Method, system and equipment for identifying association relationship between upstream and downstream customers and merchants, and medium

Abstract

The invention relates to a method, a system, equipment and a medium for identifying an incidence relation between upstream and downstream customers and merchants, the method comprises an increment analysis process and a real-time calculation process, the increment analysis process is used for converting company stock equity genealogy information into structured data containing entity and relation information, incrementally importing the structured data into a graph database, and executing a same-name entity fusion algorithm; natural person entities with the same name and corresponding investment relations are fused; the real-time calculation process comprises the following steps: judging whether company names are in a platform customer and merchant list or not, if so, executing the next step, and if not, carrying out increment analysis; obtaining investment relation information of the two parties from a graph database, obtaining an equity investment path through a path penetration algorithm and a loop identification algorithm, and screening direct control related parties; and calculating the stock holding ratio and the stock holding direction in the stock right investment path, and identifying the stock right association relationship between the two companies. Compared with the prior art, the method has the advantages of being capable of quickly identifying the incidence relation of the two parties and the like.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graph technology, and in particular to a method, system, device and medium for identifying association relationships between upstream and downstream visitors and merchants based on a knowledge graph. Background Art

[0002] Steel, as a means of production, is expensive. Once violations occur during the steel transaction process (such as financing trade, idle trade, and single-order trade), it can easily cause significant losses to the e-commerce platform.

[0003] 'Financing trade' refers to trade activities conducted by upstream suppliers and downstream customers for the sole purpose of obtaining short-term financing, where both the upstream supplier and the downstream customer are controlled by the same actual controller, or there is a specific interest relationship between the upstream and downstream.

[0004] "Idle trade" and "trade without documents" refer to the fictitious trade business through trade documents or the circulation of goods without commercial reasons in order to inflate sales revenue and expand the scale of income.

[0005] The common feature of the above-mentioned trade is that the middleman is responsible for the delivery of goods, does not pursue profit as the purpose, occurs continuously and the price difference earned is very small. The middleman bears the responsibility of controlling the goods and delivery, and bears the risk of price fluctuations from contract signing to delivery, and there is an imbalance between risks and benefits.

[0006] In online trading, e-commerce platforms need to assume the responsibilities of an intermediary: prepay the supplier in full, and the company needs to hold the inventory for a period of time, while the customer redeems the inventory in batches. If there is a close relationship between the supplier and the customer in online transactions, and the physical goods only need to be invoiced, it is easy to promote financing trade, but there may also be idle or single-order trade. Although this practice improves performance, it has potential risks and requires early warning in the contract generation stage before the transaction.

[0007] There are two main ways to determine the relationship between companies on the market. One is through external interfaces such as Qixinbao and Qichacha, and the other is to land the equity data in a traditional relational database for calculation.

[0008] The disadvantage of directly using external interfaces is that it is impossible to superimpose the platform's own risk control rules, nor is it possible to integrate risk control dimensions such as platform transaction flow data and user account information; and traditional relational databases require multiple table associations when processing multi-level equity relationship calculations, which results in low calculation efficiency, difficult code maintenance, and poor display effects.

[0009] Therefore, there is currently a lack of an efficient correlation relationship identification method that can take into account proprietary risk control rules. Summary of the invention

[0010] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a method, system, device and medium for identifying the association relationship between upstream and downstream tourists and merchants based on a knowledge graph.

[0011] The purpose of the present invention can be achieved by the following technical solutions:

[0012] According to a first aspect of the present invention, a method for identifying association relationships between passengers and merchants based on a knowledge graph is provided. The method includes an incremental parsing process and a real-time calculation process, wherein:

[0013] The incremental parsing process consists of the following steps:

[0014] Step S11, regularly obtain and update the platform merchant list, and determine the target company based on the platform merchant list;

[0015] Step S12, cyclically calling the external interface to obtain the target company's equity family tree information, converting the semi-structured data returned by the interface into structured data containing entity and relationship information and saving it;

[0016] Step S13, incrementally importing structured data into the graph database;

[0017] Step S14, executing the same-name entity fusion algorithm, merging the same-name natural person entities and corresponding investment relationships, and marking them with suspicious labels;

[0018] The real-time calculation process includes the following steps:

[0019] Step S21, obtaining the names of two companies whose association relationship needs to be identified, which are input by the user;

[0020] Step S22, determine whether both companies are in the platform merchant list, if yes, execute step S23, if no, take the non-platform merchant company as the target company, and execute steps S12-S14;

[0021] Step S23: For the two companies whose association is to be identified, the investment relationship information is obtained from the graph database, and all equity investment paths within the preset number of layers of the two companies are obtained from the graph database through the path penetration algorithm and the loop identification algorithm, and the directly controlled related parties are screened;

[0022] Step S24, calculating the shareholding ratio and shareholding direction in the equity investment path to identify the equity relationship between the two companies.

