Knowledge graph-based commercial bank verification enterprise auditing method and system, and medium

Abstract

The invention is suitable for the technical field of intelligent auditing, and provides a commercial bank verification enterprise auditing method and system based on a knowledge graph and a medium, and the method comprises the steps: firstly obtaining an auditing business data set of a target commercial bank, and then comprehensively constructing knowledge graph information according to the auditing business data set, and finally, according to the knowledge graph information and preset target entity node information, rapidly determining abnormal link information. According to the method, the knowledge graph technology can be utilized to comprehensively sort and accurately model the main body of the small and micro loan in the bank industry and the complex relationship thereof, so that the requirements on calculation and storage resources are remarkably reduced, the quick positioning of the risk of the verification enterprise is realized, the auditing efficiency is greatly improved, and the accuracy and reliability of the auditing result are improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent auditing, and more specifically, to a method, system and medium for commercial bank write-off enterprise auditing based on knowledge graph. Background Art

[0002] In the operation of commercial banks' corporate business, when the borrowing enterprise has outstanding loans and the bank's write-off department confirms that it cannot recover the remaining loan principal and interest, the bank will usually transfer these loans to its own asset disposal center, and the handling bank will no longer continue to collect repayments. This processing method is called loan write-off. When an enterprise applies for a loan, there may be collusion among internal personnel to defraud bank loans through multi-level guarantee relationships. The audit department of a commercial bank needs to audit the relationship between the write-off enterprise and the bank's employees to reveal this malicious fraud.

[0003] Since bank data is usually stored in relational databases, querying multi-level relationships requires a lot of computing and storage costs. This makes it difficult for the audit department to discover the complex relationships between write-off companies and bank employees, causing huge losses to the bank.

[0004] At present, SQL scripts are usually used to perform multiple queries on relational databases. Since there are massive tables involving original data in relational databases, a large amount of computing resources and storage resources are required, and there is a problem of low audit efficiency, which needs further improvement. Summary of the invention

[0005] Based on this, the embodiments of the present application provide a commercial bank write-off enterprise audit method, system and medium based on knowledge graph to solve the problem of low audit efficiency in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a commercial bank write-off enterprise audit method based on a knowledge graph, the method comprising:

[0007] Obtain the audit business dataset of the target commercial bank;

[0008] According to the audit business data set, construct knowledge graph information, wherein the knowledge graph information includes a plurality of entity node information and node relationship information between each of the entity node information;

[0009] According to the knowledge graph information and the preset target entity node information, the abnormal link information is determined.

[0010] Compared with the prior art, the beneficial effect is that the commercial bank write-off enterprise audit method based on knowledge graph provided in the embodiment of the present application, the terminal device can first obtain the audit business data set of the target commercial bank, and then comprehensively construct the knowledge graph information based on the audit business data set, and finally quickly determine the abnormal link information based on the knowledge graph information and the preset target entity node information, thereby avoiding the need to consume a large amount of computing resources and storage resources, greatly improving the audit efficiency, and to a certain extent solving the current problem of low audit efficiency.

[0011] In a second aspect, an embodiment of the present application provides a commercial bank write-off enterprise audit system based on a knowledge graph, the system comprising:

[0012] Audit business data set acquisition module: used to acquire the audit business data set of the target commercial bank;

[0013] A knowledge graph information construction module: used to construct knowledge graph information according to the audit business data set, wherein the knowledge graph information includes a plurality of entity node information and node relationship information between each of the entity node information;

[0014] Abnormal link information determination module: used to determine abnormal link information based on the knowledge graph information and preset target entity node information.

[0015] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect described above are implemented.

