Intelligent decision support method based on knowledge graph driving

Abstract

The invention discloses an intelligent decision support method based on knowledge graph driving, and the method comprises the following steps: S100, computer equipment carries a financial decision model, and the financial decision model gives basic values to different financial entity nodes; s200, the computer equipment receives target entity information input by a visitor, finance entity nodes similar to the target entity information are retrieved in the finance knowledge graph, and a relation subgraph is generated; s300, performing risk identification and opportunity identification on the target entity node and the multi-hop path by the financial decision model; and S400, the financial decision model combines the basic value of the target entity node, the basic value of the financial entity node and the weight coefficient of the hop path to calculate a plurality of financial decision scores of the target entity node, and according to the intelligent decision support method, the financial decision scores of different financial entity nodes are analyzed, so that the decision support efficiency is improved. A multi-angle association scheme of target entity information can be provided for a visitor, and the visitor can make a financial decision with low risk.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to an intelligent decision support method based on knowledge graph driving. BACKGROUND

[0002] The development of Internet technology provides great convenience for the communication and interaction between financial entities and information disclosure, and can conveniently show the path relationship between multiple financial entities for investors and risk assessors, but for multiple financial entities with unexpressed indirect relationship and flow risk, the investors and risk assessors are difficult to see the control relationship and investment risk behind.

[0003] Therefore, the technical personnel in the field need an intelligent decision support method which can more intuitively understand the potential control relationship and risk of the target financial entity and other financial entities to overcome the above problems. SUMMARY

[0004] In view of the above situation, in order to overcome the defects of the prior art, the present application provides an intelligent decision support method based on knowledge graph driving, in order to solve the technical defects that it is difficult to understand the hidden control relationship and investment risk between financial entities, the present application creatively analyzes and outputs the financial decision scores of different financial entity nodes between interval multi-hop paths, can provide multi-angle correlation scheme of target entity information for visitors, facilitate visitors to identify the implicit control relationship and risk propagation path of target entity information, and is beneficial to visitors to make financial decisions with lower risk.

[0005] The technical scheme adopted by the present application is as follows:

[0006] The intelligent decision support method based on knowledge graph driving according to the embodiment of the present application comprises the following steps:

[0007] S100, a computer device is loaded with a financial decision model and constructs a financial knowledge graph comprising a plurality of financial entity nodes and a plurality of relationship edges, the financial entity nodes comprise at least two of a financial enterprise, a natural person, a financial product, a legal event and a financial index, the relationship edges comprise at least one of a control relationship, an investment relationship, a guarantee relationship, a related transaction relationship and a credit behavior relationship, the financial decision model gives a basic value to different financial entity nodes and gives a weight coefficient to different relationship edges;

[0008] S200, the computer device receives target entity information input by a visitor, searches the financial entity nodes similar to the target entity information in the financial knowledge graph and defines the financial entity nodes as target entity nodes, expands the semantic relationship of the target entity nodes, and generates a relationship subgraph comprising the financial entity nodes;

[0009] S300, the financial decision model performs risk identification and opportunity identification on the multi-hop path of the target entity node and other financial entity nodes in the relationship subgraph;

[0010] S400, the financial decision model combines the basic value of the target entity node, the basic value of the financial entity node with the multi-hop path, and the weight coefficient of the multi-hop path to calculate a plurality of financial decision scores of the target entity node, and outputs a graph path in the visual relationship subgraph and the corresponding financial decision score.

[0011] According to some embodiments of the present application, the financial decision model in S100 refers to the entity attributes of the financial entity nodes to assign basic values to them, and the entity attributes include at least one of credit rating, equity ratio, asset-liability ratio, litigation record, penalty record, supply chain status, and customer composition structure.

[0012] According to the intelligent decision support method of the present application, by analyzing and outputting the financial decision scores of different financial entity nodes between interval multi-hop paths, the visitor can be provided with a multi-angle correlation scheme of target entity information, which facilitates the visitor to identify the implicit control relationship and risk propagation path of the target entity information, and is beneficial to the visitor to make a financial decision with lower risk.

