A method and device for identifying enterprise credit risk

Abstract

The present invention provides a method and device for identifying corporate credit risk, which can be used in the financial field or other fields. The identification method includes: obtaining a target bank customer who has transactions with a bank corporate customer and transaction data between the target bank customer and the bank corporate customer; determining the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer; and identifying the credit risk of the target bank customer's transaction data based on the association relationship. The present invention can reduce manual input, effectively reduce the transmission of risks, and issue timely alarms to shorten the response time and improve detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of risk prevention and control, and can be used in the financial field to identify corporate credit risks, and in particular to a method and device for identifying corporate credit risks. Background Art

[0002] With the continuous development of banking business, some enterprises, especially small and micro enterprises, lack standardized financial statements and tax audit information, have poor business transparency and are relatively easy to falsify information, resulting in information asymmetry between banks and enterprises. This makes it difficult for banks to grasp the true situation of small and micro enterprises and to fully characterize customer characteristics. There are corporate legal persons who apply for mortgage loans from banks through illegal operations. For example, in order to cash out funds, they purchase existing housing in their hands in the name of virtual buyers and obtain housing loans from banks.

[0003] At present, the technology used by the industry's risk detection system is mainly to automatically import data fields in the data table into a graph database such as Neo4j or JanusGraph through manually defined schemas, forming customer fund transaction flows or equity relationships and other associations, and to mine the hidden relationships or knowledge in seemingly normal transactions or processes through visual exploration or association analysis such as manually defined rules, thereby reducing the transmission or occurrence of risks. This traditional risk detection method is not enough to deal with risks that have strong hidden capabilities, fast risk transmission speed, no obvious characteristics, and are not detected in real time. Summary of the invention

[0004] In view of the problems in the prior art, the present invention provides a method and device for identifying corporate credit risk, which can effectively reduce the transmission of risk, issue alarms in a timely manner, shorten the response time, and improve detection efficiency.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for identifying corporate credit risk, comprising:

[0007] Acquire a target bank customer who has transactions with a bank corporate customer and transaction data between the target bank customer and the bank corporate customer;

[0008] Determining the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer;

[0009] The credit risk of the transaction data of the target bank customer is identified based on the association relationship.

[0010] Wherein, establishing the knowledge graph includes:

[0011] Obtain target data of bank customers and add machine-recognizable semantic descriptions to entities in the target data; wherein the target data includes: structured data, semi-structured data and unstructured data;

[0012] Determining a mapping relationship between entities of the structured data, the semi-structured data, and the unstructured data;

[0013] Attributes describing the entity are obtained from the target data, and the entity, the attributes of the entity, the mapping relationship of the entity, and the semantic description are imported into a graph database to form a knowledge graph.

[0014] After obtaining the target data of bank customers, it also includes:

[0015] The structured data, semi-structured data and unstructured data in the target data are processed in a unified format, and the structured data, semi-structured data and unstructured data after the unified format processing are stored.

[0016] The structured data, semi-structured data and unstructured data after unified storage format processing include:

[0017] The structured data, the semi-structured data and the unstructured data after the format is uniformly processed are stored in the form of RDF triples, multi-tuples and time series information respectively.

[0018] Wherein, determining the entity mapping relationship between the structured data, the semi-structured data and the unstructured data includes:

[0019] Determining, by a knowledge-based editing tool, a mapping relationship between entities of the structured data, the semi-structured data, and the unstructured data;

[0020] The mapping relationships include:

[0021] The corporate legal person relationship includes the corresponding relationship between corporate legal persons and individuals; the corresponding relationship between corporate stakeholders, the corresponding relationship between corporate legal persons and related attributes, the corresponding relationship between corporate stakeholders and related attributes, and the corresponding relationship between corporate legal persons;

[0022] Among them, entities include: corporate legal persons, corporate stakeholders and individuals.

[0023] Wherein, determining the association relationship between the bank corporate customer and the target bank customer according to the pre-established knowledge graph includes:

[0024] Determine, in the knowledge graph, a reachable path between the bank corporate customer and the target bank customer by at least one of reasoning based on symbolic logic, reasoning based on graph database technology, and reasoning based on statistical reasoning;

[0025] The reachable path is determined as the association relationship between the bank corporate customer and the target bank customer.

