Risk assessment method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a risk assessment method and device, equipment and a storage medium. The method comprises the steps of determining risk enterprise entity nodes related to enterprise default data according to enterprise industrial and commercial data and enterprise default data, and constructing an enterprise default risk knowledge graph based on the risk enterprise entity nodes; establishing enterprise default dynamic attribute graphs at multiple moments based on the enterprise operation data and the enterprise default risk knowledge graph, determining a risk prediction value of a target default feature according to a dynamic heterogeneous graph model based on each enterprise default dynamic attribute graph, and evaluating an enterprise default risk based on the risk prediction value of the target default feature; wherein the risk enterprise entity nodes comprise default enterprise entity nodes for generating enterprise default data and enterprise entity nodes associated with the default enterprise entity nodes. According to the embodiment of the invention, the accuracy and reliability of the enterprise default risk assessment result can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data analysis technology, and in particular to a risk assessment method, apparatus, device and storage medium. Background Art

[0002] Faced with a rapidly changing market environment, companies need to ensure whether there is any risk of default in their operations, so as to identify and resolve default risk issues in a timely manner, improve the company's operating stability, and promote continuous improvement and growth.

[0003] Traditional default risk prediction models used to implement enterprise default risk assessment all make predictions about the future based on the historical operating behaviors of micro-enterprises, ignoring the impact of macro-environmental factors on enterprise default risk, and are unable to guarantee the accuracy and reliability of enterprise risk assessment results. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a risk assessment method, apparatus, device and storage medium, which can improve the accuracy of enterprise risk assessment results to a certain extent.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] According to a first aspect of an embodiment of the present application, a risk assessment method is provided, the method comprising:

[0007] Obtain business data of enterprises and business operation data of enterprises in historical time periods;

[0008] Filtering enterprise default data from the enterprise operation data, determining risk enterprise entity nodes related to the enterprise default data according to the enterprise business data and the enterprise default data, and constructing an enterprise default risk knowledge graph based on the risk enterprise entity nodes;

[0009] Based on the enterprise operation data and the enterprise default risk knowledge graph, dynamic attribute graphs of enterprise default at multiple moments are constructed; based on each of the dynamic attribute graphs of enterprise default, a risk prediction value of a target default feature is determined according to a dynamic heterogeneous graph model; and based on the risk prediction value of the target default feature, the enterprise default risk is evaluated;

[0010] Among them, the risk enterprise entity node includes the default enterprise entity node that generates the enterprise default data and the enterprise entity node that is associated with the default enterprise entity node; the enterprise default dynamic attribute graph represents the dynamic changes of the enterprise default data; the target default feature is a default feature whose default impact degree is greater than a first preset threshold.

[0011] In some embodiments, the method further comprises:

[0012] Determine the number of inspections and the number of defaults of each of the risky enterprise entity nodes according to the enterprise business data and the enterprise default data, and determine the default rate according to the number of inspections and the number of defaults;

[0013] Delete the business data and business operation data corresponding to the high-risk enterprise entity node whose default rate is higher than the second preset threshold, as well as the business operation data of each risk enterprise entity node within the preset time period corresponding to the default rate of the high-risk enterprise entity node higher than the second preset threshold.

[0014] In some embodiments, the constructing of a dynamic attribute graph of enterprise default at multiple moments based on the enterprise operation data and the enterprise default risk knowledge graph includes:

[0015] Constructing a dynamic attribute graph of enterprise default at the current moment based on the enterprise default risk knowledge graph;

[0016] Constructing a dynamic attribute graph of corporate defaults at historical moments based on the business data of the corporate during historical time periods;

[0017] The enterprise default dynamic attribute graph at the current moment and the enterprise default dynamic attribute graph at the historical moments are combined to obtain the enterprise default dynamic attribute graphs at multiple moments.

