Enterprise association risk analysis method, device and medium based on topological map

Through topological map-based methods, analyzing enterprise association relationships and simulating risk propagation, the problem of indirect enterprise risks in the existing technology is solved, and the effectiveness and reliability of enterprise association risk analysis is improved.

CN117522139BActive Publication Date: 2024-11-08SHENZHEN HURD INNOVATION TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202311569014.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-22
Publication Date
2024-11-08
Estimated Expiration
2043-11-22

AI Technical Summary

Technical Problem

The existing enterprise-related risk analysis methods mainly analyze enterprises with direct business transactions, and cannot effectively evaluate the risks of indirect business transactions, resulting in poor analysis results.

Method used

Using topological map-based methods, standardize and correlate relationship analysis by obtaining enterprise data, build graph nodes and calculate node degree, tightness center and node impact coefficients, divide core, key and edge enterprise nodes, and use risk propagation models to simulate risk propagation. , generate a risk assessment report.

Benefits of technology

It improves the analysis effect of enterprise-related risks, can more comprehensively evaluate the relationship between enterprises and risk transmission, and provides more reliable risk assessment support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117522139B_ABST
    Figure CN117522139B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of enterprise risk analysis, and discloses a method, device and medium for analyzing enterprise association risk based on topological graphs, wherein the method comprises: analyzing the association relationship of enterprises to be evaluated; analyzing the association weight and association attribute of enterprises to be evaluated, nodeizing enterprises to be evaluated, and obtaining graph enterprise nodes; connecting graph enterprise nodes, obtaining enterprise connection edges, optimizing the layout of graph enterprise nodes and enterprise connection edges, and obtaining an optimized enterprise association graph; calculating the close centrality and betweenness centrality of graph enterprise nodes, calculating the node influence coefficient of graph enterprise nodes, dividing graph enterprise nodes into core enterprise nodes, key enterprise nodes and edge enterprise nodes; taking core enterprise nodes as the starting point, simulating risk propagation using a preset risk propagation model, obtaining risk propagation records, and constructing a risk assessment report for the enterprise to be evaluated. The present invention can improve the analysis effect of enterprise association risks.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of enterprise risk analysis, and in particular to a method, device and medium for analyzing enterprise association risks based on a topological map. Background Art

[0002] Enterprise-related risk analysis refers to the potential risks in related transactions, capital flows, business cooperation, etc. between an enterprise and other enterprises or individuals during its operation. Through enterprise-related risk analysis, it is possible to avoid problems such as loss of corporate interests, capital loss, and tax violations, thereby ensuring the normal operation and sustainable development of the enterprise.

[0003] Currently, enterprise-related risk analysis mainly determines the risk coefficient by analyzing the business status between two enterprises. This method only analyzes the enterprises that directly generate business, and cannot evaluate the risks generated by other enterprises that have indirect business transactions, resulting in poor results in enterprise-related risk analysis. Summary of the invention

[0004] The present invention provides a method, device and medium for analyzing enterprise association risks based on topological maps, the main purpose of which is to improve the analysis effect of enterprise association risks.

[0005] To achieve the above object, the present invention provides a method for analyzing enterprise association risks based on a topological map, comprising:

[0006] Acquire enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, extract data features of the standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the data features;

[0007] Based on the association relationship, analyzing the association weight and association attribute of the enterprise to be evaluated, constructing the edge connection rule of the graph enterprise node based on the association weight and association attribute, and nodeizing the enterprise to be evaluated to obtain the graph enterprise node;

[0008] The graph enterprise nodes are connected by the edge connection rule to obtain enterprise connection edges, and the layout of the graph enterprise nodes and the enterprise connection edges is optimized to obtain an optimized enterprise association graph;

[0009] Calculate the enterprise node degree of the graph enterprise node, calculate the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise node into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the closeness centrality, the betweenness centrality and the node influence coefficient;

[0010] Taking the core enterprise node as the starting point, a preset risk propagation model is used to simulate risk propagation to obtain a risk propagation record, and a risk assessment report of the enterprise to be assessed is constructed through the risk propagation record.

[0011] Optionally, the step of standardizing the enterprise data to obtain standardized enterprise data includes:

[0012] identifying data attributes of the enterprise data;

[0013] Based on the data attributes, establishing a standardization target for the enterprise data;

[0014] Based on the standardization target, construct standardization rules for the enterprise data;

[0015] The enterprise data is standardized according to the standardization rules to obtain standardized enterprise data.

[0016] Optionally, analyzing the association relationship of the enterprise to be evaluated based on the standardized enterprise data includes:

[0017] Serializing the standardized enterprise data to obtain serial enterprise data;

[0018] Marking the time nodes of the serial enterprise data;

[0019] Based on the time node, calculating the correlation coefficient of the enterprise to be evaluated;

[0020] The correlation relationship of the enterprise to be evaluated is analyzed through the correlation coefficient.