[0026] Wherein, the identifying of credit risk of the transaction data of the target bank customer based on the association relationship includes:

[0027] If the association relationship conforms to the preset association rule, the transaction data of the target bank customer is risk-marked, and a risk reminder message is generated and displayed according to the risk mark.

[0028] Wherein, if the association relationship meets the preset association rule, it includes:

[0029] The association relationship is matched with each preset verification relationship standard in the preset association rule to determine whether the association relationship conforms to the preset association rule.

[0030] After generating and displaying a risk reminder message according to the risk identifier, the method further includes:

[0031] If the association relationship does not conform to the preset association rule, a verification pass mark is added to the transaction data of the target bank customer;

[0032] The transaction data with the verification pass mark is sent to the corresponding review node to conduct the next node review on the transaction data of the target bank customer.

[0033] In a second aspect, the present invention provides a device for identifying corporate credit risk, comprising:

[0034] An acquisition module, used to acquire a target bank customer having transactions with a bank corporate customer and transaction data between the target bank customer and the bank corporate customer;

[0035] A processing module, used to determine the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer;

[0036] An identification module is used to identify the credit risk of the transaction data of the target bank customer based on the association relationship.

[0037] In a third aspect, the present invention provides an electronic 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 for identifying corporate credit risk when executing the program.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for identifying corporate credit risk.

[0039] It can be seen from the above technical solution that the present invention provides a method and device for identifying corporate credit risks, by obtaining target bank customers who have transactions with bank corporate customers and transaction data between the target bank customer and the bank corporate customer; determining the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph contains all bank customers and the association relationship between each bank customer; identifying credit risks of the target bank customer's transaction data based on the association relationship, which can realize real-time evaluation of fraudulent behavior of bank customers, greatly reduce manual input, effectively reduce risk transmission, and issue timely alarms before fraud risks occur, shorten response time, and improve detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic flow chart of a method for identifying corporate credit risk provided by an embodiment of the present invention.

[0042] Figure 2 A schematic flow chart of step S102 in the method for identifying corporate credit risk provided by an embodiment of the present invention.

[0043] Figure 3 Another flowchart diagram of step S102 in the method for identifying corporate credit risk provided by an embodiment of the present invention.

[0044] Figure 4 A schematic diagram of processing target data in a method for identifying corporate credit risk provided by an embodiment of the present invention.

[0045] Figure 5 A schematic diagram of a loan event flow chart in a method for identifying corporate credit risk provided by an embodiment of the present invention.

[0046] Figure 6 A schematic flow chart of implicit relationships of loan events in a method for identifying corporate credit risk provided by an embodiment of the present invention.

[0047] Figure 7 Schematic diagram of the structure of the device for identifying corporate credit risk in an embodiment of the present invention.

[0048] Figure 8 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 are within the scope of protection of the present invention.

[0050] The present invention provides an embodiment of a method for identifying corporate credit risk. Figure 1 The method for identifying the enterprise credit risk specifically includes the following contents:

[0051] S101: Acquire a target bank customer who has transactions with a bank corporate customer and transaction data between the target bank customer and the bank corporate customer;

[0052] In this step, the bank corporate customer is the corporate customer that needs to be identified for corporate credit risk; the target bank customer is the individual customer or corporate customer that has transactions with the corporate customer that needs to be identified for corporate credit risk. Credit risk identification of the transaction data between the target bank customer and the bank corporate customer, and judging whether the bank corporate customer has violated regulations, can effectively reduce the transmission of risks.

[0053] S102: Determine the association relationship between the bank corporate customer and the target bank customer according to a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer;

[0054] In this step, a reachable path between the bank corporate customer and the target bank customer is determined in the knowledge graph by at least one of the three methods of reasoning based on symbolic logic, reasoning based on graph database technology, and reasoning based on statistical reasoning;

[0055] The reachable path is determined as the association relationship between the bank corporate customer and the target bank customer.