[0018] In some embodiments, the method further comprises:

[0019] Determine anomaly detection features based on the business data of the enterprise and the enterprise default data;

[0020] Performing a standardization operation on the anomaly detection features to obtain a standardized data set, and constructing an anomaly detection framework based on the standardized data set;

[0021] Determining abnormal data from the enterprise business data and the enterprise default data through the anomaly detection framework;

[0022] Delete the abnormal data in the enterprise industrial and commercial data and the enterprise default data.

[0023] In some embodiments, the step of constructing an enterprise default risk knowledge graph based on the risk enterprise entity nodes includes:

[0024] Establish edge relationships between the risk enterprise entity nodes and construct the enterprise default risk knowledge graph.

[0025] In some embodiments, the establishing of the edge relationship between the venture enterprise entity nodes includes:

[0026] Connect the risk enterprise entity nodes that are related or represent the same risk type.

[0027] In some embodiments, the method further comprises:

[0028] According to the target default characteristics and the risk prediction value of the target default characteristics, business strategy recommendations are made to the risk enterprise entity nodes related to the enterprise default data.

[0029] According to a second aspect of an embodiment of the present application, a risk assessment device is provided, comprising:

[0030] Data acquisition module, used to obtain business data of enterprises and business operation data of historical time periods;

[0031] A graph construction module, used to screen enterprise default data from the enterprise operation data, determine risk enterprise entity nodes related to the enterprise default data according to the enterprise business data and the enterprise default data, and construct an enterprise default risk knowledge graph based on the risk enterprise entity nodes;

[0032] A risk assessment module, configured to construct enterprise default dynamic attribute graphs at multiple moments based on the enterprise industrial and commercial data, the enterprise operating data and the enterprise default risk knowledge graph, determine the risk prediction value of the target default feature according to the dynamic heterogeneous graph model based on each of the enterprise default dynamic attribute graphs, and assess the enterprise default risk based on the risk prediction value of the target default feature;

[0033] Among them, the risk enterprise entity node includes the default enterprise entity node that generates the enterprise default data and the enterprise entity node that is associated with the default enterprise entity node; the enterprise default dynamic attribute graph represents the dynamic changes of the enterprise default data; the target default feature is a default feature whose default impact degree is greater than a first preset threshold.

[0034] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including:

[0035] A memory for storing executable instructions;

[0036] The processor is used to implement the risk assessment method as described in the first aspect above when executing the executable instructions stored in the memory.

[0037] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, storing executable instructions for implementing the risk assessment method as described in the first aspect above when executed by a processor.

[0038] In an embodiment of the present application, business data of an enterprise and business data of an enterprise in a historical period are obtained; enterprise default data are screened from the enterprise business data, risk enterprise entity nodes related to the enterprise default data are determined based on the business data of the enterprise and the enterprise default data, and an enterprise default risk knowledge graph is constructed based on the risk enterprise entity nodes; dynamic attribute graphs of enterprise defaults at multiple moments are constructed based on the enterprise business data and the enterprise default risk knowledge graph, and based on the dynamic attribute graphs of each enterprise default, a risk prediction value of a target default feature is determined according to a dynamic heterogeneous graph model, and the enterprise default risk is evaluated based on the risk prediction value of the target default feature; wherein, the risk enterprise entity nodes include default enterprise entity nodes that generate enterprise default data and enterprise entity nodes that are associated with the default enterprise entity nodes; the enterprise default dynamic attribute graph represents the dynamic changes of enterprise default data; and the target default feature is a default feature whose default impact is greater than a first preset threshold.

[0039] In the embodiment of the present application, the enterprise default risk knowledge graph is constructed based on the default enterprise entity nodes that generate enterprise default data and the enterprise entity nodes associated with the default enterprise entity nodes. Combining the default enterprise entity nodes at the micro level and the enterprise entity nodes associated with the default enterprise entity nodes at the macro level, the risks that the enterprise may face can be more comprehensively assessed, thereby improving the accuracy and reliability of the enterprise default risk assessment results.