[0021] Optionally, the calculating the correlation coefficient of the enterprise to be evaluated based on the time node includes:

[0022] Identify data observation values ​​of the serial enterprise data corresponding to the time node;

[0023] Based on the data observation values ​​of the serial enterprise data, the correlation coefficient of the enterprise to be evaluated is calculated using the following formula:

[0024]

[0025] Among them, L represents the correlation coefficient of the enterprise to be evaluated, k represents the lag order, R_i represents the data observation value of the enterprise data series at time R, and V_i represents the data observation value of the enterprise data series at time V.

[0026] Optionally, the calculating the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree includes:

[0027] Based on the enterprise node degree, the edge density of the graph enterprise node is calculated using the following formula:

[0028]

[0029] Where ρ represents the edge density of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node;

[0030] Determine the close centrality of the graph enterprise nodes through the edge density;

[0031] Based on the enterprise node degree, the edge connection value of the graph enterprise node is calculated using the following formula:

[0032]

[0033] Among them, L i represents the edge connection value of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node;

[0034] Based on the edge connectivity value, the betweenness centrality of the graph enterprise node is determined.

[0035] Optionally, the calculating the node influence coefficient of the graph enterprise node includes:

[0036] Identify the number of nodes of the graph enterprise node;

[0037] Creating an initial matrix of the graph enterprise nodes using the number of nodes;

[0038] Determine the adjacency matrix of the initial matrix through the corresponding association relationship of the graph enterprise nodes;

[0039] Based on the adjacency matrix, the node influence coefficient of the graph enterprise node is calculated.

[0040] Optionally, the calculating the node influence coefficient of the graph enterprise node based on the adjacency matrix includes:

[0041] Traversing the adjacency matrix to obtain a traversed adjacency matrix;

[0042] Based on the traversal adjacency matrix, the node influence coefficient of the graph enterprise node is calculated using the following formula:

[0043] σ(i)=Σci,j*θ

[0044] Among them, σ(i) represents the node influence coefficient of the i-th graph enterprise node, ci,j represents the edge weight between the i-th graph enterprise node and the j-th graph enterprise node, θ represents the traversal of the adjacency matrix, i represents the i-th graph enterprise node, and j represents the j-th graph enterprise node.

[0045] Optionally, constructing a risk assessment report of the enterprise to be assessed through the risk propagation record includes:

[0046] Extract the risk propagation path, risk propagation time and risk propagation type corresponding to the risk propagation record;

[0047] Based on the risk propagation path, identifying the propagation scope of the risk propagation type;

[0048] Calculating the propagation speed of the risk propagation type based on the risk propagation path and the risk propagation time;

[0049] Analyzing the risk propagation law of the risk propagation type through the propagation scope and the propagation speed;

[0050] Based on the risk propagation law, a risk assessment report for the enterprise to be assessed is constructed.

[0051] In a second aspect, in order to solve the above problem, the present invention further provides an enterprise association risk analysis device based on a topological map, the device comprising:

[0052] An enterprise association relationship analysis module is used to obtain enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, extract data features of the standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the data features;

[0053] An enterprise connection rule construction module is used to analyze the association weight and association attribute of the enterprise to be evaluated based on the association relationship, and to construct the edge connection rule of the graph enterprise node based on the association weight and association attribute, and to node the enterprise to be evaluated to obtain a graph enterprise node;

[0054] An enterprise association graph construction module is used to connect the graph enterprise nodes through the edge connection rules to obtain enterprise connection edges, and to optimize the layout of the graph enterprise nodes and the enterprise connection edges to obtain an optimized enterprise association graph;

[0055] A graph enterprise node division module, used to calculate the enterprise node degree of the graph enterprise node, calculate the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise node into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the closeness centrality, the betweenness centrality and the node influence coefficient;

[0056] The risk assessment report construction module is used to use the core enterprise node as the starting point, use a preset risk propagation model to simulate risk propagation, obtain risk propagation records, and construct a risk assessment report for the enterprise to be assessed through the risk propagation records.

[0057] In a third aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the enterprise association risk analysis method based on a topological map as described in any one of the first aspects above.

[0058] The embodiment of the present invention analyzes the association relationship of the enterprise to be evaluated based on the standardized enterprise data to effectively analyze the relationship between enterprises, thereby providing strong support for enterprise decision-making; further, the embodiment of the present invention constructs the edge connection rules of the graph enterprise nodes based on the association weights and association attributes to achieve the connection of the enterprise to be evaluated; in the embodiment of the present invention, the enterprise connection edge refers to the edge formed after connecting the graph enterprise nodes, and the connection of the graph enterprise nodes can be connected through the edge connection tool of Gephi software, and the integration of the graph enterprise nodes can be achieved through the enterprise connection edge, thereby forming an initial topological graph; further, the embodiment of the present invention can identify the close centrality and betweenness centrality of the graph enterprise nodes in the graph by calculating the close centrality and betweenness centrality of the graph enterprise nodes. The important nodes of the enterprise nodes improve the effect of enterprise risk analysis. Furthermore, the embodiment of the present invention can further analyze the influence of the graph enterprise nodes in the graph by calculating the node influence coefficient of the graph enterprise nodes, and provide a reliable basis for the later enterprise risk analysis. Finally, the embodiment of the present invention divides the graph enterprise nodes into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the close centrality, the betweenness centrality and the node influence coefficient. The enterprises can be divided into different levels of importance, thereby improving the effect of enterprise risk analysis. Taking the core enterprise node as the starting point, the preset risk propagation model is used to simulate risk propagation, and the risk propagation record obtained can provide a data basis for analyzing risk propagation, thereby improving the effect of enterprise-related risk analysis. Therefore, the enterprise-related risk analysis method, device and medium based on the topological graph proposed in the present invention can improve the analysis effect of enterprise-related risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a process flow of a method for analyzing enterprise association risks based on a topological map provided by an embodiment of the present invention;