[0056] It should be noted that reasoning based on symbolic logic mainly includes first-order predicate logic, description logic and rule-based reasoning. Reasoning based on graph database technology is mainly based on neural network models or path ranking algorithms. Methods based on statistical reasoning, such as those based on inductive logic program (ILP), etc.

[0057] S103: Identify credit risks of the target bank customer's transaction data based on the association relationship.

[0058] In this step, the association relationship is matched with each preset verification relationship standard in the preset association rule to determine whether the association relationship conforms to the preset association rule. If the association relationship conforms to the preset association rule, the transaction data of the target bank customer is risk-marked, and a risk reminder message is generated and displayed according to the risk mark.

[0059] Furthermore, if the association relationship does not conform to the preset association rule, a verification pass mark is added to the transaction data of the target bank customer; the transaction data with the verification pass mark is sent to the corresponding review node to perform next node review on the transaction data of the target bank customer.

[0060] From the above description, it can be seen that the present invention provides a method for identifying corporate credit risks, by obtaining target bank customers who have transactions with bank corporate customers and transaction data between the target bank customer and the bank corporate customer; determining the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph contains all bank customers and the association relationship between each bank customer; identifying credit risks of the target bank customer's transaction data based on the association relationship, enabling real-time assessment of fraudulent behavior of bank customers, greatly reducing manual input, effectively reducing risk transmission, and issuing timely alarms before fraud risks occur, shortening response time, and improving detection efficiency.

[0061] In one embodiment of the present invention, see Figure 2 The step of establishing a knowledge graph in step S102 of the method for identifying corporate credit risk includes:

[0062] S201: Acquire target data of bank customers and add machine-recognizable semantic descriptions to entities in the target data; wherein the target data includes: structured data, semi-structured data and unstructured data;

[0063] In this step, structured data refers to the data lake data stored in the banking system; semi-structured data refers to office data (Notes emails) and technology data (IPS logs, etc.); unstructured data refers to litigation documents, public opinion reports, and HTML texts, etc.

[0064] Among them, entities are divided into two categories: Observable entity: an entity that can be directly observed, such as corporate customers, individual customers, lenders, etc. Entity of interest: an entity that cannot be directly observed but whose status can be inferred from the status of other entities.

[0065] In this step, machine-recognizable semantic descriptions are added to entities in the target data to generate low-level scenarios.

[0066] It should be noted that low-level context refers to the original target data collected directly, such as the accounts of corporate clients, the company's address, the social relationships of corporate clients, the accounts of lenders, the transaction records of lenders, the transaction records between real estate companies and lenders, etc. Low-level context corresponds to high-level context. High-level context refers to the context derived from the association between low-level contexts, such as customer fraud status.

[0067] In this embodiment, both the low-level scenario and the high-level scenario are composed of three elements: a group of entities, entity states, and entity input information.

[0068] S202: Determine an entity mapping relationship between the structured data, the semi-structured data, and the unstructured data;

[0069] In this step, standardized and clear associations between data are established, as well as semantic descriptions that can be understood by machines. High-level scenarios can be derived from low-level scenarios through machine learning or rule engine reasoning, that is, implicit relationships or knowledge can be obtained. That is, the mapping relationship between entities of structured data, semi-structured data, and unstructured data is determined.

[0070] Specifically, the mapping relationship between the entities of the structured data, the semi-structured data and the unstructured data is determined by a knowledge-based editing tool;

[0071] The mapping relationships include:

[0072] The corporate legal person relationship includes the corresponding relationship between corporate legal persons and individuals (such as holding relationship), the corresponding relationship between corporate stakeholders and corporate stakeholders (such as kinship), the corresponding relationship between corporate legal persons and related attributes (such as corporate common contact information), the corresponding relationship between corporate stakeholders and related attributes (such as stakeholder common contact information), and the corresponding relationship between corporate legal persons and corporate legal persons (such as corporate guarantee relationship). Entities include: corporate legal persons, corporate stakeholders, and individuals.

[0073] In this embodiment, the mapping relationship is used to construct a relationship graph with customers as entities.

