CN114118816A

CN114118816A - Risk assessment method, device and equipment and computer storage medium

Info

Publication number: CN114118816A
Application number: CN202111439469.1A
Authority: CN
Inventors: 王丽
Original assignee: CCB Finetech Co Ltd
Current assignee: CCB Finetech Co Ltd
Priority date: 2021-11-30
Filing date: 2021-11-30
Publication date: 2022-03-01
Anticipated expiration: 2041-11-30
Also published as: CN114118816B

Abstract

The application discloses a risk assessment method, a risk assessment device, risk assessment equipment and a computer storage medium. The method comprises the steps of obtaining risk assessment data of an object to be assessed; acquiring a target associated map related to the object to be evaluated from at least one knowledge map; determining a first risk influence factor of the associated object influencing the risk evaluation result of the object to be evaluated; respectively determining a self risk assessment value of the associated object and a second risk influence factor of the risk assessment value of the associated object influencing the risk assessment result of the object to be assessed according to the risk assessment data of the associated object; determining a first risk assessment value of the object to be assessed according to the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor; a risk assessment value for the object to be assessed is determined. According to the method and the device, the accuracy of the risk assessment result of the assessment object can be improved.

Description

Risk assessment method, device and equipment and computer storage medium

Technical Field

The application belongs to the technical field of finance, and particularly relates to a risk assessment method, a risk assessment device, risk assessment equipment and a computer storage medium.

Background

Currently, avoiding risks according to the risk assessment results of the subjects has become a routine choice for various organizations.

When risk assessment is performed on an assessment object, the risk assessment result of the assessment object provided by the traditional risk assessment method cannot accurately represent the risk of the assessment object.

Therefore, how to improve the accuracy of the risk assessment result of the assessment object has become a technical problem which needs to be solved urgently at present.

Disclosure of Invention

The embodiment of the application provides a risk assessment method, a risk assessment device, a risk assessment equipment and a computer storage medium, which can improve the accuracy of calculating the influence of a related object on the risk assessment result of an object to be assessed, and further improve the accuracy of the risk assessment result of the object to be assessed.

In a first aspect, an embodiment of the present application provides a risk assessment method, including:

acquiring risk assessment data of an object to be assessed, wherein the risk assessment data comprises self attribute information and investment data of the object to be assessed;

acquiring a target association graph related to the object to be evaluated from at least one knowledge graph according to the risk evaluation data, wherein the knowledge graph is an association path graph constructed according to the object to be evaluated, an association object having an investment relationship with the object to be evaluated and the investment relationship;

determining a first risk assessment value of a risk assessment result of the associated object influencing the object to be assessed according to the target associated map and the risk assessment data of the associated object;

and determining a risk assessment value of the object to be assessed according to the first risk assessment value and a second risk assessment value of the object to be assessed, wherein the second risk assessment value is the risk assessment value determined according to risk assessment data of the object to be assessed.

In an embodiment, the determining, according to the risk assessment data of the target association map and the association object, a first risk assessment value of a risk assessment result that the association object affects the object to be assessed specifically includes:

determining at least one target path between the object to be evaluated and the associated object from the target associated map according to the investment relation;

determining a first risk influence factor of the associated object influencing the risk evaluation result of the object to be evaluated according to the target path;

respectively determining a self risk assessment value of the associated object and a second risk influence factor of the risk assessment value of the associated object influencing the risk assessment result of the object to be assessed according to the risk assessment data of the associated object;

and determining a first risk assessment value of the object to be assessed according to the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor.

In one embodiment, before obtaining the target association map related to the object to be evaluated, the method further includes:

taking an object as a node, wherein the node is used for storing risk assessment data of the object;

using the investment relation between the objects as the connection line between the nodes, wherein the investment relation is determined according to the risk assessment data of the objects;

and forming the associated path graph by using the object and the connecting line.

In one embodiment, before the object is taken as a node, the method further comprises:

and preprocessing the risk assessment data of the object to obtain standardized risk assessment data for deleting repeated information and supplementing missing information.

determining the subject from the standardized risk assessment data;

determining an investment relationship between the objects based on the standardized risk assessment data.

In an embodiment, the determining, according to the target association map and the risk assessment data of the associated object, a first risk assessment value of a risk assessment result that the associated object affects the object to be assessed specifically includes:

for each associated object, calculating a first risk influence value of a risk evaluation result of the associated object influencing the object to be evaluated according to the self risk evaluation value of the associated object, the first risk influence factor and the second risk influence factor;

determining a sum of the first risk impact values as the first risk assessment value.

In an embodiment, the calculating, for each associated object, a first risk influence value of a risk evaluation result that the associated object influences the object to be evaluated according to the own risk evaluation value of the associated object, the first risk influence factor, and the second risk influence factor specifically includes:

when the target path is multiple, determining a product of the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor as a second risk influence value for each target path;

selecting the second risk influence value with the largest value as the first risk influence value;

when the target path is one, determining a product of the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor as the first risk influence value.

In one embodiment, the target association graph comprises at least one connection path between objects, the connection path comprises at least one path segment, the path segment comprises two nodes and one investment relation, the number of path segments in the target path does not exceed a first threshold,

the determining, according to the target path, a first risk influence factor by which the associated object influences a risk evaluation result of the object to be evaluated specifically includes:

for each of the target paths:

determining a first path influence factor of the associated object on the object to be evaluated according to the number of the path segments in the target path;

determining a second path influence factor of the associated object on the object to be evaluated according to the number of the path segments in the target path and the number of the path segments in the target associated map;

determining an investment influence factor of the associated object on the object to be evaluated according to the investment relation and the target path;

determining a product of the first path impact factor, the second path impact factor, and the investment impact factor as the first risk impact factor.

In an embodiment, the determining, according to the number of the path segments in the target path, a first path influence factor of the associated object on the object to be evaluated specifically includes:

and determining a calculation result with a first preset numerical value as the bottom and the number of the path segments in the target path as the exponential power as the first path influence factor.

In an embodiment, the determining, according to the number of the path segments in the target path and the total number of paths of the target association map, a second path influence factor of the associated object on the object to be evaluated specifically includes:

calculating the sum of the number of the path segments in the target path;

and determining the ratio of the sum of the number of the path segments in the target path to the number of the path segments in the target association map as the second path influence factor.

In one embodiment, the investment relationship comprises a proportion of the investment,

determining an investment influence factor of the associated object on the object to be evaluated according to the investment relation and the target path, specifically comprising:

determining a first investment influence factor corresponding to each path section in the target path according to the size relation between the investment proportion and a second threshold value;

when the target path comprises a plurality of path segments, determining the product of first investment influence factors corresponding to the path segments in the target path as the investment influence factors;

determining the first investment impact factor as the investment impact factor when the target path has only one path segment.

In an embodiment, the determining, according to a magnitude relation between the investment proportion and a second threshold, a first investment impact factor corresponding to each path segment in the target path specifically includes:

determining the investment proportion as the first investment impact factor when the investment proportion is less than a second threshold;

and when the investment proportion is greater than or equal to a second threshold value, determining a second preset numerical value as the first investment influence factor.