[0060] Figure 2 A functional module diagram of an enterprise association risk analysis device based on a topology map provided by an embodiment of the present invention;

[0061] Figure 3 A schematic diagram of the structure of an electronic device of an enterprise association risk analysis device based on a topology map provided by an embodiment of the present invention;

[0062] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0064] The embodiment of the present application provides a method for analyzing enterprise-related risks based on a topological map. The execution subject of the method for analyzing enterprise-related risks based on a topological map includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for analyzing enterprise-related risks based on a topological map can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0065] Reference Figure 1 FIG. 1 is a flow chart of a method for analyzing enterprise association risks based on a topological map according to an embodiment of the present invention. In this embodiment, the method for analyzing enterprise association risks based on a topological map includes:

[0066] S1. Acquire enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the standardized enterprise data.

[0067] In the embodiment of the present invention, the enterprise data refers to basic information, financial data, transaction data and other data of the enterprise.

[0068] Furthermore, the embodiment of the present invention obtains standardized enterprise data by standardizing the enterprise data to ensure the consistency, accuracy, reliability and interchangeability of the data. The standardized enterprise data is data obtained by normalizing and unifying various types of enterprise data.

[0069] As an embodiment of the present invention, the enterprise data is standardized to obtain standardized enterprise data, including: identifying data attributes of the enterprise data; establishing standardization goals of the enterprise data based on the data attributes; constructing standardization rules for the enterprise data based on the standardization goals; and standardizing the enterprise data according to the standardization rules to obtain standardized enterprise data.

[0070] Among them, the data attributes refer to various attributes related to the enterprise, such as business attributes, technical attributes, management attributes and other attributes; the standardization goal refers to the purpose of data standardization such as improving data quality, reducing data redundancy, and promoting data sharing; the standardization rules refer to the formulation of data standards based on business needs and actual conditions, including data format, data type, data accuracy, data unit and other rules.

[0071] Furthermore, the embodiment of the present invention provides strong support for enterprise decision-making by analyzing the association relationship of the enterprises to be evaluated based on the standardized enterprise data, and effectively analyzing the relationship between enterprises. The association relationship refers to the correlation between the enterprises to be evaluated, such as equity relationship, business relationship, cooperation relationship, etc.

[0072] As an embodiment of the present invention, analyzing the association relationship of the enterprise to be evaluated based on the standardized enterprise data includes: serializing the standardized enterprise data to obtain serial enterprise data; marking the time nodes of the serial enterprise data; calculating the association coefficient of the enterprise to be evaluated based on the time nodes; and analyzing the association relationship of the enterprise to be evaluated through the association coefficient.

[0073] Among them, the serial enterprise data refers to a data set in which the standardized enterprise data is arranged in chronological order, the time node refers to a specific point on the time axis of the serial enterprise data, which is usually used to indicate the specific moment when an event or action occurs, and the correlation coefficient refers to the degree of correlation between the enterprises to be evaluated.

[0074] Further, in an optional embodiment of the present invention, the calculation of the correlation coefficient of the enterprise to be evaluated based on the time node includes: identifying the data observation value of the serial enterprise data corresponding to the time node; and calculating the correlation coefficient of the enterprise to be evaluated based on the data observation value of the serial enterprise data using the following formula:

[0075]

[0076] Among them, L represents the correlation coefficient of the enterprise to be evaluated, k represents the lag order, R_i represents the data observation value of the enterprise data series at time R, and V_i represents the data observation value of the enterprise data series at time V.

[0077] S2. Based on the association relationship, analyze the association weight and association attribute of the enterprise to be evaluated, and based on the association weight and association attribute, construct the edge connection rules of the graph enterprise node, node the enterprise to be evaluated, and obtain the graph enterprise node.

[0078] Furthermore, the embodiment of the present invention analyzes the association weights and association attributes of the enterprises to be evaluated based on the association relationship to further understand the degree of association between the enterprises to be evaluated, and provides a data basis for the later construction of the enterprise association map. Among them, the association weight refers to the degree of association between the enterprises to be evaluated, and the association attribute refers to the subordinate relationship between the enterprises to be evaluated, such as equity attributes, business attributes, and cooperation attributes.

