Enterprise relationship identification method, device, equipment and medium based on vehicle trajectory

Abstract

The present application discloses a method, device, equipment and medium for identifying enterprise relationships based on vehicle trajectories, the method comprising: determining target stop data based on vehicle trajectories, the target stop data comprising multiple stops and enterprise information associated with each stop; generating upstream and downstream relationships between enterprises based on target stop data; constructing a directed acyclic graph based on the generated upstream and downstream relationships between enterprises; extracting the upstream enterprise chain and downstream enterprise chain corresponding to the enterprise to be mined in the directed acyclic graph, solving the problem that real transaction data is difficult to collect or Internet data is difficult to analyze. And because the vehicle trajectory is a real cargo transportation route, the authenticity of the upstream and downstream relationships between enterprises obtained from the vehicle trajectory is higher, and the established directed acyclic graph is more comprehensive, so that the upstream and downstream enterprise chains of enterprises can be obtained from the directed acyclic graph as a supply chain, and the direction of the supply chain is clear.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and medium for identifying enterprise relationships based on vehicle trajectories. Background Art

[0002] Currently, the identification of enterprise supply chain relationships mostly relies on the enterprise's transaction data or external Internet data to perform transaction data calculations or Internet data analysis to determine the enterprise's supply chain relationships.

[0003] However, existing identification methods require a large amount of real transaction data, and the data obtained is difficult to be comprehensive and complete. It is impossible to identify all companies and has certain limitations. In addition, large-scale Internet data analysis will also have problems such as large data volume and high analysis difficulty. Summary of the invention

[0004] The purpose of this application is to propose a method, device, equipment and medium for enterprise relationship identification based on vehicle trajectories in response to the deficiencies of the above-mentioned prior art. This purpose is achieved through the following technical solutions.

[0005] The first aspect of the present application proposes a method for identifying enterprise relationships based on vehicle trajectories, the method comprising:

[0006] Determining target stop data according to the collected vehicle trajectory, wherein the target stop data includes a plurality of stop points and enterprise information associated with each stop point;

[0007] Based on the target docking data, generating upstream and downstream relationships between enterprises, wherein the upstream and downstream relationships are used to characterize freight relationships;

[0008] According to all the generated upstream and downstream relationships between enterprises, a directed acyclic graph is constructed, wherein the directed acyclic graph uses enterprises as nodes and the upstream and downstream relationships between enterprises as the directions of the edges between the nodes;

[0009] In the directed acyclic graph, the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined are extracted.

[0010] The second aspect of the present application proposes a vehicle trajectory-based enterprise relationship identification device, the device comprising:

[0011] A stop point identification module, used to determine target stop data according to the collected vehicle trajectories, wherein the target stop data includes multiple stop points and enterprise information associated with each stop point;

[0012] An enterprise relationship identification module, used to generate upstream and downstream relationships between enterprises based on the target docking data, wherein the upstream and downstream relationships are used to characterize freight relationships;

[0013] A graph construction module is used to construct a directed acyclic graph based on all the generated upstream and downstream relationships between enterprises, wherein the directed acyclic graph uses enterprises as nodes and the upstream and downstream relationships between enterprises as the directions of the edges between the nodes;

[0014] The relationship mining module is used to extract the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined in the directed acyclic graph.

[0015] The third aspect of the present application proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect above.

[0016] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method described in the first aspect above.

[0017] Based on the above-mentioned method, device, equipment and medium for identifying enterprise relationships based on vehicle trajectories, the present application has at least the following beneficial effects or advantages:

[0018] The stop points are identified through vehicle trajectories and enterprises are associated with the stop points to obtain the target stop data. Since the vehicle trajectory between two stop points represents the cargo transportation route of the two enterprises associated with the two stop points, the upstream and downstream relationship between enterprises can be generated based on the target stop data. The upstream and downstream relationship represents the freight relationship. Further, a directed acyclic graph is constructed based on the upstream and downstream relationships between all generated enterprises, and the freight relationship map of all enterprises can be obtained. Therefore, through the directed acyclic graph, the upstream enterprise chain and downstream enterprise chain corresponding to the enterprise to be mined can be obtained, which solves the problem that real transaction data is difficult to collect or Internet data is difficult to analyze. And because the vehicle trajectory is a real cargo transportation route, the authenticity of the upstream and downstream relationships between enterprises obtained from the vehicle trajectory is higher, and the established directed acyclic graph is more comprehensive, so the upstream and downstream enterprise chain of the enterprise can be obtained from the directed acyclic graph as the supply chain, and the direction of the supply chain is clear.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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:

[0021] Figure 1 The present invention is a flow chart of an embodiment of a method for identifying enterprise relationships based on vehicle trajectories according to an exemplary embodiment;

[0022] Figure 2 A directed acyclic graph of enterprise relationships is shown according to an exemplary embodiment;

[0023] Figure 3 A schematic diagram of an enterprise supply chain network according to an exemplary embodiment;

[0024] Figure 4 is a schematic structural diagram of a device for identifying enterprise relationships based on vehicle trajectories according to an exemplary embodiment;

[0025] Figure 5 is a schematic diagram of a hardware structure of an electronic device according to an exemplary embodiment;

[0026] Figure 6 The figure is a schematic diagram of the structure of a storage medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0029] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0030] At present, the identification of existing enterprise supply chain relationships mostly relies on text information on the Internet or a large amount of transaction data. The authenticity of network data is difficult to ensure and the data volume is large, making mining difficult. In addition, transaction data is usually large and incomplete, which can easily form data islands and make it impossible to form an effective closed loop for the entire market analysis.