[0040] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application 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 only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 A schematic diagram of the implementation process of the risk assessment method applicable to the embodiment of the present application;

[0043] Figure 2 A schematic diagram of the structure of a risk assessment device applicable to an embodiment of the present application;

[0044] Figure 3 A schematic diagram of the structure of a risk assessment system applicable to an embodiment of the present application;

[0045] Figure 4 A schematic diagram of a hardware entity of an electronic device applicable to an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0047] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in the embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.

[0048] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0049] It should also be pointed out that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0050] In addition, the term "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0051] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0052] Traditional default risk prediction models used to implement enterprise default risk assessment all make predictions about the future based on the historical operating behaviors of micro-enterprises, ignoring the impact of macro-environmental factors on enterprise default risk, and are unable to guarantee the accuracy and reliability of enterprise risk assessment results.

[0053] The embodiment of the present application provides a risk assessment method, which constructs an enterprise default risk knowledge graph based on the default enterprise entity nodes that generate enterprise default data and the enterprise entity nodes associated with the default enterprise entity nodes. Combining the default enterprise entity nodes at the micro level and the enterprise entity nodes associated with the default enterprise entity nodes at the macro level, the risks that the enterprise may face can be more comprehensively assessed, thereby improving the accuracy and reliability of the enterprise default risk assessment results.

[0054] The specific implementation of the embodiment of the present application is described below in conjunction with the accompanying drawings of the embodiment of the present application.

[0055] See also Figure 1 , Figure 1 The risk assessment method of the embodiment of the present application is a schematic diagram of the implementation process of the risk assessment method of the embodiment of the present application. The risk assessment method of the embodiment of the present application includes the following steps:

[0056] Step S101: Obtain the business data of the enterprise and the business operation data of the enterprise in the historical time period.

[0057] Specifically, enterprise business data includes enterprise name, unified social credit code, registered address, legal representative, shareholder information, registered capital, business scope, legal risk, etc. Enterprise business data includes sales data, financial data, customer data, etc. determined based on the enterprise's orders, contracts, invoices, etc.

[0058] Exemplarily, the business data of the enterprise and the business data of the enterprise in the historical time period can be obtained. In some embodiments, indexes can be established in the database based on the business data of the enterprise (such as the unified social credit code of the enterprise, the name of the enterprise, etc.), and the business data of each enterprise can be stored in the index corresponding to each business data of the enterprise in a time series according to the time when the business data of the enterprise is obtained, so as to obtain an enterprise data table with the business data of the enterprise as the index.

[0059] In some embodiments, before establishing the enterprise data table, the acquired enterprise business data and enterprise operating data may be cleansed (for example, deleting enterprise operating data with a high probability of default, etc.) and the data format may be unified.

[0060] Step S102: Filter enterprise default data from enterprise operation data, determine risk enterprise entity nodes related to the enterprise default data based on enterprise industrial and commercial data and enterprise default data, and construct an enterprise default risk knowledge graph based on the risk enterprise entity nodes.

[0061] Among them, the risky enterprise entity nodes include the default enterprise entity nodes that generate enterprise default data and the enterprise entity nodes that are associated with the default enterprise entity nodes.

[0062] Specifically, the enterprise entity node associated with the defaulting enterprise entity node may be an enterprise entity node that has an investment relationship, a guarantee relationship, an affiliation relationship, a transaction relationship, etc. with the defaulting enterprise entity node.

[0063] For example, enterprise default data can be extracted from the enterprise data table, and enterprises related to the enterprise default data can be determined, so that the enterprises related to the enterprise default data are used as risk enterprise entity nodes. After obtaining each risk enterprise entity node, an enterprise default risk knowledge graph is constructed based on each risk enterprise entity node.

[0064] Optionally, in some embodiments, each risk enterprise entity node can be divided into different enterprise data tables according to industry type and operation scale, and each risk enterprise entity node can also be divided into different enterprise data tables according to the time resolution of enterprise operation data. When extracting enterprise default data from each enterprise data table and determining the risk enterprise entity node, the industry type, operation scale and time resolution can be included in the variables of the risk enterprise entity node to more accurately assess the enterprise's operational risk based on the industry type, operation scale and time resolution. Among them, the operation scale can be divided into four scale levels: large, medium, small and micro, and other division strategies can also be determined according to actual needs to divide the operation scale.

