Enterprise relationship analysis method, system and storage medium based on truck data

Abstract

The present application provides a method, system, and computer medium for analyzing enterprise relationships based on truck data. Specifically, multiple clusters of freight areas are obtained based on freight data; a sequence of vehicle clusters is obtained based on vehicle stop data; the cluster sequence is a plurality of clusters arranged in chronological order; cluster relationship data is obtained through data traversal and filtering based on the vehicle cluster sequence; the geographic area of the target enterprise is mapped to the cluster, and the upstream and downstream relationships of the target enterprise are obtained based on the cluster relationship data. The present application obtains upstream and downstream relationships between enterprises by analyzing freight data between enterprises, solving the problems of low efficiency and poor accuracy in the current analysis and identification of industrial relationships between enterprises.

Description

Technical Field

[0001] The present application belongs to the field of Internet technology, and specifically relates to a method, system and storage medium for analyzing enterprise relationships based on truck data. Background Art

[0002] At present, the enterprise industrial chain can objectively reflect the enterprise's operating capabilities and serve as an important reference or basis for enterprise risk identification. It also has crucial reference value in many aspects such as enterprise risk transmission and industry correlation analysis. Therefore, it is necessary to analyze and identify the industrial relations of enterprises.

[0003] However, some existing methods use invoice information to construct inter-enterprise relationships. This approach can only collect information about the companies and their relationships that generate transactions on a single platform. Alternatively, inter-enterprise relationships are obtained by analyzing public documents such as quarterly and annual reports and prospectuses. However, due to the unstructured nature of these data and the complexity of semantic understanding, this approach has very low information acquisition efficiency and accuracy. Summary of the Invention

[0004] The present invention proposes a method system and storage medium for analyzing enterprise relationships based on truck data, aiming to solve the problems of low efficiency and poor accuracy in the current analysis and identification of industrial relationships of enterprises.

[0005] According to a first aspect of an embodiment of the present application, a method for analyzing enterprise relationships based on truck data is provided, specifically comprising the following steps:

[0006] Obtain multiple clusters of freight areas based on freight data;

[0007] According to the parking data of the vehicles, a clustering area sequence of the vehicles is obtained; the clustering area sequence is a plurality of clustering areas arranged in chronological order;

[0008] According to the vehicle cluster sequence, cluster relationship data is obtained through data traversal and filtering;

[0009] The geographical area of the target enterprise is mapped into an agglomeration area, and the upstream and downstream relationships of the target enterprise are obtained based on the agglomeration area relationship data.

[0010] In some embodiments of the present application, obtaining multiple clusters of freight areas based on freight data specifically includes:

[0011] Obtain various logistics events based on vehicle aggregation data in freight data;

[0012] Freight events are screened from a variety of logistics events, and the areas corresponding to the freight events are determined through grid clustering, resulting in multiple clusters of freight areas.

[0013] In some embodiments of the present application, obtaining a vehicle gathering area sequence based on vehicle parking data specifically includes:

[0014] According to the parking data of each vehicle, a clustering area sequence of each vehicle is obtained; the clustering area sequence is a plurality of clustering areas arranged in time;

[0015] Summarizes the collection area sequence of all vehicles in the freight area over time.

[0016] In some embodiments of the present application, based on the vehicle cluster sequence, cluster relationship data is obtained by data traversal and filtering, specifically including:

[0017] Traverse all cluster sequences of a certain vehicle within the statistical period to obtain a candidate edge set; any candidate edge in the candidate edge set is a directed relationship vector formed by any two clusters;

[0018] Filter the candidate edge set by the running time threshold, straight-line distance threshold, vehicle ID restriction and / or starting and ending location restriction between cluster areas to obtain the target candidate edge;

[0019] The target candidate edges are merged and constructed to obtain the cluster relationship data.

[0020] In some embodiments of the present application, the cluster relationship data is specifically a directed weighted graph of cluster relationships, and the directed weighted graph Gω is specifically expressed as:

[0021] Gω=(A,ω);

[0022] Where A is the list of target candidate edges; ω is the weight matrix of the target candidate edge, that is, the relationship strength between the two clusters corresponding to the target candidate edge; the relationship strength includes the number of vehicles, vehicle IDs and / or running time between the two clusters.

