Enterprise transaction risk level determination method and device, equipment and medium

By constructing an enterprise transaction relationship diagram and calculating a fusion vector, and determining the transaction risk level, the problem of single transaction risk assessment in the existing technology is solved, and risk prediction and risk relationship identification of enterprise transaction objects are realized, helping enterprises avoid transaction risks.

CN119067677APending Publication Date: 2024-12-03CHINA PETROLEUM & CHEMICAL CORP +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410952815.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-12-03

Smart Images

  • Figure CN119067677A_ABST
    Figure CN119067677A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of enterprise risk control, and particularly relates to an enterprise transaction risk level determination method and device, equipment and a medium. According to the method, enterprise basic information and enterprise transaction data of each enterprise in a target enterprise group are acquired, wherein the target enterprise group comprises enterprises possibly transacted with the enterprise and enterprises already transacted with the enterprise; determining an enterprise transaction relation graph of the target enterprise group according to the enterprise basic information and the enterprise transaction data of each enterprise; determining a fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relation graph; and determining the transaction risk level of each enterprise according to the fusion vector. The risk level and the risk relationship of the enterprise transaction object can be effectively predicted, the enterprise is helped to identify the risk user before the transaction, the transaction risk is avoided, and the enterprise benefit is prevented from being damaged.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of enterprise risk control, and specifically relates to a method, device, equipment and medium for determining the risk level of enterprise transactions. Background Art

[0002] In the risk control management of corporate sales, behaviors that violate business sales interests, such as self-purchase and self-sales, reselling, etc., will bring unnecessary losses to the company. It is necessary to conduct a comprehensive risk investigation of the transaction object before the transaction begins to avoid potential transaction risks and provide the company with a correct basis for transaction decisions.

[0003] At present, the risk screening methods for transaction objects are basically centered around user profiling of the transaction object itself, and then using data analysis to find indicators that may have potential risks, thereby providing companies with a basis for decision-making and ensuring transaction security. However, this analysis method is relatively simple and cannot comprehensively determine the risk relationship between the transaction enterprise and other transaction enterprises to assess the risk level of the enterprise, which has great limitations. Summary of the invention

[0004] In response to the above technical problems, the present invention proposes a method, device, equipment and medium for determining the enterprise transaction risk level. This application obtains the basic information and enterprise transaction data of each enterprise in the target enterprise group, wherein the target enterprise group includes: enterprises that may have transactions with the enterprise and enterprises that have already had transactions with the enterprise; determines the enterprise transaction relationship diagram of the target enterprise group according to the basic information and enterprise transaction data of each enterprise; determines the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram; and determines the transaction risk level of each enterprise according to the fusion vector. It can effectively predict the risk level and risk relationship of the enterprise transaction object, help enterprises identify risky users before transactions, avoid transaction risks, and prevent damage to corporate interests.

[0005] To solve the above technical problems, the technical solution adopted by the present invention includes four aspects.

[0006] In a first aspect, a method for determining an enterprise transaction risk level is provided, comprising: obtaining basic enterprise information and enterprise transaction data of each enterprise in a target enterprise group, wherein the target enterprise group includes: enterprises that may have transactions with the present enterprise and enterprises that have already had transactions with the present enterprise; determining an enterprise transaction relationship graph of the target enterprise group based on the basic enterprise information and the enterprise transaction data of each enterprise; determining a fusion vector of each enterprise in the target enterprise group based on the enterprise transaction relationship graph; and determining the transaction risk level of each enterprise based on the fusion vector.

[0007] In some embodiments, the basic information of the enterprise includes: enterprise name, enterprise controlling shareholder information, enterprise senior executive legal person information and enterprise contact information; the enterprise transaction data includes: product name and transaction relationship with other enterprises; the enterprise transaction relationship graph of the target enterprise group is determined based on the basic information of the enterprise and the enterprise transaction data of each enterprise, including: taking the enterprise senior executive legal person information, enterprise contact information, enterprise name and product name of each enterprise as entity nodes, and taking the controlling shareholder relationship, the transaction relationship, the senior executive legal person relationship and the affiliation of the contact information between each enterprise as vector edges to determine the enterprise transaction relationship graph.