[0074] It should be noted that knowledge-based editing tools include but are not limited to Protégé and Semantic Turkey.

[0075] S203: Acquire attributes describing the entity from the target data, and import the entity, the attributes of the entity, the mapping relationship of the entity, and the semantic description into a graph database to form a knowledge graph;

[0076] In this step, the attributes of the entity include but are not limited to address, gender, occupation, etc. The entity, the mapping relationship between entities, and the attributes of entities are described in a graph model in the form of triples and imported into the graph database to form a knowledge graph.

[0077] In this embodiment, a knowledge graph can be generated based on structured data, semi-structured data and unstructured data, and the knowledge graph covers information on various aspects of bank customers, so as to obtain the association relationship between bank customers and specific targets based on the knowledge graph.

[0078] In one embodiment of the present invention, see Figure 3 After the step S201 of establishing the knowledge graph, the following contents are specifically included:

[0079] S204: performing format-unified processing on the structured data, semi-structured data and unstructured data in the target data, and storing the structured data, semi-structured data and unstructured data after the format-unified processing.

[0080] In this step, by converting the multi-source heterogeneous raw data into a unified format, it is easy to establish standardized and clear associations between the data. Figure 4 , storing structured data, semi-structured data and unstructured data after unified processing in storage format, including: using natural language processing (NLP), D2R mapping, wrappers, information extraction to obtain information data from target data and store it, specifically including:

[0081] The connection data and the database data in the structured data are processed by image mapping and D2R conversion respectively and stored in the form of RDF triples;

[0082] The XML document and the JSON document in the semi-structured data are processed by a wrapper and stored in a tuple format;

[0083] The pictures and txt files in the unstructured data are processed for information extraction and then stored in the form of time series information.

[0084] From the above description, it can be seen that the embodiments of the present invention can achieve real-time evaluation of customers and timely detect fraud such as fake mortgage loan incidents, and respond with measures such as early warning and protection, which can greatly improve the accuracy and intelligence level of identification and monitoring while reducing manual input.

[0085] The present invention also provides a specific application example of the above technical solution. Figure 5 and Figure 6 A case study of the application of an ontology-based adaptive scenario-aware risk prevention and control system in personal home mortgage loans is demonstrated.

[0086] Figure 5 It shows a seemingly normal individual mortgage loan event. The individual signs a contract with a real estate company to purchase a property. The real estate company is a corporate customer of the bank and the individual is a target bank customer. The individual applies for a loan (transaction data) from the bank using his or her ID card and the purchase contract. The bank then lends money to the developer according to the contract, and the individual begins to repay the loan. There is nothing wrong with the process of this event.

[0087] However, Figure 6 As shown in the figure, if the implicit relationship (associated relationship) is mined through massive data, it is found that these individuals are only nominal borrowers, and the identity of the borrowers is the internal employees or relatives of the developer (associated relationship), especially if it is found that there are financial transactions between the developer and these borrowers (preset verification relationship standards), there is reason to suspect that this is a fake mortgage loan event, that is, the developer purchases the existing housing in the name of a virtual buyer in order to cash out funds, and obtains a housing loan from the bank. The developer recovers the cost in advance and realizes the profit through a fake mortgage, leaving all the burdens and risks to the bank. Therefore, the adaptive scenario-aware risk prevention and control system based on ontology can enable business risk management, help financial institutions to explore the implicit relationships or knowledge in seemingly normal transactions or processes, and reduce the transmission or occurrence of risks.

[0088] From the above description, it can be seen that the technical solution of the embodiment of the present invention can perceive the capital transaction flow, equity relationship and social relationship status of the bank's customers in real time, and conduct real-time evaluation of the customer's fraudulent behavior, which greatly reduces the input of manpower. It can effectively reduce the transmission of risks, and issue warnings in time before the risk of fraud occurs, shorten the response time, and improve the detection efficiency. It can mine implicit relationships or knowledge in massive data, providing effective decision-making support for risk prevention and control.