[0065] Optionally, in some of the embodiments, constructing an enterprise default risk knowledge graph based on risk enterprise entity nodes includes: establishing edge relationships between risk enterprise entity nodes, and constructing an enterprise default risk knowledge graph.

[0066] Exemplarily, edge relationships between the risk enterprise entity nodes can be established respectively according to the association relationships between the risk enterprise entity nodes to construct an enterprise default risk knowledge graph.

[0067] Optionally, in some of the embodiments, establishing edge relationships between risk enterprise entity nodes includes: connecting risk enterprise entity nodes that are associated or represent the same risk type.

[0068] Exemplarily, the venture enterprise entity nodes that have association relationships and represent the same risk type may be connected respectively to establish edge relationships between the venture enterprise entity nodes.

[0069] Step S103: construct enterprise default dynamic attribute graphs at multiple times based on enterprise operating data and enterprise default risk knowledge graphs; determine the risk prediction value of the target default feature based on the dynamic attribute graphs of each enterprise default according to the dynamic heterogeneous graph model; and evaluate the enterprise default risk based on the risk prediction value of the target default feature.

[0070] Among them, the enterprise default dynamic attribute diagram represents the dynamic changes of enterprise default data; the target default feature is the default feature whose default impact degree is greater than the first preset threshold.

[0071] Specifically, the dynamic heterogeneous graph model is trained based on the business data of enterprises and the business data of enterprises in historical time periods. The impact degree of default and the first preset threshold can be represented by specific numerical values. The values ​​of the attributes in the dynamic attribute graph of enterprise default can include specific values ​​or severity descriptions of the corresponding default characteristics.

[0072] Optionally, in some of the embodiments, a dynamic attribute graph of enterprise default at the current moment can be constructed based on the enterprise default risk knowledge graph; a dynamic attribute graph of enterprise default at historical moments can be constructed based on enterprise operating data of historical time periods; and the dynamic attribute graph of enterprise default at the current moment and the dynamic attribute graph of enterprise default at historical moments can be combined to obtain dynamic attribute graphs of enterprise default at multiple moments.

[0073] In the embodiment of the present application, the enterprise default risk knowledge graph is constructed based on the default enterprise entity nodes that generate enterprise default data and the enterprise entity nodes associated with the default enterprise entity nodes. Combining the default enterprise entity nodes at the micro level and the enterprise entity nodes associated with the default enterprise entity nodes at the macro level, the risks that the enterprise may face can be more comprehensively assessed, thereby improving the accuracy and reliability of the enterprise default risk assessment results.

[0074] Optionally, in some of the embodiments, the number of inspections and the number of defaults of each risky enterprise entity node can be determined based on the enterprise industrial and commercial data, and the enterprise default data determined based on the enterprise operating data, and the default rate can be determined based on the number of inspections and the number of defaults; the enterprise industrial and commercial data and the enterprise operating data corresponding to the high-risk enterprise entity nodes whose default rate is higher than the second preset threshold are deleted, as well as the enterprise operating data of each risky enterprise entity node within a preset time period corresponding to the default rate of the high-risk enterprise entity node being higher than the second preset threshold.

[0075] Specifically, the second preset threshold may be a preset specific value, such as 1% or other values. The preset time period may be a time period when the default rate of the high-risk enterprise entity node is higher than the year corresponding to the second preset threshold.

[0076] For example, taking the second preset threshold being 1% and the preset time period being a year in which the default rate of the high-risk enterprise entity nodes is higher than the second preset threshold, the business data and business operation data corresponding to the high-risk enterprise entity nodes with a default rate higher than 1% can be deleted, as well as the business operation data of each risk enterprise entity node in the year corresponding to the default rate of the high-risk enterprise entity nodes being higher than 1%.