[0008] In some embodiments, determining the fusion vector of each enterprise in the target enterprise group based on the enterprise transaction relationship graph includes: determining the vector relationship graph between each enterprise and other entity nodes based on the enterprise transaction relationship graph; encoding and fusing the relationship vector graph of each enterprise to obtain the fusion vector of each enterprise.

[0009] In some embodiments, encoding and fusing the relationship vector graph of each enterprise to obtain the fusion vector of each enterprise includes: encoding and fusing each entity node and vector edge in the vector relationship graph to obtain the fusion vector of each enterprise.

[0010] In some embodiments, determining the transaction risk level of each enterprise according to the fusion vector includes: determining a risk relationship table between each enterprise and other enterprises according to the fusion vector; and determining the transaction risk level of each enterprise according to the risk relationship table.

[0011] In some embodiments, the encoding fusion of each entity node and vector edge in the vector relationship graph is implemented by the following formula to obtain the fusion vector of each enterprise:

[0012]

[0013] In the formula, Indicates the vector edge direction type is λ(r) in the K-th layer graph convolution weight matrix. λ(r) represents the relationship between the vector edge and the enterprise, including outgoing edge, incoming edge and self-connecting edge. represents the original features of node v, Represents the initial vector of the vector edge direction type r, Indicates an entity node whose entity node type is u. Entity node types include: enterprise name, legal person name, contact information, and product name.

[0014] In the second aspect, the present application proposes a device for determining the enterprise transaction risk level, comprising: a first acquisition module, used to obtain the basic information and enterprise transaction data of each enterprise in the target enterprise group; a first determination module, used to determine the enterprise transaction relationship diagram of the target enterprise group based on the basic information and enterprise transaction data of each enterprise; a second determination module, used to determine the fusion vector of each enterprise in the target enterprise group based on the enterprise transaction relationship diagram; and a third determination module, used to determine the transaction risk level of each enterprise based on the fusion vector.

[0015] In a third aspect, the present application proposes an electronic device, comprising: a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method described in any one of the first aspects is performed.

[0016] In a fourth aspect, the present application proposes a storage medium, which stores a computer program that can be executed by one or more processors, and the computer program can be used to implement any method described in the first aspect.

[0017] Beneficial effects of the invention: The invention obtains basic enterprise information and enterprise transaction data of each enterprise in the target enterprise group, wherein the target enterprise group includes: enterprises that may have transactions with the enterprise and enterprises that have already had transactions with the enterprise; determines the enterprise transaction relationship diagram of the target enterprise group according to the basic enterprise information and enterprise transaction data of each enterprise; determines the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram; and determines the transaction risk level of each enterprise according to the fusion vector. The risk level and risk relationship of the enterprise transaction object can be effectively predicted, helping enterprises to identify risky users before transactions, avoid transaction risks, and prevent damage to the interests of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The scope of the present disclosure may be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. The drawings included are:

[0019] Figure 1 An overall flow chart of a method for determining an enterprise transaction risk level provided in an embodiment of the present application;

[0020] Figure 2 An enterprise transaction relationship diagram provided for an embodiment of the present application;

[0021] Figure 3 A structural block diagram of a device for determining an enterprise transaction risk level provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0023] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0024] If similar descriptions of "first\second\third" appear in the application documents, the following instructions will be added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0026] Embodiment 1:

[0027] At present, the risk screening methods for transaction objects are basically centered around user profiling of the transaction object itself, and then using data analysis to find indicators that may have potential risks, thereby providing companies with a basis for decision-making and ensuring transaction security. However, this analysis method is relatively simple and cannot comprehensively determine the risk relationship between the transaction enterprise and other transaction enterprises to assess the risk level of the enterprise, which has great limitations.