[0089] The embodiment of the present invention provides a specific implementation of an enterprise credit risk identification device that can implement all the contents of the enterprise credit risk identification method, see Figure 7 The enterprise credit risk identification device specifically includes the following contents:

[0090] An acquisition module 10 is used to acquire a target bank customer who has transactions with a bank corporate customer and transaction data between the target bank customer and the bank corporate customer;

[0091] A processing module 20 is used to determine the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer;

[0092] The identification module 30 is used to identify the credit risk of the transaction data of the target bank customer based on the association relationship.

[0093] Wherein, establishing the knowledge graph includes:

[0094] Obtain target data of bank customers and add machine-recognizable semantic descriptions to entities in the target data; wherein the target data includes: structured data, semi-structured data and unstructured data;

[0095] Determining a mapping relationship between entities of the structured data, the semi-structured data, and the unstructured data;

[0096] Attributes describing the entity are obtained from the target data, and the entity, the attributes of the entity, the mapping relationship of the entity, and the semantic description are imported into a graph database to form a knowledge graph.

[0097] Furthermore, it also includes:

[0098] The storage module is used to perform format-unified processing on the structured data, semi-structured data and unstructured data in the target data, and store the structured data, semi-structured data and unstructured data after the format-unified processing.

[0099] The storage module includes:

[0100] The storage unit is used to store the structured data, the semi-structured data and the unstructured data after the format is uniformly processed in the form of RDF triples, multi-tuples and time series information respectively.

[0101] Wherein, determining the entity mapping relationship between the structured data, the semi-structured data and the unstructured data includes:

[0102] Determining, by a knowledge-based editing tool, a mapping relationship between entities of the structured data, the semi-structured data, and the unstructured data;

[0103] The mapping relationships include:

[0104] The corporate legal person relationship includes the corresponding relationship between corporate legal persons and individuals; the corresponding relationship between corporate stakeholders, the corresponding relationship between corporate legal persons and related attributes, the corresponding relationship between corporate stakeholders and related attributes, and the corresponding relationship between corporate legal persons;

[0105] Among them, entities include: corporate legal persons, corporate stakeholders and individuals.

[0106] The processing module 20 includes:

[0107] a processing unit, configured to determine, in the knowledge graph, a reachable path between the bank enterprise customer and the target bank customer by at least one of reasoning based on symbolic logic, reasoning based on graph database technology, and reasoning based on statistical reasoning;

[0108] The reachable path is determined as the association relationship between the bank corporate customer and the target bank customer.

[0109] The identification module 30 includes:

[0110] The identification unit is used to identify the risk of the transaction data of the target bank customer if the association relationship meets the preset association rules, and generate and display a risk reminder message according to the risk identification.

[0111] The identification unit comprises:

[0112] The first identification subunit is used to match the association relationship with each preset verification relationship standard in the preset association rule to determine whether the association relationship conforms to the preset association rule.

[0113] The identification unit also includes:

[0114] A first identification subunit, configured to add a verification pass mark to the transaction data of the target bank customer if the association relationship does not conform to a preset association rule;

[0115] The sending subunit is used to send the transaction data with the verification pass mark to the corresponding review node, so as to conduct a next node review on the transaction data of the target bank customer.

[0116] The embodiment of the enterprise credit risk identification device provided by the present invention can be specifically used to execute the processing flow of the embodiment of the enterprise credit risk identification method in the above embodiment. Its functions are not repeated here, and reference can be made to the detailed description of the above method embodiment.

[0117] From the above description, it can be seen that the enterprise credit risk identification device provided by the embodiment of the present invention obtains the target bank customer who has transactions with the bank corporate customer and the transaction data between the target bank customer and the bank corporate customer; determines the association relationship between the bank corporate customer and the target bank customer according to a pre-established knowledge graph; wherein the knowledge graph contains all bank customers and the association relationship between each bank customer; identifies the credit risk of the target bank customer's transaction data based on the association relationship, and can realize real-time evaluation of the fraudulent behavior of the bank customer, greatly reducing the manual input, can effectively reduce the transmission of risks, and timely issue an alarm before the fraud risk occurs, shortening the response time and improving the detection efficiency.

