same fleet, the corresponding two vehicles are both configured with the same fleet tag.

4. The method according to claim 1, wherein The method further comprises: The GPS data of any one of the multiple vehicles is preprocessed to obtain preprocessed GPS data of the corresponding vehicle.

5. The method according to claim 4, characterized in that The pre-processing of the GPS data of any one of the plurality of vehicles includes: performing grid processing on the GPS data of any one of the plurality of vehicles; and / or, performing time window processing on the GPS data of any one of the plurality of vehicles; and / or, performing deduplication processing on the GPS data of any one of the multiple vehicles; and / or, performing cropping processing on the GPS data of any one of the plurality of vehicles; and / or, The GPS data of any one of the plurality of vehicles is filtered.

6. A fleet identification device, characterized in that: The device comprises: An acquisition module is used to acquire GPS data of multiple vehicles and point of interest data of multiple vehicles within a preset time period and a preset range; a matching module, configured to input the GPS data of the plurality of vehicles acquired by the acquisition module into a preset matching model for matching processing, and generate corresponding matching results for determining the similarity of trajectories between the vehicles; a clustering module, configured to input the POI data of the plurality of vehicles acquired by the acquisition module into a preset secondary clustering model for clustering processing, and generate corresponding clustering results; The clustering rules adopted by the preset secondary clustering model include a first clustering rule and a second clustering rule, the clustering result includes a first clustering result generated based on the first clustering rule and a second clustering result generated based on the second clustering rule, and the inputting the point of interest data of the multiple vehicles into the preset secondary clustering model for clustering processing to generate corresponding clustering results includes: inputting the point of interest data of the multiple vehicles into the preset secondary clustering model, performing a first clustering processing based on the first clustering rule to generate the first clustering result, the first clustering result including a clustering area and multiple types of interest points to be searched; determining a corresponding vehicle gathering area based on the clustering area and the multiple types of interest points; performing a second clustering processing based on the second clustering rule and the vehicle gathering area to generate the second clustering result; The method further includes: reading the first clustering rule, the first clustering rule including: when a plurality of first vehicles to be clustered stop at a preset stop time less than or equal to a preset stop time, performing a first clustering process according to a preset clustering method, a configured first parameter distance, and a first neighborhood; reading the second clustering rule, the second clustering rule including: when the number of stop points of a plurality of second vehicles to be clustered stop at the vehicle gathering area is greater than a preset percentile and the number of the plurality of second vehicles to be clustered is greater than a second preset value, performing a second clustering process according to a configured second parameter distance and a second neighborhood; a judgment module, configured to judge whether any two vehicles among the plurality of vehicles belong to the same fleet based on the matching result generated by the matching module, the clustering result generated by the clustering module, and a preset condition; if both the matching result and the clustering result satisfy the preset condition, then the two vehicles are judged to belong to the same fleet; if not, then the two vehicles are judged not to belong to the same fleet; The output module is used to output the first recognition result obtained by the judgment module, which indicates that the vehicles belong to the same vehicle fleet; or to output the second recognition result obtained by the judgment module, which indicates that the vehicles do not belong to the same vehicle fleet.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the fleet identification method according to any one of claims 1 to 5.

8. 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 one or more processors, the computer program implements the steps of the fleet identification method according to any one of claims 1 to 5.

Images