A method and device for identifying enterprise fleets based on stop point clustering

Abstract

The present application relates to a method and device for identifying an enterprise fleet based on stop point clustering. The method includes: obtaining vehicle stop data and vehicle-enterprise association data; screening and grouping vehicle stop data and vehicle-enterprise association data to obtain stop points to be clustered that meet preset conditions; inputting the stop points to be clustered into a trained DBSCAN clustering model to obtain vehicle permanent locations; filtering and associating vehicle permanent locations to obtain vehicle permanent locations under each enterprise, and inputting the vehicle permanent locations under each enterprise into a trained DBSCAN clustering model to obtain enterprise parking lot data; calculating the coefficient of the enterprise fleet based on the enterprise parking lot data; operating the vehicles under the enterprise whose enterprise fleet coefficient is greater than or equal to a preset threshold as enterprise fleets, otherwise, operating them as non-enterprise fleets. The method improves the meticulousness and accuracy of data mining, improves vehicle transportation efficiency, and is also convenient for vehicle scheduling, statistics and related applications.

Description

Technical Field

[0001] The present application relates to the field of data mining technology, and more specifically, to a method and device for identifying an enterprise fleet based on stop point clustering. Background Art

[0002] As the main force of land transportation, trucks undertake a large part of the cargo transportation volume. In the existing technical solutions, when achieving efficient cargo transportation, cargo transportation is mainly carried out through the user's active contact. For example, after the owner determines the transportation route, he first needs to contact the companies on the route and inquire one by one by calling whether there are any goods that need to be transported. At the same time, when the owner wants to transport the goods to a certain location, he needs to contact the vehicle that transports to the location in advance. If one of the owner or the owner cannot contact the other, the goods cannot be transported, thereby reducing the efficiency of cargo transportation.

[0003] The patent application with publication number CN113222492 discloses a method for distinguishing the type of vehicle driving route, the method comprising: obtaining the historical driving trajectory points of the vehicle to be distinguished within a preset time period; calculating the POI historical stop points of the vehicle to be distinguished based on the historical driving trajectory points; preprocessing the calculated POI historical stop points of the vehicle to be distinguished to generate a target POI stop point sequence; classifying the target POI stop point sequence to generate a multi-level POI stop point sequence; and distinguishing the type of driving route corresponding to the vehicle to be distinguished based on the multi-level POI stop point sequence. However, the patent application cannot provide effective vehicle and enterprise association data and thus cannot identify the type of enterprise fleet operation, which affects vehicle transportation efficiency. Summary of the invention

[0004] Based on the above technical problems, the present invention aims to improve the efficiency of data mining based on the two DBSCAN clustering models, especially to obtain enterprise parking lot data, calculate the coefficient of the enterprise fleet based on the enterprise parking lot data, and operate the enterprise's vehicles whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as the enterprise fleet, thereby achieving the meticulousness and accuracy of data mining to adapt to various relevant application scenarios.

[0005] A first aspect of the present invention provides a method for identifying an enterprise fleet based on stop point clustering, comprising:

[0006] Obtain vehicle parking data and the associated data between vehicles and enterprises;

[0007] Screening and grouping the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions;

[0008] Input the to-be-clustered bus stops into the trained DBSCAN clustering model to obtain the vehicle's permanent location;

[0009] Filtering and associating the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and inputting the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data;

[0010] Calculate the coefficient of the enterprise fleet based on the enterprise parking lot data;

[0011] The vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold are operated as the enterprise fleet, otherwise, they are operated as non-enterprise fleet.

[0012] Specifically, the vehicle stop data includes vehicle ID, stop date, stop start time, stop end time, stop duration, stop point longitude and stop point latitude; the vehicle and enterprise association data includes the correspondence between vehicle ID and enterprise ID.

[0013] Preferably, the method further comprises: inputting the stop points to be clustered into a trained DBSCAN clustering model, and if no cluster is obtained, taking the stop point with the longest stop time and a stop time greater than a preset number of days as the vehicle's permanent residence.

