Knowledge graph construction method and system, information processing system, terminal and medium

Abstract

The invention provides a business processing-oriented knowledge graph construction method, which comprises the following steps of: constructing a knowledge graph body which comprises a plurality of entity layers; constructing a connection relation model between the entity layers; wherein each entity layer comprises one or more entity nodes; the connection relation model is used for representing a connection mode between different entity nodes in the same entity layer and a connection mode between entity nodes in different entity layers; the connection mode comprises a connection relation and a connection direction. Meanwhile, the invention provides a knowledge graph construction method in the financial field, an information processing system, a terminal and a medium. According to the invention, intelligentization and automation of a data processing flow are realized.

Description

technical field [0001] The present invention relates to the technical field of intelligent information processing, in particular to a knowledge map construction method, system, information processing system, terminal and medium. Background technique [0002] The knowledge graph is a structured semantic network knowledge base, based on the semantic network, with entities as nodes and connected nodes through semantic relationships. By using technologies such as data mining, machine learning, natural language processing, and knowledge representation to extract structured data that computers can understand from massive general or industry data, and establish a knowledge graph, it is possible to accurately and efficiently describe the concepts and concepts in the physical world. relationship. Knowledge graphs have important application value for promoting machine-oriented knowledge acquisition, sharing and innovation. At present, knowledge graphs have been widely and successful...

AI Technical Summary

Problems solved by technology

However, this patented technology only classifies the relationship between entities to achieve the purpose of layering the relationship. For any layering of entities in the knowledge graph, it cannot effectively improve the representation and application effect of knowledge in the knowledge graph.

[0007] To sum up, in the existing data processing fields involving professional laws and regulations and fine-grained requirements (such as the financial field), due to the large amount of knowledge and complex relationships, automated programs are only used for some partial functions, relying more on expert experience It takes a lot of manpower and material resources to carry out related data write-offs and audits, and it is difficult to realize the intelligentization and automation of financial processing processes

[0008] At present, there is no description or report of similar technology to the present invention, and no similar information has been collected at home and abroad

Images