[0079] As an embodiment of the present invention, the association weight and association attributes of the enterprise to be evaluated are analyzed based on the association relationship. The association weight can be determined by the association coefficient corresponding to the association relationship. The larger the correlation coefficient value, the higher the association weight. The association attribute can be analyzed by extracting the association attribute data in the association relationship.

[0080] Furthermore, the embodiment of the present invention constructs the edge connection rules of the graph enterprise nodes based on the association weights and association attributes to achieve the connection of the enterprise to be evaluated. The edge connection rules refer to the edge rules for connecting the enterprise to be evaluated, such as edge color, edge texture and other rules.

[0081] As an embodiment of the present invention, the edge connection rules of the graph enterprise node are constructed based on the association weights and the association attributes, including: determining the edge texture rules of the graph enterprise node based on the association weights; assigning the edge color rules of the graph enterprise node based on the association attributes; and constructing the edge connection rules of the graph enterprise node based on the edge texture rules and the edge color rules.

[0082] Among them, the edge texture rule refers to the construction rule of the edge texture connecting the enterprise nodes of the graph, for example, the association weight is 0.1, the connection edge texture is vertical lines, the association weight is 0.5, the connection edge texture is diagonal lines, etc. The edge color rule refers to the construction rule of the color of the connection edges between the enterprise nodes of the graph, for example, the association attribute is equity attribute, the connection edge color is red, the association attribute is business attribute, the connection edge color is black, etc.

[0083] In the embodiment of the present invention, the graph enterprise node refers to marking the enterprise to be evaluated as a node in the graph. The graph enterprise node can be generated by a node tool of Gephi software.

[0084] S3. Connect the graph enterprise nodes through the edge connection rule to obtain enterprise connection edges, optimize the layout of the graph enterprise nodes and the enterprise connection edges to obtain an optimized enterprise association graph.

[0085] In an embodiment of the present invention, the enterprise connection edge refers to the edge formed by connecting the graph enterprise nodes. The connection of the graph enterprise nodes can be connected through the edge connection tool of Gephi software. The graph enterprise nodes can be integrated through the enterprise connection edge, thereby forming an initial topological graph.

[0086] Furthermore, the embodiment of the present invention optimizes the layout of the graph enterprise nodes and the enterprise connection edges, and obtains an optimized enterprise association graph, which can more intuitively view the graph information, thereby improving the efficiency of enterprise relationship information extraction. The optimized enterprise association graph refers to adjusting the enterprise location layout to achieve a more intuitive enterprise association graph. The optimized enterprise association graph can be laid out by a layout algorithm spring.

[0087] S4. Calculate the enterprise node degree of the graph enterprise node, calculate the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise nodes into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the closeness centrality, the betweenness centrality and the node influence coefficient.

[0088] The embodiment of the present invention can provide data basis for the core division of nodes in the later stage by calculating the enterprise node degree of the graph enterprise node. The enterprise node degree refers to the number of enterprise connection edges of the graph enterprise node in the network. The enterprise node degree can be read by a marker.

[0089] Furthermore, the embodiment of the present invention can identify important nodes in the graph enterprise node by calculating the closeness centrality and betweenness centrality of the graph enterprise node, thereby improving the effect of enterprise risk analysis. Among them, the closeness centrality refers to an indicator that measures the importance of the position of a node in the network, and the betweenness centrality refers to an indicator that measures the importance of the connection role played by a node in the network.

[0090] As an embodiment of the present invention, the calculation of the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree includes: calculating the edge density of the graph enterprise node based on the enterprise node degree using the following formula:

[0091]

[0092] Where ρ represents the edge density of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node;

[0093] Determine the close centrality of the graph enterprise nodes through the edge density;

[0094] Based on the enterprise node degree, the edge connection value of the graph enterprise node is calculated using the following formula:

[0095]

[0096] Among them, L i represents the edge connection value of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node;

[0097] Based on the edge connectivity value, the betweenness centrality of the graph enterprise node is determined.

[0098] Among them, the edge density refers to the connection density of the enterprise connection edges of each graph enterprise node in the graph, and the edge connection value refers to the connection complexity of the enterprise connection edges of each graph enterprise node in the graph.

[0099] Furthermore, the embodiment of the present invention can further analyze the influence of the graph enterprise node in the graph by calculating the node influence coefficient of the graph enterprise node, providing a reliable basis for subsequent enterprise risk analysis. Among them, the node influence coefficient refers to an indicator that measures the importance of the node in the graph.

[0100] As an embodiment of the present invention, the calculation of the node influence coefficient of the graph enterprise node includes: identifying the number of nodes of the graph enterprise node; creating an initial matrix of the graph enterprise node through the number of nodes; determining the adjacency matrix of the initial matrix through the corresponding association relationships of the graph enterprise nodes; and calculating the node influence coefficient of the graph enterprise node based on the adjacency matrix.

