Dynamic concept learning and knowledge graph generation method based on partial sequence three-branch structure

Abstract

The invention discloses a dynamic concept learning and knowledge graph generation method based on a partial order three-branch structure, and the method comprises the following steps: S1, for a given original-form background and an incremental-form background, judging the type of a newly-added object according to the binary relation between the newly-added object and an original object; s2, performing incremental updating on the original concept tree based on the properties of each category according to the category of the newly added object so as to realize dynamic concept cognitive learning; and S3, according to the dynamic change of the concepts in the step S2, performing incremental deletion on each concept node, content and mutual associated edges in the original knowledge graph so as to realize incremental update of the knowledge graph. According to the method, an existing partial sequence three-branch structure generation algorithm is combined, incremental learning operation is introduced, dynamic concept cognitive learning can be achieved on the basis of dynamic data, and incremental generation of the knowledge graph is achieved.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, and in particular relates to a dynamic concept learning and knowledge graph generation method based on a partially ordered three-branch structure. Background technique [0002] With the vigorous development of the information technology industry, the information and data available to humans is showing an explosive growth trend. How to effectively process the acquired dynamic and massive data according to the thinking mode of the human brain, and extract valuable knowledge from it has become a key problem to be solved urgently. [0003] Concept cognitive learning is a method that can effectively process massive data and extract valuable knowledge from it. The knowledge map is a means to visualize the knowledge acquired through learning, so as to facilitate operations such as knowledge mining, knowledge dissemination, knowledge retrieval, and knowledge recommendation. [0004] Partial or...

AI Technical Summary

Problems solved by technology

However, the current partial order three-branch structure algorithm can only process static data, but cannot carry out conceptual cognitive learning and knowledge map generation based on dynamic data.

When new data is integrated, the current partial order three-branch structure algorithm needs to reconstruct the entire knowledge graph. When the amount of data is large, this will cause a lot of unnecessary time consumption

Therefore, the current partial order three-branch structure algorithm does not meet the knowledge processing requirements of dynamic and massive data.

Images