[0028] In view of the problems existing in the prior art, such as Figure 1 As shown, the present application provides a method for determining the enterprise transaction risk level, and the method is applied to an electronic device, and the electronic device can be a server, a mobile terminal, a computer, a cloud platform, etc. The function implemented by the device data processing provided in the embodiment of the present application can be implemented by calling a program code by a processor of the electronic device, wherein the program code can be stored in a computer storage medium, and the method for determining the enterprise transaction risk level includes:

[0029] Step S1: Obtaining basic enterprise information and enterprise transaction data of each enterprise in the target enterprise group, wherein the target enterprise group includes: enterprises that may have transactions with the enterprise and enterprises that have already had transactions with the enterprise.

[0030] Transactions between enterprises are normal behaviors of enterprises, but in the process of enterprise transactions, it is necessary to screen and evaluate the enterprises involved in the transaction to reduce transaction risks. Therefore, we need to determine the transaction risk level of enterprises that may have transactions with our enterprise and enterprises that have already traded with our enterprise. Generally speaking, some of the obvious information of enterprises is easy to find, but there are some enterprises that do not have any risks on the surface, but they may have multiple affiliated companies, and may use affiliated companies to do some things that are detrimental to the enterprise. Therefore, it is difficult to determine the transaction risk of the enterprise based on the relevant information of a single enterprise. Therefore, in order to improve the transaction security of our enterprise in this application, it is necessary to judge the transaction risk of each enterprise from the relationship between the enterprise groups. The relationship between each enterprise can be determined through the basic information and enterprise transaction data of each enterprise.

[0031] Therefore, in this application, it is necessary to obtain the basic information and transaction data of each enterprise in the target enterprise group. The basic information of the enterprise includes: enterprise name, enterprise holding information, enterprise executive legal person information and enterprise contact information. The enterprise transaction data includes: product name and transaction relationship.

[0032] Step S2: Determine the enterprise transaction relationship diagram of the target enterprise group according to the enterprise basic information and the enterprise transaction data of each enterprise.

[0033] In order to more intuitively express the relationship between the various enterprises in the target enterprise group, the enterprise transaction relationship diagram of the target enterprise group is determined in this application based on the basic information and enterprise transaction data of each enterprise.

[0034] Therefore, in some embodiments, step S2 of "determining the enterprise transaction relationship diagram of the target enterprise group according to the enterprise basic information and the enterprise transaction data of each enterprise" includes:

[0035] Step 21: Determine the enterprise transaction relationship graph by using the corporate executive legal person information, corporate contact information, corporate name and product name of each enterprise as entity nodes, and the participating and controlling relationships, transaction relationships, executive legal person relationships and contact information affiliations between each enterprise as vector edges.

[0036] The enterprise transaction relationship diagram expresses the relationship between each enterprise. In the enterprise transaction relationship diagram, the enterprise name, product name, contact information and senior executive legal person name are used as entity nodes, and then the relationship between each enterprise is determined based on the relationship between the participating and controlling shares, transaction relationship, senior executive legal person affiliation and contact number between the enterprises as the connecting line. The connecting line is a vector edge and is directional. For example, if enterprise A holds a stake in enterprise B, then the participating and controlling shareholding relationship line between enterprise A and enterprise B is from enterprise A to enterprise B. In the transaction relationship, it can be a supply relationship and a customer relationship. Therefore, the obtained enterprise transaction relationship diagram is as follows: Figure 2 shown.

[0037] Step S3: Determine the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram.

[0038] because Figure 2 There are fewer enterprises in the target enterprise group and the relationships are relatively simple, so we can easily obtain the relationship between each enterprise through observation. However, in actual operation, since there are many enterprises in the target enterprise group and the relationships between enterprises are complex, it is difficult to obtain the final result through direct observation. Therefore, in this application, the enterprise transaction relationship graph needs to be processed. Since the relationship between each entity node is expressed in the form of vectors, we can fuse the vector edges of a certain enterprise as the center to obtain a fused vector.