[0101] Among them, the number of nodes refers to the number of graph enterprise nodes. When the initial matrix is ​​created, all elements in the matrix are set to 0, indicating that there is no association between the graph enterprise nodes. The adjacency matrix is ​​a matrix used to represent the connection relationship between the graph enterprise nodes in the graph.

[0102] Furthermore, in an optional embodiment of the present invention, the node influence coefficient of the graph enterprise node is calculated based on the adjacency matrix, including: traversing the adjacency matrix to obtain a traversed adjacency matrix; and calculating the node influence coefficient of the graph enterprise node based on the traversed adjacency matrix using the following formula:

[0103] σ(i)=Σci,j*θ

[0104] Among them, σ(i) represents the node influence coefficient of the i-th graph enterprise node, ci,j represents the edge weight between the i-th graph enterprise node and the j-th graph enterprise node, θ represents the traversal of the adjacency matrix, i represents the i-th graph enterprise node, and j represents the j-th graph enterprise node.

[0105] The edge weight refers to the length of the shortest path from node i to node j, and the edge weight can be implemented by the Dijkstra algorithm.

[0106] Furthermore, the embodiment of the present invention divides the graph enterprise nodes into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the close centrality, the betweenness centrality and the node influence coefficient, so as to divide enterprises into different levels of importance, thereby improving the effect of enterprise risk analysis. Among them, the core enterprise node refers to an enterprise with a high status and influence in the enterprise graph network, the key enterprise node refers to an enterprise with a high status and influence in the enterprise graph network, and the edge enterprise node refers to an enterprise with a relatively low status and influence in the enterprise graph network.

[0107] As an embodiment of the present invention, the division of the graph enterprise nodes into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the close centrality, the betweenness centrality and the node influence coefficient can be obtained by adding the close centrality, the betweenness centrality and the node influence coefficient of the graph enterprise node to obtain the total impact value of the enterprise, and according to the total impact value, the corresponding impact threshold is divided to divide the core enterprise node, the key enterprise node and the edge enterprise node. Wherein, the total impact value refers to the value obtained by adding the close centrality, the betweenness centrality and the node influence coefficient, and the impact threshold refers to dividing the total impact value into three different thresholds, for example, the impact threshold 0 to 1 represents the edge enterprise node, the impact threshold 1 to 2 represents the key enterprise node, and the impact threshold 2 to 3 represents the core enterprise.

[0108] S5. Taking the core enterprise node as the starting point, simulating risk propagation using a preset risk propagation model to obtain a risk propagation record, and constructing a risk assessment report for the enterprise to be assessed through the risk propagation record.

[0109] Furthermore, the embodiment of the present invention uses the core enterprise node as the starting point and uses a preset risk propagation model to simulate risk propagation, and the risk propagation record obtained can provide a data basis for analyzing risk propagation, thereby improving the effect of enterprise-related risk analysis. Among them, the risk propagation model refers to a model that simulates the process of risk propagation in a graph network, such as an infectious disease model, a probability theory model, a network propagation model, and the risk propagation record refers to a log of the process of risk propagation in a graph network. The simulation of risk propagation using a preset risk propagation model can be simulated by inputting preset risk types into the risk propagation model. Among them, the risk types include financial risks, health risks, information security risks, and other risks.

[0110] Furthermore, the embodiment of the present invention constructs a risk assessment report for the enterprise to be assessed through the risk propagation record, and can timely discover the enterprise's potential risk factors, thereby providing a basis for the enterprise to formulate corresponding risk prevention measures.

[0111] As an embodiment of the present invention, constructing the risk assessment report of the enterprise to be assessed through the risk propagation record includes: extracting the risk propagation path, risk propagation time and risk propagation type corresponding to the risk propagation record; based on the risk propagation path, identifying the propagation range of the risk propagation type; based on the risk propagation path and the risk propagation time, calculating the propagation speed of the risk propagation type; through the propagation range and the propagation speed, analyzing the risk propagation law of the risk propagation type; based on the risk propagation law, constructing the risk assessment report of the enterprise to be assessed.

[0112] Among them, the risk propagation path refers to the path composed of enterprise connection edges passed through during the risk propagation process, the risk propagation time refers to the time experienced during the risk propagation process, the propagation range refers to the range of enterprise nodes involved in the risk propagation process, the propagation speed refers to the risk propagation speed during the risk propagation process, and the risk propagation law refers to the law of risk propagation, such as the propagation duration of different types of risks, the degree of impact of different types of risks and other laws.