In a second aspect, an embodiment of the present application provides a risk assessment apparatus, including:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring risk assessment data of an object to be assessed, and the risk assessment data comprises self attribute information and investment data of the object to be assessed;

a second obtaining module, configured to obtain a target association graph related to the object to be evaluated from at least one knowledge graph according to the risk assessment data, where the knowledge graph is an association path graph constructed according to the object to be evaluated, an association object having an investment relationship with the object to be evaluated, and the investment relationship;

the first determining module is used for determining a first risk influence factor of the associated object influencing the risk evaluation result of the object to be evaluated according to the target associated map;

the second determining module is used for respectively determining the self risk assessment value of the associated object and a second risk influence factor of the risk assessment value of the associated object influencing the risk assessment result of the object to be assessed according to the risk assessment data of the associated object;

a third determining module, configured to determine a first risk assessment value of the object to be assessed according to the own risk assessment value of the associated object, the first risk influence factor, and the second risk influence factor;

and a fourth determining module, configured to determine a risk assessment value of the object to be assessed according to the first risk assessment value and a second risk assessment value of the object to be assessed, where the second risk assessment value is a risk assessment value determined according to risk assessment data of the object to be assessed.

In a third aspect, an embodiment of the present application provides a risk assessment apparatus, including: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements the risk assessment method described in any embodiment of the present application.

In a fourth aspect, embodiments of the present application provide a computer storage medium having computer program instructions stored thereon, where the computer program instructions, when executed by a processor, implement a risk assessment method as described in any of the embodiments of the present application.

In a fifth aspect, the present application provides a computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the risk assessment method described in any of the embodiments of the present application.

According to the risk assessment method, the risk assessment device, the risk assessment equipment and the computer storage medium, the risk assessment value of the object to be assessed is a result of assessment and determination according to the first risk assessment value and the second risk assessment value. The first risk assessment value is a value obtained by integrating a target association map and risk assessment data of the associated object, the target association map is a map reflecting risk influence of the associated object on the object to be assessed in the target association map, and the risk assessment data of the associated object and the target association map reflect the risk influence of the risk of the associated object on the object to be assessed. The first risk assessment value obtained by integrating the risk assessment data of the associated object and the target associated map comprehensively considers the risk influence of the self risk of the associated object after the self risk of the associated object is transmitted to the object to be assessed in the target associated map, measures the influence of the associated object on the object to be assessed, and improves the accuracy of calculating the influence of the associated object on the risk assessment result of the object to be assessed. The second risk assessment value is obtained from the risk assessment data of the assessment object itself, and is an assessment result regarding the risk of the object to be assessed itself. Therefore, the evaluation result obtained based on the first risk evaluation value and the second risk evaluation value comprehensively considers the risk influence factor of the associated object after the self risk of the associated object is transmitted to the object to be evaluated in the target associated map and the risk influence factor of the object to be evaluated, and improves the accuracy of calculating the influence of the associated object on the risk evaluation result of the object to be evaluated and the accuracy of the risk evaluation result of the object to be evaluated.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a risk assessment method according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of another risk assessment method provided in an embodiment of the present application;

FIG. 3 is a schematic flow chart of yet another risk assessment method according to an embodiment of the present application;

FIG. 4 is a schematic flow chart of yet another risk assessment method according to an embodiment of the present application;

FIG. 5 is a schematic flow chart of yet another risk assessment method according to an embodiment of the present application;

FIG. 6 is a schematic flow chart of yet another risk assessment method according to an embodiment of the present application;

FIG. 7 is a schematic flow chart of yet another risk assessment method according to an embodiment of the present application;

FIG. 8 is a schematic view of a risk assessment device according to an embodiment of the present application;

fig. 9 is a schematic view of a risk assessment device according to an embodiment of the present application.

Detailed Description

Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.

For ease of understanding, the terms used in this application will first be described,

unstructured data, which refers to data that does not have a predefined data model or is not organized in a predefined manner, is characterized by non-characteristics and ambiguity relative to traditional files in databases or tags. Illustratively, "enterprise XX3 is a company that has been established for 10 years and has a registered capital of 4000 ten thousand. "this sentence is an unstructured data.

The structured data is data with values in a fixed format in a record file, can be represented and stored by using a relational database, and can be realized by logically expressing a two-dimensional table structure. The general characteristics are as follows: data is in row units, one row of data represents information of one entity, and the attribute of each row of data is the same. Illustratively, the following table shows that the data may be a structured data.

Name of an enterprise	Registered capital
		XX1	2000 ten thousand
XX2	3000 ten thousand

Semi-structured data is data that is intermediate between structured data (e.g., data in relational databases, object-oriented databases) and unstructured data (e.g., sound, image files, etc.). Semi-structured data is a form of structured data, but it does not conform to the data model structure associated with relational databases or other forms of data tables, but contains relevant tags to separate semantic elements and to layer records and fields. It is therefore also referred to as a self-describing structure.

Standardized data refers to data that is organized in a uniformly defined manner by processing structured data, unstructured data, and semi-structured data.

The inventors have discovered that with the continued development of capital and economic markets, a large number of credit bodies are generated in the financial field, including market trading, investment trading, and the like. The credit body comprises organization bodies such as banks, enterprises, investment companies and security companies, and also comprises character bodies such as enterprise high-level governments and investors. The credit principals have complex credit association relationships, so that when some credit principal or some credit principals have low credit or lose credit, the probability of the credit risk event faced by other closely related principals is increased. Therefore, the problem of how to effectively and accurately evaluate enterprise risks and analyze the propagation of risks in a credit relationship network is noticed by the inventor.

The inventor also finds that the traditional risk early warning method can only provide early warning for a single enterprise, and only considers the single-layer incidence relation of the enterprise. However, with the commercial change of the economic market and the financial innovation of the scientific and technological market, the technical means of artificial intelligence, big data, cloud computing and the like are continuously merged with the penetration of the financial field. Credit entities such as companies and natural people form an intricate relationship network, and the data volume contained behind the relationship network is huge, so that effective analysis cannot be performed through a traditional tool. The knowledge graph is used as a novel artificial intelligence method and gradually plays a role in the fields of risk prediction, anti-fraud and the like. The enterprise map is a concrete implementation of the knowledge map in the financial field, and is a vertical domain knowledge map for describing the relationship among enterprises.

Moreover, risks are often conducted by the associated enterprise of the trusted party. Therefore, the inventor thinks that the financial field also needs to analyze the risk of the enterprise related to the enterprise to be evaluated based on the enterprise map, establish a credit relationship mining model, and improve the pre-judging capability of the organizations such as banks for the operation risk.

Therefore, the inventor provides a risk assessment method combining an enterprise map, after a default event of a public enterprise is obtained, the influence generated by the event is analyzed, particularly other enterprises closely related to the event are analyzed, and risk early warning of the related enterprises of the enterprise to be assessed can be provided through the enterprise map. The method for evaluating the risks by combining the enterprise map can fully utilize the multilayer associated information of the enterprise map, considers the propagation characteristics of the risks in the enterprise related network formed by the enterprise map, analyzes the credit qualification of the enterprise associated with the enterprise to be evaluated, judges whether the enterprise to be evaluated is closely associated with the enterprise with low credit, and further quickly and efficiently analyzes the risk condition of the enterprise to be evaluated.