[0031] Based on this, the present application proposes a method for identifying enterprise relationships based on vehicle trajectories, which identifies stop points through vehicle trajectories and associates enterprises with the stop points to obtain target stop data. Since the vehicle trajectory between two stop points represents the cargo transportation route of the two enterprises associated with the two stop points, the upstream and downstream relationships between enterprises can be generated based on the target stop data. The upstream and downstream relationships represent the freight relationship. Further, a directed acyclic graph is constructed based on the upstream and downstream relationships between all generated enterprises, and the freight relationship map of all enterprises can be obtained. Thus, through the directed acyclic graph, the upstream enterprise chain and downstream enterprise chain corresponding to the enterprise to be mined can be obtained, which solves the problem that real transaction data is difficult to collect or Internet data is difficult to analyze. And because the vehicle trajectory is a real cargo transportation route, the authenticity of the upstream and downstream relationships between enterprises obtained from the vehicle trajectory is higher, and the established directed acyclic graph is more comprehensive, so that the upstream and downstream enterprise chains of enterprises can be obtained from the directed acyclic graph as a supply chain, and the direction of the supply chain is clear.

[0032] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The several specific embodiments listed can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0033] Figure 1 The flowchart of an embodiment of a method for identifying enterprise relationships based on vehicle trajectories according to an exemplary embodiment includes the following steps 101 to 104:

[0034] Step 101: determining target stop data according to the collected vehicle trajectories, the target stop data including a plurality of stop points and enterprise information associated with each stop point;

[0035] Step 102: Based on the target docking data, an upstream and downstream relationship between enterprises is generated, and the upstream and downstream relationship is used to characterize the freight relationship;

[0036] Step 103: construct a directed acyclic graph based on all the generated upstream and downstream relationships between enterprises, where the directed acyclic graph uses enterprises as nodes and the upstream and downstream relationships between enterprises as the directions of the edges between the nodes;

[0037] Step 104: In the directed acyclic graph, extract the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined.

[0038] The target stop data can be understood as the stop data generated by the vehicle transporting goods calculated from the vehicle trajectory, which may include the stop points belonging to the loading and unloading stops and the enterprise information associated with each stop point. The data representation of the stop point may include but is not limited to: stop longitude, stop latitude, stop start time, stop end time, stop duration and other data. Enterprise information may include but is not limited to enterprise code, industrial and commercial information, industry or industry and other information.

[0039] The collected vehicle trajectories may include the vehicle trajectories of all vehicles collected within a preset time period (eg, within 12 months), target stop data is determined for each vehicle's vehicle trajectory, and upstream and downstream relationships between enterprises are generated based on the target stop data.

[0040] The upstream and downstream relationship between enterprises can be understood as indicating which enterprise is the upstream enterprise and which is the downstream enterprise between the two enterprises. The upstream enterprise can be understood as the supplier, and the downstream enterprise can be understood as the purchaser. Therefore, the upstream and downstream relationship between enterprises can indicate the direction of freight flow.

[0041] The directed acyclic graph can be understood as a freight relationship map of all companies mined from vehicle trajectories. Figure 2 In the directed acyclic graph shown, the first-level upstream enterprise of enterprise C is enterprise A, there are two first-level downstream enterprises: enterprise B and enterprise D, and the second-level downstream enterprise is enterprise N.

[0042] In a directed acyclic graph, the process of extracting the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined can be implemented by using a transfer algorithm in related technologies, and this application does not make any specific limitations on this.

[0043] The upstream enterprise chain can be understood as the enterprise supply chain obtained upward from the enterprise to be mined as the starting node in the directed acyclic graph, and the downstream enterprise chain can be understood as the enterprise supply chain obtained downward from the enterprise to be mined as the starting node in the directed acyclic graph.

[0044] For example, Figure 2 Taking enterprise C in as the enterprise to be mined as an example, the upstream enterprise chain includes: enterprise A→enterprise C, and the downstream enterprise chain includes: enterprise C→enterprise B, enterprise D→enterprise N.

[0045] At this point, the above Figure 1The enterprise relationship identification process based on vehicle trajectory shown in the figure identifies the stop points through the vehicle trajectory and associates the enterprises with the stop points to obtain the target stop data. Since the vehicle trajectory between the two stop points represents the cargo transportation route of the two enterprises associated with the two stop points, the upstream and downstream relationship between enterprises can be generated based on the target stop data. The upstream and downstream relationship represents the freight relationship. Further, a directed acyclic graph is constructed based on the upstream and downstream relationships between all the generated enterprises, and the freight relationship map of all enterprises can be obtained. Thus, the upstream enterprise chain and downstream enterprise chain corresponding to the enterprise to be mined can be obtained through the directed acyclic graph, which solves the problem that real transaction data is difficult to collect or Internet data is difficult to analyze. And because the vehicle trajectory is a real cargo transportation route, the authenticity of the upstream and downstream relationship between enterprises obtained from the vehicle trajectory is higher, and the established directed acyclic graph is more comprehensive, so the upstream and downstream enterprise chain of the enterprise can be obtained from the directed acyclic graph as the supply chain, and the direction of the supply chain is clear.

[0046] In some embodiments of the present application, the process of step 101 may include:

[0047] A plurality of stops are extracted from the vehicle trajectory, and the POI (Point Of Interest) to which each stop belongs is determined. Then, based on the preset POI-enterprise relationship data and the POI to which each stop belongs, enterprise information is associated with each stop, and stops that are not for loading and unloading are deleted from the plurality of stops, and the remaining stops and the enterprise information associated with the remaining stops are used as target stop data.