[0039] Therefore, in some embodiments, step S3 of "determining the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram" includes:

[0040] Step S31: Determine a vector relationship diagram between each enterprise and other entity nodes according to the enterprise transaction relationship diagram.

[0041] Step S32: Encode and fuse the relationship vector graph of each enterprise to obtain the fusion vector of each enterprise.

[0042] In some embodiments, step S32 "encode and fuse the relationship vector graph of each enterprise to obtain the fusion vector of each enterprise" includes:

[0043] Step S321: Encode and fuse each entity node and vector edge in the vector relationship graph to obtain the fusion vector of each enterprise.

[0044] When there are too many companies in the target enterprise group, the entire enterprise transaction relationship graph will be very complicated. Therefore, in this application, when it is necessary to obtain the fusion vector of an enterprise, the enterprise and its corresponding vector edges and related entity nodes need to be extracted to form the vector relationship graph of the enterprise. Then, the vectors in the vector relationship graph are encoded and fused. When encoding and fusion, different weights are given to different relationships, that is, different weights are given to the vector edges between the central enterprise and other entity nodes, and finally a fusion vector that can express the relationship between the enterprise and other actual nodes is obtained.

[0045] In some embodiments, step S32 "encoding and fusing the relationship vector graph of each enterprise to obtain the fusion vector of each enterprise" is implemented by the following formula:

[0046]

[0047] In the formula, Indicates the vector edge direction type is λ(r) in the K-th layer graph convolution weight matrix. λ(r) represents the relationship between the vector edge and the enterprise, including outgoing edge, incoming edge and self-connecting edge. represents the original features of node v, Represents the initial vector of the vector edge direction type r, Indicates an entity node whose entity node type is u. Entity node types include: enterprise name, legal person name, contact information, and product name.

[0048] Step S4: Determine the transaction risk level of each enterprise according to the fusion vector.

[0049] After determining the fusion vector of each enterprise, it is easy to analyze the transaction relationship between this enterprise and other enterprises, and finally obtain the transaction risk level of this enterprise.

[0050] In some embodiments, step S4 “determining the transaction risk level of each enterprise according to the fusion vector” includes:

[0051] Step S41: Determine a risk relationship table between each enterprise and other enterprises according to the fusion vector.

[0052] In some embodiments, step S41 "determining a risk relationship table of each enterprise with other enterprises according to the fusion vector" includes:

[0053] Step S411: Decode the fusion vector to obtain a relationship table between each enterprise and other enterprises.

[0054] Step S412: Determine a risk relationship table between each enterprise and other enterprises according to preset rules and the association relationship table.

[0055] Step S42: Determine the transaction risk level of each enterprise according to the risk relationship table.

[0056] After the coding fusion, the relationship between the target enterprise and other entity nodes is very clear, but the main purpose of this application is to understand the connection between each enterprise, and the entity nodes are not all enterprises, but also include contact information, legal person name and product name. However, we can use contact information, legal person name and product name as intermediate nodes to better clarify the relationship between enterprises. Therefore, in this application, after decoding the fusion vector, we can get the relationship table between each enterprise. In the relationship table, it will be indicated that the target enterprise and other enterprises have relationships in those aspects, such as the situation where enterprise A and enterprise B have common executives. At this time, we sort out the relationship between these enterprises and get the risk relationship table between the target enterprise and other enterprises. Of course, in the process of sorting, it is also necessary to sort according to the preset rules. This preset rule mainly depends on which relationship between the enterprise is more interested in. After filtering the relationship that the enterprise is interested in, a risk relationship table that meets the purpose of the enterprise is obtained. After obtaining the risk relationship table, we can assign risk levels according to the number of relationships between the target enterprise and each enterprise in the risk relationship table. Then the risk levels between the target enterprise and all other enterprises are summarized to obtain the final transaction risk level of the target enterprise.