Moreover, the inventor also provides that when the enterprise risk to be evaluated is evaluated by using the enterprise map, the risk influence of the enterprise associated with the enterprise to be evaluated can be calculated by accumulation of the product of the risk of the associated enterprise and the risk influence factor calculated by using the enterprise map, compared with the technical model which has more parameters and large calculation amount and does not have the capability of performing incremental updating on incremental data, the method provided by the inventor can calculate the incremental information, and is convenient for fast model iteration. The influence of the risk of the associated enterprise on the risk assessment result of the enterprise to be assessed can be more reliably estimated by comprehensively considering the self risk of the associated enterprise, for example, the influence of the self attribute of the associated enterprise or the historical risk of the associated enterprise in various aspects.

In order to solve the problems of the prior art, embodiments of the present application provide a risk assessment method, apparatus, device, and computer storage medium. First, a risk assessment method provided by the embodiment of the present application is described below.

Fig. 1 illustrates a risk assessment method provided in an embodiment of the present application, where the method includes:

s110, acquiring risk assessment data of an object to be assessed, wherein the risk assessment data comprises self attribute information and investment data of the object to be assessed.

And S120, acquiring a target association graph related to the object to be evaluated from at least one knowledge graph according to the risk evaluation data, wherein the knowledge graph is an association path graph constructed according to the object to be evaluated, the association object having an investment relationship with the object to be evaluated and the investment relationship.

S130, determining a first risk assessment value of a risk assessment result of the associated object influencing the object to be assessed according to the target associated map and the risk assessment data of the associated object.

S140, determining a risk assessment value of the object to be assessed according to the first risk assessment value and a second risk assessment value of the object to be assessed, wherein the second risk assessment value is the risk assessment value determined according to risk assessment data of the object to be assessed.

In the embodiment of the present application, the risk assessment value of the object to be assessed is a result of assessment determination based on the first risk assessment value and the second risk assessment value. The first risk assessment value is a value obtained by integrating a target association map and risk assessment data of the associated object, the target association map is a map reflecting risk influence of the associated object on the object to be assessed in the target association map, and the risk assessment data of the associated object and the target association map reflect the risk influence of the risk of the associated object on the object to be assessed. The first risk assessment value obtained by integrating the risk assessment data of the associated object and the target associated map comprehensively considers the risk influence of the self risk of the associated object after the self risk of the associated object is transmitted to the object to be assessed in the target associated map, measures the influence of the associated object on the object to be assessed, and improves the accuracy of calculating the influence of the associated object on the risk assessment result of the object to be assessed. The second risk assessment value is obtained from the risk assessment data of the assessment object itself, and is an assessment result regarding the risk of the object to be assessed itself. Therefore, the evaluation result obtained based on the first risk evaluation value and the second risk evaluation value comprehensively considers the risk influence factor of the associated object after the self risk of the associated object is transmitted to the object to be evaluated in the target associated map and the risk influence factor of the object to be evaluated, and improves the accuracy of calculating the influence of the associated object on the risk evaluation result of the object to be evaluated and the accuracy of the risk evaluation result of the object to be evaluated.

The above steps are described in detail below.

In S110, specifically, the investment data of the object to be evaluated is obtained according to the own attribute information of the object to be evaluated, and the data including the own attribute information of the object to be evaluated and the investment data is used as the risk assessment data of the object to be evaluated.

In one embodiment, the investment data may include invested data and associated transactional data. The self attribute information may include, but is not limited to, business registration information of the enterprise, historical credit risk information of the enterprise, and key persona information of the enterprise.

In one embodiment, the business registration information may include, but is not limited to, at least one of business name, business registration capital, business status, and fulfillment date. The enterprise historical credit risk information may include, but is not limited to, at least one of list information of enterprises in which the company is listed as heavily distrusted illegal, enterprise abnormal operation information, illegal behavior information, administrative penalty information, and credit default information. The administrative penalty information may include, but is not limited to, at least one of the number of times the enterprise is advertised, the number of times the enterprise is opened, the number of times the enterprise is administered, the category of the enterprise is administered, and the strength of the enterprise is administered. The enterprise key persona information may include at least one of high-level manager information and stakeholder information of the enterprise. The senior manager information may include, but is not limited to, senior manager identification information and credit rating information, and the shareholder information may include, but is not limited to, shareholder identification information and credit rating information. The credit evaluation information may include, but is not limited to, at least one of character performed loss information, restricted consumption information, restricted travel information, and possession black asset information.

The specific description above for S110 is described below for S120.

In S120, specifically, by inputting a search instruction including risk assessment data of the object to be assessed, a knowledge graph including the object to be assessed is found, and the knowledge graph including the object to be assessed is taken as a target association graph.

Illustratively, when the object to be evaluated is an enterprise, the enterprise name of the object is enterprise a, the registered capital is 2000 ten thousand yuan, the investment proportion of the object to enterprise B is 15%, and the database for creating the key path graph is a Neo4j graph database, a node with the enterprise name of enterprise a, the registered capital of 2000 ten thousand yuan and the investment proportion of enterprise B of 15% is queried by using a query language supported by the Neo4j graph database, and the knowledge graph including the node is used as the target association graph of enterprise a.

In order to analyze the risk propagation characteristics of the associated object and further improve the accuracy of the evaluation result of the object to be evaluated, in an embodiment, as shown in fig. 2, another risk evaluation method provided in an embodiment of the present application may further include, before obtaining a target association map associated with the object to be evaluated, the method further includes:

s210, using the object as a node, wherein the node is used for storing risk assessment data of the object.

S220, using the investment relation between the objects as the connection line between the nodes, wherein the investment relation is determined according to the risk assessment data of the objects.

And S230, forming the associated path graph by the object and the connecting line.

In the embodiment of the application, the associated path graph is formed by taking objects as nodes and investment relations between the objects as connecting lines, and the nodes also store the risk investment data of each object, and is a path graph which takes the investment relations between the objects and the attributes of the objects into consideration, takes the investment relations between the objects as the connecting lines, reflects the degree of closeness of the relations between the objects, and further reflects risk propagation between the nodes. When one or more nodes are at risk, the risk retransmission characteristics of the occurring risks in the graph can be analyzed through the associated path graph, so that the influence of the risks on other nodes can be measured, and the accuracy of the evaluation result of the object to be evaluated can be further improved.

Details of S210-S230 are described below.

In S210, specifically, an N-dimensional feature vector that can characterize each object is extracted from the risk assessment data of the object, and the N-dimensional vector is used as a node.