[0048] Among them, POI can be understood as a geographical object, such as a corporate office, gas station, service area, repair shop, parking area, restaurant, ferry, etc. The data representation of POI can be an electronic fence and attribute features.

[0049] The specific method for determining the POI to which each stop point belongs is: using a relevant algorithm to calculate the POI to which the stop point belongs according to the stop longitude and the stop latitude of the stop point.

[0050] The POI-enterprise relationship data is the pre-set POI office points included in each enterprise, that is, some enterprises may have offices in multiple locations, each of which belongs to a POI.

[0051] Non-loading and unloading stops may include multiple conditions such as the stop duration being less than the preset time, the POI being a gas station, service area, repair shop, parking area, restaurant or ferry, etc. In other words, stops that meet any of these conditions are considered non-loading and unloading stops.

[0052] In this embodiment, after the stop points are extracted from the vehicle trajectory, the POI to which each stop point belongs is calculated, so that the stop points that are not for loading and unloading can be excluded according to the POI to which they belong, thereby improving the accuracy of enterprise relationship recognition.

[0053] In some embodiments of the present application, the process of step 102 may include:

[0054] The freight status of each group of adjacent docking points in the target docking data is determined, and the upstream and downstream relationships between enterprises are generated according to the freight status of each group of adjacent docking points and the enterprise information respectively associated with each docking point in the target docking data.

[0055] Adjacent stops can be understood as the two stops corresponding to the next stop of a vehicle. By taking the next stop in chronological order for each stop in the target stop data, multiple groups of adjacent stops can be obtained. Each group of adjacent stops can be regarded as a vehicle transportation. Since each stop is associated with enterprise information, each group of adjacent stops can also be regarded as a vehicle transportation between two enterprises.

[0056] Exemplarily, assuming that the n stop points in the target stop data are arranged in positive time order: T1, T2, T3....Tn, n-1 groups of adjacent stop points can be obtained: T1-T2, T2-T3, T3-T4....T(n-1)-Tn.

[0057] The freight status can include loaded and empty. Loaded means that adjacent stops indicate a loaded transportation, and empty means that adjacent stops indicate an empty transportation.

[0058] It is worth explaining here that for the same vehicle, goods are usually transported back and forth between two enterprises. Therefore, the target stop data of each vehicle usually generates a set of upstream and downstream relationships between enterprises, but it does not rule out the possibility of generating multiple sets of upstream and downstream relationships between enterprises.

[0059] In this embodiment, since each group of adjacent stops in the target stop data can be considered as a vehicle transportation between two enterprises, the upstream and downstream relationships between enterprises can be accurately identified by determining the freight status of the adjacent stops and based on the freight status of the adjacent stops and the enterprise information associated with each stop in the target stop data.

[0060] In some embodiments of the present application, with respect to the process of determining the freight status of each group of adjacent stop points in the target stop data, the freight status of each group of adjacent stop points can be identified from different dimensions. For each group of adjacent stop points, the freight status of the adjacent stop points can be identified as loading cargo according to any dimension, and the freight status of the adjacent stop points can be determined as loading cargo.

[0061] Optionally, different dimensions may include mileage dimension, industry dimension, scenario dimension and route dimension.

[0062] The mileage dimensions are:

[0063] For each group of adjacent stops, the vehicle mileage or high-speed mileage ratio is calculated using the vehicle trajectory between the adjacent stops. When the mileage exceeds the preset mileage or the high-speed mileage ratio exceeds the preset ratio, the freight status of the adjacent stops is determined to be cargo. The high-speed mileage ratio refers to the ratio of high-speed trajectories in the vehicle trajectory between the adjacent stops.

[0064] The industry dimensions are:

[0065] For each group of adjacent stops, the freight status of the adjacent stops is determined to be cargo-carrying according to the fact that the industries of the enterprise information associated with each of the adjacent stops meet the preset upstream and downstream relationships. That is, the industries to which the currently associated enterprises of the adjacent stops belong to and the industries to which the next associated enterprises belong meet the preset upstream and downstream relationships. For example, the preset upstream and downstream relationships may include: coal mining industry to coal wholesale industry, coal mining industry to steel mill industry.

[0066] The scene dimensions are:

[0067] For each group of adjacent stops, the freight status of the adjacent stops is determined to be cargo-carrying according to the attribute characteristics of the POIs to which the adjacent stops belong respectively meeting the preset conditions. That is, the adjacent stops are determined to be cargo-carrying if the current stop to the next stop meets the preset conditions. For example, the preset conditions may include: the current stop is a farmland, the next stop is an agricultural and sideline product processing enterprise, and the vehicle type corresponding to the adjacent stops is a livestock vehicle, the current stop has no POI but the next stop belongs to a slaughterhouse.

[0068] The line dimensions are:

[0069] According to the number of groups of adjacent docking points associated with the same enterprise information in the target docking data, the corresponding transport trips between the two enterprises in the two transport directions are counted. The associated same enterprise information means that the two enterprises associated with each group of adjacent docking points are consistent. According to the corresponding transport trips between the two enterprises in the two transport directions, the freight status of each group of adjacent docking points corresponding to the two enterprises is determined.

[0070] The route dimension refers to the situation where there are multiple transportations between two enterprises, that is, in the target stop data, there are multiple groups of adjacent stop points for the associated enterprises A and B.