[0014] Furthermore, the stop points to be clustered are input into the trained DBSCAN clustering model to obtain the vehicle residence, including:

[0015] Input the to-be-clustered stop points into the trained DBSCAN clustering model;

[0016] The number of stops, the number of days of stops and / or the total duration of stops in the clusters obtained based on the model are stored in descending order;

[0017] A preset number of stops at the front in descending order are used as permanent vehicle locations.

[0018] Furthermore, the vehicle stop data and the associated data between vehicles and enterprises are screened and grouped to obtain the stop points to be clustered that meet the preset conditions, including:

[0019] Select a stop point with a preset stop duration;

[0020] Group the selected stops by vehicle ID;

[0021] Analyze and determine the stops to be clustered that meet the preset conditions.

[0022] Furthermore, filtering and associating the vehicle permanent locations to obtain the vehicle permanent locations under each enterprise includes:

[0023] Filtering the vehicle permanent location to obtain the vehicle permanent location of the target vehicle;

[0024] Selecting a vehicle permanent location whose quantile of the vehicle permanent location of the target vehicle is greater than a preset value;

[0025] The vehicle ID and the enterprise ID are associated to obtain the permanent location of the vehicle under each enterprise.

[0026] Furthermore, the calculating of the coefficient of the enterprise fleet based on the enterprise parking lot data includes:

[0027] The associated data of vehicles and enterprises are associated with the parking lot data of the enterprises, and the number of associated vehicles is recorded as n, where n is a natural number;

[0028] Aggregate the data by enterprise ID, obtain the number of vehicles associated with the enterprise parked in the enterprise parking lot and record it as m, where m is a natural number;

[0029] Divide m by n as the enterprise fleet coefficient.

[0030] A second aspect of the present invention provides a device for identifying an enterprise fleet based on stop point clustering, the device comprising:

[0031] An acquisition module is used to acquire vehicle parking data and associated data between vehicles and enterprises;

[0032] A stop point screening module is used to screen and group the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions;

[0033] A first clustering module is used to input the to-be-clustered stops into a trained DBSCAN clustering model to obtain a vehicle permanent location;

[0034] The second clustering module is used to filter and associate the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and input the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data;

[0035] A fleet coefficient calculation module, used to calculate the coefficient of the enterprise fleet based on the enterprise parking lot data;

[0036] The identification module is used to operate the vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as the enterprise fleet, otherwise, operate them as non-enterprise fleet.

[0037] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0038] Obtain vehicle parking data and the associated data between vehicles and enterprises;

[0039] Screening and grouping the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions;

[0040] Input the to-be-clustered bus stops into the trained DBSCAN clustering model to obtain the vehicle's permanent location;

[0041] Filtering and associating the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and inputting the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data;

[0042] Calculate the coefficient of the enterprise fleet based on the enterprise parking lot data;

[0043] The vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold are operated as the enterprise fleet, otherwise, they are operated as non-enterprise fleet.

[0044] A fourth aspect of the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0045] Obtain vehicle parking data and the associated data between vehicles and enterprises;

[0046] Screening and grouping the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions;

[0047] Input the to-be-clustered bus stops into the trained DBSCAN clustering model to obtain the vehicle's permanent location;

[0048] Filtering and associating the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and inputting the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data;

[0049] Calculate the coefficient of the enterprise fleet based on the enterprise parking lot data;

[0050] The vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold are operated as the enterprise fleet, otherwise, they are operated as non-enterprise fleet.

[0051] The beneficial effects of the present application are as follows: the present application screens and groups vehicle parking data and associated data between vehicles and enterprises, obtains parking points to be clustered that meet preset conditions, inputs the parking points to be clustered into the trained DBSCAN clustering model, obtains vehicle permanent locations, and improves the efficiency of data mining; and obtains enterprise parking lot data through secondary DBSCAN clustering, calculates the coefficient of the enterprise fleet based on the enterprise parking lot data, and operates the vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as the enterprise fleet, thereby improving the detail and accuracy of data mining, being able to quickly find the operation status of the corresponding enterprise fleet in relevant application scenarios, improving vehicle transportation efficiency, and facilitating vehicle scheduling, statistics and related applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present application and, together with the description, serve to explain the principles of the present application.