[0017] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0019] Figure 1 It is a flowchart of a commercial bank write-off enterprise audit method provided by an embodiment of the present application;

[0020] Figure 2It is a flowchart of step S200 in the commercial bank write-off enterprise audit method provided by an embodiment of the present application;

[0021] Figure 3 It is a schematic diagram of the natural person-enterprise relationship information provided by an embodiment of the present application;

[0022] Figure 4 It is a flowchart after step S200 in the commercial bank write-off enterprise audit method provided by an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of a risk event provided by an embodiment of the present application;

[0024] Figure 6 It is a module block diagram of a commercial bank write-off enterprise audit system provided by an embodiment of the present application;

[0025] Figure 7 It is a schematic diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0030] See also Figure 1 , Figure 1 It is a flow chart of the commercial bank write-off enterprise audit method based on knowledge graph provided in the embodiment of the present application. In the present embodiment, the execution subject of the commercial bank write-off enterprise audit method is a terminal device. It is understandable that the types of terminal devices include but are not limited to mobile phones, tablet computers, laptops, ultra-mobile personal computers (Ultra-Mobile Personal Computer, UMPC), netbooks, personal digital assistants (Personal Digital Assistant, PDA), etc. The embodiment of the present application does not impose any restrictions on the specific types of terminal devices.

[0031] See also Figure 1 The commercial bank write-off enterprise audit method provided in the embodiment of the present application includes but is not limited to the following steps:

[0032] In S100, the audit business data set of the target commercial bank is obtained.

[0033] Specifically, the terminal device can obtain the audit business data set of the target commercial bank, wherein the audit business data set can be a variety of data tables. Exemplarily, the audit business data set includes a basic enterprise information subset, a basic enterprise core personnel information subset, a write-off time information subset, a credit card user information subset, a debit card user information subset, an enterprise investment information subset, a transaction information subset, a guarantee relationship information subset, a retail customer information subset, a corporate customer information subset, a group customer information subset and an employee information subset. The basic enterprise information subset can be a data table related to the basic enterprise information, the basic enterprise core personnel information subset can be a data table related to the basic enterprise core personnel information, and the write-off time information subset can be a data table related to the basic enterprise information. It may be a data table about cancellation time information, the credit card user information subset may be a data table about credit card user information, the debit card user information subset may be a data table about debit card user information, the enterprise investment information subset may be a data table about enterprise investment information, the transaction information subset may be a data table about transaction information, the guarantee relationship information subset may be a data table about guarantee relationship information, the retail customer information subset may be a data table about retail customer information, the corporate customer information subset may be a data table about corporate customer information, the group customer information subset may be a data table about group customer information, and the employee information subset may be a data table about employee information.

[0034] In S200, knowledge graph information is constructed based on the audit business data set.

[0035] Specifically, after the terminal device obtains the audit business data set, the terminal device can effectively construct knowledge graph information based on the audit business data set, wherein the knowledge graph information includes multiple entity node information and node relationship information between each entity node information.

[0036] Among some possible implementations, in order to better fit the audit scenario of commercial banks, please refer to Figure 2 Step S200 includes but is not limited to the following steps:

[0037] In S210, multiple designated entity node information is determined according to the audit business data set.

[0038] Specifically, the terminal device can determine multiple designated entity node information based on the audit business data set, where the types of designated entity node information include retail customer node information, corporate customer node information, write-off enterprise node information, group customer node information and internal employee node information.

[0039] In some possible implementations, in order to better fit the audit scenarios of commercial banks, the unique identification code of retail customer node information can be the ID number, the unique identification code of corporate customer node information can be the company name, the unique identification code of write-off company node information can be the write-off company name, the unique identification code of group customer node information can be the group name, and the unique identification code of internal employee node information can be the employee ID number, so as to better fit the main research objects of commercial banks.

[0040] In S220, based on a preset person-enterprise relationship classification set, the natural person-enterprise relationship information corresponding to each designated entity node information is determined.

[0041] Specifically, after the terminal device determines multiple designated entity node information, the terminal device can determine the natural person-enterprise relationship information corresponding to each designated entity node information based on a preset person-enterprise relationship classification set, thereby effectively defining the relationship between natural persons and enterprises.