[0023] In some embodiments of the present application, before merging and constructing the target candidate edges to obtain the cluster relationship data, the following steps are further included:

[0024] Through spatial association, establish the connection between the cluster area and the map POI, and use the attributes of the map POI as the characteristics of the cluster area; or,

[0025] Through spatial association, determine whether the cluster contains the target road; if it does, use the road attributes of the target road as the cluster feature; or,

[0026] The vehicle information of the vehicles parked in the cluster area during the statistical period is used as the cluster area feature.

[0027] In some embodiments of the present application, target candidate edges are merged and constructed to obtain cluster relationship data, specifically including:

[0028] Eliminate invalid clusters based on their characteristics; invalid clusters include service areas, gas stations, toll booths, parking lots, repair stations, checkpoints, roadside stops, and construction sites.

[0029] Remove target candidate edges corresponding to invalid clusters;

[0030] The remaining target candidate edges are merged using the starting cluster area ID and the ending cluster area ID as unique identifiers to obtain the cluster area relationship data; at the same time, the relationship strength between the cluster areas is counted and recorded.

[0031] In some embodiments of the present application, the geographical area of the target enterprise is mapped into an agglomeration area, and the upstream and downstream relationships of the target enterprise are obtained based on the agglomeration area relationship data, specifically including:

[0032] Obtain the geographic area of the target enterprise and convert the geographic area of the target enterprise into a grid ID list of map information;

[0033] Through the pre-set mapping rules between the grid ID list and the cluster ID list, the cluster corresponding to the target enterprise is searched and mapped;

[0034] Obtain the upstream and downstream relationships of the target enterprises based on the cluster relationship data.

[0035] According to a second aspect of an embodiment of the present application, a business relationship analysis system based on truck data is provided, specifically comprising:

[0036] Aggregation area module: used to obtain multiple aggregation areas of the freight area based on freight data;

[0037] Clustering area sequence module: used to obtain the clustering area sequence of vehicles based on the vehicle parking data; the clustering area sequence is a plurality of clustering areas arranged in chronological order;

[0038] Cluster relationship module: used to obtain cluster relationship data through data traversal and filtering based on the cluster sequence of vehicles;

[0039] Enterprise relationship module: used to map the geographical area of the target enterprise into a cluster area, and obtain the upstream and downstream relationships of the target enterprise based on the cluster area relationship data.

[0040] According to a third aspect of an embodiment of the present application, a device for analyzing enterprise relationships based on truck data is provided, comprising:

[0041] Memory: used to store executable instructions; and

[0042] Processor: used to connect to the memory to execute executable instructions to complete the enterprise relationship analysis method based on truck data.

[0043] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored; the computer program is executed by a processor to implement a method for analyzing enterprise relationships based on truck data.

[0044] The enterprise relationship analysis method, system, and computer medium based on truck data in the embodiments of the present application are used. Specifically, multiple clusters of freight areas are obtained based on freight data; based on vehicle parking data, a sequence of vehicle clusters is obtained; the cluster sequence is multiple clusters arranged in chronological order; based on the vehicle cluster sequence, cluster relationship data is obtained through data traversal and filtering; the geographic area of the target enterprise is mapped to the cluster, and the upstream and downstream relationships of the target enterprise are obtained based on the cluster relationship data. This application obtains upstream and downstream relationships between enterprises by analyzing freight data between enterprises, solving the problems of low efficiency and poor accuracy in the current analysis and identification of industrial relationships between enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 : shows a schematic diagram of the steps of the enterprise relationship analysis method based on truck data according to an embodiment of the present application;

[0047] Figure 2 : A schematic diagram of the steps for obtaining cluster area relationship data according to an embodiment of the present application is shown;

[0048] Figure 3 ] shows a schematic diagram of the aggregation region sequence in S103 according to an embodiment of the present application;

[0049] Figure 4 : shows a schematic diagram of the principle of mapping rules between the grid ID list and the cluster ID list according to an embodiment of the present application;