[0113] The embodiment of the present invention analyzes the association relationship of the enterprise to be evaluated based on the standardized enterprise data to effectively analyze the relationship between enterprises, thereby providing strong support for enterprise decision-making; further, the embodiment of the present invention constructs the edge connection rules of the graph enterprise nodes based on the association weights and association attributes to achieve the connection of the enterprise to be evaluated; in the embodiment of the present invention, the enterprise connection edge refers to the edge formed after connecting the graph enterprise nodes, and the connection of the graph enterprise nodes can be connected through the edge connection tool of Gephi software, and the integration of the graph enterprise nodes can be achieved through the enterprise connection edge, thereby forming an initial topological graph; further, the embodiment of the present invention can identify the close centrality and betweenness centrality of the graph enterprise nodes in the graph by calculating the close centrality and betweenness centrality of the graph enterprise nodes. The important nodes of the enterprise nodes improve the effect of enterprise risk analysis. Furthermore, the embodiment of the present invention can further analyze the influence of the graph enterprise nodes in the graph by calculating the node influence coefficient of the graph enterprise nodes, and provide a reliable basis for the later enterprise risk analysis. Finally, the embodiment of the present invention divides the graph enterprise nodes into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the close centrality, the betweenness centrality and the node influence coefficient. The enterprises can be divided into different levels of importance, thereby improving the effect of enterprise risk analysis. Taking the core enterprise node as the starting point, the preset risk propagation model is used to simulate risk propagation, and the risk propagation record obtained can provide a data basis for analyzing risk propagation, thereby improving the effect of enterprise-related risk analysis. Therefore, the enterprise-related risk analysis method based on topological graph proposed in the present invention can improve the analysis effect of enterprise-related risks.

[0114] like Figure 2 , which is a functional module diagram of an enterprise association risk analysis device based on a topology map provided by an embodiment of the present invention.

[0115] The enterprise association risk analysis device 200 based on topological map of the present invention can be installed in an electronic device. According to the functions to be implemented, the enterprise association risk analysis device 200 based on topological map can include an enterprise association relationship analysis module 201, an enterprise connection rule construction module 202, an enterprise association map construction module 203, a map enterprise node division module 204 and a risk assessment report construction module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0116] In this embodiment, the functions of each module / unit are as follows:

[0117] The enterprise association relationship analysis module 201 is used to obtain enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, extract data features of the standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the data features;

[0118] The enterprise connection rule construction module 202 is used to analyze the association weight and association attribute of the enterprise to be evaluated based on the association relationship, and to construct the edge connection rule of the graph enterprise node based on the association weight and association attribute, and to node the enterprise to be evaluated to obtain the graph enterprise node;

[0119] The enterprise association graph construction module 203 is used to connect the graph enterprise nodes through the edge connection rules to obtain enterprise connection edges, and optimize the layout of the graph enterprise nodes and the enterprise connection edges to obtain an optimized enterprise association graph;

[0120] The graph enterprise node division module 204 is used to calculate the enterprise node degree of the graph enterprise node, calculate the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise node into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the closeness centrality, the betweenness centrality and the node influence coefficient;

[0121] The risk assessment report construction module 205 is used to use the core enterprise node as a starting point, use a preset risk propagation model to simulate risk propagation, obtain risk propagation records, and construct a risk assessment report for the enterprise to be assessed through the risk propagation records.

[0122] In detail, each module described in the enterprise association risk analysis device 200 based on topological map in the embodiment of the present invention adopts the same technical means as the enterprise association risk analysis method based on topological map described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0123] An embodiment of the present invention provides an electronic device for implementing a method for analyzing enterprise association risks based on a topology map.

[0124] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as an enterprise association risk analysis method program based on a topological map.

[0125] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory (for example, executing an enterprise association risk analysis program based on a topology map, etc.), and calls data stored in the memory to execute various functions of the electronic device and process data.

[0126] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory can also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory can also include both an internal storage unit of the electronic device and an external storage device. The memory can not only be used to store application software and various types of data installed in the electronic device, such as the code of an enterprise-related risk analysis program based on a topological map, but can also be used to temporarily store data that has been output or is to be output.

[0127] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0128] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0129] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0130] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0131] The enterprise association risk analysis program based on the topology map stored in the memory of the electronic device is a combination of multiple instructions, and when running in the processor, it can achieve:

[0132] Acquire enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, extract data features of the standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the data features;

[0133] Based on the association relationship, analyzing the association weight and association attribute of the enterprise to be evaluated, constructing the edge connection rule of the graph enterprise node based on the association weight and association attribute, and nodeizing the enterprise to be evaluated to obtain the graph enterprise node;

[0134] The graph enterprise nodes are connected by the edge connection rule to obtain enterprise connection edges, and the layout of the graph enterprise nodes and the enterprise connection edges is optimized to obtain an optimized enterprise association graph;

[0135] Calculate the enterprise node degree of the graph enterprise node, calculate the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise node into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the closeness centrality, the betweenness centrality and the node influence coefficient;

[0136] Taking the core enterprise node as the starting point, a preset risk propagation model is used to simulate risk propagation to obtain a risk propagation record, and a risk assessment report of the enterprise to be assessed is constructed through the risk propagation record.