[0013] According to some embodiments of the present application, S300 comprises the following steps:

[0014] S301, the computer device accesses a financial database, and the financial decision model performs embedded learning on the multi-hop path of the target entity node;

[0015] S302, the financial decision model matches similar historical entities in the financial database according to the entity attributes of the target entity node, and identifies whether the target entity node and the relationship subgraph are of the same type structure;

[0016] S303, the financial decision model predicts the risk relationship edge and the opportunity relationship edge of the target entity node based on the knowledge graph evolution of the historical entities in the financial database.

[0017] According to some embodiments of the present application, the financial decision score is the total value of the product of the basic value of the financial entity node in the multi-hop path and the weight coefficient of the relationship edge, the weight coefficient is inversely proportional to the length of the relationship edge, and is proportional to the confidence of the relationship edge and the importance of the financial entity node.

[0018] According to some optional embodiments of the present application, when the visitor executes the instruction of deleting the relationship edge or merging the financial entity node on the relationship subgraph, the financial decision model adjusts the weight coefficient.

[0019] The application has the following beneficial effects by adopting the above structure:

[0020] (1) By analyzing and outputting the financial decision scores of different financial entity nodes between interval multi-hop paths, the visitor can be provided with a multi-angle correlation scheme of target entity information, which facilitates the visitor to identify the implicit control relationship and risk propagation path of the target entity information, and is conducive to the visitor to make a financial decision with lower risk.

[0021] Additional aspects and advantages of the present application will be described in the following description, some of which will become apparent from the following description, or will be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a flowchart of an intelligent decision support method based on knowledge graph driving according to some embodiments of the present application;

[0023] Figure 2 is a flowchart of part of the steps of an intelligent decision support method based on knowledge graph driving according to some embodiments of the present application.

[0024] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, and are used to explain the present application together with embodiments of the present application, and do not constitute a limitation on the present application. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0026] In the description of the present application, it should be understood that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0027] An intelligent decision support method based on knowledge graph driving according to an embodiment of the present application comprises the following steps:

[0028] S100, the computer device carries a financial decision model and constructs a financial knowledge graph comprising a plurality of financial entity nodes and a plurality of relationship edges, the financial entity nodes comprising at least two of a financial enterprise, a natural person, a financial product, a legal event and a financial indicator, the relationship edges comprising at least one of a control relationship, an investment relationship, a guarantee relationship, a related transaction relationship and a credit behavior relationship, the financial decision model assigning a basic value to different financial entity nodes and assigning a weight coefficient to different relationship edges;

[0029] S200, the computer device receives target entity information input by a visitor, retrieves a financial entity node similar to the target entity information in the financial knowledge graph and defines the financial entity node as a target entity node, performs semantic relationship expansion on the target entity node, and generates a relationship subgraph comprising the financial entity node;

[0030] S300, the financial decision model performs risk identification and opportunity identification on a multi-hop path of the target entity node and other financial entity nodes in the relationship subgraph;

[0031] S400, the financial decision model combines the basic value of the target entity node, the basic value of the financial entity node existing in the multi-hop path and the weight coefficient of the multi-hop path, calculates a plurality of financial decision scores of the target entity node, and outputs a graph path in the visualized relationship subgraph and the corresponding financial decision scores.

[0032] According to some embodiments of the present application, in S100, the financial decision model refers to the entity attributes of the financial entity nodes to assign basic values to the financial entity nodes, the entity attributes comprising at least one of a credit rating, a stock ownership ratio, an asset-liability ratio, a lawsuit record, a penalty record, a supply chain status and a customer composition structure.

[0033] According to the intelligent decision support method of the present application, by analyzing and outputting the financial decision scores of different financial entity nodes between the multi-hop paths, a multi-angle correlation scheme of the target entity information can be provided for the visitor, so that the visitor can identify the implicit control relationship and the risk propagation path of the target entity information, and the visitor can make a financial decision with low risk.