[0023] In the step S12, the semi-structured equity genealogy data is converted into a structured entity table and a relationship table, wherein the entity table stores the company and natural person node information, and the relationship table stores the investment and employment relationship between two nodes.

[0024] The node information in the entity table includes name / company name, entity unique identification code, entity tag, wherein the entity tag includes enterprise, natural person and institutional organization.

[0025] The relationship information in the relationship table includes the unique identification code of the starting node, the unique identification code of the target node, the name of the starting node, the name of the target node, the shareholding ratio, the shareholding amount, and the relationship type, among which the relationship types include industrial and commercial shareholders, top ten shareholders, major shareholders, and positions.

[0026] The method of obtaining all equity investment paths within the preset number of layers of the two companies from the graph database through the path penetration algorithm and the loop identification algorithm and screening directly controlled related parties includes the following steps:

[0027] Search for all equity investment paths from the starting node to the target node;

[0028] Traverse each equity investment path and determine the number of nodes and relationships in each path and their corresponding quantities. If the numbers of the two are equal, it means that there is no loop, otherwise, there is a loop;

[0029] If there is no loop, the starting node of each relationship in the path and the shareholding ratio between the two nodes are output, and one of the companies with the to-be-identified relationship is used as the initial reference point to determine the shareholding direction;

[0030] If the reference point is the starting node, the shareholding direction is outward investment, and the tail node of the relationship is used as the new reference point; if the reference point is the tail node, the shareholding direction is invested, and the corresponding shareholding ratio is converted to a negative number, and the starting node of the relationship is used as the new reference point;

[0031] If the number of relationships in the path is 2, and the shareholding directions are external investment and investment, the intermediate node is the directly controlled related party of the related party to be identified;

[0032] Output the non-circular equity investment path of the related party to be identified, as well as the nodes within the path, shareholding direction, and list of directly controlled entities.

[0033] The equity relationship described includes: the two companies have a relationship between directors, supervisors, and senior managers or natural persons holding more than 5% of the shares; the two companies are each other's direct or indirect shareholders; the two companies have common shareholders and the penetrating shareholding is greater than the prescribed ratio; the two companies have a common subsidiary and the penetrating shareholding ratio is greater than the prescribed ratio; the two companies have a sister company relationship and the penetrating shareholding ratio is greater than the prescribed ratio.

[0034] The identified equity relationship types include:

[0035] Type 1: The two companies have a direct or indirect equity relationship exceeding the specified shareholding ratio within the specified equity investment relationship level;

[0036] Type 2: The common shareholders, subsidiaries or brother companies of the two companies have direct or indirect equity relationship with the two companies exceeding the specified shareholding ratio;

[0037] Type 3: The legal person or directors, supervisors and senior managers of one company also serve as the legal person or directors, supervisors and senior managers of the other company or hold shares exceeding the specified shareholding ratio.

[0038] According to a second aspect of the present invention, a system for identifying association relationships between passengers and merchants based on a knowledge graph is provided, comprising:

[0039] The incremental parsing module performs the following steps:

[0040] Step S11, regularly obtain and update the platform merchant list, and determine the target company based on the platform merchant list;

[0041] Step S12, cyclically calling the external interface to obtain the target company's equity family tree information, converting the semi-structured data returned by the interface into structured data containing entity and relationship information and saving it;

[0042] Step S13, incrementally importing structured data into the graph database;

[0043] Step S14, executing the same-name entity fusion algorithm, merging the same-name natural person entities and corresponding investment relationships, and marking them with suspicious labels;

[0044] A real-time computing module is used to perform the following steps:

[0045] Step S21, obtaining the names of two companies whose association relationship needs to be identified, which are input by the user;

[0046] Step S22, determine whether both companies are in the platform merchant list, if yes, execute step S23, if no, take the non-platform merchant company as the target company, and execute steps S12-S14;

[0047] Step S23: For the two companies whose association is to be identified, the investment relationship information is obtained from the graph database, and all equity investment paths within the preset number of layers of the two companies are obtained from the graph database through the path penetration algorithm and the loop identification algorithm, and the directly controlled related parties are screened;

[0048] Step S24, calculating the shareholding ratio and shareholding direction in the equity investment path to identify the equity relationship between the two companies.