[0077] Optionally, business operating data that lacks integrity (eg, business operating data that has a contract but lacks payment amount, payment account number, or invoice information) may also be deleted.

[0078] Optionally, the correlation between the entity nodes of each risk enterprise can be determined through an association analysis algorithm, and the edges with low correlation in the enterprise default risk knowledge graph can be deleted.

[0079] In the embodiment of the present application, the data corresponding to the high-risk enterprise entity nodes with higher default rates and the enterprise operation data with insufficient integrity are deleted to improve the generalization ability and accuracy of the enterprise default risk knowledge graph determined based on the enterprise industrial and commercial data and the enterprise operation data, thereby improving the accuracy of assessing the enterprise default risk.

[0080] Optionally, in some of the embodiments, anomaly detection features can also be determined based on the enterprise industrial and commercial data and the enterprise default data; the anomaly detection features can be standardized to obtain a standardized data set, and an anomaly detection framework can be constructed based on the standardized data set; abnormal data can be determined from the enterprise industrial and commercial data and the enterprise default data through the anomaly detection framework; and the abnormal data in the enterprise industrial and commercial data and the enterprise default data can be deleted.

[0081] Specifically, the anomaly detection feature is a feature of the abnormal data determined based on the abnormal data in the enterprise business data and the enterprise default data. The standardization operation may be a standard deviation standardization operation or other types of standardization operations.

[0082] Exemplarily, anomaly detection features can be determined based on abnormal data in corporate business data and corporate default data; the anomaly detection features are normalized by standard deviation to obtain a standardized data set, and an anomaly detection framework is constructed based on the standardized data set.

[0083] In some embodiments, after determining the abnormal data, the abnormal data can be reduced in dimension (for example, the abnormal data can be viewed only from the time dimension, industry type dimension, region dimension or other dimensions), and the reduced abnormal data can be visualized to obtain a partial image of the abnormal data, so as to adjust the algorithm parameters in the abnormal monitoring framework according to the partial image of the abnormal data.

[0084] In the embodiment of the present application, abnormal data in the enterprise industrial and commercial data and the enterprise default data are deleted, so as to improve the accuracy of the subsequent enterprise default dynamic attribute graph, thereby improving the accuracy of assessing the enterprise default risk.

[0085] Optionally, in some of the embodiments, business strategy recommendations may be made to risky enterprise entity nodes associated with enterprise default data based on target default characteristics and risk prediction values ​​of the target default characteristics.

[0086] Specifically, the risk enterprise entity nodes related to the enterprise default data include the default enterprise entity nodes that generate the enterprise default data and the enterprise entity nodes that are associated with the default enterprise entity nodes. The enterprise entity nodes that are associated with the default enterprise entity nodes may be enterprise entity nodes that have an investment relationship, guarantee relationship, affiliation relationship, transaction relationship, etc. with the default enterprise entity nodes.

[0087] For example, based on the risk prediction values ​​of the default characteristics and the target default characteristics, business strategy recommendations can be made for the defaulting enterprise entity nodes that generate the enterprise default data and the enterprise entity nodes that are associated with the defaulting enterprise entity nodes. For example, risk warnings and business strategy recommendations can be provided for industry types, counterparties, etc.

[0088] In an embodiment of the present application, business strategy recommendations are made to risky enterprise entity nodes related to enterprise default data so that the risky enterprise entity nodes can adjust their business strategies in a timely manner according to the business strategy recommendations, thereby avoiding business risks to a certain extent and improving business stability.