Illustratively, when using the Neo4j graph database, if the risk assessment data of the objects conform to the requirements of the data structure in the database, directly importing the risk assessment data of each object into the database; and if the risk assessment data of the objects do not accord with the data structure requirement in the database, preprocessing the risk assessment data to guide the risk assessment data to accord with the data structure requirement of the database, and then importing the risk assessment data of each object into the database. The specific introduction method is not limited in the present application. Illustratively, the risk assessment data for each object may be read by writing program code compatible with the Neo4j database.

Illustratively, when using the Neo4j graph database, a node is first created, and then from the processed risk assessment data for each object, the object's own attribute information is added to the node as an N-dimensional feature vector characterizing each object. Nodes can be viewed, added, modified, and deleted in the Neo4j graph database.

In order to construct the association path graph more efficiently, in an embodiment, as an example graph of a flow of a risk assessment method provided by an embodiment of the present application shown in fig. 3, before an object is used as a node, the method may further include:

s310, determining the object according to the standardized risk assessment data.

Specifically, the self attribute value of each object is labeled through self attribute information in the standardized risk assessment data of each object, so that an N-dimensional feature vector capable of representing the object is obtained, and the N-dimensional vector represents the object.

Illustratively, when using the Neo4j graph database, each node capable of characterizing an object is initialized by normalizing risk assessment data, a node is first created, and then different self-attribute information of each object is added to the corresponding attribute under the node, which may be an N-dimensional feature vector characterizing the object, representing a specific object.

S320, determining the investment relation among the objects according to the standardized risk assessment data.

Specifically, the investment attribute between the objects is obtained through the investment data in the standardized risk assessment data of each object, and the investment attribute is used as the investment relationship.

In one embodiment, the investment attribute may include a proportion of investment, it being understood that the share proportion is 100% (per shareholder funding/total investment) and the share proportion is also a proportion of investment, according to a share proportion calculation formula.

In the embodiment of the application, the objects and the investment relationship among the objects are determined according to clean and clear standardized risk assessment data, so that the determination efficiency of determining the objects and the investment relationship among the objects is improved, and the efficiency of constructing the association path graph is further improved.

In order to more efficiently utilize the risk assessment data of the object, in an embodiment, as an exemplary flowchart of a risk assessment method provided in an embodiment of the present application shown in fig. 4, before the object is used as a node, the method may further include:

s410, preprocessing the risk assessment data of the object to obtain standardized risk assessment data of deleting repeated information and supplementing missing information.

Specifically, data cleaning and preprocessing operations are carried out on structured data and semi-structured data in risk assessment data to obtain data which are deleted of repeated information and supplemented of missing information and organized in a unified definition mode, and the obtained data are gathered into a data pool; and analyzing and extracting unstructured data in the risk assessment data by using a natural language processing algorithm to obtain data which is organized in a unified definition mode and deletes repeated information and supplements missing information, and importing the obtained standardized data into a data pool.

In the embodiment of the application, the risk assessment data of the object is processed into the standardized risk assessment data after the repeated information is deleted and the missing information is supplemented, the risk assessment data of the object is processed into the data organized in a unified definition mode, the data can be directly processed or utilized, and the utilization efficiency of the risk assessment data is improved.

The above is a specific description of S210.

In S220, specifically, a specific investment attribute between the objects is obtained according to the investment data in the risk assessment data of each object, the investment attribute is used as an attribute of the relationship to form an investment relationship between the objects, and the created nodes are connected by the investment relationship.

Illustratively, when using the Neo4j graph database, a relationship between two nodes is first created, the investment proportions between objects derived from the processed risk assessment data are labeled in the created relationship, and as an attribute of the relationship, the relationship with the attribute as a complete investment relationship can connect the nodes representing the objects.

It should be noted that, in the embodiment of the present application, the creation order of the nodes and the relationships is not limited, the nodes may be created according to the risk assessment data of each object first and then the relationships connecting the nodes are created, or the nodes and the relationships may be created simultaneously according to the risk assessment data of each object.

In S230, specifically, the nodes are connected by investment relations until the nodes are connected by one or more investment relations and there is no independent node, and one completes creation of the associated path graph.

The specific description above for S120 is described below for S130.

In S130, specifically, the self risk assessment value of the associated object is calculated from the risk assessment data of the associated object, and the first risk assessment value is determined from the environment in which the associated object is located in the target association map in consideration of the propagation influence of the risk of the associated object on the risk assessment result of the object to be assessed.

In order to accurately measure the influence of the risk of the associated object on the risk assessment result of the object to be assessed, in an embodiment, as shown in fig. 5, a flowchart of another risk assessment method provided in an embodiment of the present application, where the determining, according to the risk assessment data of the target association map and the associated object, a first risk assessment value of the risk assessment result of the associated object influencing the object to be assessed may include:

s131, determining at least one target path between the object to be evaluated and the associated object from the target associated map according to the investment relation.

S132, determining a first risk influence factor of the associated object influencing the risk evaluation result of the object to be evaluated according to the target path.

S133, respectively determining the self risk assessment value of the associated object and a second risk influence factor of the risk assessment value of the associated object influencing the risk assessment result of the object to be assessed according to the risk assessment data of the associated object.

S134, determining a first risk assessment value of the object to be assessed according to the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor.

In the embodiment of the application, the first risk influence factor is determined through a target path in the target association map, the characteristic that the risk of the associated object propagates along the target path in the target association map is considered, the second risk influence factor is obtained according to the self risk evaluation value of the associated object, and the risk influence of the risk of the associated object on the object to be evaluated is considered. The first risk assessment value after integrating the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor considers the risk influence of the self risk of the associated object after being transmitted to the object to be assessed in the target associated map, considers the propagation characteristic of the risk besides the risk self, and improves the accuracy of measuring the influence of the risk of the associated object on the risk assessment result of the object to be assessed.

S131-S134 are described in detail below.

In S131, specifically, with the node of the object to be evaluated as a starting point, the node of the associated object, which forms a connection path with the node of the object to be evaluated in an investment relationship, is searched for. And taking the nodes of the object to be evaluated, the nodes of the associated object and the connecting lines between the nodes as associated paths. And selecting at least one associated path as a target path.

Illustratively, taking the node enterprise 1 of the object to be evaluated as a starting point, finding out the connection path between the nodes of the associated object which forms the connection path with the enterprise 1 by the investment relationship as "enterprise 1-investment ratio 0.4-enterprise 3-investment ratio 0.3-enterprise 2" and "enterprise 1-investment ratio 0.2-enterprise 2". At least one of enterprise 1, investment proportion 0.2, enterprise 2, enterprise 1, investment proportion 0.4, enterprise 3, investment proportion 0.3, enterprise 2 and enterprise 1, investment proportion 0.4 and enterprise 3 is selected as a target path.

In S132, specifically, the magnitude of the first risk influence factor is cooperatively influenced by the target path between the object to be evaluated and the associated object and the target association map as a whole.

In order to further improve the calculation accuracy of the influence of the associated object on the risk assessment result of the object to be assessed, in an embodiment, as shown in fig. 6, in an embodiment, the target association graph includes at least one connection path between the objects, the connection path includes at least one path segment, the path segment includes two nodes and one investment relationship, the number of the path segments in the target path does not exceed a first threshold,

the determining, according to the target path, a first risk influencing factor by which the associated object influences a risk assessment result of the object to be assessed may include,

for each of the target paths:

s1321, determining a first path influence factor of the associated object on the object to be evaluated according to the number of the path segments in the target path.