[0050] Figure 5 : shows a schematic diagram of the downstream relationship of a certain enterprise according to an embodiment of the present application;

[0051] Figure 6 : shows a schematic structural diagram of an enterprise relationship analysis system based on truck data according to an embodiment of the present application;

[0052] Figure 7Schematic diagram of the structure of the enterprise relationship analysis device based on truck data according to an embodiment of the present application is shown in FIG. DETAILED DESCRIPTION

[0053] During the implementation of this application, the inventors discovered that current enterprise and industry relationship analysis, such as using invoice information to construct inter-enterprise relationships, can only capture the information generated by transactions on a single platform and their relationships. Another example is analyzing public documents such as quarterly and annual reports and prospectuses to obtain inter-enterprise relationships. However, due to the unstructured nature of text and the complexity of semantic understanding, this method raises questions about the efficiency and accuracy of information acquisition.

[0054] Based on this, this application constructs upstream and downstream relationships of enterprises based on data such as freight vehicle stops and geographic information through grid clustering, cluster relationship mining, spatial information association, etc., to provide data support for macro and micro analysis of logistics-related industries.

[0055] Specifically, the present application is a method, system and computer medium for analyzing enterprise relationships based on truck data, which obtains multiple clusters of freight areas based on freight data; obtains a cluster sequence of vehicles based on vehicle stop data; the cluster sequence is multiple clusters arranged according to time; obtains cluster relationship data based on the cluster sequence of vehicles through data traversal and filtering; maps the geographical area of the target enterprise to the cluster, and obtains the upstream and downstream relationships of the target enterprise based on the cluster relationship data.

[0056] This application obtains the upstream and downstream relationships between enterprises by analyzing the freight data between enterprises, solving the current problems of low efficiency and poor accuracy in analyzing and identifying the industrial relationships of enterprises.

[0057] In order to make the technical solutions and advantages of the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, and are not an exhaustive list of all the embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other unless they conflict.

[0058] Example 1

[0059] Figure 1 Schematic diagram of the steps of the enterprise relationship analysis method based on truck data according to an embodiment of the present application is shown in FIG.

[0060] like Figure 1 As shown, the enterprise relationship analysis method based on truck data in the embodiment of the present application specifically includes the following steps:

[0061] S101: Acquire multiple clusters of freight areas according to freight data.

[0062] Specifically, first, multiple logistics events are obtained based on the vehicle aggregation data in the freight data; then, freight events are screened from the multiple logistics events, and the areas corresponding to the freight events are determined through grid clustering to obtain multiple clustering areas of the freight area.

[0063] In practice, given that areas where freight vehicles gather are likely to host logistics events, these logistics events in the aggregated data can be divided into loading and unloading, rest, refueling, and congestion events. From the numerous logistics events, freight events related to logistics, such as loading and unloading, are identified, while rest, refueling, and congestion events are considered non-freight events. The clustering areas of freight events are then further determined.

[0064] Using grid clustering, the clustering areas of freight events are clustered based on map information to obtain multiple clusters. Finally, the corresponding mapping rules are obtained by matching the cluster ID list with the grid ID list.

[0065] S102: Obtain a vehicle gathering area sequence based on the vehicle parking data.

[0066] Specifically, based on the parking data of each vehicle, the clustering area sequence of each vehicle is obtained; the clustering area sequence is a plurality of clustering areas arranged according to time; and then the clustering area sequences of all vehicles in the freight area within a period of time are summarized.

[0067] S103: Obtain clustering area relationship data through data traversal and filtering based on the clustering area sequence of the vehicles.

[0068] Figure 2 Schematic diagram of the steps for obtaining cluster area relationship data according to an embodiment of the present application is shown in FIG.

[0069] like Figure 2 As shown, the specific steps include:

[0070] S1031: Traverse all clustering area sequences of a certain vehicle within the statistical period to obtain a candidate edge set; any candidate edge in the candidate edge set is a directed relationship vector formed by any two clustering areas;

[0071] S1032: Filter the candidate edge set based on the running time threshold between clusters, the straight-line distance threshold, the vehicle ID restriction, and / or the starting and ending location restrictions to obtain the target candidate edge;

[0072] S1033: Merge and construct target candidate edges to obtain cluster relationship data.

