Business risk assessment method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the field of data processing, and relates to a business risk assessment method and device, computer equipment and a storage medium, and the method comprises the following steps: constructing a risk knowledge graph according to business data; acquiring a risk conduction path in the risk knowledge graph based on a graph search algorithm; acquiring associated risk event information in a database according to the risk conduction path, and analyzing the associated risk event information according to a data mining algorithm to obtain risk event influence information; quantifying the risk event influence information, and training a risk event influence evaluation model according to quantified risk event influence index data; performing risk simulation evolution according to the risk conduction path and the risk event influence evaluation model to obtain a risk event influence result; and performing risk analysis according to the risk event influence result to obtain a comprehensive risk value. According to the invention, accurate risk assessment can be carried out on business of an enterprise.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, specifically to the field of financial technology, and in particular to a business risk assessment method, device, computer equipment and storage medium. Background Art

[0002] In the field of financial technology, enterprise risk identification is a key link to ensure the steady development of business. With the rapid development of technologies such as big data and artificial intelligence, knowledge graphs, as a powerful tool, are widely used in enterprise risk management, especially in the identification of risk transmission paths. However, most traditional risk transmission path identification methods only focus on the existence of the path, ignoring the important characteristic that risks will gradually decay during the transmission process.

[0003] In actual business scenarios, risks often do not exist in isolation, but are transmitted through various complex entity relationships. These relationships may involve different departments and business processes within the enterprise, or may span to external market environments, partners, etc.

[0004] However, when dealing with complex relationships between multi-level entities, how to effectively quantify the risk attenuation effect on the path has become a key technical challenge. During the transmission process, the intensity and scope of risk will gradually weaken due to the influence of various factors, such as time, distance, and the effectiveness of control measures. If this attenuation effect cannot be accurately quantified, the identification results of the risk transmission path will be difficult to accurately reflect the actual risk situation, which will have a great impact on the qualitative characterization of the company's business risks and is not conducive to the healthy development of the company. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a business risk assessment method, apparatus, computer equipment and storage medium to solve the problem of being unable to effectively and accurately assess the risk of an enterprise's business.

[0006] In order to solve the above technical problems, the present application provides a business risk assessment method, which adopts the following technical solutions:

[0007] Acquire business data, and construct a risk knowledge graph based on the business data;

[0008] Obtaining risk transmission paths in the risk knowledge graph based on a graph search algorithm;

[0009] Acquire associated risk event information in a database according to the risk transmission path, and analyze the associated risk event information according to a data mining algorithm to obtain risk event impact information;

[0010] Quantifying the risk event impact information, and training a risk event impact assessment model based on the quantified risk event impact indicator data;

[0011] Perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result;

[0012] Conduct risk analysis based on the impact of the risk event to obtain a comprehensive risk value.

[0013] Furthermore, the step of obtaining business data and constructing a risk knowledge graph based on the business data specifically includes:

[0014] Preprocessing the business data to obtain standard business data, and extracting risk event entities and risk event attribute information from the standard business data;

[0015] Performing causal relationship analysis on the risk event entity and the risk event attribute information to obtain a causal relationship result;

[0016] Determine whether the causal relationship result is a causal relationship;

[0017] If the causal relationship result is that the causal relationship exists, converting the risk event entity and the risk event attribute information into a knowledge graph node and a knowledge graph edge based on a knowledge representation method;

[0018] The risk knowledge graph is constructed according to the knowledge graph nodes and the knowledge graph edges.

[0019] Furthermore, the step of obtaining the risk transmission path in the risk knowledge graph based on the graph search algorithm specifically includes:

[0020] Acquire risk entities and risk entity relationships from the risk knowledge graph;

[0021] Constructing a risk transmission model according to the risk entities and the risk entity relationships;

[0022] Based on the graph search algorithm, a transmission path search is performed in the risk knowledge graph to obtain an initial risk transmission path;

[0023] Calculate the risk value of the initial risk transmission path according to the transmission rules and weights defined by the risk transmission model;

[0024] Determine whether the risk value is greater than or equal to a preset risk threshold;

[0025] If the risk value is greater than or equal to the preset risk threshold, the initial risk transmission path is marked as the risk transmission path.

[0026] Furthermore, the step of acquiring the associated risk event information in the database according to the risk transmission path, and analyzing the associated risk event information according to the data mining algorithm to obtain the risk event impact information specifically includes:

[0027] Performing a matching query in the database according to the risk transmission path to obtain associated risk event information related to the target risk event;

[0028] Performing association rule mining on the associated risk event information according to an association rule mining algorithm to obtain risk event association rules and risk event association strength;

[0029] Constructing a risk event association network according to the risk event association rules and risk event association strengths;

[0030] Performing low-dimensional vector representation learning on the risk event association network to obtain a risk event embedding vector;

[0031] Clustering the risk event embedding vectors according to a preset clustering algorithm to obtain risk event clusters;

[0032] The impact degree of the risk event and the loss scale of the risk event are calculated according to the risk event clusters, and the impact degree of the risk event and the loss scale of the risk event are used as the risk event impact information.

[0033] Furthermore, the step of quantifying the risk event impact information and training the risk event impact assessment model based on the quantified risk event impact indicator data specifically includes:

[0034] Quantifying the risk event impact information according to preset quantitative indicator rules to obtain the risk event impact indicator data;

[0035] The pre-constructed initial impact assessment model is trained according to the risk event impact indicator data to obtain the risk event impact assessment model.

