Domain knowledge pushing method based on knowledge graph

Abstract

The invention discloses a domain knowledge pushing method based on a knowledge graph. The domain knowledge pushing method comprises the steps of collecting domain knowledge texts to construct a text knowledge base; performing semantic analysis and topic modeling on the knowledge base text; obtaining semantic distribution vectors of the nodes through domain knowledge graph embedding; establishing task context features according to the user task description and the task theme; performing entity alignment according to domain entities in the task description and the knowledge graph, performing feature extension based on graph node paths and graph node semantic distribution features, and performing task associated knowledge recall; performing text similarity calculation on the recalled text and the user task text to obtain candidate text scores; and pushing the sorting result text to the user according to the score. The text matching degree and the user experience of domain knowledge pushing are improved through node associated knowledge of the knowledge graph and a graph embedding technology.

Description

technical field [0001] The invention belongs to computer application technology, and specifically relates to a domain knowledge pushing method based on a knowledge graph. Background technique [0002] In the increasingly large-scale production and fierce service competition, with the continuous emergence of large-scale and complex business systems, enterprises have carried out a large amount of business knowledge management and accumulated a large amount of rich system management knowledge. Large-scale complex systems inevitably have many defects, and regular system inspections and defect repairs are required. However, at present, on-site maintenance operations are generally carried out systematically through the accumulation of staff's technology and experience, and there is a lack of effective and practical intelligent support means to help staff perform standardized operations and quickly obtain relevant knowledge of system failures and relevant information. Quick update...

AI Technical Summary

Problems solved by technology

Due to the imperfection of theoretical methods, it often leads to cold start, and problems such as limited and rigid push content caused by the Matthew effect

[0005] The classic recommendation algorithm often serves a variety of products and recommends various forms of information, including pictures, audio, text, video, commodities, etc. It is not suitable for the push of professional knowledge in various industries or fields

Images