[0073] Among them, in S1032, when filtering the candidate edge set through the running time threshold, straight-line distance threshold, vehicle ID restriction and / or starting and ending point location restriction between the cluster areas, the present application adopts a time window-based clipping method.

[0074] Figure 3 A schematic diagram of the aggregation region sequence in S103 according to an embodiment of the present application is shown in FIG.

[0075] First, the time series of a single vehicle’s stop points is combined with the aggregated clusters to form a sequence of different clusters for a single vehicle.

[0076] like Figure 3 As shown, for a cluster region A in the sequence i , which is consistent with any subsequent cluster A i+1 、A i+2 ...A i+k ...A n Can form a binary directed relationship A i A i+k In a single cargo transport, a certain gathering area will only have a valid business-meaningful relationship with a limited number of downstream locations.

[0077] To prevent the number of relationships from exploding, this paper introduces a time window to prune invalid cluster relationships. The method is as follows:

[0078] 1) Traverse all cluster sequences of a vehicle within the calculation period (such as one year) and generate a candidate edge set A i A j ;

[0079] 2) Calculate A i A j Average speed v ij ; The calculation method is the distance between the two gathering intervals divided by the distance of the vehicle from gathering area A i To gathering area A j The time taken, average speed v ij The calculation formula is:

[0080]

[0081] Among them, S ij is the distance between two clustering intervals, t j , t i The vehicles passing through the gathering area A j 、A i Recording time.

[0082] 3) Determine the average speed v ij Relationship with the empirical speed v0, if v ijIf it is greater than v0, the edge is retained, otherwise it is pruned. The empirical speed v0 is a pre-set value.

[0083] Finally, by limiting the running time threshold between clusters, candidate edges that are not within the range are filtered out.

[0084] Similarly, the candidate edge set can be optionally filtered by a straight-line distance threshold, a vehicle ID restriction, and / or a start and end point location restriction.

[0085] The final generated includes the running time of the two clusters (A i+k The starting stop time of the stop collection minus A i The end stop time of the stop collection), straight-line distance (A i+k The geometric center of the set of stops in A i The distance between the geometric center of the stop point set and the vehicle ID, the administrative district of the starting and ending points, and other information i A i+k .

[0086] In a preferred embodiment, the present application takes into account that the time window used for the edges generated at this time is too loose, and the candidate edges formed cannot constitute a valid fence relationship.

[0087] To solve this problem, this application uses the quantile method for further filtering.

[0088] First, all candidate edges starting from Administrative District X and ending in Administrative District Y are aggregated to calculate a list of inter-administrative-district travel times. This list of travel times is then used to perform a secondary screening of valid relationships. The method involves selecting the 10th percentile of the sorted travel time list (meaning the time taken by the most efficient vehicle) as the benchmark time, multiplying it by a certain efficiency factor (e.g., 1.5, meaning the travel time is 1.5 times that of the leading vehicle). This method then filters out edges with a travel time greater than this 10th percentile. The quantile method is used because, compared to the mean, the quantile is a more stable statistic.

[0089] Specific implementation examples are as follows:

[0090] For example, aggregating by administrative district between Beijing and Shanghai generates a sorted list of travel times (e.g., the fastest is 300 minutes, the slowest is 1200 minutes), representing the travel times between the two cities' clusters. Assuming the list length is 100, the time recorded at position 10, for example, 420 minutes, is used. Finally, the time recorded at position 10% of the total list length in the sorted list is used as the base time.

[0091] In some embodiments of the present application, after obtaining the target candidate edge through S1032, it also includes: establishing a connection between the cluster area and the map POI through spatial association, and using the attributes of the map POI as the cluster area feature; judging whether the cluster area contains the target road through spatial association; if it contains, then using the road attributes as the cluster area feature; and using the vehicle information of the vehicles parked in the cluster area during the statistical period as the cluster area feature.