[0071] The two transportation directions can be understood as the directions from enterprise A to enterprise B and from enterprise B to enterprise A. Exemplarily, assume that the number of groups of adjacent stops associated with enterprise A and enterprise B is 10 groups, the number of groups indicating the direction from enterprise A to enterprise B is 6 groups, and the number of groups indicating the direction from enterprise B to enterprise A is 4 groups. Then, the number of transportation trips from enterprise A to enterprise B is 6, and the number of transportation trips from enterprise B to enterprise A is 4.

[0072] Based on the respective transportation trips of the two enterprises in the two transportation directions, the freight status of each group of adjacent stops corresponding to the two enterprises can be determined, which may include: when both transportation trips are greater than a preset value, calculate the trip ratio according to the two transportation trips, and determine whether the vehicle is one-way transportation or two-way transportation based on the trip ratio. When it is determined to be one-way transportation, determine the freight status of the adjacent stops in the transportation direction with the larger transportation trip as loaded, and determine the freight status of the adjacent stops in the transportation direction with the smaller transportation trip as unloaded; when it is determined to be two-way transportation, obtain the vehicle's permanent residence based on the vehicle trajectory between each group of adjacent stops associated with the two enterprises, screen the first type of stops and the second type of stops among each group of adjacent stops. The first type of stops are the stops reached after departing from the vehicle's permanent residence, and the second type of stops are the stops before returning to the vehicle's permanent residence. Identify the first type of stops as loading points and the second type of stops as unloading points. Then, for each group of adjacent stops, if the adjacent stop indicates the direction from the loading point to the unloading point, determine the freight status of the adjacent stop as loaded; if the adjacent stop indicates the direction from the unloading point to the loading point, determine the freight status of the adjacent stop as unloaded.

[0073] Specifically, define I A-B to represent the number of transportation trips from enterprise A to enterprise B, and I B-A to represent the number of transportation trips from enterprise B to enterprise A, and n represents the judgment threshold for one-way transportation and two-way transportation.

[0074] When both I A-B and I B-A are greater than t, the calculation formula for the trip ratio is:

[0075]

[0076] If r < n, it is determined to be one-way transportation, and the larger of I A-B and I B-A is loaded, and the other is unloaded;

[0077] If r ≥ n, it is determined to be two-way transportation, obtain the vehicle's permanent residence, the stops reached after departing from the vehicle's permanent residence are loading points, the stops before returning to the vehicle's permanent residence are unloading points, and the direction from the loading point to the unloading point is determined as loaded, and the direction from the unloading point to the loading point is determined as unloaded.

[0078] In this embodiment, the freight status of each group of adjacent stops is identified from different dimensions such as mileage dimension, industry dimension, scenario dimension and route dimension. As long as any dimension identifies the freight status of the adjacent stops as being loaded with cargo, the freight status of the adjacent stops will be determined as being loaded with cargo, so as to increase the amount of freight data of the enterprise and ensure the accuracy of identifying the upstream and downstream relationships of the enterprise.

[0079] In some embodiments of the present application, the process of generating upstream and downstream relationships between enterprises based on the freight status of each group of adjacent docking points and the enterprise information respectively associated with each docking point in the target docking data may include:

[0080] Adjacent stops whose freight status is loading are selected in each group of adjacent stops, and freight statistical indicators between enterprises in two transportation directions are generated according to the selected adjacent stops and the enterprise information respectively associated with each stop included in the selected adjacent stops. Then, the upstream and downstream relationships between enterprises are determined by using the respective freight statistical indicators between enterprises in two transportation directions.

[0081] Among them, since each group of adjacent stops represents a vehicle transportation between two enterprises and has directionality, it is necessary to obtain the freight statistical indicators of the two enterprises in the two transportation directions respectively.

[0082] Freight statistical indicators can be regarded as freight-related characteristics between enterprises. The freight statistical indicators can include freight trips, incoming cargo ratio, outgoing cargo ratio, cargo classification, etc.

[0083] Freight trips refer to the number of trips in which the freight status of two enterprises is freight in a certain transportation direction, that is, the number of trips from one enterprise to another. For example, the number of groups of adjacent stops of associated enterprises A and B is 10, the number of groups of adjacent stops in the direction from enterprise A to enterprise B is 8, and the corresponding freight trips are 8, and the number of groups of adjacent stops in the direction from enterprise B to enterprise A is 2, and the corresponding freight trips are 2.

[0084] The purchase ratio refers to the proportion of cargo trips between two enterprises in a certain transportation direction, from the perspective of the enterprise serving as the unloading point, to the total cargo trips corresponding to the enterprise. The total cargo trips refers to the sum of cargo trips transporting goods from various enterprises to this enterprise.

[0085] The shipment ratio refers to the proportion of freight trips between two enterprises in a certain transportation direction, from the perspective of the enterprise serving as the loading point, to the total freight trips corresponding to the enterprise. The total freight trips refer to the sum of freight trips transporting goods from the enterprise to various enterprises.

[0086] By utilizing the freight statistical indicators of each enterprise in the two transportation directions, the upstream and downstream relationships between enterprises are determined. The specific method is: the upstream and downstream relationships between enterprises are determined according to the transportation direction corresponding to the maximum cargo trips.

[0087] For example, the number of cargo trips from enterprise A to enterprise B is 20, and the number of cargo trips from enterprise B to enterprise A is 2. The upstream and downstream relationships between enterprises A and B are marked as: enterprise A is the upstream enterprise, and enterprise B is the downstream enterprise.

[0088] In this embodiment, adjacent docking points in a cargo-carrying state are screened out and freight statistical indicators of enterprises in two transportation directions are calculated. Thus, the upstream and downstream relationships between enterprises can be accurately identified based on the calculated freight statistical indicators.