S1322, determining a second path influence factor of the associated object on the object to be evaluated according to the number of the path segments in the target path and the number of the path segments in the target associated map.

S1323, determining an investment influence factor of the associated object on the object to be evaluated according to the investment relation and the target path.

S1324, determining the product of the first path influence factor, the second path influence factor and the investment influence factor as the first risk influence factor.

In the embodiment of the application, the first risk influence factor is an influence factor which comprehensively considers the first path influence factor, the second path influence factor and the investment influence factor. The first path influence factor is an influence factor obtained by considering the distance between the associated object and the object to be evaluated, and reflects the propagation characteristic of the risk of the associated object. The second path influence factor is an influence factor obtained by considering the influence of the associated object in the target associated map, and reflects the propagation characteristic of the risk of the associated object more accurately by combining the first path influence factor. The investment influence factor is the influence of the investment relation on the risk evaluation result of the object to be evaluated, and the first risk influence factor obtained by combining the first path influence factor and the second path influence factor comprehensively considers the risk influence and the risk propagation characteristic of the associated object and the influence brought by the investment relation between the associated object and the object to be evaluated, so that the accuracy and the reliability of the calculation of the influence of the associated object on the risk evaluation result of the object to be evaluated are further improved.

Details of S1321-S1324 are described below.

In S1321, specifically, the size of the number of path segments in the target path is inversely proportional to the size of the first path influence factor. The smaller the number of the path segments in the target path is, the closer the associated object is to the object to be evaluated, the greater the influence of the risk evaluation result of the object to be evaluated is, the greater the first path influence factor is, and vice versa.

Furthermore, as mentioned above, the target path is an associated path having a number of path segments smaller than the first threshold. The first threshold value may be selected according to actual conditions.

In order to reduce operations while fully utilizing the association information among the multilayer objects in the target association map, and avoid exponential increase of the calculation amount with the increase of the scale and complexity of the target association map, in one embodiment, the first threshold is set to be 3.

Illustratively, when the association path between the enterprise 4 to be evaluated and the enterprise 5 to be evaluated is "enterprise 4 — investment ratio 0.2 — enterprise 5" and "enterprise 4 — investment ratio 0.3 — enterprise 6 — investment ratio 0.2 — enterprise 7 — investment ratio 0.1 — enterprise 8 — investment ratio 0.3 — enterprise 5", the association path "enterprise 4 — investment ratio 0.2 — enterprise 5" with the number of path segments less than or equal to 3 is selected as the target path.

In order to improve the accuracy of quantifying the influence of the associated object on the risk assessment result of the object to be assessed, in an embodiment, the determining, according to the number of the path segments in the target path, a first path influence factor of the associated object on the object to be assessed may include,

Specifically, the number of the path segments in the target path is recorded as x, and the first preset value is recorded as α_distanceThe first path influence factor is calculated according to equation 1.

α_distance ^xFormula 1

In one embodiment, α_distanceMay take 0.618.

Exemplary, α_distanceTaking 0.618, when the target path between the enterprise 4 to be evaluated and the enterprise 5 to be associated is "enterprise 4-investment ratio 0.2-enterprise 5", the first path influence factor of the risk evaluation result of the enterprise 4 to be evaluated by the enterprise 5 to be associated is 0.618¹。

In the embodiment of the application, the number of the path segments in the target path represents the closeness degree of the association relationship between the objects to a certain extent, the longer the path from the associated object with the risk possibly occurring, that is, the larger the number of the path segments of the object to be evaluated, the weaker the influence of the associated object is, and the influence is exponentially reduced as the number of the path segments in the target path is larger, so that the influence of the associated object on the object to be evaluated is better described, and the accuracy of calculation of the influence of the associated object on the risk evaluation result of the object to be evaluated is improved.

The above is a specific description of S1321, and S1322 is described below.

In S1322, specifically, the size of the second path influence factor is influenced by both the size of the number of path segments in the target path and the size of the number of path segments in the target association map, the size of the second path influence factor is directly proportional to the size of the number of path segments in the target path, and the size of the second path influence factor is inversely proportional to the size of the number of path segments in the target association map.

The inventor thinks that the definition of the node degree refers to the number of entities which have path connection with the current node in the graph relation network. For example, if there is an edge connection between the current node y and the associated node i, a child node degree between the previous node y and the associated node i is d (i, y) ═ 1, and if there is no connection, it is 0, where the relationship d represents the child node degree. The node degree of the current node y is expressed as

Wherein n is the total number of all nodes associated with the current node y in a certain graph relation network. Then, the node degree can indicate the association relationship between the current node y and other nodes in a certain graph relation network.

Therefore, the inventor proposes that in the target association graph, the ratio of the node degree of the object to be evaluated to the total number of path segments in the target association graph is used as a node degree influence factor, namely a second path influence factor, so that the node degree influence factor can be reflected in the target association graph which takes the investment relation as a connecting line and represents that investment behaviors or transaction behaviors exist between a certain object and other objects. When the second path influence factor is larger, more investment behaviors or transaction behaviors are assumed to exist between the certain object and other objects, and correspondingly, the influence is larger or more easily influenced by other objects.

Therefore, the accuracy of calculation of influence of the associated object on the risk assessment result of the object to be assessed is improved. In one embodiment, determining the second path influence factor of the associated object on the object to be evaluated may include:

and calculating the sum of the number of the path segments in the target path.

Specifically, the number of path segments in the target path between the evaluation object and each associated object is added to serve as the node degree of the object to be evaluated.

Specifically, the sum of the number of the path segments in the target path calculated in the previous step is compared with the number of the path segments in the target association map, and the obtained ratio is used as a second path influence factor.

It should be noted that the form of the comparison value in the embodiments of the present application is not limited, and the ratio may be a fraction, a decimal or a percentage.

Illustratively, if the sum of the number of path segments of the target path, each of which has the number of path segments not exceeding 3, is 40, and the number of path segments in the target association map is 100, then the second path influence factor is equal to 0.4.

In the embodiment of the application, the second path influence factor is a ratio of a sum of the number of the path segments in the target path to the total number of the paths of the target association map, and is a risk influence factor which embodies influence of the associated object and influence possibility of the object to be evaluated. For example, when the sum of the number of path segments in the target path is larger, it indicates that the more related objects are connected to the object to be evaluated, the more easily the object to be evaluated is affected by the related objects. When the ratio of the total number of the path segments in the target path to the total number of the paths of the target association map is larger, the influence of the association object on the evaluation object is larger, and the influence of the association object is reflected.

The above is a specific description of S1322, and S1323 is described below.

In S1323, specifically, the investment impact factor is affected by the investment relation and the target path, and when the investment proportion is larger, the smaller the number of path segments of the target path is, the larger the investment impact factor is, and vice versa.