[0092] This involves building a profile of the clustered areas. Specifically, this involves mining cluster characteristics by combining data such as map POIs, road networks, and vehicle information. For POI data, this involves first mining the underlying tags within the POIs themselves. For example, by using keywords in POI names, we can identify names and type tags that are strongly related to logistics, such as gas stations, service areas, logistics parks, industrial parks, factories and mines, airports, docks, maintenance stations, and parking lots.

[0093] Then, through spatial association, a connection is established between the cluster and the POI, and the POI attributes are transferred to the cluster. For road network data, spatial association can be directly used to determine whether the cluster contains roads and transfer attributes such as road grade to the cluster. For vehicle information, by analyzing the collection of vehicles that have stopped in the target cluster, in-depth information such as vehicle type distribution, number of active days, dwelling duration distribution, and operating hours distribution can be obtained.

[0094] Next, in step S1033, the target candidate edges are merged and constructed to obtain cluster relationship data, which specifically includes:

[0095] According to the characteristics of the cluster areas, invalid cluster areas are removed; invalid cluster areas include service areas, gas stations, toll stations, parking lots, maintenance stations, checkpoints, roadside stops and construction sites; the target candidate edges corresponding to invalid cluster areas are removed; the remaining target candidate edges are merged with the starting cluster area ID and the end cluster area ID as unique identifiers to obtain the cluster area relationship data; at the same time, the relationship strength between the cluster areas is counted and recorded.

[0096] In this embodiment, the cluster relationship data is specifically a directed weighted graph of cluster relationships. The directed weighted graph Gω is specifically expressed as:

[0097] Gω=(A,ω);

[0098] Where A is the list of target candidate edges; ω is the weight matrix of the target candidate edge, that is, the relationship strength between the two clusters corresponding to the target candidate edge; the relationship strength includes the number of vehicles, vehicle IDs and / or running time between the two clusters.

[0099] Among them, the weight matrix of ω can be specifically expressed as:

[0100]

[0101] Any target candidate edge can be expressed as i , A j >,ω ij Representatives from cluster A i To gathering area A j strength of the relationship.

[0102] S104: Map the geographical area of the target enterprise into an agglomeration area, and obtain the upstream and downstream relationships of the target enterprise based on the agglomeration area relationship data.

[0103] Specifically, first, the actual geographical area of the target enterprise is obtained, and the geographical area of the target enterprise is converted into a grid ID list of map information; through the pre-set mapping rules of the grid ID list and the cluster ID list, the cluster area corresponding to the target enterprise is searched and mapped; and the upstream and downstream relationships of the target enterprise are obtained based on the cluster area relationship data.

[0104] Figure 4 Schematic diagram showing the principle of mapping rules between grid ID list and cluster ID list according to an embodiment of the present application.

[0105] The mapping rules between the grid ID list and the cluster ID list are preset, that is, an inverted index from the grid ID to the cluster ID is established to facilitate the search of upstream and downstream relationships.

[0106] like Figure 4 As shown in the figure, after obtaining the actual fence area A for a target enterprise, in order to quickly associate the actual fence area A with the cluster area B it hits, we first need to use a function to convert the actual fence into a list of grid IDs it covers, and then query the cluster area corresponding to each sub-grid ID. The purpose of the inverted index is to establish a mapping between grid IDs and cluster areas.

[0107] Figure 5 A schematic diagram of the downstream relationship of a certain enterprise according to an embodiment of the present application is shown in FIG.

[0108] Finally, if Figure 5 As shown in Figure 1, the downstream relationship of a company in southwest China generated based on the logistics map can be analyzed to find the downstream administrative regions, companies, and corresponding relationship strengths that have business ties with the company.

[0109] ​The enterprise relationship analysis method based on truck data in the embodiment of the present application is used. Specifically, multiple clusters of freight areas are obtained based on freight data; based on vehicle parking data, a sequence of vehicle clusters is obtained; the cluster sequence is multiple clusters arranged in chronological order; based on the vehicle cluster sequence, cluster relationship data is obtained through data traversal and filtering; the geographic area of the target enterprise is mapped to the cluster, and the upstream and downstream relationships of the target enterprise are obtained based on the cluster relationship data. This application obtains upstream and downstream relationships between enterprises by analyzing freight data between enterprises, solving the problems of low efficiency and poor accuracy in the current analysis and identification of industrial relationships between enterprises.