[0036] Furthermore, the step of performing risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result specifically includes:

[0037] Constructing a risk transmission network topology structure according to the risk transmission path;

[0038] Setting the probability distribution of risk events according to the risk event impact assessment model;

[0039] Based on the Monte Carlo simulation method and the probability distribution of the risk events, the risk conduction network topology structure is subjected to risk simulation evolution to obtain the risk status of the network nodes;

[0040] Calculate the cumulative impact of risk according to the risk status of the network node to obtain a first impact assessment result;

[0041] Calculate the indirect impact of risk based on the cascade time effect analysis method and the first impact assessment result to obtain a second impact assessment result;

[0042] The first impact assessment result and the second impact assessment result are integrated to obtain the risk event impact result.

[0043] Furthermore, the step of performing risk analysis according to the impact result of the risk event to obtain a comprehensive risk value specifically includes:

[0044] Constructing a risk event judgment matrix based on the analytic hierarchy process, and calculating risk event weight coefficients based on the risk event judgment matrix;

[0045] Acquire a risk path event set according to the risk transmission path;

[0046] The risk path event set is weighted and summed according to the risk event weight coefficient and the risk event impact result to obtain the comprehensive risk value.

[0047] In order to solve the above technical problems, the embodiment of the present application also provides a business risk assessment device, which adopts the following technical solution:

[0048] A graph construction module, used to obtain business data and construct a risk knowledge graph based on the business data;

[0049] A path acquisition module, used for acquiring risk transmission paths in the risk knowledge graph based on a graph search algorithm;

[0050] An impact analysis module is used to obtain related risk event information in a database according to the risk transmission path, and analyze the related risk event information according to a data mining algorithm to obtain risk event impact information;

[0051] A model training module is used to quantify the risk event impact information and train a risk event impact assessment model based on the quantified risk event impact indicator data;

[0052] A risk evolution module, used to perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result;

[0053] The risk analysis module is used to perform risk analysis based on the impact results of the risk event to obtain a comprehensive risk value.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0055] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of any of the above business risk assessment methods when executing the computer-readable instructions.

[0056] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0057] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of any of the above business risk assessment methods.

[0058] Compared with the prior art, the embodiment of the present application has the following beneficial effects: the embodiment acquires business data and constructs a risk knowledge graph according to the business data; acquires the risk transmission path in the risk knowledge graph based on the graph search algorithm; acquires the associated risk event information in the database according to the risk transmission path, and analyzes the associated risk event information according to the data mining algorithm to obtain the risk event impact information; quantifies the risk event impact information, and trains the risk event impact assessment model according to the quantified risk event impact indicator data; performs risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result; performs risk analysis according to the risk event impact result to obtain the comprehensive risk value. Thus, the business of the enterprise can be effectively and accurately assessed, so as to facilitate the risk qualitative assessment of the enterprise according to the assessment situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0061] Figure 2 A flowchart according to an embodiment of a business risk assessment method of the present application;

[0062] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S10;

[0063] Figure 4 yes Figure 2 A flowchart of a specific implementation of step S20;

[0064] Figure 5 yes Figure 2 A flowchart of a specific implementation of step S30;

[0065] Figure 6 yes Figure 2 A flowchart of a specific implementation of step S40;

[0066] Figure 7 yes Figure 2 A flowchart of a specific implementation of step S50;

[0067] Figure 8 yes Figure 2 A flowchart of a specific implementation of step S60;

[0068] Fig. 9 is a structural schematic diagram of an embodiment of a business risk assessment device according to the present application;

[0069] Fig.10 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0071] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor does it refer to non-related or alternative embodiments that are mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0072] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0073] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0074] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0075] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0076] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0077] It should be noted that the business risk assessment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the business risk assessment device is generally set in the server / terminal device.

[0078] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0079] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for business risk assessment according to the present application. The business risk assessment method comprises the following steps:

[0080] Step S10, acquiring business data, and constructing a risk knowledge graph based on the business data;

[0081] In this embodiment, business data refers to data related to the business of an enterprise, including business entities, business association information, business process information, etc., where business entities refer to various objects directly related to the business of an enterprise, such as customers, products, orders, advertisements, employees, etc. Each business entity has its own unique attributes and characteristics; business association information is used to describe the relationship between business entities, such as the relationship between customers and orders, the association between products, the affiliation between employees and departments, etc.; business process information records various processes and steps in the operation process of an enterprise, such as sales process, procurement process, production process, etc. The risk knowledge graph is a knowledge graph data constructed based on the risk event entities and risk event attribute information extracted from the business data. By constructing the risk knowledge graph, it is convenient to obtain the risk transmission path in the future.

[0082] Step S20, obtaining a risk transmission path in the risk knowledge graph based on a graph search algorithm;

[0083] In this embodiment, the graph search algorithm is a type of algorithm used to find specific nodes or paths in graph structure data, where the graph structure data is a set of nodes (or vertices) and edges connecting these nodes. The graph search algorithm can use the A* algorithm, which is a heuristic search algorithm that selects the next node to be visited by using the evaluation function f(n)=g(n)+h(n) to achieve path search, where g(n) is the actual cost from the source node to the current node, and h(n) is the estimated cost from the current node to the target node. The risk transmission path is a specific path for the risk to spread or affect different risk entities. When the risk occurs on a certain entity, it will spread to other entities along these associations or relationships to form a risk transmission path. These paths not only reveal the way and direction of risk transmission, but also reflect the mutual influence and degree of association between risks in different entities.