[0137] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0138] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0139] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0140] Acquire enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, extract data features of the standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the data features;

[0141] Based on the association relationship, analyzing the association weight and association attribute of the enterprise to be evaluated, constructing the edge connection rule of the graph enterprise node based on the association weight and association attribute, and nodeizing the enterprise to be evaluated to obtain the graph enterprise node;

[0142] The graph enterprise nodes are connected by the edge connection rule to obtain enterprise connection edges, and the layout of the graph enterprise nodes and the enterprise connection edges is optimized to obtain an optimized enterprise association graph;

[0143] Calculate the enterprise node degree of the graph enterprise node, calculate the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise node into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the closeness centrality, the betweenness centrality and the node influence coefficient;

[0144] Taking the core enterprise node as the starting point, a preset risk propagation model is used to simulate risk propagation to obtain a risk propagation record, and a risk assessment report of the enterprise to be assessed is constructed through the risk propagation record.

[0145] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0146] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, 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 solution of this embodiment.

[0147] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0148] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0149] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0150] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application device that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0151] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for analyzing enterprise association risks based on topological maps, characterized in that: The method comprises: Acquire enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, extract data features of the standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the data features, wherein the analysis of the association relationship of the enterprise to be evaluated based on the standardized enterprise data includes: serializing the standardized enterprise data to obtain serial enterprise data; marking the time nodes of the serial enterprise data; calculating the association coefficient of the enterprise to be evaluated based on the time nodes; analyzing the association relationship of the enterprise to be evaluated through the association coefficient, wherein the calculation of the association coefficient of the enterprise to be evaluated based on the time nodes includes: Identify data observation values ​​of the serial enterprise data corresponding to the time node; Based on the data observation values ​​of the serial enterprise data, the correlation coefficient of the enterprise to be evaluated is calculated using the following formula: Among them, L represents the correlation coefficient of the enterprise to be evaluated, k represents the lag order, R_i represents the data observation value of the enterprise data series at time R, and V_i represents the data observation value of the enterprise data series at time V; Based on the association relationship, the association weight and association attribute of the enterprise to be evaluated are analyzed; based on the association weight and association attribute, the edge connection rule of the graph enterprise node is constructed; the enterprise to be evaluated is nodeized to obtain a graph enterprise node, wherein the edge connection rule of the graph enterprise node is constructed based on the association weight and association attribute, including: determining the edge texture rule of the graph enterprise node based on the association weight; allocating the edge color rule of the graph enterprise node based on the association attribute; constructing the edge connection rule of the graph enterprise node based on the edge texture rule and the edge color rule; The graph enterprise nodes are connected by the edge connection rule to obtain enterprise connection edges, and the layout of the graph enterprise nodes and the enterprise connection edges is optimized to obtain an optimized enterprise association graph; Calculate the enterprise node degree of the graph enterprise node, calculate the closeness centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise node into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the closeness centrality, the betweenness centrality and the node influence coefficient, wherein the calculation of the node influence coefficient of the graph enterprise node includes: identifying the number of nodes of the graph enterprise node; creating an initial matrix of the graph enterprise node through the number of nodes; determining the adjacency matrix of the initial matrix through the corresponding association relationship of the graph enterprise nodes; and calculating the node influence coefficient of the graph enterprise node based on the adjacency matrix. The calculation of the node influence coefficient of the graph enterprise node based on the adjacency matrix includes: Traversing the adjacency matrix to obtain a traversed adjacency matrix; Based on the traversal adjacency matrix, the node influence coefficient of the graph enterprise node is calculated using the following formula: σ(i)=Σci,j*θ Among them, σ(i) represents the node influence coefficient of the i-th graph enterprise node, ci,j represents the edge weight between the i-th graph enterprise node and the j-th graph enterprise node, θ represents the traversal adjacency matrix, i represents the i-th graph enterprise node, and j represents the j-th graph enterprise node; The step of calculating the closeness centrality and betweenness centrality of the graph enterprise nodes based on the enterprise node degrees includes: Based on the enterprise node degree, the edge density of the graph enterprise node is calculated using the following formula: Where ρ represents the edge density of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node; Determine the close centrality of the graph enterprise nodes through the edge density; Based on the enterprise node degree, the edge connection value of the graph enterprise node is calculated using the following formula: Among them, L i represents the edge connection value of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node; Determining the betweenness centrality of the graph enterprise node based on the edge connectivity value; Taking the core enterprise node as the starting point, a preset risk propagation model is used to simulate risk propagation to obtain a risk propagation record, and a risk assessment report of the enterprise to be assessed is constructed through the risk propagation record.

2. The enterprise association risk analysis method based on topological graph according to claim 1, characterized in that: The step of standardizing the enterprise data to obtain standardized enterprise data includes: identifying data attributes of the enterprise data; Based on the data attributes, establishing a standardization target for the enterprise data; Based on the standardization target, construct standardization rules for the enterprise data; The enterprise data is standardized according to the standardization rules to obtain standardized enterprise data.