In order to improve the accuracy of measuring the influence of the associated object on the risk assessment result of the object to be assessed, in one embodiment, the investment relation comprises the investment proportion between the object to be assessed and the associated object,

determining the investment impact factor of the associated object on the object to be evaluated according to the investment relation and the target path may include,

in particular, the magnitude of the first investment impact factor is influenced by a magnitude relationship between the investment proportion and the second threshold.

In one embodiment, the determining the first investment impact factor corresponding to each path segment in the target path according to the size relationship between the investment proportion and the second threshold may include,

determining the investment proportion as the first investment impact factor when the investment proportion is less than a second threshold.

Specifically, the selection of the second threshold and the second preset value varies according to actual conditions, in the embodiment of the present application, the second threshold is equal to 0.5, the second preset value is equal to 1 as an example, and when the proportion of the investment amount of the related object to the object to be evaluated in the total investment amount is less than 0.5, the first investment impact factor is the investment proportion between the objects. When the proportion of the investment amount of the associated object to the object to be evaluated in the total investment amount is greater than or equal to 0.5, the first investment influence factor is 1.

In the embodiment of the application, when the first investment influence factor is the investment proportion, the influence of the investment relation between the objects on the objects is intuitively reflected. And when the investment proportion is larger than a second threshold value, the first investment influence factor takes a second preset numerical value, and the influence degree of the object with the larger payment acceptance investment proportion on the related object is reflected to be far larger than that of other objects with the payment acceptance investment proportion smaller than the second threshold value. Different influence degrees of the investment proportion on the object are considered, and the accuracy of calculating the influence of the associated object on the risk evaluation result of the object to be evaluated is improved.

And when the target path comprises a plurality of path segments, determining the product of the first investment influence factors corresponding to the path segments in the target path as the investment influence factor.

Illustratively, one target path between the enterprise 6 to be evaluated and the enterprise 7 to be associated is "enterprise 6 — investment ratio 0.4 — enterprise 3 — investment ratio 0.5 — enterprise 7", and then the enterprise 7 to be associated has an investment impact factor of 0.4 × 1 — 0.4 for the enterprise 6 to be evaluated.

Illustratively, one target path between the enterprise 4 to be evaluated and the enterprise 5 to be associated is "enterprise 4 — investment proportion 0.2 — enterprise 5", and then the enterprise 4 to be evaluated is affected by the enterprise 5 to be associated with an investment of 0.2.

In the embodiment of the application, the influence of the investment proportion on the object to be evaluated is considered, the determination of the investment influence factor is related to the second threshold value and the number of the path segments in the target path, the propagation effect of the investment proportion in the target path is considered, and the accuracy of measuring the influence of the associated object on the risk evaluation result of the object to be evaluated is improved.

In S1324, in particular, the first risk influencing factor is the first path influencing factor and the second path influencing factor is the investment influencing factor.

The above is a specific description of S132, and S133 is described below.

In S133, specifically, a calculator for calculating the risk assessment value of the object is pre-trained by using the historical risk assessment data of the object and using a machine learning random Gradient Regression (SGD Regression) algorithm. When the risk value of the object is evaluated, the risk evaluation value of the object and a second risk influence factor of the risk evaluation value of the object influencing the risk evaluation results of other objects are obtained by calculation of the calculator. And inputting the risk assessment data of the associated object into a calculator to obtain a self risk assessment value of the associated object and a second risk influence factor of the risk assessment value of the associated object influencing the risk assessment result of the object to be assessed.

In S134, specifically, the first risk assessment value is the maximum value of the sum of the products of the own risk assessment value, the first risk influence factor, and the second risk influence factor of each of the related objects related to the object to be assessed.

In order to improve the iteration speed of calculating the influence of the associated object on the risk assessment result of the object to be assessed, in an embodiment, as shown in fig. 7, a further schematic flow chart of the risk assessment method provided in an embodiment of the present application, the determining, according to the risk assessment data of the target association map and the associated object, a first risk assessment value of the risk assessment result of the associated object influencing the object to be assessed may include:

s1341, for each associated object, calculating a first risk influence value of a risk evaluation result that the associated object influences the object to be evaluated according to the own risk evaluation value of the associated object, the first risk influence factor, and the second risk influence factor.

S1342, determining the sum of the first risk impact values as the first risk assessment value.

In the embodiment of the present application, the first risk influence value is an influence value of a risk evaluation result of each associated object to an object to be evaluated, and the first risk evaluation value is a sum of the first risk influence values. For the newly added associated object, the first risk influence value of the newly added associated object is added to the previously calculated first risk assessment value, so that a new first risk assessment value can be obtained. That is to say, the calculation of the first risk assessment value is additive, and for the newly added associated object, only the influence value of the newly added associated object on the risk assessment result of the object to be assessed and the influence value of the newly added associated object as the source node on the risk assessment results of other associated objects having an investment relationship with the newly added associated object need to be calculated. For the newly added risk of the associated object, only the influence value of the risk evaluation result of the object to be evaluated of the risk needs to be calculated, and the newly added influence value is accumulated into the original risk evaluation value of the object to be evaluated. That is to say, the first risk influence values of all the associated objects do not need to be calculated again for the newly added data, so that the situation that the total calculation is carried out again after incremental data exists is avoided, and the iteration speed of calculating the influence of the associated objects on the risk evaluation result of the object to be evaluated is increased.

S1341-S1342 are described in detail below.

In S1341, specifically, a maximum value of an influence of each associated object having a target path with the object to be evaluated on the object to be evaluated is calculated, and the maximum value is used as a final value of a risk evaluation result that the associated object influences the object to be evaluated, that is, a first risk influence value.

In order to improve the accuracy of calculating the influence value of the associated object on the risk assessment result of the object to be assessed, and at the same time, facilitate processing of new data, in an embodiment, the calculating, for each associated object, a first risk influence value of the risk assessment result of the associated object on the object to be assessed according to the self risk assessment value of the associated object, the first risk influence factor, and the second risk influence factor may include,

when the target path is multiple, determining a product of the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor as a second risk influence value for each target path.

Specifically, the number of path segments in a target path between an object to be evaluated and an associated object is recorded as a, and the product of a first risk influence factor and a second risk influence factor is recorded as a risk influence factor c_adjustThe self risk assessment value of the related object is recorded as r_aiIndicates the target roadAnd self risk assessment value of the ith associated object in the path section a away from the object to be assessed. Second risk impact value r_ai*c_adjust. The method for ordering the associated objects is not limited in the embodiments of the present application.

And selecting the second risk influence value with the maximum value as the first risk influence value.

Specifically, the maximum value of the second risk influence value under each target path calculated in the previous step is taken as the first risk influence value.

Specifically, there is only one path between the associated object and the object to be evaluated, and the first risk impact value is equal to the product of the first risk impact factor, the second risk impact factor, and the own risk assessment value of the associated object, where the risk assessment result of the object to be evaluated is affected by the associated object.