[0042] For example, see Figure 3 , the human-enterprise relationship classification set includes human-enterprise relationship classification information, natural person relationship classification information and enterprise relationship classification information. The natural person-enterprise relationship information includes human-enterprise relationship information, natural person relationship information and enterprise relationship information. The human-enterprise relationship information is used to describe the relationship between natural persons and enterprises, that is, Figure 3 The “person-enterprise relationship” in the ; natural person relationship information is used to describe the relationship between natural persons, that is, Figure 3 The enterprise relationship information is used to describe the relationship between enterprises, that is, Figure 3In the "enterprise-enterprise relationship", the person-enterprise relationship information corresponds to the person-enterprise relationship classification information, the natural person relationship information corresponds to the natural person relationship classification information, and the enterprise relationship information corresponds to the enterprise relationship classification information.

[0043] In S230, based on a preset business data characteristic classification set, business data relationship information corresponding to each designated entity node information is determined.

[0044] Specifically, after the terminal device determines the natural person-enterprise relationship information corresponding to each designated entity node information, the terminal device can quickly determine the business data relationship information corresponding to each designated entity node information based on a preset business data characteristic classification set.

[0045] For example, see Figure 3 The business data characteristic classification set includes information characteristic classification information, credit characteristic classification information and capital characteristic classification information. The business data relationship information includes information relationship information, credit relationship information and capital relationship information. The information relationship information is Figure 3 In the "information category", credit relationship information is Figure 3 In the "credit category", the capital relationship information is Figure 3 "Funds" in the "Funds" category; information-related relationship information corresponds to information-characteristic classification information, credit-related relationship information corresponds to credit-characteristic classification information, and funds-related relationship information corresponds to funds-characteristic classification information.

[0046] In some possible implementations, in order to optimize the knowledge graph information and clean and process the data involved in relationship mining after modeling the entity relationships, please refer to Figure 4 After step S200, the method further includes but is not limited to the following steps:

[0047] In S201, an enterprise name information subset is generated according to the enterprise basic information subset.

[0048] Specifically, the terminal device may generate an enterprise name information subset based on the enterprise basic information subset, wherein the enterprise name information subset includes a plurality of enterprise name information.

[0049] In S202, based on the enterprise name information subset, it is determined whether there is a name defect event in the knowledge graph information.

[0050] Specifically, after the terminal device generates a subset of enterprise name information, the terminal device can determine whether there is a name defect event in the knowledge graph information based on the enterprise name information subset, where the name defect event is used to describe the lack of any enterprise name information in the knowledge graph information, and / or the lack of characters in the enterprise name in the knowledge graph information.

[0051] In S203, if there is a name defect event in the knowledge graph information, the knowledge graph information is supplemented based on the enterprise name information subset to supplement the missing enterprise name information in the knowledge graph information, or to supplement the missing characters in the knowledge graph information.

[0052] Specifically, if there is a name defect event in the knowledge graph information, the terminal device can compensate for the knowledge graph information based on the enterprise name information subset, thereby supplementing the missing enterprise name information in the knowledge graph information, or supplementing the missing characters in the knowledge graph information.

[0053] It should be noted that when a company name is missing, it can be supplemented by internal data related to the company or by collecting external data.

[0054] In S204, based on the enterprise name information subset, it is determined whether there is an expired name event in the knowledge graph information.

[0055] Specifically, the terminal device can determine whether there is an expired name event in the knowledge graph information based on the enterprise name information subset.

[0056] In S205, if there is an expired name event in the knowledge graph information, the knowledge graph information is updated based on the enterprise name information subset to update the expired and unchanged enterprise name information in the knowledge graph information.

[0057] Specifically, if there is an expired name event in the knowledge graph information, the terminal device can update the knowledge graph information based on the enterprise name information subset to update the expired and unchanged enterprise name information in the knowledge graph information, thereby achieving unified encoding of the enterprise name when the name of the same enterprise is different in different data tables due to industrial and commercial changes to the enterprise, to ensure the consistency of the enterprise name.