[0049] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the method described above is implemented when the processor executes the program.

[0050] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program implements the method described when executed by a processor.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention is based on the knowledge graph of equity investment relationships, and uses a graph algorithm to quickly calculate and judge the types of association relationships between the upstream and downstream merchants on the platform. The operator inputs the names of the upstream and downstream merchants to query whether there is an association relationship between the two companies and the specific type of the association relationship, without the need to call an interface or perform analysis. In addition, the present invention can also customize rules to achieve association relationship determination under customized rules. The present invention can help the Internet steel trading platform to timely lock in possible illegal trading behaviors (financing trade, idle trade, and single-order trade) in centralized operations and online trading links, and reduce the possibility of risk events. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a flow chart of the method of the present invention;

[0054] Figure 2 This is a schematic diagram of the relationship between the directors, supervisors, and senior managers of two companies and natural persons holding more than 5% of the shares in one embodiment;

[0055] Figure 3 Schematic diagram of the relationship between two companies being direct or indirect shareholders of each other in one embodiment, wherein (3a) represents that they are direct shareholders of each other, and (3b) represents that they are indirect shareholders of each other;

[0056] Figure 4 Schematic diagram of the relationship between two companies having a common shareholder and a penetration shareholding greater than a prescribed ratio in an embodiment, wherein (4a) is a schematic diagram of the case where the common shareholder is a natural person, and (4b) is a schematic diagram of the case where the common shareholder is a company;

[0057] Figure 5 A schematic diagram of the relationship between two companies in an embodiment where there are common subsidiaries and the penetration shareholding is greater than a prescribed ratio;

[0058] Figure 6 It is a schematic diagram of the relationship between two companies in an embodiment in which there is a brother company relationship and the penetration shareholding ratio is greater than a prescribed ratio. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0060] In order to cope with the rapid growth of platform transaction business, reduce manual operations, and improve the accuracy and processing efficiency of the judgment of the association relationship between merchants, the present invention introduces the knowledge graph technology. Knowledge graph is a technology that expresses the association relationship between entity nodes through a semantic network. Graph technology is currently widely used in the risk control systems of banks and other financial institutions. Application scenarios include fraud gang identification, capital chain (circle) identification, mining and derivation of implicit relationships between enterprises, and risk event association transmission. The calculation method based on the knowledge graph can greatly improve the efficiency of association judgment. Based on the equity investment graph, the present invention uses a graph algorithm to quickly realize the functions of investment path query, ring path investigation, and multi-layer shareholding ratio penetration calculation between two companies. It can quickly determine the type of equity relationship between two merchants and realize automatic risk transaction warning. The present invention includes a timed incremental parsing process and a real-time calculation process: the timed incremental parsing process can ensure that the equity data of newly registered merchants on the day is parsed and implemented, and can also ensure the real-time performance of the equity data of platform merchants in the current month; the real-time calculation process can calculate the association relationship between upstream and downstream merchants according to custom rules such as platform risk control management files and output the judgment result. Figure 1 As shown, the specific implementation steps are as follows:

[0061] 1) The incremental parsing process includes the following steps:

[0062] Step S11, obtaining and updating the platform merchant list on a daily basis, synchronizing the merchant information newly registered on that day, and determining the target company based on the platform merchant list;

[0063] Step S12, looping and calling the external interface, obtaining the equity genealogy information (json format) within the three layers of the target company, converting the semi-structured data returned by the interface into structured data containing entity and relationship information, writing and saving in MySQL, including company entity, natural person entity, investment relationship (starting entity, target entity, investment amount, shareholding ratio), abnormal analysis record table, and resolved list;

[0064] Step S13, by executing the scheduled task of the APOC plug-in, incrementally importing the structured data in MySQL into the Neo4j graph database;

[0065] Step S14, execute the same-name entity fusion algorithm, fuse the same-name natural person entities and corresponding investment relationships, and add a suspected label. In this embodiment, since the identity ID of the natural person cannot be obtained, the suspected judgment is only based on the same-name situation.