[0034] According to some embodiments of the present application, S300 comprises the following steps:

[0035] S301, the computer device accesses a financial database, and the financial decision model performs embedded learning on the multi-hop path of the target entity node;

[0036] S302, the financial decision model matches similar historical entities in the financial database according to the entity attributes of the target entity node, and identifies whether the target entity node and the relationship subgraph are of the same type of structure;

[0037] S303. The financial decision-making model is based on the evolution of the knowledge graph of historical entities in the financial database to predict the risk relationship edges and opportunity relationship edges of the target entity nodes.

[0038] According to some embodiments of the present invention, the financial decision score is the sum of the products of the basic values ​​of the financial entity nodes in the multi-hop path and the weight coefficients of the relation edges. The weight coefficients are inversely proportional to the length of the relation edges, directly proportional to the confidence level of the relation edges, and directly proportional to the importance of the financial entity nodes.

[0039] According to some optional embodiments of the present invention, when a visitor executes an instruction to delete a relation edge or merge a financial entity node on the relation subgraph, the financial decision model adjusts the weight coefficients.

[0040] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0041] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0042] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A knowledge graph driven intelligent decision support method, characterized in that, The method comprises the following steps: S100, a computer device carries a financial decision model and constructs a financial knowledge graph comprising a plurality of financial entity nodes and a plurality of relationship edges, the financial entity nodes comprising at least two of a financial enterprise, a natural person, a financial product, a legal event and a financial indicator, the relationship edges comprising at least one of a control relationship, an investment relationship, a guarantee relationship, a related transaction relationship and a credit behavior relationship, the financial decision model assigning a basic value to different financial entity nodes and assigning a weight coefficient to different relationship edges; S200, the computer device receives target entity information input by a visitor, retrieves the financial entity nodes similar to the target entity information in the financial knowledge graph and defines the financial entity nodes as target entity nodes, performs semantic relationship expansion on the target entity nodes, and generates a relationship subgraph comprising the financial entity nodes; S300, the financial decision model performs risk identification and opportunity identification on the multi-hop paths of the target entity nodes and other financial entity nodes in the relationship subgraph; S400, the financial decision model combines the basic value of the target entity nodes, the basic values of the financial entity nodes existing in the multi-hop paths and the weight coefficients of the multi-hop paths, calculates a plurality of financial decision scores of the target entity nodes, and outputs a graph path in the relationship subgraph and the corresponding financial decision scores in a visualized manner. 2.The knowledge graph driven intelligent decision support method of claim 1, wherein, In S100, the financial decision model refers to entity attributes of the financial entity nodes to assign basic values to the financial entity nodes, the entity attributes comprising at least one of a credit rating, a stock ownership ratio, an asset-liability ratio, a lawsuit record, a penalty record, a supply chain status and a customer composition structure. 3.The knowledge graph driven intelligent decision support method of claim 2, wherein, S300 comprises the following steps: S301, the computer device accesses a financial database, and the financial decision model performs embedded learning on the multi-hop paths of the target entity nodes; S302, the financial decision model matches similar historical entities in the financial database according to entity attributes of the target entity nodes, identifies whether the target entity nodes and the relationship subgraph are of the same type of structure; S303, the financial decision model predicts risk relationship edges and opportunity relationship edges of the target entity nodes based on the evolution of a knowledge graph of the historical entities in the financial database. 4.The knowledge graph driven intelligent decision support method of claim 3, wherein, The financial decision score is a total value of the product of the basic values of the financial entity nodes in the multi-hop paths and the weight coefficients of the relationship edges, the weight coefficient being inversely proportional to the length of the relationship edge, and being proportional to the confidence of the relationship edge and the importance of the financial entity node. 5.The knowledge graph driven intelligent decision support method of claim 4, wherein, When the visitor executes an instruction of deleting the relationship edges or merging the financial entity nodes on the relationship subgraph, the financial decision model adjusts the weight coefficients.

Images