[0089] In some embodiments of the present application, the attributes of the edges between nodes in the directed acyclic graph may use freight statistics indicators. As mentioned above, freight statistics indicators may include not only the number of cargo trips, but also the proportion of incoming cargo and the proportion of outgoing cargo;

[0090] After executing step 104, the method may further include:

[0091] For each level included in the upstream enterprise chain, when there are multiple enterprises in this level, the core enterprises of this level are screened from each enterprise based on the purchase ratio of each enterprise in this level and the enterprises in the next level of this level. When the number of enterprises in this level is 1, the enterprise in this level is taken as the core enterprise of this level, and then the core enterprises obtained for each level are used to generate the core upstream enterprise chain of the enterprises to be mined.

[0092] The core enterprise in the upstream enterprise chain can be understood as the enterprise that contributes the most to the enterprises at the next level. In other words, the enterprises at the current level can be regarded as suppliers, and the enterprises at the next level can be regarded as buyers. If there are multiple suppliers corresponding to the buyers, the one that contributes the most to the buyers is the core supplier.

[0093] Optionally, since the size of the purchase ratio can represent the size of the contribution, when there are multiple enterprises in this level, the enterprise with the largest purchase ratio among the enterprises included in this level can be regarded as the core enterprise.

[0094] For example, as mentioned above Figure 2As shown, the upstream enterprise chain of the enterprise D to be mined is: Enterprise D→Enterprise B, Enterprise C→Enterprise A. It can be seen that Enterprise D is the core enterprise in the first level, and Enterprise A is the core enterprise in the third level. For the second level, assuming that the purchases of Enterprise B and Enterprise D account for 80%, and the purchases of Enterprise C and Enterprise D account for 20%, then Enterprise B in the second level is the core enterprise. It can be obtained that the core upstream enterprise chain of Enterprise D is: Enterprise D→Enterprise B→Enterprise A.

[0095] Furthermore, it may also include:

[0096] For each level included in the downstream enterprise chain, when there are multiple enterprises in this level, the core enterprises of this level are screened from the enterprises included in this level according to the shipment ratio of each enterprise in this level and the enterprises in the previous level of this level. When the number of enterprises in this level is 1, the enterprise in this level is taken as the core enterprise of the level, and then the core enterprises obtained for each level are used to generate the downstream core enterprise chain of the enterprises to be mined.

[0097] The core enterprise in the downstream enterprise chain can be understood as the enterprise that contributes the most to the enterprises at the previous level. In other words, the enterprises at the current level can be regarded as purchasers, and the enterprises at the previous level can be regarded as suppliers. If there are multiple purchasers corresponding to a supplier, the one that contributes the most to the supplier is the core purchaser.

[0098] Optionally, since the size of the shipment ratio can represent the size of the contribution, when there are multiple enterprises in this level, the enterprise with the largest shipment ratio among the enterprises included in this level can be regarded as the core enterprise.

[0099] For example, as mentioned above Figure 2 As shown, the downstream enterprise chain of enterprise C to be mined is: enterprise C→enterprise B, enterprise D→enterprise N. It can be seen that enterprise C is the core enterprise in the first level, and enterprise N is the core enterprise in the third level. For the second level, the shipment share of enterprise B and enterprise C is 80%, and the shipment share of enterprise D and enterprise C is 20%. Then enterprise B in the second level is the core enterprise. It can be obtained that the core upstream enterprise chain of enterprise C is: enterprise C→enterprise B→enterprise N.

[0100] In the above embodiment, by using the purchase ratio and shipment ratio in the freight statistical indicators to focus on filtering the upstream enterprise chain and the downstream enterprise chain of the enterprise to be mined, the core upstream enterprise chain and the core downstream enterprise chain of the enterprise to be mined can be further obtained, so as to mine the upstream and downstream core enterprises of the enterprise from the perspective of the enterprise.

[0101] It should be noted that it may further include:

[0102] The core downstream enterprise chains and core upstream enterprise chains of the enterprises to be discovered that belong to the same industry are obtained, and then the core downstream enterprise chains and core upstream enterprise chains of the enterprises to be discovered are integrated to generate the enterprise supply chain network of the industry.

[0103] Industry refers to the general term for business formats composed of various related industries with different divisions of labor. Industry refers to a collection of units engaged in economic activities of the same nature. Industry covers a wider range. There may be multiple industries to which the companies to be explored belong to the same industry. Therefore, companies belonging to the same industry can be obtained based on industry representative companies, business information or network information.

[0104] After the initial enterprise supply chain network is generated by fusion, if there is a problem that a certain enterprise has a conflicting upstream and downstream relationship with the enterprise to be mined, the upstream correlation score and downstream correlation score of the enterprise with respect to the enterprise to be mined can be determined. If the upstream correlation score is greater than the downstream correlation score, the relationship between the enterprise and the enterprises connected in the downstream direction indicated by the downstream correlation score is cut off; if the upstream correlation is less than the downstream correlation score, the relationship between the enterprise and the enterprises connected in the upstream direction indicated by the upstream correlation score is cut off.

[0105] Among them, the downstream correlation score is used to indicate the downstream direction, specifically, the product of the correlation scores from the enterprise to be mined → the enterprise (downstream transmission) to each passed level is taken as the downstream correlation score; the upstream correlation score is used to indicate the upstream direction, specifically, the product of the correlation scores from the enterprise to be mined ← the enterprise (upstream transmission) to each passed level is taken as the upstream correlation score.