[0058] In S206, based on the enterprise name information subset, it is determined whether there is an incorrect name event in the knowledge graph information.

[0059] Specifically, the terminal device can determine whether there are incorrect name events in the knowledge graph information based on the enterprise name information subset.

[0060] It should be noted that the terminal device can check whether there is erroneous data in the data by using an outlier verification method or a field length verification method.

[0061] In S207, if there is an erroneous name event in the knowledge graph information, the knowledge graph information is repaired based on the enterprise name information subset to correct the erroneous enterprise name information in the knowledge graph information.

[0062] Specifically, if there is an incorrect name event in the knowledge graph information, the terminal device can repair the knowledge graph information based on the enterprise name information subset, thereby verifying and repairing the erroneous data found in the detection, and correcting the erroneous enterprise name information in the knowledge graph information.

[0063] In S300, abnormal link information is determined based on the knowledge graph information and preset target entity node information.

[0064] Specifically, the terminal device can quickly determine abnormal link information based on the knowledge graph information and preset target entity node information, where the target entity node information includes target write-off enterprise information, target employee information and target retail customer information.

[0065] Without loss of generality, when constructing knowledge graph information, the terminal device can use the Neo4j database to store the graph data model of the knowledge graph information, which is beneficial for obtaining the relevant data model through the graph database after data migration.

[0066] Exemplarily, the structure of the data model may be as shown in Table 1 below.

[0067] Table 1 Entity relationship structure table

[0068]

[0069]

[0070] In some possible implementations, in order to determine abnormal link information, step S300 includes but is not limited to the following steps:

[0071] In S310, based on the target write-off enterprise information, target employee information and target retail customer information, a global search process is performed on the knowledge graph information to determine abnormal link information.

[0072] Specifically, the terminal device can perform global retrieval processing on the knowledge graph information based on the target write-off enterprise information, target employee information and target retail customer information, and effectively determine the abnormal link information, wherein the starting node of the abnormal link information is the target write-off enterprise information, the ending node of the abnormal link information is the target employee information, and the abnormal link information includes at least one target retail customer information, and the target retail customer information is located between the starting node and the ending node.

[0073] For example, see Figure 5 , Figure 5Except for the first row of the top column, cells with the same grayscale can represent the same enterprise or individual. Specifically, cells with "retail customers" can represent nodes that must be passed between the write-off enterprise and the employees. Without loss of generality, when there is an important relationship between the write-off enterprise and the employees, and the relationship is separated by at least one retail customer, it can be regarded as a risk event. Exemplarily, when there can be 0 to 2 corporate customers between the write-off enterprise and the retail customer, and there are 0 to 2 retail customers between the retail customer and the employee, it can be regarded as a risk event. Exemplarily, the edge between each entity point is determined as a 1-layer relationship, and then analyzed based on audit experience to determine the important relationships including information relationships and collateral sharing relationships in person-to-person relationships, and then determine the risk events. Exemplarily, the terminal device can also select the relationship between some edges between each entity point as a screening condition, calculate the risk events that meet the requirements, and query all routes between the write-off enterprise and the employees, as well as the corporate customers and retail customers passing through the routes, to ultimately realize the mining of risk events, thereby realizing outward expansion from the corporate customer corresponding to the write-off enterprise as the starting point until the employee entity is queried, and if it is expanded to another write-off enterprise point or group customer point, the exploration of the path is terminated, the employee points on the path are saved, and other paths are continued to be queried, and the corporate relationship between employees and customers is retained in the corporate customer and employee relationship corresponding to the write-off enterprise found, and other redundant data is eliminated.

[0074] It should be noted that this application can further mine the highest-rated risk events under the same business scenario, identify risk events involving employees participating in the business handling of write-off enterprises, and visualize the employees and links with the highest risk event ratings through knowledge graphs, thereby greatly reducing the time for mining and discovering risk events and significantly improving the work efficiency of bank audits.