[0053] The present application can be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0054] Figure 1 A schematic diagram of the steps of a method for identifying an enterprise fleet based on stop point clustering in an exemplary embodiment of the present application is shown;

[0055] Figure 2 A schematic diagram of the structure of an enterprise fleet identification device based on stop point clustering according to an exemplary embodiment of the present application is shown;

[0056] Figure 3 A schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application is shown;

[0057] Figure 4 A schematic diagram of a storage medium provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0058] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present application. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present application. It is obvious to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present application, some technical features known in the art are not described.

[0059] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of the features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0060] Now, exemplary embodiments according to the present application will be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in a variety of different forms and should not be construed as being limited to the embodiments described herein. The accompanying drawings are not drawn to scale, and certain details may be magnified and certain details may be omitted for the purpose of clear expression. The shapes of the various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are merely exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0061] The following is attached to the instruction manual Figure 1-4 Several embodiments are given to describe exemplary implementations according to the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the implementations of the present application are not limited in this regard. On the contrary, the implementations of the present application can be applied to any applicable scenario.

[0062] Embodiment 1:

[0063] This embodiment implements a method for identifying enterprise fleets based on stop point clustering, such as Figure 1 As shown, including:

[0064] S1. Obtain vehicle parking data and associated data between vehicles and enterprises;

[0065] S2. Filter and group the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions;

[0066] S3, input the stops to be clustered into the trained DBSCAN clustering model to obtain the vehicle's permanent location;

[0067] S4. Filter and associate the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and input the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data;

[0068] S5. Calculate the coefficient of the enterprise fleet based on the enterprise parking lot data;

[0069] S6. The vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold are operated as the enterprise fleet; otherwise, they are operated as non-enterprise fleets.

[0070] It should be noted here that DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a relatively early (1996) and more representative density-based clustering algorithm. The main goal of the algorithm is to require less domain knowledge to determine input parameters compared to partition-based clustering methods and hierarchical clustering methods; to discover clusters of arbitrary shapes; and to have better efficiency on large-scale databases. DBSCAN can divide sufficiently high-density areas into clusters and can discover clusters of arbitrary shapes in noisy spatial databases.

[0071] Specifically, the vehicle stop data includes vehicle ID, stop date, stop start time, stop end time, stop duration, stop point longitude and stop point latitude; the associated data of vehicles and enterprises includes the correspondence between vehicle ID and enterprise ID.

[0072] Preferably, the method further comprises: inputting the clustered stop points into a trained DBSCAN clustering model, and if no cluster is obtained, taking the stop point with the longest stop time and a stop time greater than a preset number of days as the vehicle's permanent residence.

[0073] Furthermore, the stop points to be clustered are input into the trained DBSCAN clustering model to obtain the vehicle's permanent residence, including: inputting the stop points to be clustered into the trained DBSCAN clustering model; storing the number of stops, the number of stop days and / or the total stop duration in the cluster obtained based on the model in descending order; and taking a preset number of stop points at the front in the descending order as the vehicle's permanent residence.

[0074] Furthermore, the vehicle stop data and the associated data between the vehicle and the enterprise are screened and grouped to obtain the stop points to be clustered that meet the preset conditions, including: selecting stop points with a preset stop time range; grouping the selected stop points by vehicle ID; analyzing and determining the stop points to be clustered that meet the preset conditions.

[0075] Furthermore, the vehicle permanent location is filtered and associated to obtain the vehicle permanent location under each enterprise, including: filtering the vehicle permanent location to obtain the vehicle permanent location of the target vehicle; selecting the vehicle permanent location whose quantile is greater than a preset value in the vehicle permanent location of the target vehicle; and associating the vehicle ID and the enterprise ID to obtain the vehicle permanent location under each enterprise.