[0084] Step S30, acquiring associated risk event information in a database according to the risk transmission path, and analyzing the associated risk event information according to a data mining algorithm to obtain risk event impact information;

[0085] In this embodiment, the associated risk event information is historical risk event data related to the target risk event of the risk transmission path, and the associated risk event information is obtained by matching and querying the risk transmission path in a database, which can be a pre-established risk transmission path knowledge graph or knowledge database. The data mining algorithm adopts an association rule mining algorithm, which analyzes the transaction records (or event records) in the associated risk event information to find out the frequently occurring item sets (or event combinations) and the association relationship between them, thereby realizing association analysis and effectively obtaining risk event impact information.

[0086] Step S40, quantifying the risk event impact information, and training a risk event impact assessment model based on the quantified risk event impact indicator data;

[0087] In this embodiment, the risk event impact information includes the risk event impact degree and the risk event loss scale, wherein the risk event impact degree refers to the depth and breadth of the direct or indirect impact on the business entity after the risk event occurs, and the risk event loss scale refers to the actual economic, financial or material losses suffered by the business entity after the risk event occurs. The risk event impact degree and the risk event loss scale are quantified by the preset quantitative indicator rules to obtain the risk event impact indicator data, and then the risk event impact assessment model that can calculate the impact score of each risk event is trained based on the risk impact indicator data.

[0088] Step S50, performing risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result;

[0089] In this embodiment, risk simulation evolution is performed based on the Monte Carlo simulation method. The Monte Carlo simulation method, also known as the random simulation method or the statistical simulation method, is based on the statistical sampling theory and uses random numbers to perform sampling experiments or random simulations on the statistics of existing data of random variables to obtain a certain digital feature of the statistic and use it as the numerical solution to the problem to be solved. According to the risk transmission path and the risk event impact assessment model, risk simulation evolution is performed based on the Monte Carlo simulation method to obtain the risk status of the network node, and then the first impact assessment result of the cumulative risk impact and the second impact assessment result of the indirect risk impact are calculated based on the risk status of the network node. The first impact assessment result and the second impact assessment result are merged to obtain the final risk event impact result.

[0090] Step S60: Perform risk analysis based on the impact results of the risk event to obtain a comprehensive risk value.

[0091] In this embodiment, the risk event impact result is the impact result of the risk event on the risk transmission path. The risk analysis of the risk event impact result includes the calculation of the risk event weight coefficient and the acquisition of the risk path event set, wherein the risk event weight coefficient is calculated based on the risk event judgment matrix, and the risk event judgment matrix refers to the risk event pairwise judgment matrix, which is also called the pairwise comparison matrix or judgment matrix. The risk event pairwise judgment matrix is ​​a matrix tool used in the analytic hierarchy process (AHP) to compare the relative importance of different risk events at the same level. By comparing the relative importance of different risk events at the same level, weights are assigned to these risk events, and then weighted sum calculation is performed with the assigned weights to obtain the comprehensive risk value of the risk event.

[0092] This embodiment acquires business data, builds a risk knowledge graph based on the business data; acquires the risk transmission path in the risk knowledge graph based on the graph search algorithm; acquires the associated risk event information in the database based on the risk transmission path, and analyzes the associated risk event information based on the data mining algorithm to obtain the risk event impact information; quantifies the risk event impact information, and trains the risk event impact assessment model based on the quantified risk event impact indicator data; performs risk simulation evolution based on the risk transmission path and the risk event impact assessment model to obtain the risk event impact result; performs risk analysis based on the risk event impact result to obtain the comprehensive risk value. This effectively conducts accurate risk assessment on the business of the enterprise, so as to facilitate the qualitative risk assessment of the enterprise according to the assessment situation.

[0093] refer to Figure 3 In some optional implementations of this embodiment, step S10 includes the following steps:

[0094] Step S101, preprocessing the business data to obtain standard business data, and extracting risk event entities and risk event attribute information from the standard business data;

[0095] In this embodiment, the preprocessing of business data includes data cleaning (removing duplicate data, processing missing values, correcting erroneous data, etc.) and data conversion (converting business data into a standard format). Through natural language processing (NLP) technology or rule matching methods, risk event entities (such as transaction anomalies, customer defaults, etc.) and related risk event attribute information (such as event time, location, amount involved, etc.) are extracted from standard business data.

[0096] Step S102, performing causal relationship analysis on the risk event entity and the risk event attribute information to obtain a causal relationship result;

[0097] In this embodiment, the causal relationship between risk event entities is analyzed based on natural language processing technology, where the causal relationship refers to the existence of a causal relationship between two events or states, that is, one event (cause) leads to the occurrence of another event (result). Pre-written rules or patterns can be used to identify trigger words and iconic expressions in causal relationships, and the rules can be based on language dependency features such as word meaning, grammar, and syntactic structure. By identifying causal conjunctions (such as "because", "so", "due to", etc.), causal analysis can also be performed on risk event entities and risk event attribute information based on causal analysis algorithms such as Bayesian networks, thereby effectively obtaining causal relationship results.

[0098] Step S103, determining whether the causal relationship result is a causal relationship;

[0099] In this embodiment, the causal relationship result includes the existence of a causal relationship and the non-existence of a causal relationship. The causal relationship result is analyzed to effectively identify whether the causal relationship result indicates the existence of a causal relationship.

[0100] Step S104: if the causal relationship result is that the causal relationship exists, converting the risk event entity and the risk event attribute information into a knowledge graph node and a knowledge graph edge based on a knowledge representation method;

[0101] In this embodiment, based on a preset knowledge representation method (such as RDF (Resource Description Framework)), risk event entities and attribute information are converted into knowledge graph nodes and edges, where nodes represent risk event entities or attributes, and edges represent causal relationships or other associations between them.