[0075] The implementation principle of the commercial bank write-off enterprise audit method based on the knowledge graph in the embodiment of the present application is as follows: the terminal device can first obtain the audit business data set of the target commercial bank, and then comprehensively construct the knowledge graph information based on the audit business data set, and finally quickly determine the abnormal link information based on the knowledge graph information and the preset target entity node information, thereby avoiding the need to consume a large amount of computing resources and storage resources, and greatly improving the audit efficiency.

[0076] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. 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.

[0077] The embodiment of the present application also provides a commercial bank write-off enterprise audit system based on knowledge graph. For the convenience of explanation, only the parts related to the present application are shown, such as Figure 6 As shown, the system 60 includes:

[0078] Audit business data set acquisition module 61: used to acquire the audit business data set of the target commercial bank;

[0079] The knowledge graph information construction module 62 is used to construct the knowledge graph information according to the audit business data set, wherein the knowledge graph information includes a plurality of entity node information and node relationship information between each entity node information;

[0080] Abnormal link information determination module 63: used to determine abnormal link information based on knowledge graph information and preset target entity node information.

[0081] Optionally, the audit business data set includes a basic enterprise information subset, a core enterprise personnel basic information subset, a write-off time information subset, a credit card user information subset, a debit card user information subset, an enterprise investment information subset, a transaction information subset, a guarantee relationship information subset, a retail customer information subset, a corporate customer information subset, a group customer information subset, and an employee information subset.

[0082] Optionally, the knowledge graph information construction module 62 includes:

[0083] The designated entity node information determination submodule is used to determine multiple designated entity node information according to the audit business data set, wherein the types of designated entity node information include retail customer node information, corporate customer node information, write-off enterprise node information, group customer node information and internal employee node information;

[0084] The human-enterprise relationship information determination submodule is used to determine the natural person-enterprise relationship information corresponding to each designated entity node information based on a preset human-enterprise relationship classification set, wherein the human-enterprise relationship classification set includes human-enterprise relationship classification information, natural person relationship classification information and enterprise relationship classification information, and the natural person-enterprise relationship information includes human-enterprise relationship information, natural person relationship information and enterprise relationship information, the human-enterprise relationship information corresponds to the human-enterprise relationship classification information, the natural person relationship information corresponds to the natural person relationship classification information, and the enterprise relationship information corresponds to the enterprise relationship classification information;

[0085] Business data relationship information determination submodule: used to determine the business data relationship information corresponding to each designated entity node information based on a preset business data characteristic classification set, wherein the business data characteristic classification set includes information characteristic classification information, credit characteristic classification information and capital characteristic classification information, and the business data relationship information includes information relationship information, credit relationship information and capital relationship information, the information relationship information corresponds to the information characteristic classification information, the credit relationship information corresponds to the credit characteristic classification information, and the capital relationship information corresponds to the capital characteristic classification information.

[0086] Optionally, the system 60 further includes:

[0087] An enterprise name information subset generation module: used to generate an enterprise name information subset according to an enterprise basic information subset, wherein the enterprise name information subset includes a plurality of enterprise name information;

[0088] Name defect event judgment module: used to judge whether there is a name defect event in the knowledge graph information based on the enterprise name information subset, where the name defect event is used to describe the lack of any enterprise name information in the knowledge graph information and / or the lack of characters in the enterprise name in the knowledge graph information;

[0089] Enterprise name information subset supplementation module: used to supplement the knowledge graph information based on the enterprise name information subset if there is a name defect event in the knowledge graph information, so as to supplement the missing enterprise name information in the knowledge graph information, or supplement the missing characters in the knowledge graph information;

[0090] Expired name event judgment module: used to judge whether there is an expired name event in the knowledge graph information based on the enterprise name information subset;

[0091] Enterprise name information subset update module: used to update the knowledge graph information based on the enterprise name information subset if there is an expired name event in the knowledge graph information, so as to update the expired and unchanged enterprise name information in the knowledge graph information;

[0092] Wrong name event judgment module: used to judge whether there is a wrong name event in the knowledge graph information based on the enterprise name information subset;

[0093] Enterprise name information subset repair module: used to repair the knowledge graph information based on the enterprise name information subset if there is an incorrect name event in the knowledge graph information, so as to correct the incorrect enterprise name information in the knowledge graph information.