In the embodiment of the application, when a plurality of target paths exist, the first risk influence value is the maximum value of the product of the self risk evaluation value of each associated object, the first risk influence factor and the second risk influence factor, the highest risk influence is considered, and the accuracy of calculating the influence value of the associated object on the risk evaluation result of the associated object is improved.

The above is a specific description of S1341, and S152 is described below.

In S1342, specifically, the sum of the first risk influence values of each of the associated objects having the target path therebetween with the object to be evaluated calculated in the previous step is taken as the first risk assessment value. Let the first risk assessment value be R, let the maximum value of the number of path segments in the target path be z, and the first risk assessment value be R, which can be expressed by equation 2. In formula 2, r_ki*c_adjustRepresenting a first risk influence value, r_kiA self risk assessment value representing the ith associated object in the target path from the kth path segment of the object to be assessed,

representing the sum of the first risk impact values of the associated objects involved in all target paths. Equation 2 may also be understood as calculating a sum of products of the risk assessment value of the ith associated object and the risk influence factor of the kth path segment from the object to be assessed in the target path until the product of the risk assessment value of the last associated object and the risk influence factor of the zth path segment from the object to be assessed in the target path is accumulated.

Illustratively, as mentioned above, in the embodiment of the present application, the number of path segments of the target path does not exceed the first threshold, and in the embodiment of the present application, when the first threshold is equal to 3 as an example, the first risk assessment value R is,

the above is a specific description of S130.

In S140, specifically, the risk assessment data of the object to be assessed is input to the calculator described in S133, a second risk assessment value of the object to be assessed is obtained, and the first risk assessment value and the second risk assessment value are added to obtain a risk assessment value of the object to be assessed.

In an application scenario, firstly, credit data of an enterprise, namely risk assessment data, is obtained, structured, semi-structured and unstructured data in the credit data are processed by using a Python programming language, and the processed credit data are imported into a data pool;

secondly, constructing an enterprise map, namely a target association map, creating nodes and relations by using a Neo4j map database, initializing each enterprise node in the enterprise map by using the previously acquired credit data, connecting the enterprise nodes according to the investment relations among the enterprises, and labeling the relations and the attributes of the nodes in the enterprise map according to the attribute information of the enterprises in the credit data of the enterprises and the investment data;

and then carrying out enterprise risk assessment. The risk is propagated along each path in the enterprise graph by taking a certain node in the enterprise graph as an initial point, the risk influence value of each node is calculated, the credit risk assessment value of a certain enterprise is finally obtained, and a program product for calculating the risk influence value of each node by using the enterprise graph can be written by using a Python programming language.

Based on the risk assessment method provided by any one of the embodiments, the application further provides an embodiment of a risk assessment device. See in particular fig. 8.

Fig. 8 shows a schematic view of a risk assessment apparatus according to an embodiment of the present application. As shown in fig. 8, the apparatus may include:

a first obtaining module 810, configured to obtain risk assessment data of an object to be assessed, where the risk assessment data includes attribute information of the object to be assessed and investment data;

a second obtaining module 820, configured to obtain a target association graph related to the object to be evaluated from at least one knowledge graph according to the risk assessment data, where the knowledge graph is an association path graph constructed according to the object to be evaluated, an association object having an investment relationship with the object to be evaluated, and the investment relationship;

a first determining module 830, configured to determine, according to the target association map and the risk assessment data of the associated object, a first risk assessment value of a risk assessment result that the associated object affects the object to be assessed;

a second determining module 840, configured to determine a risk assessment value of the object to be assessed according to the first risk assessment value and a second risk assessment value of the object to be assessed, where the second risk assessment value is determined according to risk assessment data of the object to be assessed.

In the apparatus of the embodiment of the application, the risk assessment value of the object to be assessed is a result of assessment determination according to the first risk assessment value and the second risk assessment value. The first risk assessment value is a value obtained by integrating a target association map and risk assessment data of the associated object, the target association map is a map reflecting risk influence of the associated object on the object to be assessed in the target association map, and the risk assessment data of the associated object and the target association map reflect the risk influence of the risk of the associated object on the object to be assessed. The first risk assessment value obtained by integrating the risk assessment data of the associated object and the target associated map comprehensively considers the risk influence of the self risk of the associated object after the self risk of the associated object is transmitted to the object to be assessed in the target associated map, measures the influence of the associated object on the object to be assessed, and improves the accuracy of calculating the influence of the associated object on the risk assessment result of the object to be assessed. The second risk assessment value is obtained from the risk assessment data of the assessment object itself, and is an assessment result regarding the risk of the object to be assessed itself. Therefore, the evaluation result obtained based on the first risk evaluation value and the second risk evaluation value comprehensively considers the risk influence factor of the associated object after the self risk of the associated object is transmitted to the object to be evaluated in the target associated map and the risk influence factor of the object to be evaluated, and improves the accuracy of calculating the influence of the associated object on the risk evaluation result of the object to be evaluated and the accuracy of the risk evaluation result of the object to be evaluated.

In an embodiment, before obtaining the target association map related to the object to be evaluated, the second obtaining module 820 may further include:

the first sub-module is used for taking an object as a node, wherein the node is used for storing risk assessment data of the object.

And the second sub-module is used for using the investment relation between the objects as the connecting line between the nodes, wherein the investment relation is determined according to the risk assessment data of the objects.

A forming submodule for forming the associated path diagram by the object and the connecting line

In the embodiment of the application, the associated path graph formed by interaction of the modules is formed by taking objects as nodes and taking investment relations between the objects as connecting lines, and the nodes also store the risk investment data of each object, and is a path graph considering the investment relations between the objects and the attributes of the objects, and the investment relations between the objects are taken as the connecting lines to reflect the degree of closeness of the relations between the objects, so as to reflect risk propagation between the nodes. When one or more nodes are at risk, the risk retransmission characteristics of the occurring risks in the graph can be analyzed through the associated path graph, so that the influence of the risks on other nodes can be measured, and the accuracy of the evaluation result of the object to be evaluated can be further improved.

In an embodiment, before the object is used as the node, the first sub-module may further include:

a first determination unit for determining the object based on the standardized risk assessment data.

A second determination unit for determining an investment relationship between the objects based on the standardized risk assessment data.

In the embodiment of the application, the units interact with each other to ensure that the investment relationship between the objects is determined according to clean and clear standardized risk assessment data, so that the determination efficiency of determining the investment relationship between the objects is improved, and the efficiency of constructing the association path graph is further improved.

In one embodiment, the first sub-module may further include:

and the preprocessing unit is used for preprocessing the risk assessment data of the object to obtain standardized risk assessment data for deleting repeated information and supplementing missing information.

In the embodiment of the application, the preprocessing unit processes the risk assessment data of the object into the standardized risk assessment data after deleting repeated information and supplementing missing information, and processes the risk assessment data of the object into the data organized in a unified definition mode, so that the data can be directly processed or utilized, and the utilization efficiency of the risk assessment data is improved.

In one embodiment, the first determining module 830 may include:

and the first determining submodule is used for determining at least one target path between the object to be evaluated and the associated object from the target associated map according to the investment relation.