[0089] See also Figure 2 , Figure 2 201 is a schematic diagram of the structure of a risk assessment device applicable to an embodiment of the present application. The risk assessment device of the embodiment of the present application includes a data acquisition module 201, a graph construction module 202 and a risk assessment module 203. Among them:

[0090] Data acquisition module 201, used to acquire business data of enterprises and business operation data of enterprises in historical time periods;

[0091] A graph construction module 202 is used to filter enterprise default data from enterprise operation data, determine risk enterprise entity nodes related to enterprise default data based on enterprise business data and enterprise default data, and construct an enterprise default risk knowledge graph based on risk enterprise entity nodes;

[0092] The risk assessment module 203 is used to construct a dynamic attribute graph of enterprise default at multiple moments based on the enterprise industrial and commercial data, enterprise operation data and enterprise default risk knowledge graph, determine the risk prediction value of the target default feature based on the dynamic attribute graph of each enterprise default according to the dynamic heterogeneous graph model, and assess the enterprise default risk based on the risk prediction value of the target default feature;

[0093] Among them, the risk enterprise entity nodes include the default enterprise entity nodes that generate enterprise default data and the enterprise entity nodes that are associated with the default enterprise entity nodes; the enterprise default dynamic attribute graph represents the dynamic changes of enterprise default data; the target default feature is the default feature whose default impact degree is greater than the first preset threshold.

[0094] Optionally, in some of the embodiments, the data acquisition module 201 is specifically used to: determine the number of inspections and the number of defaults of each risky enterprise entity node based on the enterprise industrial and commercial data and the enterprise default data, and determine the default rate based on the number of inspections and the number of defaults; delete the enterprise industrial and commercial data and enterprise operating data corresponding to the high-risk enterprise entity nodes whose default rate is higher than a second preset threshold, and the enterprise operating data of each risky enterprise entity node within a preset time period corresponding to the default rate of the high-risk enterprise entity node being higher than the second preset threshold.

[0095] Optionally, in some of the embodiments, the risk assessment module 203 is specifically used to: construct a dynamic attribute graph of enterprise default at the current moment based on the enterprise default risk knowledge graph; construct a dynamic attribute graph of enterprise default at historical moments based on enterprise operating data of historical time periods; combine the dynamic attribute graph of enterprise default at the current moment and the dynamic attribute graph of enterprise default at historical moments to obtain dynamic attribute graphs of enterprise default at multiple moments.

[0096] Optionally, in some of the embodiments, the graph construction module 202 is specifically used to: determine anomaly detection features based on enterprise industrial and commercial data and enterprise default data; perform standardization operations on the anomaly detection features to obtain a standardized data set, and construct an anomaly detection framework based on the standardized data set; determine abnormal data from the enterprise industrial and commercial data and enterprise default data through the anomaly detection framework; and delete abnormal data from the enterprise industrial and commercial data and enterprise default data.

[0097] Optionally, in some of the embodiments, the graph construction module 202 is specifically used to: establish edge relationships between risk enterprise entity nodes and construct an enterprise default risk knowledge graph.

[0098] Optionally, in some of the embodiments, the graph construction module 202 is specifically used to connect risk enterprise entity nodes that are associated or represent the same risk type.

[0099] Optionally, in some of the embodiments, the risk assessment module 203 is specifically used to make business strategy recommendations for risky enterprise entity nodes related to enterprise default data based on target default characteristics and risk prediction values ​​of the target default characteristics.

[0100] The risk assessment device of this embodiment is used to implement the corresponding risk assessment method in the aforementioned embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here. In addition, the functional implementation of each module in the risk assessment device of the embodiment of the present application can refer to the description of the corresponding part in the aforementioned method embodiment, which will not be repeated here.

[0101] See also Figure 3 , Figure 3Schematic diagram of the structure of the risk assessment system applicable to the embodiment of the present application. The risk assessment system of the embodiment of the present application includes a data collection module 301, a default feature analysis module 302 and a default risk assessment module 303. Among them:

[0102] The data acquisition module 301 includes a data acquisition unit 3011 and a data preprocessing unit 3012 .

[0103] The data collection unit 3011 is used to collect corporate business data (company name, unified social credit code, registered address, legal representative, shareholder information, registered capital, business scope, legal risk, etc.) and corporate operating data (sales data, financial data, customer data, etc. determined based on the company's orders, contracts, invoices, etc.).