[0118] The present application provides an embodiment of an electronic device for implementing all or part of the content of the enterprise credit risk identification method. The electronic device specifically includes the following content:

[0119] A processor, a memory, a communications interface and a bus; wherein the processor, the memory and the communications interface communicate with each other through the bus; the communications interface is used to realize information transmission between related devices; the electronic device can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the electronic device can be implemented with reference to the embodiment of the method for realizing the enterprise credit risk identification and the embodiment of the device for realizing the enterprise credit risk identification, and the contents thereof are incorporated herein and the repeated parts are not repeated.

[0120] Figure 8 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 8 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Figure 8is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0121] In one embodiment, the function of identifying corporate credit risk may be integrated into the central processor 9100. The central processor 9100 may be configured to perform the following control:

[0122] Obtain target bank customers who have transactions with bank corporate customers and transaction data between the target bank customer and the bank corporate customer; determine the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer; and identify credit risks of the target bank customer's transaction data based on the association relationship.

[0123] From the above description, it can be seen that the electronic device provided by the embodiment of the present application obtains the target bank customer who has transactions with the bank corporate customer and the transaction data between the target bank customer and the bank corporate customer; determines the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph contains all bank customers and the association relationship between each bank customer; identifies the credit risk of the target bank customer's transaction data based on the association relationship, and can realize real-time evaluation of the fraudulent behavior of the bank customer, greatly reducing the manpower input, effectively reducing the transmission of risks, and issuing timely alarms before the risk of fraud occurs, shortening the response time, and improving the detection efficiency.

[0124] In another embodiment, the enterprise credit risk identification device can be configured separately from the central processor 9100. For example, the enterprise credit risk identification device can be configured as a chip connected to the central processor 9100, and the enterprise credit risk identification function can be realized through the control of the central processor.

[0125] like Figure 8 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 8 In addition, the electronic device 9600 may also include Figure 8 For components not shown, reference may be made to the prior art.

[0126] like Figure 8As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0127] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0128] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0129] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0130] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0131] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0132] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0133] The embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps of the method for identifying corporate credit risk in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements all the steps of the method for identifying corporate credit risk in the above embodiment. For example, when the processor executes the computer program, the following steps are implemented:

[0134] Obtain target bank customers who have transactions with bank corporate customers and transaction data between the target bank customer and the bank corporate customer; determine the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer; and identify credit risks of the target bank customer's transaction data based on the association relationship.

[0135] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present invention obtains the target bank customer who has transactions with the bank corporate customer and the transaction data between the target bank customer and the bank corporate customer; determines the association relationship between the bank corporate customer and the target bank customer according to a pre-established knowledge graph; wherein the knowledge graph contains all bank customers and the association relationship between each bank customer; identifies the credit risk of the target bank customer's transaction data based on the association relationship, and can realize real-time evaluation of the fraudulent behavior of the bank customer, greatly reducing the manual input, effectively reducing the transmission of risks, and issuing timely alarms before the risk of fraud occurs, thereby shortening the response time and improving the detection efficiency.

[0136] Although the present invention provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, in a parallel processor or multi-threaded processing environment).

[0137] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, devices (systems) or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0141] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict. The present invention is not limited to any single aspect, any single embodiment, or any combination and / or replacement of these aspects and / or embodiments. Moreover, each aspect and / or embodiment of the present invention can be used alone or in combination with one or more other aspects and / or embodiments thereof.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for identifying corporate credit risk, characterized in that: include: Acquire a target bank customer who has transactions with a bank corporate customer and transaction data between the target bank customer and the bank corporate customer; Determining the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer; Identifying credit risks of the target bank customer's transaction data based on the association relationship; Establishing the knowledge graph includes: Obtain target data of bank customers and add machine-recognizable semantic descriptions to entities in the target data; wherein the target data includes: structured data, semi-structured data and unstructured data; the entities in the target data can be added with machine-recognizable semantic descriptions to generate low-level scenarios; the low-level scenarios are the original target data directly collected; The higher-order scenario corresponds to the lower-order scenario and refers to the scenario derived through the association between the lower-order scenarios; Determining a mapping relationship between entities of the structured data, the semi-structured data, and the unstructured data; Attributes describing the entity are obtained from the target data, and the entity, the attributes of the entity, the mapping relationship of the entity, and the semantic description are imported into a graph database to form a knowledge graph.