[0106] The correlation score of each level = (number of freight trips between the two enterprises at this level and the next level / total number of freight trips in the same direction)*(1 / number of floors corresponding to this level).

[0107] For example, if Figure 3 As shown, Figure 3 The enterprise supply chain network is generated by integrating the core upstream enterprise chain and the core downstream enterprise chain of the enterprise to be excavated 1 with the core upstream enterprise chain and the core downstream enterprise chain of the enterprise to be excavated 2. It can be seen that enterprise C is both the upstream and the downstream of the enterprise to be excavated 2, which is a contradiction.

[0108] Since the route from enterprise 2 to enterprise C to be mined will pass through enterprise E at the first level and enterprise C at the second level, the downstream correlation score = correlation score of the first level * correlation score of the second level = (8 / (5+8)*1 / 1)*(2 / 2*1 / 2) = 0.3; since enterprise C to enterprise 2 to be mined will pass through enterprise A at the first level and enterprise 2 at the second level, the upstream correlation score = correlation score of the first level * correlation score of the second level = (10 / 10*1 / 1)*(5 / 5*1 / 2) = 0.5.

[0109] Since 0.5>0.3, we can conclude that the relationship between enterprise C and enterprise E is cut off.

[0110] In this embodiment, by integrating the core downstream enterprise chains and core upstream enterprise chains of the enterprises to be mined belonging to the same industry, the enterprise supply chain network of the industry is obtained, which is conducive to a more comprehensive understanding of the development and distribution of the industry.

[0111] Based on the description of the above embodiments, the present application may also provide a specific implementation process of enterprise relationship identification, including the following processing steps:

[0112] Step 1: Get vehicle trajectory;

[0113] Step 2: Identify the stop points in the vehicle trajectory;

[0114] Step 3: Calculate the POI to which the stop belongs and associate the enterprise with the stop;

[0115] Step 4: Eliminate stops that are not for loading and unloading, and eliminate stops that do not meet the stop time requirements, and obtain stops that are for loading and unloading;

[0116] Step 5: Consider each group of adjacent stops belonging to loading and unloading stops as one vehicle transportation, and identify the freight status of each group of adjacent stops, i.e., loaded or empty;

[0117] Step 6: Keep each group of adjacent stops with the freight status of cargo, and count the freight statistical indicators of each enterprise in the two transportation directions, namely, the number of cargo trips, the proportion of incoming cargo, and the proportion of outgoing cargo;

[0118] Step 7: Determine the upstream and downstream relationships between enterprises;

[0119] Step 8: Use the generated upstream and downstream relationships between all enterprises to construct a directed acyclic graph;

[0120] Step 9: Mining upstream and downstream enterprises of the mined enterprises based on the directed acyclic graph.

[0121] Corresponding to the aforementioned embodiment of the enterprise relationship identification method based on vehicle trajectory, the present application also provides an embodiment of an enterprise relationship identification device based on vehicle trajectory.

[0122] Figure 4 FIG. 1 is a schematic diagram of a structure of a device for identifying enterprise relationships based on vehicle trajectories according to an exemplary embodiment. The device is used to execute the method for identifying enterprise relationships based on vehicle trajectories provided in any of the above embodiments. Figure 4 As shown, the enterprise relationship identification device based on vehicle trajectory includes:

[0123] A stop point identification module 410 is used to determine target stop data according to the collected vehicle trajectory, wherein the target stop data includes multiple stop points and enterprise information associated with each stop point;

[0124] An enterprise relationship identification module 420, for generating upstream and downstream relationships between enterprises based on the target docking data, wherein the upstream and downstream relationships are used to characterize freight relationships;

[0125] A graph construction module 430 is used to construct a directed acyclic graph based on all the generated upstream and downstream relationships between enterprises, wherein the directed acyclic graph uses enterprises as nodes and the upstream and downstream relationships between enterprises as the directions of the edges between the nodes;

[0126] The relationship mining module 440 is used to extract the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined in the directed acyclic graph.

[0127] In an optional implementation, the stop point identification module 410 is specifically used to extract multiple stop points from the vehicle trajectory; determine the point of interest (POI) to which each stop point belongs; associate enterprise information with each stop point based on preset POI-enterprise relationship data and the POI to which each stop point belongs; delete the stop points that are not loading and unloading stops among the multiple stop points, and use the remaining stop points and the enterprise information associated with the remaining stop points as target stop data; the non-loading and unloading stops at least include a stop duration less than a preset time and a POI that is a gas station, service area, repair shop, parking area, restaurant or ferry.

[0128] In an optional implementation, the enterprise relationship identification module 420 is specifically used to determine the freight status of each group of adjacent docking points in the target docking data; and generate upstream and downstream relationships between enterprises based on the freight status of each group of adjacent docking points and the enterprise information associated with each docking point in the target docking data.

[0129] In an optional implementation, the enterprise relationship identification module 420 is specifically used to identify the freight status of each group of adjacent stop points in the target stop data from different dimensions during the process of determining the freight status of each group of adjacent stop points in the target stop data; for each group of adjacent stop points, the freight status of the adjacent stop points is identified as loading according to any dimension, and the freight status of the adjacent stop points is determined as loading.