[0104] The data preprocessing unit 3012 is used to clean the business data and business operation data collected by the data collection unit 3011 (for example, deleting business operation data with a high probability of default and business data and business operation data with insufficient integrity, etc.) and unify the data format.

[0105] The default feature analysis module 302 includes a knowledge graph construction unit 3021 and a knowledge graph update unit 3022 .

[0106] The knowledge graph construction unit 3021 is used to filter enterprise default data from enterprise business data, determine risk enterprise entity nodes related to the enterprise default data based on enterprise industrial and commercial data and enterprise default data, and construct an enterprise default risk knowledge graph based on the risk enterprise entity nodes.

[0107] The knowledge graph updating unit 3022 is used to determine the correlation between the entity nodes of each risk enterprise through an association analysis algorithm, delete the edges with low correlation in the enterprise default risk knowledge graph, and obtain an updated enterprise default risk knowledge graph.

[0108] The default risk assessment module 303 includes a dynamic attribute graph construction unit 3031 and a default risk assessment unit 3032 .

[0109] The dynamic attribute graph construction unit 3031 is used to construct a dynamic attribute graph of enterprise default at multiple moments based on the enterprise operating data and the enterprise default risk knowledge graph.

[0110] The default risk assessment unit 3032 is used to determine the risk prediction value of the target default feature based on the dynamic attribute graph of each enterprise default according to the dynamic heterogeneous graph model, and assess the enterprise default risk based on the risk prediction value of the target default feature.

[0111] The risk assessment system of this embodiment is used to implement the corresponding risk assessment method in the aforementioned embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here. In addition, the functional implementation of each module in the risk assessment system of the embodiment of the present application can refer to the description of the corresponding part in the aforementioned method embodiment, which will not be repeated here.

[0112] An embodiment of the present application provides a computer program, including a computer-readable code. When the computer-readable code is run in a computer device, a processor in the computer device executes some or all of the steps for implementing the above method.

[0113] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium, and in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK) and the like.

[0114] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above computer program and computer program product embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the computer program and computer program product embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0115] Figure 4 A schematic diagram of a hardware entity of an electronic device applicable to an embodiment of the present application is shown in FIG. Figure 4 As shown, the hardware entity of the electronic device 400 includes: a processor 401 and a memory 402, wherein the memory 402 stores a computer program that can be run on the processor 401, and the processor 401 implements the steps in the method of any of the above embodiments when executing the program.

[0116] The memory 402 stores computer programs that can be run on the processor. The memory 402 is configured to store instructions and applications executable by the processor 401. It can also cache data to be processed or processed by the processor 401 and various modules in the electronic device 400 (for example, image data, audio data, voice communication data, and video communication data). This can be achieved through flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0117] When the processor 401 executes the program, the steps of any of the above risk assessment methods are implemented. The processor 401 generally controls the overall operation of the electronic device 400.

[0118] An embodiment of the present application provides a computer storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the steps of the risk assessment method of any of the above embodiments.

[0119] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0120] The processor may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understandable that the electronic device that implements the functions of the processor may also be other, and the embodiments of the present application are not specifically limited.

[0121] The above-mentioned computer storage medium / memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM) and the like; it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0122] It should be understood that "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments. The above description of each embodiment tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. For the sake of brevity, this article will not repeat them.

[0123] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical or other forms.

[0125] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed on multiple network units; some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0126] In addition, all functional modules in the embodiments of the present application may be integrated into one processing unit, or each module may be a separate unit, or two or more modules may be integrated into one unit; the above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0127] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0128] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0129] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0130] The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0131] The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0132] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A risk assessment method, characterized in that: include: Obtain business data of enterprises and business operation data of historical periods; Filtering enterprise default data from the enterprise operation data, determining risk enterprise entity nodes related to the enterprise default data according to the enterprise business data and the enterprise default data, and constructing an enterprise default risk knowledge graph based on the risk enterprise entity nodes; Based on the enterprise operation data and the enterprise default risk knowledge graph, dynamic attribute graphs of enterprise default at multiple moments are constructed; based on each of the dynamic attribute graphs of enterprise default, a risk prediction value of a target default feature is determined according to a dynamic heterogeneous graph model; and based on the risk prediction value of the target default feature, the enterprise default risk is evaluated; Among them, the risk enterprise entity node includes the default enterprise entity node that generates the enterprise default data and the enterprise entity node that is associated with the default enterprise entity node; the enterprise default dynamic attribute graph represents the dynamic changes of the enterprise default data; the target default feature is a default feature whose default impact degree is greater than a first preset threshold.