And the second determining submodule is used for determining a first risk influence factor of the associated object influencing the risk evaluation result of the object to be evaluated according to the target path.

And the third determining submodule is used for respectively determining the self risk assessment value of the associated object and a second risk influence factor of the risk assessment value of the associated object influencing the risk assessment result of the object to be assessed according to the risk assessment data of the associated object.

And the fourth determining submodule is used for determining the first risk assessment value of the object to be assessed according to the self risk assessment value of the associated object, the first risk influence factor and the second risk influence factor.

In one embodiment, the target association graph includes at least one connection path between objects, the connection path includes at least one path segment, the path segment includes two nodes and one investment relation, the number of the path segments in the target path is less than a first threshold, the second determining submodule may include,

for each of the target paths:

and the third determining unit is used for determining the first path influence factor of the associated object on the object to be evaluated according to the number of the path segments in the target path.

And the fourth determining unit is used for determining a second path influence factor of the associated object on the object to be evaluated according to the number of the path segments in the target path and the number of the path segments in the target associated map.

And the fifth determining unit is used for determining the investment influence factor of the associated object on the object to be evaluated according to the investment relation and the target path.

A sixth determining unit, configured to determine a product of the first path impact factor, the second path impact factor, and the investment impact factor as the first risk impact factor.

In the embodiment of the application, the first risk influence factor is an influence factor which comprehensively considers the first path influence factor, the second path influence factor and the investment influence factor. The first path influence factor is an influence factor obtained by considering the distance between the associated object and the object to be evaluated, and reflects the propagation characteristic of the risk of the associated object. The second path influence factor is an influence factor obtained by considering the influence of the associated object in the target associated map, and reflects the propagation characteristic of the risk of the associated object more accurately by combining the first path influence factor. The investment influence factor is the influence of the investment relation on the risk evaluation result of the object to be evaluated, and the first risk influence factor obtained by combining the first path influence factor and the second path influence factor comprehensively considers the risk influence and the risk propagation characteristic of the associated object and the influence brought by the investment relation between the associated object and the object to be evaluated, so that the accuracy and the reliability of the calculation of the influence of the associated object on the risk evaluation result of the object to be evaluated are further improved. Moreover, the first risk influence factor is the product of the first path influence factor, the second path influence factor and the investment influence factor, when a new associated object is added, the first risk influence factor of the new associated object can be determined by the same method, parameters required by risk evaluation do not need to be calculated and estimated in a large scale, incremental data can be conveniently processed, and quick iteration can be realized.

In one embodiment, the third determining module 830 may include:

and a fifth determining submodule, configured to calculate, for each associated object, a first risk influence value of a risk evaluation result that the associated object affects the object to be evaluated, according to the self risk evaluation value of the associated object, the first risk influence factor, and the second risk influence factor.

A sixth determining sub-module for determining a sum of the first risk impact values as the first risk assessment value.

In the embodiment of the present application, the first risk influence value is an influence value of a risk evaluation result of each associated object to the object to be evaluated, and the first risk evaluation value is a sum of the first risk influence values. For the newly added associated object, the first risk influence value of the newly added associated object is added to the previously calculated first risk assessment value, so that a new first risk assessment value can be obtained. That is to say, the calculation of the first risk assessment value has an additive property, the first risk influence values of all the associated objects do not need to be calculated again for the newly added associated objects, the situation that the full-scale calculation is carried out again after incremental data exists is avoided, and the iteration speed of calculating the influence of the associated objects on the risk assessment result of the object to be assessed is improved.

In addition, in combination with the risk assessment method in the above embodiments, as shown in fig. 9, embodiments of the present application may provide a risk assessment apparatus, which may include a processor 910 and a memory 920 storing computer program instructions.

Specifically, the processor 910 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.

Memory 920 may include mass storage for data or instructions. By way of example, and not limitation, memory 920 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 920 may include removable or non-removable (or fixed) media, where appropriate. The memory 920 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 920 is non-volatile solid-state memory. In certain embodiments, memory 920 comprises Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.

The processor 910 may implement any one of the above-described methods for risk assessment by reading and executing computer program instructions stored in the memory 920.

In one example, the electronic device may also include a communication interface 930 and a bus 940. As shown in fig. 9, the processor 910, the memory 920, and the communication interface 930 are connected via a bus 940 to complete communication therebetween.

The communication interface 930 is mainly used to implement communication between modules, devices, units and/or devices in this embodiment.

The bus 940 includes hardware, software, or both to couple the components of the electronic device to one another. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 940 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

The risk assessment device may perform the risk assessment method in the embodiments of the present application, thereby implementing the risk assessment method described in any embodiment of the present application.

In addition, in combination with the above method for risk assessment, embodiments of the present application may provide a computer storage medium having computer program instructions stored thereon, which when executed by a processor, implement the risk assessment method of any of the above embodiments.

It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.

The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.

Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.

As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.

Claims

1. A method of risk assessment, comprising:

2. The method according to claim 1, wherein the determining a first risk assessment value of a risk assessment result that the associated object affects the object to be assessed according to the risk assessment data of the target association map and the associated object specifically comprises:

3. The method according to claim 1, further comprising, prior to obtaining a target association map associated with the subject to be evaluated:

4. The method of claim 3, wherein prior to having an object as a node, the method further comprises:

5. The method of any of claims 3-4, prior to having the object as a node, the method further comprising:

determining the subject from the standardized risk assessment data;

6. The method according to claim 2, wherein the determining a first risk assessment value of a risk assessment result that the associated object affects the object to be assessed according to the risk assessment data of the target association map and the associated object specifically comprises:

7. The method according to claim 6 or 2, wherein the calculating, for each of the associated objects, a first risk influence value of a risk evaluation result that the associated object influences the object to be evaluated according to the own risk evaluation value of the associated object, the first risk influence factor, and the second risk influence factor specifically includes:

8. The method according to claim 2 or 3, wherein the target association graph comprises at least one connection path between objects, the connection path comprising at least one path segment, the path segment comprising two of the nodes and one of the investment relations, the number of path segments in the target path not exceeding a first threshold,

for each of the target paths:

9. The method according to claim 8, wherein the determining, according to the number of the path segments in the target path, a first path impact factor of the associated object on the object to be evaluated specifically includes:

10. The method according to claim 8, wherein the determining a second path influence factor of the associated object on the object to be evaluated according to the number of the path segments in the target path and the total number of paths of the target association map specifically includes:

calculating the sum of the number of the path segments in the target path;

11. The method of claim 8, wherein the investment relationship comprises a proportion of investment,

12. The method according to claim 11, wherein the determining a first investment impact factor corresponding to each path segment in the target path according to a magnitude relationship between the investment ratio and a second threshold specifically includes:

13. A risk assessment device, characterized in that the device comprises:

14. A risk assessment device, characterized in that the device comprises: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements a risk assessment method according to any of claims 1-12.

15. A computer storage medium having computer program instructions stored thereon that, when executed by a processor, implement the risk assessment method of any one of claims 1-12.

16. A computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the risk assessment method according to any one of claims 1-12.