2. The method for identifying corporate credit risk according to claim 1, characterized in that: After obtaining the target data of bank customers, it also includes: The structured data, semi-structured data and unstructured data in the target data are processed in a unified format, and the structured data, semi-structured data and unstructured data after the unified format processing are stored.

3. The method for identifying corporate credit risk according to claim 2, characterized in that: The structured data, semi-structured data and unstructured data after unified storage format processing include: The structured data, the semi-structured data and the unstructured data after the format is uniformly processed are stored in the form of RDF triples, multi-tuples and time series information respectively.

4. The method for identifying corporate credit risk according to claim 1, characterized in that: The determining of the entity mapping relationship between the structured data, the semi-structured data and the unstructured data includes: Determining, by a knowledge-based editing tool, a mapping relationship between entities of the structured data, the semi-structured data, and the unstructured data; The mapping relationships include: The corporate legal person relationship includes the corresponding relationship between corporate legal persons and individuals; the corresponding relationship between corporate stakeholders, the corresponding relationship between corporate legal persons and related attributes, the corresponding relationship between corporate stakeholders and related attributes, and the corresponding relationship between corporate legal persons; Among them, entities include: corporate legal persons, corporate stakeholders and individuals.

5. The method for identifying corporate credit risk according to claim 1, characterized in that: The determining the association relationship between the bank enterprise customer and the target bank customer according to the pre-established knowledge graph includes: Determine, in the knowledge graph, a reachable path between the bank corporate customer and the target bank customer by at least one of reasoning based on symbolic logic, reasoning based on graph database technology, and reasoning based on statistical reasoning; The reachable path is determined as the association relationship between the bank corporate customer and the target bank customer.

6. The method for identifying corporate credit risk according to claim 1, characterized in that: The identifying of credit risk of the transaction data of the target bank customer based on the association relationship includes: If the association relationship conforms to the preset association rule, the transaction data of the target bank customer is risk-marked, and a risk reminder message is generated and displayed according to the risk mark.

7. The method for identifying corporate credit risk according to claim 6, characterized in that: If the association relationship meets the preset association rules, it includes: The association relationship is matched with each preset verification relationship standard in the preset association rule to determine whether the association relationship conforms to the preset association rule.

8. The method for identifying corporate credit risk according to claim 6, characterized in that: After generating and displaying a risk reminder message according to the risk identifier, the method further includes: If the association relationship does not conform to the preset association rule, a verification pass mark is added to the transaction data of the target bank customer; The transaction data with the verification pass mark is sent to the corresponding review node to conduct the next node review on the transaction data of the target bank customer.

9. A device for identifying corporate credit risk, characterized in that: include: An acquisition module, used to acquire a target bank customer having transactions with a bank corporate customer and transaction data between the target bank customer and the bank corporate customer; A processing module, used to determine the association relationship between the bank corporate customer and the target bank customer based on a pre-established knowledge graph; wherein the knowledge graph includes all bank customers and the association relationship between each bank customer; An identification module, used for identifying credit risks of the transaction data of the target bank customer based on the association relationship; Establishing the knowledge graph includes: Obtain target data of bank customers and add machine-recognizable semantic descriptions to entities in the target data; wherein the target data includes: structured data, semi-structured data and unstructured data; the entities in the target data can be added with machine-recognizable semantic descriptions to generate low-level scenarios; the low-level scenarios are the original target data directly collected; The higher-order scenario corresponds to the lower-order scenario and refers to the scenario derived through the association between the lower-order scenarios; Determining a mapping relationship between entities of the structured data, the semi-structured data, and the unstructured data; Attributes describing the entity are obtained from the target data, and the entity, the attributes of the entity, the mapping relationship of the entity, and the semantic description are imported into a graph database to form a knowledge graph.

10. An electronic 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 program, the steps of the method for identifying corporate credit risk according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying corporate credit risk as described in any one of claims 1 to 8 are implemented.

Images