[0076] Furthermore, the coefficient of the enterprise fleet is calculated based on the enterprise parking lot data, including: associating the associated data between the vehicle and the enterprise with the enterprise parking lot data, and recording the number of associated vehicles as n, where n is a natural number; aggregating the data through the enterprise ID, obtaining the number of vehicles parked in the enterprise parking lot among the associated vehicles of the enterprise and recording it as m, where m is a natural number; and dividing m by n as the enterprise fleet coefficient.

[0077] This application screens and groups vehicle parking data and related data between vehicles and enterprises to obtain parking points to be clustered that meet preset conditions, and inputs the parking points to be clustered into the trained DBSCAN clustering model to obtain vehicle permanent locations, thereby improving the efficiency of data mining; and obtains enterprise parking lot data through secondary DBSCAN clustering, calculates the coefficient of the enterprise fleet based on the enterprise parking lot data, and operates the vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as the enterprise fleet, thereby improving the detail and accuracy of data mining, and being able to quickly find the operation status of the corresponding enterprise fleet in relevant application scenarios, which is convenient for vehicle scheduling, statistics and related applications.

[0078] Embodiment 2:

[0079] This embodiment implements a method for identifying an enterprise fleet based on stop point clustering, including: obtaining vehicle stop data and vehicle-enterprise association data; filtering and grouping the vehicle stop data and vehicle-enterprise association data to obtain stop points to be clustered that meet preset conditions; inputting the stop points to be clustered into a trained DBSCAN clustering model to obtain vehicle permanent locations; filtering and associating the vehicle permanent locations to obtain the vehicle permanent locations under each enterprise, and inputting the vehicle permanent locations under each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data; calculating the coefficient of the enterprise fleet based on the enterprise parking lot data; operating the vehicles under the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as an enterprise fleet, otherwise, operating as a non-enterprise fleet. The specific description of the steps is as follows.

[0080] The first step is to obtain vehicle parking data and the associated data between vehicles and enterprises.

[0081] In the specific implementation process, vehicle stop data and the associated data between vehicles and enterprises can be collected in relevant software or manually. Vehicle stop data include vehicle ID, stop date, stop start time, stop end time, stop duration, stop point longitude and stop point latitude, etc.; the associated data between vehicles and enterprises include the correspondence between vehicle ID and enterprise ID.

[0082] The second step is to filter and group the vehicle stop data and the associated data between vehicles and enterprises to obtain the stops to be clustered that meet the preset conditions.

[0083] The vehicle stop data and the associated data between the vehicle and the enterprise are screened and grouped to obtain the stop points to be clustered that meet the preset conditions, including: selecting stop points with a preset stop time range; grouping the selected stop points by vehicle ID; analyzing and determining the stop points to be clustered that meet the preset conditions. For example, in a possible specific implementation, the stop points are filtered by the stop time of the stop point>=30 minutes, and the different stop points are grouped by vehicle ID. The minimum number of clustered stop points is set to 100 through analysis. If the number of clustered stop points of the vehicle is less than 100, the remaining points are used to make up 100. If the vehicle has not been put into operation for nearly 10 days, the last stop position point is also added to the clustered stop points.

[0084] The third step is to input the stops to be clustered into the trained DBSCAN clustering model to obtain the vehicle’s permanent location.

[0085] DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a relatively early (1996) and representative density-based clustering algorithm. The main goal of the algorithm is to require less domain knowledge to determine input parameters compared to partition-based clustering methods and hierarchical clustering methods; to discover clusters of arbitrary shapes; and to have better efficiency on large-scale databases. DBSCAN can divide sufficiently high-density areas into clusters and can discover clusters of arbitrary shapes in noisy spatial databases.