[0066] In one embodiment, the semi-structured equity family tree information obtained is as follows:

[0067]

[0068]

[0069] Subsequently, the semi-structured equity genealogy data is converted into structured entity tables and relationship tables, wherein the entity table stores the company and natural person node information, and the relationship table stores the investment and employment relationship between two nodes; the node information in the entity table includes name / company name, entity unique identification code, entity label, wherein the entity label includes enterprise, natural person and institutional organization; the relationship information in the relationship table includes the starting node unique identification code, the target node unique identification code, the starting node name, the target node name, the shareholding ratio, the shareholding amount, and the relationship type, wherein the relationship type includes industrial and commercial shareholders, the top ten shareholders, the main shareholders, and employment. The specific structured data fields and their meanings are shown in Table 1.

[0070] Table 1

[0071]

[0072]

[0073] 2) Real-time calculation process, including the following steps:

[0074] Step S21, obtaining the names of two companies whose association relationship needs to be identified, which are input by the user;

[0075] Step S22, determine whether both companies are on the platform merchant list, if yes, execute step S23, if not, take the non-platform merchant company as the target company, execute steps S12-S14, analyze and implement the corresponding equity investment and directors, supervisors and senior management data;

[0076] Step S23: For the two companies whose association is to be identified, the investment relationship information is obtained from the graph database, and all equity investment paths within 6 layers of the two companies are obtained from the graph database through the path penetration algorithm and the loop identification algorithm, and the directly controlled related parties are screened;

[0077] Step S24, according to the terms of the platform risk control management document, calculate the shareholding ratio and shareholding direction in the equity investment path to identify the equity relationship between the two companies.

[0078] The specific path penetration algorithm and loop identification algorithm perform the following steps:

[0079] Search for all equity investment paths from the starting node to the target node;

[0080] Traverse each equity investment path and determine the number of nodes and relationships in each path and their corresponding quantities. If the numbers of the two are equal, it means that there is no loop, otherwise, there is a loop;

[0081] If there is no loop, the starting node of each relationship in the path and the shareholding ratio between the two nodes are output, and one of the companies with the to-be-identified relationship is used as the initial reference point to determine the shareholding direction;

[0082] If the reference point is the starting node, the shareholding direction is outward investment, and the tail node of the relationship is used as the new reference point; if the reference point is the tail node, the shareholding direction is invested, and the corresponding shareholding ratio is converted to a negative number, and the starting node of the relationship is used as the new reference point;

[0083] If the number of relationships in the path is 2, and the shareholding directions are external investment and investment, the intermediate node is the directly controlled related party of the related party to be identified;

[0084] Output the non-circular equity investment path of the related party to be identified, as well as the nodes within the path, shareholding direction, and list of directly controlled entities.

[0085] The types of equity relationships identified by the real-time calculation process include:

[0086] Type 1: The two companies have a direct or indirect equity relationship exceeding the specified shareholding ratio within the specified equity investment relationship level;

[0087] Type 2: The common shareholders, subsidiaries or brother companies of the two companies have direct or indirect equity relationship with the two companies exceeding the specified shareholding ratio;

[0088] Type 3: The legal person or directors, supervisors and senior managers of one company also serve as the legal person or directors, supervisors and senior managers of the other company or hold shares exceeding the specified shareholding ratio.

[0089] Specifically, as shown below, including the following situations:

[0090] ① There is a relationship between the directors, supervisors and senior managers of the two companies or between individuals holding more than 5% of the shares, such as Figure 2 As shown, Company A and Company C are related;

[0091] ② The two companies are direct or indirect shareholders of each other, such as Figure 3As shown, in (3a), there is an association relationship between Company A and Company B, and in (3b), there is an association relationship between Company A and Company C;

[0092] ③ The two companies have common shareholders and the penetrating shareholding is greater than the prescribed ratio (5%), such as Figure 4 As shown, in (4a), there is an association relationship between Company A and Company C, and in (4b), there is an association relationship between Company A and Company G;

[0093] ④ The two companies have a common subsidiary, and the penetration shareholding ratio is greater than the prescribed ratio (5%), such as Figure 5 As shown, Company A and Company E are related;

[0094] ⑤ There is a brother company relationship between the two companies, and the penetration shareholding ratio is greater than the prescribed ratio (5%), such as Figure 6 As shown, Company A and Company E are associated with each other.