[0130] In an optional implementation, the different dimensions include any combination of mileage dimension, industry dimension, scenario dimension and route dimension; the mileage dimension is: for each group of adjacent stops, the vehicle mileage or high-speed mileage ratio is calculated by using the vehicle trajectory between the adjacent stops, and when the mileage exceeds a preset mileage or the high-speed mileage ratio exceeds a preset ratio, the freight status of the adjacent stops is determined to be cargo; the industry dimension is: for each group of adjacent stops, the freight status of the adjacent stops is determined to be cargo based on the industry to which the enterprise information associated with each of the adjacent stops belongs in accordance with the preset upstream and downstream relationship. cargo; the scenario dimension is: for each group of adjacent stops, according to the attribute characteristics of the POI to which the adjacent stops respectively belong meeting the preset conditions, the freight status of the adjacent stops is determined to be cargo; the route dimension is: according to the number of groups of adjacent stops associated with the same enterprise information in the target stop data, the corresponding transport trips between the two enterprises in the two transport directions are counted; the associated same enterprise information means that the two enterprises associated with each group of adjacent stops are consistent; according to the corresponding transport trips between the two enterprises in the two transport directions, the freight status of each group of adjacent stops corresponding to the two enterprises is determined.

[0131] In an optional implementation, the enterprise relationship identification module 420 is specifically used to select adjacent stops whose freight status is cargo in each group of adjacent stops during the process of generating upstream and downstream relationships between enterprises based on the freight status of each group of adjacent stops and the enterprise information respectively associated with each stop in the target stop data; generate freight statistical indicators of the enterprises in two transportation directions based on the selected adjacent stops and the enterprise information respectively associated with each stop included in the selected adjacent stops; and determine the upstream and downstream relationships between enterprises using the freight statistical indicators of the enterprises in two transportation directions.

[0132] In an optional implementation, the freight statistical indicators include freight trips; the enterprise relationship identification module 420 is specifically used to determine the upstream and downstream relationships between enterprises according to the transportation direction corresponding to the maximum freight trips when using the respective freight statistical indicators of the enterprises in two transportation directions to determine the upstream and downstream relationships between enterprises.

[0133] In an optional implementation, the attributes of the edges between nodes in the directed acyclic graph are freight statistics indicators, and the freight statistics indicators include the proportion of incoming goods and the proportion of outgoing goods; the device also includes ( Figure 4 Not shown):

[0134] The core enterprise mining module is used for, after the relationship mining module 440, for each level included in the upstream enterprise chain, when there are multiple enterprises in the level, selecting the core enterprise of the level from the enterprises according to the purchase ratio of each enterprise in the level and the enterprises in the next level of the level; when the number of enterprises in the level is 1, taking the enterprise in the level as the core enterprise of the level; and using the core enterprises obtained for each level to generate the core upstream enterprise chain of the enterprise to be mined.

[0135] In an optional implementation, the core enterprise mining module is also used to select the core enterprises of each level included in the downstream enterprise chain based on the shipment ratio of each enterprise in the level and the enterprises in the previous level of the level when there are multiple enterprises in the level; when the number of enterprises in the level is 1, take the enterprise in the level as the core enterprise of the level; and use the core enterprises obtained for each level to generate the core downstream enterprise chain of the enterprise to be mined.

[0136] In an optional implementation, the device further includes ( Figure 4 Not shown):

[0137] The industrial chain mining module is used to obtain the core downstream enterprise chain and the core upstream enterprise chain of the enterprise to be mined belonging to the same industry after the relationship mining module 440; integrate the obtained core downstream enterprise chain and core upstream enterprise chain of each enterprise to be mined to generate the enterprise supply chain network of the industry.

[0138] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0139] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0140] The embodiment of the present application also provides an electronic device corresponding to the enterprise relationship identification method based on vehicle trajectory provided in the above embodiment, so as to execute the above enterprise relationship identification method based on vehicle trajectory.

[0141] Figure 5 6 is a hardware structure diagram of an electronic device according to an exemplary embodiment, the electronic device includes: a communication interface 601, a processor 602, a memory 603 and a bus 604; wherein the communication interface 601, the processor 602 and the memory 603 communicate with each other through the bus 604. The processor 602 can execute the enterprise relationship identification method based on vehicle trajectory described above by reading and executing machine executable instructions corresponding to the control logic of the enterprise relationship identification method based on vehicle trajectory in the memory 603. The specific content of the method is referred to the above embodiment, which will not be repeated here.

[0142] The memory 603 mentioned in this application can be any electronic, magnetic, optical or other physical storage device, and can contain storage information, such as executable instructions, data, etc. Specifically, the memory 603 can be RAM (Random Access Memory), flash memory, storage drive (such as hard disk drive), any type of storage disk (such as optical disk, DVD, etc.), or similar storage medium, or a combination thereof. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 601 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0143] The bus 604 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 603 is used to store programs, and the processor 602 executes the programs after receiving execution instructions.

[0144] Processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in processor 602 or an instruction in software form. The above-mentioned processor 602 can be a general-purpose processor, including a network processor (Network Processor, referred to as NP), 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, etc. The disclosed methods, steps and logic block diagrams 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 conjunction with the embodiments of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor are combined to execute.

[0145] The electronic device provided in the embodiment of the present application and the enterprise relationship identification method based on vehicle trajectory 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.

[0146] The present application also provides a computer-readable storage medium corresponding to the enterprise relationship identification method based on vehicle trajectory provided in the above embodiment. Figure 6 As shown, 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 run by a processor, the enterprise relationship identification method based on vehicle trajectories provided in any of the aforementioned embodiments will be executed.

[0147] It should be noted that 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.