[0086] Input the stop points to be clustered into the trained DBSCAN clustering model to obtain the vehicle permanent place, including: input the stop points to be clustered into the trained DBSCAN clustering model; store the number of stops, the number of days of stops and / or the total duration of stops in the clusters obtained based on the model in descending order; and use the preset number of stops at the front in the descending order as the vehicle permanent place. In a possible specific implementation, the stop points to be clustered are input into the trained DBSCAN clustering model. If no cluster is obtained, the stop points with the longest stop time and the stop time greater than the preset number of days are taken as the vehicle permanent place. The DBSCAN clustering model needs to be trained in advance, clustered by DBSCAN, parameters are adjusted, and the optimal parameters of the model are determined by manual sampling verification, so the cluster of each vehicle cluster is the permanent place of the vehicle. However, if a special case occurs, if a certain vehicle does not form a cluster, the point with the longest stop time (for example: 10 days) of this vehicle is used as the vehicle permanent place.

[0087] The fourth step is to filter and associate the vehicle permanent locations to obtain the vehicle permanent locations under each enterprise, and input the vehicle permanent locations under each enterprise into the trained DBSCAN clustering model to obtain the enterprise parking lot data.

[0088] In a specific implementation, the vehicle permanent location is filtered and associated to obtain the vehicle permanent location under each enterprise, including: filtering the vehicle permanent location to obtain the vehicle permanent location of the target vehicle; selecting the vehicle permanent location whose percentile is greater than a preset value among the vehicle permanent locations of the target vehicle; associating the vehicle ID and the enterprise ID to obtain the vehicle permanent location under each enterprise. For example: the number of stops of the filtered vehicle permanent location is greater than 3, for example, a certain vehicle has 5 vehicle permanent locations, namely 100, 50, 30, 2, and 2 points, then the reserved permanent locations are 100, 50, and 30. Then, if it is greater than or equal to the 75th percentile, the 5 permanent locations will retain the points of 100 and 50, and then the vehicle ID and the enterprise ID will be associated, which will form a situation where one enterprise is associated with multiple vehicles, and then the permanent location of the vehicle under the enterprise is input for aggregation. The optimization method is similar to the way of obtaining the vehicle permanent location. For example, there are clusters of enterprises, such as 1000, 800, 300, 100, and 30. If we filter by greater than 300, the parking lots of enterprises left are 1000 and 800.

[0089] The fifth step is to calculate the coefficient of the enterprise fleet based on the enterprise parking lot data.

[0090] The coefficient of the enterprise fleet is calculated based on the enterprise parking lot data, including: associating the associated data of the vehicle and the enterprise with the enterprise parking lot data, recording the number of associated vehicles as n, where n is a natural number; aggregating the data by enterprise ID, obtaining the number of vehicles associated with the enterprise parked in the enterprise parking lot and recording it as m, where m is a natural number; dividing m by n as the enterprise fleet coefficient. In a specific implementation, an enterprise is associated with many vehicles, such as 30 vehicles, but some of them are the enterprise's vehicles, such as 25, and will be parked in the enterprise's parking lot, and some are not the enterprise's vehicles, and the other 5 will not be parked in the enterprise's parking lot. Then the enterprise fleet coefficient r = 25 / 30, if two decimal places are retained, r = 0.83.

[0091] Step 6: The vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold are operated as enterprise fleets, otherwise, they are operated as non-enterprise fleets.

[0092] Specifically, if the enterprise vehicles with a value greater than 0.7 are operated as enterprise fleets, then r=0.83 in the above example meets the conditions and belongs to enterprise fleet operation; if r=0.69, it belongs to non-enterprise fleet operation.

[0093] This application screens and groups vehicle parking data and related data between vehicles and enterprises to obtain parking points to be clustered that meet preset conditions, and inputs the parking points to be clustered into the trained DBSCAN clustering model to obtain vehicle permanent locations, thereby improving the efficiency of data mining; and obtains enterprise parking lot data through secondary DBSCAN clustering, calculates the coefficient of the enterprise fleet based on the enterprise parking lot data, and operates the vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as the enterprise fleet, thereby improving the detail and accuracy of data mining, and being able to quickly find the operation status of the corresponding enterprise fleet in relevant application scenarios, which is convenient for vehicle scheduling, statistics and related applications.