[0095] During the contract generation process, the operator inputs the company names of the purchaser and the seller, outputs the association determination result through the above method, and provides information prompts to the operator to reduce the risk of illegal trade.

[0096] The present invention is applied to the risk control scenario in the field of steel e-commerce, and aims to quickly determine the type of association relationship between upstream and downstream customers and merchants based on customized risk control management rules. The present invention stores and calculates equity investment data through knowledge graph technology. The knowledge graph has the ability to quickly query many-to-many relationships and perform deep penetration, which can ensure the efficiency of equity penetration calculation; the incremental parsing process of the present invention can ensure the real-time nature of equity investment graph data; the present invention can superimpose the platform's own risk control management rules, and then accurately determine the type of association relationship between upstream and downstream customers and merchants. The knowledge graph also supports the integration of multiple risk control dimensions such as platform customer transaction relationship data and user account information, and has scalability. The present invention incorporates knowledge graph technology into the platform risk control scenario to help remind operations and marketing personnel of the relationship between upstream and downstream customers and merchants for each business, thereby reducing the risk of possible illegal trade.

[0097] The above is an introduction to the method embodiment. The following is a further explanation of the solution of the present invention through a system embodiment.

[0098] A system for identifying association relationships between passengers and merchants based on knowledge graph, including:

[0099] The incremental parsing module performs the following steps:

[0100] Step S11, regularly obtain and update the platform merchant list, and determine the target company based on the platform merchant list;

[0101] Step S12, cyclically calling the external interface to obtain the target company's equity family tree information, converting the semi-structured data returned by the interface into structured data containing entity and relationship information and saving it;

[0102] Step S13, incrementally importing structured data into the graph database;

[0103] Step S14, executing the same-name entity fusion algorithm, merging the same-name natural person entities and corresponding investment relationships, and marking them with suspicious labels;

[0104] A real-time computing module is used to perform the following steps:

[0105] Step S21, obtaining the names of two companies whose association relationship needs to be identified, which are input by the user;

[0106] Step S22, determine whether both companies are in the platform merchant list, if yes, execute step S23, if no, take the non-platform merchant company as the target company, and execute steps S12-S14;

[0107] Step S23: For the two companies whose association is to be identified, the investment relationship information is obtained from the graph database, and all equity investment paths within the preset number of layers of the two companies are obtained from the graph database through the path penetration algorithm and the loop identification algorithm, and the directly controlled related parties are screened;

[0108] Step S24, calculating the shareholding ratio and shareholding direction in the equity investment path to identify the equity relationship between the two companies.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0110] The electronic device of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0111] Multiple components in the device are connected to the I / O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunication networks.

[0112] The processing unit performs the various methods and processes described above, such as methods S11 to S14, S21 to S24. For example, in some embodiments, methods S11 to S14, S21 to S24 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S11 to S14, S21 to S24 described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute methods S11 to S14, S21 to S24 by any other appropriate means (e.g., by means of firmware).

[0113] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0114] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for identifying the association relationship between tourists and merchants based on knowledge graph, characterized in that: The method includes an incremental parsing process and a real-time calculation process, wherein: The incremental parsing process consists of the following steps: Step S11, regularly obtain and update the platform merchant list, and determine the target company based on the platform merchant list; Step S12, cyclically calling the external interface to obtain the target company's equity family tree information, converting the semi-structured data returned by the interface into structured data containing entity and relationship information and saving it; Step S13, incrementally importing structured data into the graph database; Step S14, executing the same-name entity fusion algorithm, merging the same-name natural person entities and corresponding investment relationships, and marking them with suspicious labels; The real-time calculation process includes the following steps: Step S21, obtaining the names of two companies whose association relationship needs to be identified, which are input by the user; Step S22, determine whether both companies are in the platform merchant list, if yes, execute step S23, if no, take the non-platform merchant company as the target company, and execute steps S12-S14; Step S23: For the two companies whose association is to be identified, the investment relationship information is obtained from the graph database, and all equity investment paths within the preset number of layers of the two companies are obtained from the graph database through the path penetration algorithm and the loop identification algorithm, and the directly controlled related parties are screened; Step S24, calculating the shareholding ratio and shareholding direction in the equity investment path to identify the equity relationship between the two companies.

2. According to the method for identifying the association relationship between passengers and merchants based on knowledge graph in claim 1, it is characterized in that: In the step S12, the semi-structured equity genealogy data is converted into a structured entity table and a relationship table, wherein the entity table stores the company and natural person node information, and the relationship table stores the investment and employment relationship between two nodes.