[0110] Example 2

[0111] This embodiment provides a business relationship analysis system based on truck data. For details not disclosed in the business relationship analysis system based on truck data of this embodiment, please refer to the specific implementation content of the business relationship analysis method based on truck data in other embodiments.

[0112] Figure 6 Schematic diagram of the structure of the enterprise relationship analysis system based on truck data according to an embodiment of the present application is shown in FIG.

[0113] like Figure 6 As shown, the enterprise relationship analysis system based on truck data of an embodiment of the present application specifically includes a cluster module 10, a cluster sequence module 20, a cluster relationship module 30 and an enterprise relationship module 40.

[0114] Specifically,

[0115] Aggregation area module 10: used to obtain multiple aggregation areas of the freight area according to the freight data.

[0116] Specifically, first, multiple logistics events are obtained based on the vehicle aggregation data in the freight data; then, freight events are screened from the multiple logistics events, and the areas corresponding to the freight events are determined through grid clustering to obtain multiple clustering areas of the freight area.

[0117] The gathering area sequence module 20 is used to obtain the gathering area sequence of the vehicle according to the parking data of the vehicle.

[0118] Specifically, based on the parking data of each vehicle, the clustering area sequence of each vehicle is obtained; the clustering area sequence is a plurality of clustering areas arranged according to time; and then the clustering area sequences of all vehicles in the freight area within a period of time are summarized.

[0119] Cluster relationship module 30: used to obtain cluster relationship data through data traversal and filtering according to the cluster sequence of vehicles.

[0120] Specifically, the method includes: traversing all cluster area sequences of a certain vehicle within the statistical period to obtain a set of candidate edges; any candidate edge is a directed relationship vector composed of any two cluster areas; filtering the candidate edge set through the running time threshold, straight-line distance threshold, vehicle ID restriction and / or starting and ending point location restriction between cluster areas to obtain the target candidate edge; merging and constructing the target candidate edges to obtain cluster area relationship data.

[0121] Among them, after obtaining the target candidate edge, it also includes: establishing a connection between the cluster area and the map POI through spatial association, and using the attributes of the map POI as the cluster area feature; judging whether the cluster area contains the target road through spatial association; if it does, then the road attribute is used as the cluster area feature; and using the vehicle information of the vehicles parked in the cluster area during the statistical period as the cluster area feature.

[0122] Enterprise relationship module 40: used to map the geographical area of the target enterprise into an aggregation area, and obtain the upstream and downstream relationships of the target enterprise based on the aggregation area relationship data.

[0123] Specifically, first, the actual geographical area of the target enterprise is obtained, and the geographical area of the target enterprise is converted into a grid ID list of map information; through the pre-set mapping rules of the grid ID list and the cluster ID list, the cluster area corresponding to the target enterprise is searched and mapped; and the upstream and downstream relationships of the target enterprise are obtained based on the cluster area relationship data.

[0124] The enterprise relationship analysis system based on truck data in the embodiment of the present application is adopted. Specifically, the clustering area module 10 obtains multiple clustering areas in the freight area according to the freight data; the clustering area sequence module 20 obtains the vehicle's clustering area sequence according to the vehicle's parking data; the clustering area sequence is multiple clustering areas arranged according to time; the clustering area relationship module 30 obtains clustering area relationship data according to the vehicle's clustering area sequence through data traversal and filtering; the enterprise relationship module 40 maps the geographical area of the target enterprise into a clustering area, and obtains the upstream and downstream relationship of the target enterprise according to the clustering area relationship data.

[0125] This application obtains the upstream and downstream relationships between enterprises by analyzing the freight data between enterprises, solving the current problems of low efficiency and poor accuracy in analyzing and identifying the industrial relationships of enterprises.

[0126] Example 3

[0127] This embodiment provides a business relationship analysis device based on truck data. For details not disclosed in the business relationship analysis device based on truck data in this embodiment, please refer to the specific implementation content of the business relationship analysis method or system based on truck data in other embodiments.