[0057] Of course, in some embodiments, steps S1-S4 can be completed with the help of a computer, where steps S3-S42 can be completed by using a neural network, such as by building a graph neural network model based on CompGCN optimization. After training the graph neural network model, the steps between steps S3-S42 can be completed, where the Encoder-Decoder framework is used in the graph neural network model, and Entity Embedding and Relation Embedding are combined for Aggregation in the Encoder stage, and then the TransE method is used in the Decoder stage to decode the (h, r, t) triple. Because Relation Embedding is introduced in the Encoder stage, the advantage is that the Encoder and Decoder encode the same set of Relation Embedding, making representation learning more accurate.

[0058] This application obtains the basic information and enterprise transaction data of each enterprise in the target enterprise group, wherein the target enterprise group includes: enterprises that may have transactions with the enterprise and enterprises that have already had transactions with the enterprise; determines the enterprise transaction relationship diagram of the target enterprise group according to the basic information and enterprise transaction data of each enterprise; determines the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram; and determines the transaction risk level of each enterprise according to the fusion vector. It can effectively predict the risk level and risk relationship of the enterprise transaction object, help enterprises identify risky users before transactions, avoid transaction risks, and prevent damage to enterprise interests.

[0059] Embodiment 2:

[0060] Based on the foregoing embodiments, the embodiments of the present application provide a device for determining the enterprise transaction risk level. The modules included in the device and the units included in each module can be implemented by a processor in a computer device; of course, they can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Microprocessor Unit), a digital signal processor (DSP, Digital Signal Processing) or a field programmable gate array (FPGA, Field Programmable Gate Array), etc.

[0061] like Figure 3 As shown, a device for determining an enterprise transaction risk level includes: a first acquisition module 1, a first determination module 2, a second determination module 3 and a third determination module 4.

[0062] The first acquisition module 1 is used to acquire the basic information and enterprise transaction data of each enterprise in the target enterprise group. The first determination module 2 is used to determine the enterprise transaction relationship diagram of the target enterprise group according to the basic information and enterprise transaction data of each enterprise. The second determination module 3 is used to determine the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram. The third determination module 4 is used to determine the transaction risk level of each enterprise according to the fusion vector.

[0063] In some embodiments, the first determination module 2 includes: a fourth determination module.

[0064] The fourth determination module is used to determine the enterprise transaction relationship graph using the corporate executive legal person information, corporate contact information, corporate name and product name of each enterprise as entity nodes, and the participating and controlling relationship, transaction relationship, executive legal person relationship and contact information affiliation between each enterprise as vector edges.

[0065] In some embodiments, the second determination module 3 includes: a fifth determination module and a first execution module.

[0066] The fifth determination module is used to determine the vector relationship diagram between each enterprise and other entity nodes according to the enterprise transaction relationship diagram. The first execution module is used to encode and fuse the relationship vector diagram of each enterprise to obtain the fusion vector of each enterprise.

[0067] In some embodiments, the first execution module includes: a second execution module.

[0068] The second execution module is used to encode and fuse each entity node and vector edge in the vector relationship graph to obtain the fusion vector of each enterprise.

[0069] In some embodiments, the third determination module 4 includes: a sixth determination module and a seventh determination module.

[0070] The sixth determination module is used to determine the risk relationship table between each enterprise and other enterprises according to the fusion vector. The seventh determination module is used to determine the transaction risk level of each enterprise according to the risk relationship table.

[0071] In some embodiments, the sixth determination module includes: a third execution module and an eighth determination module.

[0072] The third execution module is used to decode the fusion vector to obtain an association relationship table between each enterprise and other enterprises. The eighth determination module is used to determine a risk relationship table between each enterprise and other enterprises according to a preset rule and the association relationship table.

[0073] Each module in the above-mentioned device for determining the enterprise transaction risk level can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the device in the form of hardware, or can be stored in the memory in the processing device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation.

[0074] Embodiment 3:

[0075] The third aspect provides an electronic device, including a storage device and a processor, wherein the storage device stores a computer program, and when the processor executes the computer program, the steps of a method for determining the risk level of enterprise transactions are implemented.

