Information system-oriented knowledge graph construction method, device and electronic equipment

Abstract

The invention discloses an information system-oriented knowledge graph construction method, a device and electronic equipment. The method comprises the steps of collecting multi-source heterogeneous data of an information system; performing data integration and knowledge extraction, and acquiring triple data for the structured data, the semi-structured data and the non-structured data; setting a main graph and an auxiliary graph; traversing each entity e in each auxiliary graph gi, obtaining an entity e1' with the same name as the entity e from the main graph G, and fusing the entity e with the entity e1'on the main graph G by adopting a preset same-name entity fusion method; traversing each entity e in each auxiliary graph gi, finding out an entity e2'with a name different from that of the entity e from the main graph G, and fusing the entity e with the entity e2' on the main graph G by adopting a preset entity fusion method with different names; constructing a knowledge graph; according to the method, the decision precision is improved by adopting self-adaptive double-threshold setting in entity disambiguation, the operation complexity is reduced by adopting a similarity multi-step calculation method in co-exponential digestion, and the co-exponential digestion speed is increased.

Description

technical field [0001] The invention relates to the field of data semantic analysis, in particular to an information system-oriented knowledge map construction method, device and electronic equipment. Background technique [0002] Since entering the era of big data, with the rapid development of the Internet and information technology, all walks of life have begun to pay attention to the collection, processing, management and application of massive data, thus deriving numerous large and complex information systems. Although various fields are constantly combining information technology to manage business and optimize production, due to various business branches, large data scale, single data processing technology and other reasons, although the current information system has rich data resources, it is difficult for data accumulation and knowledge understanding. They are all in their infancy, and there is still a lot of room for improvement from the full utilization of data. ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an information system-oriented knowledge map construction method, device and electronic equipment, avoiding the binary segmentation method with a single threshold setting in the prior art when entity disambiguation removes ambiguity or redundant data, resulting in the same name Misjudgment and decision-making of whether entities are synonymous and the problem of low accuracy, as well as the problem of high computational complexity and slow computational speed when coreference resolution removes redundant data

Images