[0102] Step S105: if the causal relationship result is that the causal relationship does not exist, the risk event entity and the risk event attribute information are marked as having no causal relationship;

[0103] In this embodiment, corresponding non-causal relationship marks can be added to risk event entities and risk event attribute information that do not have a causal relationship, so as to effectively distinguish risk event entities and risk event attribute information that do not have a causal relationship.

[0104] Step S106, constructing the risk knowledge graph according to the knowledge graph nodes and the knowledge graph edges.

[0105] In this embodiment, the transformed nodes and edges are integrated into a complete risk knowledge graph through a knowledge graph construction tool. The steps for constructing a risk knowledge graph include: creating a new graph database in the knowledge graph construction tool, configuring the connection parameters of the database, such as host name, port number, user name and password, etc.; defining the node type according to the type and attribute of the risk event entity, and defining the edge type and the type and value range of the relationship attribute according to the relationship between the entities; using the import function or API provided by the tool to import the transformed node and edge data into the graph database, and check whether the graph database contains all the expected nodes and edges, and verify whether the attributes of the nodes and edges are correct. After the verification is passed, the construction of the risk knowledge graph is completed.

[0106] This embodiment obtains standard business data by preprocessing the business data, and extracts risk event entities and risk event attribute information from the standard business data; performs causal relationship analysis on the risk event entities and the risk event attribute information to obtain causal relationship results; determines whether the causal relationship results show that a causal relationship exists; if the causal relationship results show that a causal relationship exists, the risk event entities and the risk event attribute information are converted into knowledge graph nodes and knowledge graph edges based on the knowledge representation method; and constructs the risk knowledge graph according to the knowledge graph nodes and the knowledge graph edges. Thus, a risk knowledge graph constructed based on the risk event entities and risk event attribute information of the business data is effectively obtained to facilitate the subsequent acquisition of risk transmission paths.

[0107] refer to Figure 4 In some optional implementations of this embodiment, step S20 includes the following steps:

[0108] Step S201, obtaining risk entities and risk entity relationships from the risk knowledge graph;

[0109] In this embodiment, the risk entity refers to the subject facing the risk, which can be an enterprise, an individual, a project, an asset, etc. The risk entity relationship includes the association relationship between risk entities (such as equity relationship, guarantee relationship, supply chain relationship, etc.), the relationship between risk events and risk entities (such as a certain enterprise faces risk due to a certain event), and risk attributes (such as the type, level, and scope of impact of the risk).

[0110] Step S202, constructing a risk transmission model according to the risk entity and the risk entity relationship;

[0111] In this embodiment, the risk transmission model is used to define the rules and weights for risk transmission between entities. The rules for risk transmission between entities can be defined based on the entities and relationships in the risk knowledge graph. For example, when a company encounters credit risk, its subsidiaries may face risks due to equity relationships; when a company provides guarantees for other companies, if the guaranteed company defaults, the guaranteeing company may face risks due to the guarantee relationship. According to the rules and actual conditions of risk transmission, a weight is assigned to each relationship, which represents the possibility or intensity of risk transmission on the relationship, and can be determined by historical data analysis methods. The nodes, edges, and weights in the risk knowledge graph are imported into the model to define the algorithm and process of risk transmission.

[0112] Step S203, searching for a transmission path in the risk knowledge graph based on a graph search algorithm to obtain an initial risk transmission path;

[0113] In this embodiment, the graph search algorithm uses the A* algorithm, which determines the starting entity of risk transmission, which is usually the source of the risk event, and sets the end point of the search, which can be a specific risk entity or a set of risk entities that meet certain conditions. Then, the A* algorithm is used to search from the starting point in the risk knowledge graph until the end point is reached or all possible paths are traversed, and all the transmission paths found are recorded as the initial risk transmission paths. These paths are composed of a series of connected risk entities and the relationships between them.

[0114] Step S204, calculating the risk value of the initial risk transmission path according to the transmission rules and weights defined by the risk transmission model;

[0115] In this embodiment, the conduction rules and corresponding weights of the relationships between risk entities are obtained from the risk conduction model, and the risk value can be expressed as a function of all risk entities and their relationship weights on the path. For example, risk value = Σ(entity risk value * relationship weight), where Σ represents summation, the entity risk value can be determined according to the risk type and level of the entity, and the risk type and level can be determined according to the preset risk entity mapping table, and the relationship weight reflects the possibility or intensity of risk conduction between entities, which can be set in advance. For each risk conduction path under the record, its risk value is calculated according to the defined risk value calculation formula, thereby obtaining the risk value of the initial risk conduction path.

[0116] Step S205, determining whether the risk value is greater than or equal to a preset risk threshold;

[0117] In this embodiment, the preset risk threshold is a judgment threshold set according to historical data, and the calculated risk value is compared with the preset risk threshold to effectively judge whether the risk value is greater than or equal to the preset risk threshold.

[0118] Step S206, if the risk value is greater than or equal to the preset risk threshold, marking the initial risk transmission path as the risk transmission path;

[0119] In this embodiment, the marking process is performed by adding a corresponding risk transmission path identifier to the initial risk transmission path, and the risk transmission path identifier may be a specific number or text field information.

[0120] Step S207: if the risk value is less than the preset risk threshold, the initial risk transmission path is marked as a non-risk transmission path.

[0121] In this embodiment, the marking process is performed by adding a corresponding non-risk conduction path identifier to the initial risk conduction path, and the non-risk conduction path identifier may be a specific number or text field information.