[0094] Embodiment 3:

[0095] This embodiment provides a device for identifying a corporate fleet based on stop point clustering, such as Figure 2 As shown, the device comprises:

[0096] The acquisition module 301 is used to acquire vehicle parking data and associated data between vehicles and enterprises;

[0097] The stop point screening module 302 is used to screen and group the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions;

[0098] The first clustering module 303 is used to input the to-be-clustered stops into the trained DBSCAN clustering model to obtain the vehicle's permanent location;

[0099] The second clustering module 304 is used to filter and associate the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and input the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data;

[0100] A fleet coefficient calculation module 305, used to calculate the coefficient of the enterprise fleet based on the enterprise parking lot data;

[0101] The identification module 306 is used to operate the vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as the enterprise fleet, otherwise, operate them as non-enterprise fleet.

[0102] Please refer to the following Figure 3 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 3As shown, the electronic device 2 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, and the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and when the processor 200 runs the computer program, it executes the enterprise fleet identification method based on stop point clustering provided in any of the aforementioned embodiments of the present application, and the electronic device can be an electronic device with a touch-sensitive display.

[0103] The memory 201 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 203 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0104] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store a program, and the processor 200 executes the program after receiving an execution instruction. The enterprise fleet identification method based on stop point clustering disclosed in any implementation of the embodiment of the present application may be applied to the processor 200, or implemented by the processor 200.

[0105] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 200. The above processor 200 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.

[0106] The electronic device provided in the embodiment of the present application and the enterprise fleet identification method based on stop point clustering 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.

[0107] The present application also provides a computer-readable storage medium corresponding to the enterprise fleet identification method based on stop point clustering provided in the above embodiment. Figure 4 , Figure 4 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is executed by a processor, the enterprise fleet identification method based on stop point clustering provided in any of the aforementioned embodiments is executed.

[0108] In addition, examples of the computer-readable storage medium 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.

[0109] The embodiments of the present application also provide a computer program product, including a computer program, which, when executed by a processor, implements the steps of the enterprise fleet identification method based on stop point clustering provided in any of the aforementioned embodiments, the steps of the method including: obtaining vehicle stop data and vehicle-enterprise association data; screening and grouping the vehicle stop data and vehicle-enterprise association data to obtain stop points to be clustered that meet preset conditions; inputting the stop points to be clustered into a trained DBSCAN clustering model to obtain vehicle permanent locations; filtering and associating the vehicle permanent locations to obtain the vehicle permanent locations under each enterprise, and inputting the vehicle permanent locations under each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data; calculating the coefficient of the enterprise fleet based on the enterprise parking lot data; operating the vehicles under the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as an enterprise fleet, otherwise, operating them as a non-enterprise fleet.

[0110] It should be noted that the algorithms and displays provided herein are not inherently related to any particular computer, virtual device or other device. Various general devices can also be used together with the teachings based thereon. According to the above description, it is obvious that the structure required for constructing such devices is constructed. In addition, the present application is not directed to any specific programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the above description of specific languages ​​is to disclose the best implementation mode of the present application. In the specification provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this specification.

[0111] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present application.

[0112] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition they can be divided into multiple submodules or subunits or subassemblies. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification and all processes or units of any method or device disclosed in this manner can be combined in any combination. Unless otherwise clearly stated, each feature disclosed in this specification can be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0113] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the creation device of the virtual machine according to the embodiment of the present application. The present application can also be implemented as a device or device program for executing part or all of the methods described herein. The program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0114] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for identifying enterprise fleets based on stop point clustering, characterized in that: include: Obtain vehicle parking data and the associated data between vehicles and enterprises; Screening and grouping the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions; Input the to-be-clustered bus stops into the trained DBSCAN clustering model to obtain the vehicle's permanent location; Filtering and associating the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and inputting the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data; Calculate the coefficient of the enterprise fleet based on the enterprise parking lot data; The vehicles of the enterprise whose coefficient of the enterprise fleet is greater than or equal to a preset threshold are operated as the enterprise fleet, otherwise, they are operated as non-enterprise fleets; The calculating of the coefficient of the enterprise fleet based on the enterprise parking lot data comprises: The associated data of vehicles and enterprises are associated with the parking lot data of the enterprises, and the number of associated vehicles is recorded as n, where n is a natural number; Aggregate the data by enterprise ID, obtain the number of vehicles associated with the enterprise parked in the enterprise parking lot and record it as m, where m is a natural number; Divide m by n as the enterprise fleet coefficient.