[0076] Embodiment 4:

[0077] The fourth aspect provides a storage medium, which stores a computer program that can be executed by one or more processors, and the computer program can be used to implement the steps of any one of the methods for determining the enterprise transaction risk level in the first aspect.

[0078] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0079] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0080] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0082] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0083] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0084] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read Only Memory), disks or optical disks, etc. Various media that can store program codes.

[0085] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a controller to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0086] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining the risk level of enterprise transactions, characterized in that: include: Obtaining basic enterprise information and enterprise transaction data of each enterprise in the target enterprise group, wherein the target enterprise group includes: enterprises that may have transactions with the enterprise and enterprises that have already had transactions with the enterprise; Determine the enterprise transaction relationship diagram of the target enterprise group according to the enterprise basic information and the enterprise transaction data of each enterprise; Determine the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram; The transaction risk level of each enterprise is determined according to the fusion vector.

2. The method according to claim 1, characterized in that The basic information of the enterprise includes: enterprise name, enterprise holding information, enterprise senior executive legal person information and enterprise contact information; the enterprise transaction data includes: product name and transaction relationship with other enterprises; the enterprise transaction relationship diagram of the target enterprise group determined according to the basic information and enterprise transaction data of each enterprise includes: The enterprise transaction relationship graph is determined by taking the corporate executive legal person information, corporate contact information, corporate name and product name of each enterprise as entity nodes, and the participating and controlling relationship, the transaction relationship, the executive legal person relationship and the affiliation of the contact information between each enterprise as vector edges.

3. The method according to claim 2, characterized in that The step of determining the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram includes: Determine a vector relationship diagram between each enterprise and other entity nodes according to the enterprise transaction relationship diagram; The relationship vector graph of each enterprise is encoded and fused to obtain the fusion vector of each enterprise.

4. The method according to claim 3, characterized in that The encoding and fusing of the relationship vector graph of each enterprise to obtain the fusion vector of each enterprise includes: Each entity node and vector edge in the vector relationship graph is encoded and fused to obtain the fusion vector of each enterprise.

5. The method according to claim 1, characterized in that: Determining the transaction risk level of each enterprise according to the fusion vector includes: Determine a risk relationship table of each enterprise with other enterprises according to the fusion vector; The transaction risk level of each enterprise is determined according to the risk relationship table.

6. The method according to claim 5, characterized in that Determining the risk relationship table of each enterprise with other enterprises according to the fusion vector includes: Decoding each of the fusion vectors to obtain a correlation table of each enterprise with other enterprises; The risk relationship table of each enterprise with other enterprises is determined according to the preset rules and the association relationship table.

7. The method according to claim 4, characterized in that The encoding and fusion of each entity node and vector edge in the vector relationship graph is implemented by the following formula to obtain the fusion vector of each enterprise: In the formula, Indicates the vector edge direction type is λ(r) in the K-th layer graph convolution weight matrix. λ(r) represents the relationship between the vector edge and the enterprise, including outgoing edge, incoming edge and self-connecting edge. represents the original features of node v, Represents the initial vector of the vector edge direction type r, Indicates an entity node whose entity node type is u. Entity node types include: enterprise name, legal person name, contact information, and product name.

8. A device for determining the risk level of enterprise transactions, characterized in that: include: The first acquisition module is used to acquire basic enterprise information and enterprise transaction data of each enterprise in the target enterprise group; A first determination module, configured to determine an enterprise transaction relationship diagram of the target enterprise group according to the enterprise basic information and the enterprise transaction data of each enterprise; A second determination module is used to determine the fusion vector of each enterprise in the target enterprise group according to the enterprise transaction relationship diagram; The third determination module is used to determine the transaction risk level of each enterprise according to the fusion vector.

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

10. A storage medium, wherein a computer program stored in the storage medium can be executed by one or more processors, wherein the computer program can be used to implement the method according to any one of claims 1 to 7.