[0094] Optionally, the target entity node information includes target write-off enterprise information, target employee information and target retail customer information; the above abnormal link information determination module 63 includes:

[0095] Abnormal link information determination submodule: used to perform global retrieval processing on the knowledge graph information based on the target write-off enterprise information, target employee information and target retail customer information, and determine the abnormal link information, wherein the starting node of the abnormal link information is the target write-off enterprise information, the ending node of the abnormal link information is the target employee information, and the abnormal link information includes at least one target retail customer information, and the target retail customer information is located between the starting node and the ending node.

[0096] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0097] The present application also provides a terminal device, such as Figure 7 As shown, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71. When the processor 71 executes the computer program 73, the steps in the above-mentioned commercial bank write-off enterprise audit method embodiment are implemented, such as Figure 1 Steps S100 to S300 shown; or, when the processor 71 executes the computer program 73, the functions of each module in the above device are realized, for example Figure 6 The functions of modules 61 to 63 are shown.

[0098] The terminal device 70 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server, and the terminal device 70 includes but is not limited to a processor 71 and a memory 72. Those skilled in the art will appreciate that Figure 7 It is only an example of the terminal device 70 and does not constitute a limitation of the terminal device 70. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 70 may also include input and output devices, network access devices, buses, etc.

[0099] Among them, the processor 71 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0100] The memory 72 may be an internal storage unit of the terminal device 70, such as a hard disk or memory of the terminal device 70, or the memory 72 may be an external storage device of the terminal device 70, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device 70; further, the memory 72 may also include both an internal storage unit and an external storage device of the terminal device 70, and the memory 72 may also store a computer program 73 and other programs and data required by the terminal device 70, and the memory 72 may also be used to temporarily store data that has been output or is to be output.

[0101] One embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.; the computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0102] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, all equivalent changes made according to the methods, principles, and structures of the present application should be included in the protection scope of the present application.

Claims

1. A commercial bank write-off enterprise audit method based on knowledge graph, characterized in that: The method comprises: Obtain the audit business dataset of the target commercial bank; According to the audit business data set, construct knowledge graph information, wherein the knowledge graph information includes a plurality of entity node information and node relationship information between each of the entity node information; Abnormal link information is determined based on the knowledge graph information and preset target entity node information.

2. The method according to claim 1, characterized in that The audit business data set includes a basic enterprise information subset, a core enterprise personnel basic information subset, a write-off time information subset, a credit card user information subset, a debit card user information subset, an enterprise investment information subset, a transaction information subset, a guarantee relationship information subset, a retail customer information subset, a corporate customer information subset, a group customer information subset and an employee information subset.

3. The method according to claim 2, characterized in that The step of constructing knowledge graph information based on the audit business data set includes: Determine a plurality of designated entity node information according to the audit business data set, wherein the types of the designated entity node information include retail customer node information, corporate customer node information, write-off enterprise node information, group customer node information and internal employee node information; Based on a preset human-enterprise relationship classification set, determine the natural person-enterprise relationship information corresponding to each of the designated entity node information, wherein the human-enterprise relationship classification set includes human-enterprise relationship classification information, natural person relationship classification information and enterprise relationship classification information, the natural person-enterprise relationship information includes human-enterprise relationship information, natural person relationship information and enterprise relationship information, the human-enterprise relationship information corresponds to the human-enterprise relationship classification information, the natural person relationship information corresponds to the natural person relationship classification information, and the enterprise relationship information corresponds to the enterprise relationship classification information; Based on a preset business data characteristic classification set, the business data relationship information corresponding to each of the designated entity node information is determined, wherein the business data characteristic classification set includes information characteristic classification information, credit characteristic classification information and capital characteristic classification information, and the business data relationship information includes information class relationship information, credit class relationship information and capital class relationship information, the information class relationship information corresponds to the information characteristic classification information, the credit class relationship information corresponds to the credit characteristic classification information, and the capital class relationship information corresponds to the capital characteristic classification information.