[0148] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the enterprise relationship identification method based on vehicle trajectories provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0149] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0150] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0151] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for identifying enterprise relationships based on vehicle trajectories, characterized in that: The method comprises: Determining target stop data according to the collected vehicle trajectory, wherein the target stop data includes a plurality of stop points and enterprise information associated with each stop point; Based on the target docking data, generating upstream and downstream relationships between enterprises, wherein the upstream and downstream relationships are used to characterize freight relationships; According to all the generated upstream and downstream relationships between enterprises, a directed acyclic graph is constructed, wherein the directed acyclic graph uses enterprises as nodes and the upstream and downstream relationships between enterprises as the directions of the edges between the nodes; In the directed acyclic graph, the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined are extracted.

2. The method according to claim 1, characterized in that Determining target stop data according to the collected vehicle trajectory includes: extracting a plurality of stop points in the vehicle trajectory; Determine the point of interest (POI) for each stop; According to the preset POI-enterprise relationship data and the POI to which each stop belongs, associate enterprise information with each stop; The stop points that are not for loading and unloading are deleted from the multiple stops, and the remaining stops and the enterprise information associated with the remaining stops are used as target stop data; the non-loading and unloading stops at least include stops with a duration less than a preset time and POIs such as gas stations, service areas, repair shops, parking areas, restaurants or ferries.

3. The method according to claim 1, characterized in that The generating of upstream and downstream relationships between enterprises based on the target docking data includes: Determine the freight status of each group of adjacent docking points in the target docking data; According to the freight status of each group of adjacent docking points and the enterprise information respectively associated with each docking point in the target docking data, the upstream and downstream relationships between enterprises are generated.

4. The method according to claim 3, characterized in that The determining of the freight status of each group of adjacent docking points in the target docking data includes: Identify the freight status of each group of adjacent docking points in the target docking data from different dimensions; For each group of adjacent stop points, if the freight status of the adjacent stop points is identified as being loaded with cargo according to any dimension, the freight status of the adjacent stop points is determined to be loaded with cargo.

5. The method according to claim 4, characterized in that The different dimensions include any combination of mileage dimension, industry dimension, scenario dimension and route dimension; The mileage dimension is: for each group of adjacent stops, the vehicle mileage or high-speed mileage ratio is calculated using the vehicle trajectory between the adjacent stops, and when the mileage exceeds a preset mileage or the high-speed mileage ratio exceeds a preset ratio, the freight status of the adjacent stops is determined to be cargo; The industry dimension is: for each group of adjacent stop points, according to the industries to which the enterprise information associated with each of the adjacent stop points belongs meeting the preset upstream and downstream relationship, the freight status of the adjacent stop points is determined to be cargo; The scenario dimension is: for each group of adjacent stops, according to the attribute characteristics of the POIs to which the adjacent stops belong respectively meeting the preset conditions, determining that the freight status of the adjacent stops is cargo; The route dimension is: according to the number of groups of adjacent stop points associated with the same enterprise information in the target stop data, the corresponding transport trips between two enterprises in two transport directions are counted; the associated same enterprise information means that the two enterprises associated with each group of adjacent stop points are consistent; According to the corresponding transport trips between the two enterprises in the two transport directions, the freight status is determined by determining each group of adjacent stop points corresponding to the two enterprises.

6. The method according to claim 3, characterized in that: The generating of upstream and downstream relationships between enterprises according to the freight status of each group of adjacent docking points and the enterprise information respectively associated with each docking point in the target docking data includes: Select adjacent stops whose freight status is "carrying goods" from each group of adjacent stops; Generate freight statistics indicators for the enterprises in two transportation directions according to the selected adjacent stops and the enterprise information respectively associated with each stop included in the selected adjacent stops; By utilizing the freight statistical indicators of each enterprise in the two transportation directions, the upstream and downstream relationships between enterprises can be determined.

7. The method according to claim 6, characterized in that The freight statistics indicators include freight trips; The above-mentioned use of the freight statistical indicators of the enterprises in the two transportation directions to determine the upstream and downstream relationships between the enterprises includes: The upstream and downstream relationships between enterprises are determined according to the transportation direction corresponding to the maximum cargo trips.

8. The method according to any one of claims 1 to 7, characterized in that: The attributes of the edges between nodes in the directed acyclic graph are freight statistics indicators, and the freight statistics indicators include the proportion of incoming goods and the proportion of outgoing goods; After extracting the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined in the directed acyclic graph, the method further includes: For each level included in the upstream enterprise chain, if there are multiple enterprises in the level, the core enterprise of the level is selected from the enterprises according to the purchase ratio of each enterprise in the level and the enterprises in the next level of the level; When the number of enterprises in the level is 1, the enterprise in the level is regarded as the core enterprise of the level; The core enterprises obtained for each level are used to generate the core upstream enterprise chain of the enterprise to be mined.

9. The method according to claim 8, characterized in that After extracting the upstream enterprise chain and the downstream enterprise chain corresponding to the enterprise to be mined in the directed acyclic graph, the method further includes: For each level included in the downstream enterprise chain, if there are multiple enterprises in the level, the core enterprises of the level are selected from the enterprises according to the shipment ratio of each enterprise in the level to the enterprises in the previous level of the level; When the number of enterprises in the level is 1, the enterprise in the level is regarded as the core enterprise of the level; The core enterprises obtained for each level are used to generate the core downstream enterprise chain of the enterprise to be mined.

10. The method according to claim 9, characterized in that The method further comprises: Obtain the core downstream enterprise chain and core upstream enterprise chain of the enterprises to be discovered belonging to the same industry; The core downstream enterprise chains and core upstream enterprise chains of each enterprise to be discovered are integrated to generate an enterprise supply chain network for the industry.

Images