2. The enterprise fleet identification method based on stop point clustering according to claim 1 is characterized in that: The vehicle stop data includes vehicle ID, stop date, stop start time, stop end time, stop duration, stop point longitude and stop point latitude; the vehicle and enterprise association data includes the correspondence between vehicle ID and enterprise ID.

3. The enterprise fleet identification method based on stop point clustering according to claim 2 is characterized in that: The method further includes: inputting the to-be-clustered stop points into a trained DBSCAN clustering model, and if no cluster is obtained, taking the stop point with the longest stop time and a stop time greater than a preset number of days as the vehicle's permanent residence.

4. The enterprise fleet identification method based on stop point clustering according to claim 3 is characterized in that: The stop points to be clustered are input into the trained DBSCAN clustering model to obtain the vehicle residence, including: Input the to-be-clustered stop points into the trained DBSCAN clustering model; The number of stops, the number of days of stops and / or the total duration of stops in the clusters obtained based on the model are stored in descending order; A preset number of stops at the front in descending order are used as permanent vehicle locations.

5. The enterprise fleet identification method based on stop point clustering according to claim 3 is characterized in that: The vehicle parking data and the associated data between vehicles and enterprises are screened and grouped to obtain parking points to be clustered that meet preset conditions, including: Select a stop point with a preset stop duration; Group the selected stops by vehicle ID; Analyze and determine the stops to be clustered that meet the preset conditions.

6. The enterprise fleet identification method based on stop point clustering according to claim 3 is characterized in that: The filtering and associating of the vehicle permanent locations to obtain the vehicle permanent locations under each enterprise includes: Filtering the vehicle permanent location to obtain the vehicle permanent location of the target vehicle; Selecting a vehicle permanent location whose quantile of the vehicle permanent location of the target vehicle is greater than a preset value; The vehicle ID and the enterprise ID are associated to obtain the permanent location of the vehicle under each enterprise.

7. A device for identifying enterprise fleets based on stop point clustering, characterized in that: The device comprises: An acquisition module is used to acquire vehicle parking data and associated data between vehicles and enterprises; A stop point screening module is used to screen and group the vehicle stop data and the associated data between the vehicle and the enterprise to obtain the stop points to be clustered that meet the preset conditions; A first clustering module is used to input the to-be-clustered stops into a trained DBSCAN clustering model to obtain a vehicle permanent location; The second clustering module is used to filter and associate the vehicle permanent locations to obtain the vehicle permanent locations of each enterprise, and input the vehicle permanent locations of each enterprise into the trained DBSCAN clustering model to obtain enterprise parking lot data; A fleet coefficient calculation module, used to calculate the coefficient of the enterprise fleet based on the enterprise parking lot data; An identification module, used for operating the enterprise vehicles whose coefficient of the enterprise fleet is greater than or equal to a preset threshold as the enterprise fleet, otherwise, operating them as non-enterprise fleets; The calculating of the coefficient of the enterprise fleet based on the enterprise parking lot data comprises: The associated data of vehicles and enterprises are associated with the parking lot data of the enterprises, and the number of associated vehicles is recorded as n, where n is a natural number; Aggregate the data by enterprise ID, obtain the number of vehicles associated with the enterprise parked in the enterprise parking lot and record it as m, where m is a natural number; Divide m by n as the enterprise fleet coefficient.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images