[0122] This embodiment obtains risk entities and risk entity relationships from the risk knowledge graph; constructs a risk transmission model based on the risk entities and risk entity relationships; searches for transmission paths in the risk knowledge graph based on a graph search algorithm to obtain an initial risk transmission path; calculates the risk value of the initial risk transmission path based on the transmission rules and weights defined in the risk transmission model; determines whether the risk value is greater than or equal to a preset risk threshold; if the risk value is greater than or equal to the preset risk threshold, marks the initial risk transmission path as the risk transmission path; if the risk value is less than the preset risk threshold, marks the initial risk transmission path as a non-risk transmission path. In this way, the risk transmission path is effectively extracted from the risk knowledge graph based on the transmission rules and weights of risks in risk entities, so as to facilitate the subsequent acquisition of associated risk event information.

[0123] refer to Figure 5 In some optional implementations of this embodiment, step S30 includes the following steps:

[0124] Step S301, performing a matching query in the database according to the risk transmission path to obtain associated risk event information related to the target risk event;

[0125] In this embodiment, the database may be a pre-established risk transmission path knowledge graph or knowledge database, which includes information such as risk events, risk entities, relationships between them, and risk transmission paths. According to the identified risk transmission paths, query conditions are defined, which include the starting risk event, risk entities and relationships on the path, etc., and matching queries are performed in the database to find associated risk event information related to the target risk event, and all matched associated risk event information is extracted.

[0126] Step S302, performing association rule mining on the associated risk event information according to an association rule mining algorithm to obtain risk event association rules and risk event association strengths;

[0127] In this embodiment, the associated risk event information is preprocessed to obtain standard and effective associated risk event information, and the preprocessing includes data deduplication, data cleaning, format unification, etc. Then, an association rule mining algorithm is used to mine the associated risk event information to identify the association rules and association strengths between risk events. The association rule mining algorithm can use the Apriori algorithm.

[0128] Step S303, constructing a risk event association network according to the risk event association rules and risk event association strengths;

[0129] In this embodiment, the structure of the risk event association network is defined based on the mined association rules and association strengths, and the structure includes nodes (representing risk events) and edges (representing associations between risk events). By creating a node for each risk event in the network graph and creating edges between nodes based on the association rules and association strengths, the risk event association network is effectively constructed, where the weight of the edge can represent the association strength.

[0130] Step S304, performing low-dimensional vector representation learning on the risk event association network to obtain a risk event embedding vector;

[0131] In this embodiment, for the risk event association network, a network embedding algorithm is used to learn the low-dimensional vector representation of each risk event to obtain the risk event embedding vector. Among them, the network embedding algorithm can use the Node2Vec algorithm, train the risk low-dimensional representation model through the Node2Vec algorithm and the risk event association network, and then extract the embedding vector of each risk event from the trained risk low-dimensional representation model to obtain the risk event embedding vector. This vector is usually a fixed-dimensional, continuous, real-number vector used to capture the structure and relationship information of risk events in the network.

[0132] Step S305, clustering the risk event embedding vectors according to a preset clustering algorithm to obtain risk event clusters;

[0133] In this embodiment, the DBSCAN clustering algorithm can be used to cluster the risk event embedding vector. By determining the two key parameters of the DBSCAN algorithm: eps (neighborhood radius) and minPts (minimum number of included points), and for each point in the risk event embedding vector, check whether it has been visited. If the point has not been visited, perform the following steps: a. Calculate the number of points in the eps neighborhood of the point. b. If the number of points in the neighborhood is greater than or equal to minPts, mark the point as a core point and create a new cluster. c. Recursively expand the cluster, add all points in the neighborhood of the core point to the cluster, and mark them as visited. d. If the number of points in the neighborhood is less than minPts, mark the point as a noise point. For each newly created core point, check whether the points in its neighborhood also belong to the core point. If so, add these points and the points in their neighborhood to the cluster and mark them as visited. Repeat this process until the cluster can no longer be expanded to effectively obtain the clustered risk event cluster.

[0134] Step S306: Calculate the risk event impact degree and the risk event loss scale according to the risk event clusters, and use the risk event impact degree and the risk event loss scale as the risk event impact information.

[0135] In this embodiment, for each risk event cluster, the impact degree of the risk event can be obtained by averaging the impact degrees of all risk events in the cluster, and the impact degree can be a quantitative indicator, such as the probability of the event occurring, the scope or duration of the impact, etc. The loss scale of the risk event can be obtained by averaging the loss scale of all risk events in the cluster, and the loss scale can be a financial indicator, such as direct economic loss, indirect economic loss or total loss, etc.

[0136] This embodiment obtains the associated risk event information related to the target risk event by performing matching query in the database according to the risk transmission path; performs association rule mining on the associated risk event information according to the association rule mining algorithm to obtain the risk event association rule and the risk event association strength; constructs a risk event association network according to the risk event association rule and the risk event association strength; performs low-dimensional vector representation learning on the risk event association network to obtain the risk event embedding vector; clusters the risk event embedding vector according to the preset clustering algorithm to obtain the risk event clustering cluster; calculates the risk event impact degree and the risk event loss scale according to the risk event clustering cluster, and uses the risk event impact degree and the risk event loss scale as the risk event impact information. Thus, the risk event impact information including the risk event impact degree and the loss scale is effectively calculated according to the risk event association rule and the association strength, so as to facilitate the subsequent training of the risk event impact assessment model.

[0137] Continue to refer Figure 6 In some optional implementations of this embodiment, step S40 includes the following steps:

[0138] Step S401, quantifying the risk event impact information according to a preset quantification index rule to obtain the risk event impact index data;

[0139] In this embodiment, the preset quantitative index rules include direct economic losses, indirect economic losses, environmental impact, social impact, etc. According to the quantitative index rules, the risk event impact information is converted into a series of quantitative index data, thereby obtaining risk event impact index data.