[0128] Figure 7Schematic diagram of the structure of the enterprise relationship analysis device 400 based on truck data according to an embodiment of the present application is shown in FIG.

[0129] like Figure 7 As shown, the enterprise relationship analysis device 400 includes:

[0130] Memory 402: used to store executable instructions; and

[0131] Processor 401: used to connect with memory 402 to execute executable instructions to complete the motion vector prediction method.

[0132] Those skilled in the art will understand that Figure 7 This is merely an example of the enterprise relationship analysis device 400 and does not constitute a limitation of the enterprise relationship analysis device 400. The enterprise relationship analysis device 400 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the enterprise relationship analysis device 400 may also include input and output devices, network access devices, buses, etc.

[0133] The processor 401 (Central Processing Unit, CPU) may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor 401 may be any conventional processor. The processor 401 is the control center of the enterprise relationship analysis device 400, connecting various components of the entire enterprise relationship analysis device 400 using various interfaces and circuits.

[0134] Memory 402 can be used to store computer-readable instructions. Processor 401 implements the various functions of enterprise relationship analysis device 400 by running or executing the computer-readable instructions or modules stored in memory 402 and accessing data stored in memory 402. Memory 402 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on the use of enterprise relationship analysis device 400. Furthermore, memory 402 may include a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, a read-only memory (ROM), a random access memory (RAM), or other non-volatile or volatile storage devices.

[0135] If the modules integrated into enterprise relationship analysis device 400 are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the processes in the above-described method embodiments by instructing the relevant hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When executed by a processor, these computer-readable instructions can implement the steps of each of the above-described method embodiments.

[0136] Example 4

[0137] This embodiment provides a computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the enterprise relationship analysis method based on truck data in other embodiments.

[0138] The enterprise relationship analysis device and computer storage medium based on truck data in the embodiment of the present application obtain multiple clusters of freight areas based on freight data; obtain a sequence of vehicle clusters based on vehicle parking data; the cluster sequence is multiple clusters arranged in chronological order; based on the vehicle cluster sequence, cluster relationship data is obtained through data traversal and filtering; the geographic area of the target enterprise is mapped to the cluster, and the upstream and downstream relationships of the target enterprise are obtained based on the cluster relationship data. The present application obtains upstream and downstream relationships between enterprises by analyzing freight data between enterprises, solving the problems of low efficiency and poor accuracy in the current analysis and identification of industrial relationships between enterprises.

[0139] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0140] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0143] The terms used in this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The singular forms "a," "the," and "the" used in this invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0144] It should be understood that although the terms "first," "second," "third," etc. may be used in the present invention to describe various information, such information should not be limited to these terms. These terms are merely used to distinguish information of the same type from one another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. Depending on the context, the term "if" as used herein may be interpreted as "when," "when," or "in response to determining."

[0145] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0146] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for analyzing enterprise relationships based on truck data, characterized in that: The following steps are involved: Obtain multiple clusters of freight areas based on freight data; Obtaining a vehicle gathering area sequence based on the vehicle parking data; the gathering area sequence is a plurality of gathering areas arranged in chronological order; According to the vehicle's clustering area sequence, clustering area relationship data is obtained through data traversal and filtering; Mapping the target enterprise's geographical area into clusters, and obtaining the target enterprise's upstream and downstream relationships based on the cluster relationship data; The method of obtaining cluster area relationship data by traversing and filtering data based on the cluster area sequence of the vehicle specifically includes: Traverse all clustering area sequences of a certain vehicle within the statistical period to obtain a candidate edge set; any candidate edge in the candidate edge set is a directed relationship vector formed by any two clustering areas; Filter the candidate edge set by using a running time threshold between clusters, a straight-line distance threshold, a vehicle ID restriction, and / or a starting and ending point location restriction to obtain a target candidate edge; Merging and constructing the target candidate edges to obtain cluster relationship data; Mapping the geographical area of the target enterprise into an agglomeration area and obtaining the upstream and downstream relationship of the target enterprise according to the agglomeration area relationship data specifically includes: Obtain the geographic area of the target enterprise and convert the geographic area of the target enterprise into a grid ID list of map information; By using the pre-set mapping rules between the grid ID list and the cluster ID list, the cluster corresponding to the target enterprise is searched and mapped; The upstream and downstream relationships of the target enterprise are obtained based on the cluster relationship data.