4. The method according to claim 3, characterized in that After constructing the knowledge graph information according to the audit business data set, the method further includes: Generate an enterprise name information subset according to the enterprise basic information subset, wherein the enterprise name information subset includes a plurality of enterprise name information; Based on the enterprise name information subset, determine whether there is a name defect event in the knowledge graph information, wherein the name defect event is used to describe that any of the enterprise name information is missing in the knowledge graph information, and / or the enterprise name in the knowledge graph information is missing characters; If the name defect event exists in the knowledge graph information, the knowledge graph information is supplemented based on the enterprise name information subset to supplement the missing enterprise name information in the knowledge graph information, or to supplement the missing characters in the knowledge graph information; Based on the enterprise name information subset, determining whether there is an expired name event in the knowledge graph information; If the expired name event exists in the knowledge graph information, the knowledge graph information is updated based on the enterprise name information subset to update the expired and unchanged enterprise name information in the knowledge graph information; Based on the enterprise name information subset, determining whether there is an incorrect name event in the knowledge graph information; If the erroneous name event exists in the knowledge graph information, the knowledge graph information is repaired based on the enterprise name information subset to correct the erroneous enterprise name information in the knowledge graph information.

5. The method according to claim 4, characterized in that The target entity node information includes target write-off enterprise information, target employee information and target retail customer information; The determining of abnormal link information according to the knowledge graph information and preset target entity node information includes: Based on the target write-off enterprise information, the target employee information and the target retail customer information, the knowledge graph information is globally searched and processed to determine abnormal link information, wherein the starting node of the abnormal link information is the target write-off enterprise information, the ending node of the abnormal link information is the target employee information, and the abnormal link information includes at least one target retail customer information, and the target retail customer information is located between the starting node and the ending node.

6. A commercial bank write-off enterprise audit system based on knowledge graph, characterized in that: The system comprises: Audit business data set acquisition module: used to acquire the audit business data set of the target commercial bank; A knowledge graph information construction module: used to construct knowledge graph information according to the audit business data set, wherein the knowledge graph information includes a plurality of entity node information and node relationship information between each of the entity node information; Abnormal link information determination module: used to determine abnormal link information based on the knowledge graph information and preset target entity node information.

7. The system according to claim 6, characterized in that The knowledge graph information building module includes: The designated entity node information determination submodule is used to determine a plurality of designated entity node information according to the audit business data set, wherein the types of the designated entity node information include retail customer node information, corporate customer node information, write-off enterprise node information, group customer node information and internal employee node information; A human-enterprise relationship information determination submodule: used to determine the natural person-enterprise relationship information corresponding to each of the designated entity node information based on a preset human-enterprise relationship classification set, wherein the human-enterprise relationship classification set includes human-enterprise relationship classification information, natural person relationship classification information, and enterprise relationship classification information, the natural person-enterprise relationship information includes human-enterprise relationship information, natural person relationship information, and enterprise relationship information, the human-enterprise relationship information corresponds to the human-enterprise relationship classification information, the natural person relationship information corresponds to the natural person relationship classification information, and the enterprise relationship information corresponds to the enterprise relationship classification information; Business data relationship information determination submodule: used to determine the business data relationship information corresponding to each of the designated entity node information based on a preset business data characteristic classification set, wherein the business data characteristic classification set includes information characteristic classification information, credit characteristic classification information and capital characteristic classification information, and the business data relationship information includes information class relationship information, credit class relationship information and capital class relationship information, the information class relationship information corresponds to the information characteristic classification information, the credit class relationship information corresponds to the credit characteristic classification information, and the capital class relationship information corresponds to the capital characteristic classification information.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images