3. According to the method for identifying the association relationship between passengers and merchants based on knowledge graph in claim 2, it is characterized in that: The node information in the entity table includes name / company name, entity unique identification code, entity tag, wherein the entity tag includes enterprise, natural person and institutional organization.

4. The method for identifying the association relationship between passengers and merchants based on knowledge graph according to claim 2 is characterized in that: The relationship information in the relationship table includes the unique identification code of the starting node, the unique identification code of the target node, the name of the starting node, the name of the target node, the shareholding ratio, the shareholding amount, and the relationship type, among which the relationship types include industrial and commercial shareholders, top ten shareholders, major shareholders, and positions.

5. The method for identifying the association relationship between passengers and merchants based on knowledge graph according to claim 1 is characterized in that: The method of obtaining all equity investment paths within the preset number of layers of the two companies from the graph database through the path penetration algorithm and the loop identification algorithm and screening directly controlled related parties includes the following steps: Search for all equity investment paths from the starting node to the target node; Traverse each equity investment path and determine the number of nodes and relationships in each path and their corresponding quantities. If the numbers of the two are equal, it means that there is no loop, otherwise, there is a loop; If there is no loop, the starting node of each relationship in the path and the shareholding ratio between the two nodes are output, and one of the companies with the to-be-identified relationship is used as the initial reference point to determine the shareholding direction; If the reference point is the starting node, the shareholding direction is outward investment, and the tail node of the relationship is used as the new reference point; if the reference point is the tail node, the shareholding direction is invested, and the corresponding shareholding ratio is converted to a negative number, and the starting node of the relationship is used as the new reference point; If the number of relationships in the path is 2, and the shareholding directions are external investment and investment, the intermediate node is the directly controlled related party of the related party to be identified; Output the non-circular equity investment path of the related party to be identified, as well as the nodes within the path, shareholding direction, and list of directly controlled entities.

6. The method for identifying the association relationship between passengers and merchants based on knowledge graph according to claim 1, characterized in that: The equity relationship described includes: the two companies have a relationship between directors, supervisors, and senior managers or natural persons holding more than 5% of the shares; the two companies are each other's direct or indirect shareholders; the two companies have common shareholders and the penetrating shareholding is greater than the prescribed ratio; the two companies have a common subsidiary and the penetrating shareholding ratio is greater than the prescribed ratio; the two companies have a sister company relationship and the penetrating shareholding ratio is greater than the prescribed ratio.

7. The method for identifying the association relationship between passengers and merchants based on knowledge graph according to claim 1 is characterized in that: The identified equity relationship types include: Type 1: The two companies have a direct or indirect equity relationship exceeding the specified shareholding ratio within the specified equity investment relationship level; Type 2: The common shareholders, subsidiaries or brother companies of the two companies have direct or indirect equity relationship with the two companies exceeding the specified shareholding ratio; Type 3: The legal person or directors, supervisors and senior managers of one company also serve as the legal person or directors, supervisors and senior managers of the other company or hold shares exceeding the specified shareholding ratio.

8. A system for identifying the association relationship between tourists and merchants based on knowledge graph, characterized in that: include: The incremental parsing module performs the following steps: Step S11, regularly obtain and update the platform merchant list, and determine the target company based on the platform merchant list; Step S12, cyclically calling the external interface to obtain the target company's equity family tree information, converting the semi-structured data returned by the interface into structured data containing entity and relationship information and saving it; Step S13, incrementally importing structured data into the graph database; Step S14, executing the same-name entity fusion algorithm, merging the same-name natural person entities and corresponding investment relationships, and marking them with suspicious labels; A real-time computing module is used to perform the following steps: Step S21, obtaining the names of two companies whose association relationship needs to be identified, which are input by the user; Step S22, determine whether both companies are in the platform merchant list, if yes, execute step S23, if no, take the non-platform merchant company as the target company, and execute steps S12-S14; Step S23: For the two companies whose association is to be identified, the investment relationship information is obtained from the graph database, and all equity investment paths within the preset number of layers of the two companies are obtained from the graph database through the path penetration algorithm and the loop identification algorithm, and the directly controlled related parties are screened; Step S24, calculating the shareholding ratio and shareholding direction in the equity investment path to identify the equity relationship between the two companies.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images