[0140] Step S402: training a pre-built initial impact assessment model according to the risk event impact indicator data to obtain the risk event impact assessment model.

[0141] In this embodiment, a risk event sample set is first obtained, which includes multiple risk events, and the key features of each risk event in the risk event sample set are extracted to obtain the feature vector of each risk event; the initial impact assessment model is constructed using the hierarchical analysis method, and the feature vector of the risk event is input into the initial impact assessment model for training to map the feature vector of each risk event to a corresponding impact score. The initial impact assessment model is then trained using the risk event impact indicator data to obtain a risk event impact assessment model that can output the impact score of each risk event.

[0142] This embodiment quantifies the risk event impact information according to the preset quantitative index rules to obtain the risk event impact index data; and trains the pre-built initial impact assessment model according to the risk event impact index data to obtain the risk event impact assessment model. Thus, a risk event impact assessment model that can accurately assess the impact score of each risk event is effectively obtained.

[0143] Continue to refer Figure 7 In some optional implementations of this embodiment, step S50 includes the following steps:

[0144] Step S501, constructing a risk conduction network topology structure according to the risk conduction path;

[0145] In this embodiment, each entity or system that may be affected by the risk is defined as a node in the network. The node can be a specific asset, department, process or system component, etc. According to the identified risk transmission path, connections (i.e., edges) are established between the network nodes. These connections indicate that the risk can be transmitted from one node to another through these paths. All nodes and connections are combined together to form a risk transmission network topology.

[0146] Step S502, setting the risk event probability distribution according to the risk event impact assessment model;

[0147] In this embodiment, the risk event impact assessment model is used to obtain the type, scale, frequency of occurrence and other characteristics of the risk event, and these characteristics will be used to determine the probability distribution of the risk event. According to the characteristics of the risk event, a suitable probability distribution type (such as normal distribution, Poisson distribution, exponential distribution, etc.) is selected to ensure that the selected distribution can accurately reflect the probability of occurrence of the risk event. In this embodiment, the above-mentioned probability distribution type can adopt a normal distribution, and the probability distribution of the risk event is obtained by setting the parameters of the selected probability distribution (such as mean, variance, shape parameters, etc.). Among them, the above-mentioned parameters will be used to generate a random sample of risk events.

[0148] Step S503, performing risk simulation evolution on the risk transmission network topology structure based on the Monte Carlo simulation method and the risk event probability distribution to obtain the network node risk status;

[0149] In this embodiment, the steps of risk simulation evolution based on the Monte Carlo simulation method include initializing the network state: before the simulation starts, the risk state of the network node is initialized to zero or a certain benchmark value; generating risk event samples: randomly generating a series of risk event samples according to the set risk event probability distribution; simulating the risk transmission process: for each generated risk event sample, simulating its transmission process in the network, and calculating the accumulation and evolution of risk on each node according to the network topology and the properties of the node (such as risk tolerance, recovery capacity, etc.); updating the network state: during the simulation process, the risk state of the network node is updated in real time according to the result of risk transmission; repeating the simulation process: repeating the above simulation process multiple times, and regenerating risk event samples and updating the network state each time the simulation is performed; recording and analyzing the results: after the simulation is completed, recording the network state in each time step, the risk level of the node and other information, and performing statistical analysis on this information to understand the evolution law and trend of risk in the network. After multiple Monte Carlo simulations, the risk state of each network node in different time steps can be obtained, and these states can be expressed as the risk value, risk level or risk distribution of the node.

[0150] Step S504, calculating the cumulative risk impact according to the risk status of the network node to obtain a first impact assessment result;

[0151] In this embodiment, the current risk level of each node is obtained based on the risk status data of each node in the risk transmission network topology structure, and the cumulative impact of the risk in the entire network is calculated for all nodes in the network based on their risk status and importance in the network (such as node connectivity, centrality, etc.). The cumulative impact can be calculated by traversing the network and performing weighted summation of the risk status of each node, wherein the weight in the weighted summation step can be determined based on the risk status of the network node. Based on the calculation result of the cumulative impact, the first impact assessment result of the risk event is obtained, and the first impact assessment result can be expressed as a specific numerical value, risk level or risk distribution, etc.

[0152] Step S505, calculating the indirect impact of risk based on the cascaded time-effect analysis method and the first impact assessment result to obtain a second impact assessment result;

[0153] In this embodiment, the cascading failure analysis method is used to study the correlation and chain reaction between risk events. The correlation and dependency between nodes in the network are analyzed through cascading failure analysis to identify risk paths that may cause chain reactions. Based on the identified correlation and chain reaction, the indirect impact caused by the risk event in the network is calculated. The indirect impact may include the diffusion range of node failure, the number of affected nodes, the depth of risk propagation, etc. Based on the calculation result of the indirect impact, the second impact assessment result of the risk event is obtained, and the second impact assessment result can be expressed as a specific value, risk level or risk distribution, etc.

[0154] Step S506: merge the first impact assessment result and the second impact assessment result to obtain the risk event impact result.

[0155] In this embodiment, a weighted average method can be used to merge the first impact assessment result and the second impact assessment result. The weighted average can be calculated based on the preset first impact weight and the second impact weight. The first impact weight and the second impact weight can be determined based on the relative importance of direct impact and indirect impact through expert judgment, historical data or other methods to assign different weights to the first impact assessment result and the second impact assessment result. According to the weighted average method, the first impact assessment result and the second impact assessment result are weighted and summed to obtain a risk event assessment result that describes the overall impact of the risk event. The risk event assessment result can be expressed as a comprehensive risk value, risk level or risk distribution, etc.