2. The enterprise relationship analysis method according to claim 1, characterized in that: The obtaining of multiple clusters of freight areas according to freight data specifically includes: Obtaining a plurality of logistics events according to vehicle aggregation data in the freight data; Freight events are screened from the multiple logistics events, and regions corresponding to the freight events are determined through grid clustering to obtain multiple clustered areas of the freight region.

3. The enterprise relationship analysis method according to claim 1, characterized in that: The cluster relationship data is specifically a directed weighted graph of cluster relationships. The directed weighted graph Gω is specifically expressed as: Gω=(A,ω); Where A is the list of target candidate edges; ω is the weight matrix of the target candidate edges, that is, the relationship strength between the two clusters corresponding to the target candidate edges; the relationship strength includes the number of vehicles, vehicle IDs and / or running time between the two clusters.

4. The enterprise relationship analysis method according to claim 3, characterized in that: Before merging and constructing the target candidate edges to obtain cluster relationship data, the method further includes: Through spatial association, establish the connection between the cluster area and the map POI, and use the attributes of the map POI as the characteristics of the cluster area; or, By spatial association, determine whether the cluster contains the target road; if so, use the road attributes of the target road as the cluster feature; or, The vehicle information of the vehicles parked in the cluster area during the statistical period is used as the cluster area feature.

5. The enterprise relationship analysis method according to claim 4, characterized in that: Merging and constructing the target candidate edges to obtain cluster relationship data specifically includes: Eliminate invalid clusters based on their characteristics; invalid clusters include service areas, gas stations, toll booths, parking lots, repair stations, checkpoints, roadside stops, and construction sites; Remove target candidate edges corresponding to invalid clusters; The remaining target candidate edges are merged using the starting cluster area ID and the ending cluster area ID as unique identifiers to obtain the cluster area relationship data; at the same time, the relationship strength between the cluster areas is counted and recorded.

6. An enterprise relationship analysis system based on truck data, characterized in that: Specifically include: Aggregation area module: used to obtain multiple aggregation areas of the freight area based on freight data; Clustering area sequence module: used to obtain a clustering area sequence of vehicles based on the parking data of the vehicles; the clustering area sequence is a plurality of clustering areas arranged in chronological order; Cluster relationship module: used to obtain cluster relationship data through data traversal and filtering according to the cluster sequence of the vehicle; Obtaining cluster area relationship data through data traversal and filtering based on the cluster area sequence of the vehicle, specifically comprising: traversing all cluster area sequences of a certain vehicle within a statistical period to obtain a candidate edge set; any candidate edge in the candidate edge set is a directed relationship vector formed by any two cluster areas; filtering the candidate edge set based on a running time threshold, a straight-line distance threshold, a vehicle ID restriction, and / or a start and end point location restriction between cluster areas to obtain a target candidate edge; merging and constructing the target candidate edges to obtain the cluster area relationship data; Enterprise relationship module: used to map the geographical area of the target enterprise into a cluster area, and obtain the upstream and downstream relationships of the target enterprise based on the cluster area relationship data; mapping the geographical area of the target enterprise into a cluster area, and obtaining the upstream and downstream relationships of the target enterprise based on the cluster area relationship data, specifically includes: obtaining the geographical area of the target enterprise, and converting the geographical area of the target enterprise into a grid ID list of map information; searching and mapping to obtain the cluster area corresponding to the target enterprise through pre-set mapping rules of the grid ID list and the cluster area ID list; obtaining the upstream and downstream relationships of the target enterprise based on the cluster area relationship data.

7. An enterprise relationship analysis device based on truck data, characterized in that: include: Memory: used to store executable instructions; as well as Processor: used to connect to the memory to execute the executable instructions to complete the enterprise relationship analysis method based on truck data as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that A computer program is stored thereon; the computer program is executed by a processor to implement the enterprise relationship analysis method based on truck data as described in any one of claims 1-5.

Images