3. The enterprise association risk analysis method based on topological graph according to claim 1, characterized in that: The risk assessment report of the enterprise to be assessed is constructed through the risk propagation record, including: Extract the risk propagation path, risk propagation time and risk propagation type corresponding to the risk propagation record; Based on the risk propagation path, identifying the propagation scope of the risk propagation type; Calculating the propagation speed of the risk propagation type based on the risk propagation path and the risk propagation time; Analyzing the risk propagation law of the risk propagation type through the propagation scope and the propagation speed; Based on the risk propagation law, a risk assessment report for the enterprise to be assessed is constructed.

4. A device for analyzing enterprise association risks based on topological maps, characterized in that: The device is used to execute the enterprise association risk analysis method based on topological graph according to any one of claims 1 to 3, and comprises: The enterprise association relationship analysis module is used to obtain enterprise data of the enterprise to be evaluated, standardize the enterprise data to obtain standardized enterprise data, extract data features of the standardized enterprise data, and analyze the association relationship of the enterprise to be evaluated based on the data features, wherein the analysis of the association relationship of the enterprise to be evaluated based on the standardized enterprise data includes: serializing the standardized enterprise data to obtain serial enterprise data; marking the time nodes of the serial enterprise data; calculating the association coefficient of the enterprise to be evaluated based on the time nodes; analyzing the association relationship of the enterprise to be evaluated through the association coefficient, wherein the calculation of the association coefficient of the enterprise to be evaluated based on the time nodes includes: Identify data observation values ​​of the serial enterprise data corresponding to the time node; Based on the data observation values ​​of the serial enterprise data, the correlation coefficient of the enterprise to be evaluated is calculated using the following formula: Among them, L represents the correlation coefficient of the enterprise to be evaluated, k represents the lag order, R_i represents the data observation value of the enterprise data series at time R, and V_i represents the data observation value of the enterprise data series at time V; An enterprise connection rule construction module is used to analyze the association weight and association attribute of the enterprise to be evaluated based on the association relationship, construct the edge connection rule of the graph enterprise node based on the association weight and association attribute, and node the enterprise to be evaluated to obtain a graph enterprise node, wherein the edge connection rule of the graph enterprise node is constructed based on the association weight and association attribute, including: determining the edge texture rule of the graph enterprise node based on the association weight; allocating the edge color rule of the graph enterprise node based on the association attribute; and constructing the edge connection rule of the graph enterprise node based on the edge texture rule and the edge color rule; An enterprise association graph construction module is used to connect the graph enterprise nodes through the edge connection rules to obtain enterprise connection edges, and to optimize the layout of the graph enterprise nodes and the enterprise connection edges to obtain an optimized enterprise association graph; A graph enterprise node division module is used to calculate the enterprise node degree of the graph enterprise node, calculate the close centrality and betweenness centrality of the graph enterprise node based on the enterprise node degree, calculate the node influence coefficient of the graph enterprise node, and divide the graph enterprise node into core enterprise nodes, key enterprise nodes and edge enterprise nodes based on the close centrality, the betweenness centrality and the node influence coefficient. The calculation of the node influence coefficient of the graph enterprise node includes: identifying the number of nodes of the graph enterprise node; creating an initial matrix of the graph enterprise node through the number of nodes; determining the adjacency matrix of the initial matrix through the corresponding association relationship of the graph enterprise nodes; calculating the node influence coefficient of the graph enterprise node based on the adjacency matrix. The calculation of the node influence coefficient of the graph enterprise node based on the adjacency matrix includes: Traversing the adjacency matrix to obtain a traversed adjacency matrix; Based on the traversal adjacency matrix, the node influence coefficient of the graph enterprise node is calculated using the following formula: σ(i)=Σci,j*θ Among them, σ(i) represents the node influence coefficient of the i-th graph enterprise node, ci,j represents the edge weight between the i-th graph enterprise node and the j-th graph enterprise node, θ represents the traversal adjacency matrix, i represents the i-th graph enterprise node, and j represents the j-th graph enterprise node; The step of calculating the closeness centrality and betweenness centrality of the graph enterprise nodes based on the enterprise node degrees includes: Based on the enterprise node degree, the edge density of the graph enterprise node is calculated using the following formula: Where ρ represents the edge density of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node; Determine the close centrality of the graph enterprise nodes through the edge density; Based on the enterprise node degree, the edge connection value of the graph enterprise node is calculated using the following formula: Among them, L i represents the edge connection value of the i-th graph enterprise node, D i represents the enterprise node degree of the i-th graph enterprise node, and B represents the total number of enterprise connection edges of the graph enterprise node; Determining the betweenness centrality of the graph enterprise node based on the edge connectivity value; The risk assessment report construction module is used to use the core enterprise node as the starting point, use a preset risk propagation model to simulate risk propagation, obtain risk propagation records, and construct a risk assessment report for the enterprise to be assessed through the risk propagation records.

5. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the enterprise association risk analysis method based on topological maps as described in any one of claims 1 to 3 is implemented.

Citation Information

Patent Citations

  • Enterprise association graph construction method, device and device, and computer readable medium

    CN111861120A

  • Server node importance analysis method

    CN113726564A

  • Knowledge graph-based listed enterprise illegal risk prediction method

    CN116384551A