[0156] This embodiment constructs a risk conduction network topology structure according to the risk conduction path; sets the risk event probability distribution according to the risk event impact assessment model; performs risk simulation evolution on the risk conduction network topology structure based on the Monte Carlo simulation method and the risk event probability distribution to obtain the risk status of the network nodes; calculates the cumulative risk impact according to the network node risk status to obtain a first impact assessment result; calculates the indirect risk impact based on the cascade time analysis method and the first impact assessment result to obtain a second impact assessment result; and merges the first impact assessment result with the second impact assessment result to effectively obtain the risk event impact result that comprehensively considers the cumulative risk impact and the indirect risk impact of the risk event, so as to facilitate subsequent risk analysis and processing.

[0157] Continue to refer Figure 8 In some optional implementations of this embodiment, step S60 includes the following steps:

[0158] S601, constructing a risk event judgment matrix based on the analytic hierarchy process, and calculating a risk event weight coefficient based on the risk event judgment matrix;

[0159] In this embodiment, the basic information and related information of each risk event are obtained according to the pre-established risk event library, and the overall impact assessment result data of each risk event is obtained from the risk event library. Then, the hierarchical analysis method is used to construct a pairwise judgment matrix of risk events, calculate the eigenvector corresponding to the maximum eigenvalue of the judgment matrix, and normalize the eigenvector, that is, divide the elements of each row by the sum of the row to obtain the normalized judgment matrix, and add the normalized judgment matrix row by row to obtain the weight value of each risk event. These weight values ​​are normalized to obtain the risk event weight coefficient of each risk event.

[0160] S602, obtaining a risk path event set according to the risk transmission path;

[0161] In this embodiment, a risk path event set is formed by determining the risk events on each path along the risk conduction path in the risk conduction network.

[0162] S603: Perform weighted sum calculation on the risk path event set according to the risk event weight coefficient and the risk event impact result to obtain the comprehensive risk value.

[0163] In this embodiment, each risk event impact result is multiplied by the corresponding risk event weight coefficient, and then all the results are added together to obtain a comprehensive risk value.

[0164] This embodiment constructs a risk event judgment matrix based on the hierarchical analysis method, and calculates the risk event weight coefficient based on the risk event judgment matrix; obtains a risk path event set according to the risk transmission path; and performs weighted summation calculation on the risk path event set according to the risk event weight coefficient and the risk event impact result, thereby effectively obtaining a comprehensive risk value that further considers the weight of the risk event in terms of risk, so as to provide reliable judgment information for the enterprise to conduct risk qualitative analysis.

[0165] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0166] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0167] Further references Fig. 9 , as a response to the above Figure 1 The present application provides an embodiment of a business risk assessment device, and the device embodiment is Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0168] like Fig. 9 As shown, the business risk assessment device 700 described in this embodiment includes: a graph construction module 701, a path acquisition module 702, an impact analysis module 703, a model training module 704, a risk evolution module 705, and a risk analysis module 706. Among them:

[0169] A graph construction module 701 is used to obtain business data and construct a risk knowledge graph based on the business data;

[0170] A path acquisition module 702, used to acquire a risk transmission path in the risk knowledge graph based on a graph search algorithm;

[0171] The impact analysis module 703 is used to obtain the associated risk event information in the database according to the risk transmission path, and analyze the associated risk event information according to the data mining algorithm to obtain the risk event impact information;

[0172] A model training module 704 is used to quantify the risk event impact information and train a risk event impact assessment model based on the quantified risk event impact indicator data;

[0173] The risk evolution module 705 is used to perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result;

[0174] The risk analysis module 706 is used to perform risk analysis based on the impact results of the risk events to obtain a comprehensive risk value.

[0175] By adopting the above-mentioned business risk assessment device, this embodiment can obtain business data, build a risk knowledge graph based on the business data; obtain the risk transmission path in the risk knowledge graph based on the graph search algorithm; obtain the associated risk event information in the database according to the risk transmission path, and analyze the associated risk event information according to the data mining algorithm to obtain the risk event impact information; quantify the risk event impact information, and train the risk event impact assessment model according to the quantified risk event impact indicator data; perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result; perform risk analysis according to the risk event impact result to obtain the comprehensive risk value. In this way, the business of the enterprise can be effectively and accurately assessed, so as to facilitate the risk qualitative assessment of the enterprise according to the assessment situation.

[0176] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.

[0177] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 8 with components 81-83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0178] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0179] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 8. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions of the business risk assessment method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0180] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run computer-readable instructions stored in the memory 81 or process data, such as computer-readable instructions for running the business risk assessment method.

[0181] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0182] By adopting the above-mentioned computer device, this embodiment can obtain business data, build a risk knowledge graph based on the business data; obtain the risk transmission path in the risk knowledge graph based on the graph search algorithm; obtain the associated risk event information in the database according to the risk transmission path, and analyze the associated risk event information according to the data mining algorithm to obtain the risk event impact information; quantify the risk event impact information, and train the risk event impact assessment model according to the quantified risk event impact indicator data; perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result; perform risk analysis according to the risk event impact result to obtain the comprehensive risk value. In this way, the business of the enterprise can be effectively and accurately assessed, so as to facilitate the risk qualitative assessment of the enterprise according to the assessment situation.

[0183] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the business risk assessment method as described above.