2. The method according to claim 1, characterized in that The method further comprises: Determine the number of inspections and the number of defaults of each of the risk enterprise entity nodes according to the enterprise business data and the enterprise default data, and determine the default rate according to the number of inspections and the number of defaults; Delete the business data and business operation data corresponding to the high-risk enterprise entity node whose default rate is higher than the second preset threshold, as well as the business operation data of each risk enterprise entity node within the preset time period corresponding to the default rate of the high-risk enterprise entity node higher than the second preset threshold.

3. The method according to claim 1, characterized in that The step of constructing a dynamic attribute graph of enterprise default at multiple moments based on the enterprise operation data and the enterprise default risk knowledge graph includes: Constructing a dynamic attribute graph of enterprise default at the current moment based on the enterprise default risk knowledge graph; Constructing a dynamic attribute graph of corporate defaults at historical moments based on the business data of the corporate during historical time periods; The enterprise default dynamic attribute graph at the current moment and the enterprise default dynamic attribute graph at the historical moments are combined to obtain the enterprise default dynamic attribute graphs at multiple moments.

4. The method according to claim 1, characterized in that: The method further comprises: Determine anomaly detection features based on the business data of the enterprise and the enterprise default data; Performing a standardization operation on the anomaly detection features to obtain a standardized data set, and constructing an anomaly detection framework based on the standardized data set; Determining abnormal data from the enterprise business data and the enterprise default data through the anomaly detection framework; Delete the abnormal data in the enterprise industrial and commercial data and the enterprise default data.

5. The method according to claim 1, characterized in that The step of constructing an enterprise default risk knowledge graph based on the risk enterprise entity nodes includes: Establish edge relationships between the risk enterprise entity nodes and construct the enterprise default risk knowledge graph.

6. The method according to claim 5, characterized in that The step of establishing the edge relationship between the venture enterprise entity nodes includes: Connect the risk enterprise entity nodes that are related or represent the same risk type.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: According to the target default characteristics and the risk prediction value of the target default characteristics, business strategy recommendations are made to the risk enterprise entity nodes related to the enterprise default data.

8. A risk assessment device, characterized in that: include: Data acquisition module, used to obtain business data of enterprises and business operation data of historical time periods; A graph construction module, used to screen enterprise default data from the enterprise operation data, determine risk enterprise entity nodes related to the enterprise default data according to the enterprise business data and the enterprise default data, and construct an enterprise default risk knowledge graph based on the risk enterprise entity nodes; A risk assessment module, configured to construct enterprise default dynamic attribute graphs at multiple moments based on the enterprise industrial and commercial data, the enterprise operating data and the enterprise default risk knowledge graph, determine the risk prediction value of the target default feature according to the dynamic heterogeneous graph model based on each of the enterprise default dynamic attribute graphs, and assess the enterprise default risk based on the risk prediction value of the target default feature; Among them, the risk enterprise entity node includes the default enterprise entity node that generates the enterprise default data and the enterprise entity node that is associated with the default enterprise entity node; the enterprise default dynamic attribute graph represents the dynamic changes of the enterprise default data; the target default feature is a default feature whose default impact degree is greater than a first preset threshold.

9. An electronic device, characterized in that: include: A memory for storing executable instructions; A processor, configured to implement the risk assessment method according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to implement the risk assessment method described in any one of claims 1 to 7 when executed by a processor.

Images