[0184] By adopting the above-mentioned computer-readable storage medium, this embodiment can obtain business data, build a risk knowledge graph based on the business data; obtain the risk transmission path in the risk knowledge graph based on the graph search algorithm; obtain the associated risk event information in the database according to the risk transmission path, and analyze the associated risk event information according to the data mining algorithm to obtain the risk event impact information; quantify the risk event impact information, and train the risk event impact assessment model according to the quantified risk event impact indicator data; perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result; perform risk analysis according to the risk event impact result to obtain the comprehensive risk value. In this way, the business of the enterprise can be effectively and accurately assessed, so as to facilitate the risk qualitative assessment of the enterprise according to the assessment situation.

[0185] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0186] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

[0187] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

Claims

1. A business risk assessment method, characterized in that: The steps include: Acquire business data, and construct a risk knowledge graph based on the business data; Obtaining risk transmission paths in the risk knowledge graph based on a graph search algorithm; Acquire associated risk event information in a database according to the risk transmission path, and analyze the associated risk event information according to a data mining algorithm to obtain risk event impact information; Quantifying the risk event impact information, and training a risk event impact assessment model based on the quantified risk event impact indicator data; Perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result; Conduct risk analysis based on the impact of the risk event to obtain a comprehensive risk value.

2. The business risk assessment method according to claim 1, characterized in that: The step of obtaining business data and constructing a risk knowledge graph according to the business data specifically includes: Preprocessing the business data to obtain standard business data, and extracting risk event entities and risk event attribute information from the standard business data; Performing causal relationship analysis on the risk event entity and the risk event attribute information to obtain a causal relationship result; Determine whether the causal relationship result is a causal relationship; If the causal relationship result is that the causal relationship exists, converting the risk event entity and the risk event attribute information into a knowledge graph node and a knowledge graph edge based on a knowledge representation method; The risk knowledge graph is constructed according to the knowledge graph nodes and the knowledge graph edges.

3. The business risk assessment method according to claim 1, characterized in that: The step of obtaining the risk transmission path in the risk knowledge graph based on the graph search algorithm specifically includes: Acquire risk entities and risk entity relationships from the risk knowledge graph; Constructing a risk transmission model according to the risk entities and the risk entity relationships; Based on the graph search algorithm, a transmission path search is performed in the risk knowledge graph to obtain an initial risk transmission path; Calculate the risk value of the initial risk transmission path according to the transmission rules and weights defined by the risk transmission model; Determine whether the risk value is greater than or equal to a preset risk threshold; If the risk value is greater than or equal to the preset risk threshold, the initial risk transmission path is marked as the risk transmission path.

4. The business risk assessment method according to claim 1, characterized in that: The step of acquiring the associated risk event information in the database according to the risk transmission path, and analyzing the associated risk event information according to the data mining algorithm to obtain the risk event impact information specifically includes: Performing a matching query in the database according to the risk transmission path to obtain associated risk event information related to the target risk event; Performing association rule mining on the associated risk event information according to an association rule mining algorithm to obtain risk event association rules and risk event association strength; Constructing a risk event association network according to the risk event association rules and risk event association strengths; Performing low-dimensional vector representation learning on the risk event association network to obtain a risk event embedding vector; Clustering the risk event embedding vectors according to a preset clustering algorithm to obtain risk event clusters; The impact degree of the risk event and the loss scale of the risk event are calculated according to the risk event clusters, and the impact degree of the risk event and the loss scale of the risk event are used as the risk event impact information.

5. The business risk assessment method according to claim 1, characterized in that: The step of quantifying the risk event impact information and training the risk event impact assessment model according to the quantified risk event impact indicator data specifically includes: Quantifying the risk event impact information according to preset quantitative indicator rules to obtain the risk event impact indicator data; The pre-constructed initial impact assessment model is trained according to the risk event impact indicator data to obtain the risk event impact assessment model.

6. The business risk assessment method according to claim 1, characterized in that: The step of performing risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result specifically includes: Constructing a risk transmission network topology structure according to the risk transmission path; Setting the probability distribution of risk events according to the risk event impact assessment model; Based on the Monte Carlo simulation method and the probability distribution of the risk events, the risk conduction network topology structure is subjected to risk simulation evolution to obtain the risk status of the network nodes; Calculate the cumulative impact of risk according to the risk status of the network node to obtain a first impact assessment result; Calculate the indirect impact of risk based on the cascade time effect analysis method and the first impact assessment result to obtain a second impact assessment result; The first impact assessment result and the second impact assessment result are integrated to obtain the risk event impact result.

7. The business risk assessment method according to claim 1, characterized in that: The step of performing risk analysis according to the impact result of the risk event to obtain a comprehensive risk value specifically includes: Constructing a risk event judgment matrix based on the analytic hierarchy process, and calculating risk event weight coefficients based on the risk event judgment matrix; Acquire a risk path event set according to the risk transmission path; The risk path event set is weighted and summed according to the risk event weight coefficient and the risk event impact result to obtain the comprehensive risk value.

8. A business risk assessment device, characterized in that: include: A graph construction module, used to obtain business data and construct a risk knowledge graph based on the business data; A path acquisition module, used for acquiring risk transmission paths in the risk knowledge graph based on a graph search algorithm; An impact analysis module is used to obtain related risk event information in a database according to the risk transmission path, and analyze the related risk event information according to a data mining algorithm to obtain risk event impact information; A model training module is used to quantify the risk event impact information and train a risk event impact assessment model based on the quantified risk event impact indicator data; A risk evolution module, used to perform risk simulation evolution according to the risk transmission path and the risk event impact assessment model to obtain the risk event impact result; The risk analysis module is used to perform risk analysis based on the impact results of the risk event to obtain a comprehensive risk value.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the business risk assessment method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the business risk assessment method according to any one of claims 1 to 7 are implemented.

Images