Knowledge graph searching and positioning method and system, electronic equipment and storage medium

Abstract

The invention relates to a knowledge graph searching and positioning method and a system, electronic equipment and a storage medium. The searching and positioning method comprises the following stepsof obtaining a searching request of a user; extracting one or more keywords from the search request of the user; selecting a node keyword from the one or more keywords; searching in the knowledge graph according to the node keyword, and positioning to a sub-graph corresponding to the node keyword; and searching in the sub-graph according to other keywords, positioning to a node corresponding to the search request, and generating an instruction according to the node. According to the method, traversal of all nodes of the whole knowledge graph in the searching and positioning process is avoided,the situation that the calculation and processing speed is reduced due to the huge and complex structure of the knowledge graph is avoided, and the operation efficiency of the knowledge graph is improved.

Description

technical field [0001] The present invention relates to the technical field of intelligent control, in particular to a search and location method, system, electronic device and storage medium of a knowledge graph. Background technique [0002] With the gradual development of knowledge graph technology, more and more industries have begun to establish business knowledge graphs. The current development of big data technology has brought more and more data to knowledge graphs. How to store, search, and reason and apply them has become a waiting The problem solved by mutual balance is currently only based on the structural characteristics of the knowledge map, using the path relationship between entities for reasoning. For multi-path and long-path reasoning problems, the current application performance is limited to a certain extent. This is because each time the node is positioned. It is necessary to traverse the large-scale nodes of the knowledge map, so the structure of the k...

AI Technical Summary

Problems solved by technology

[0002] With the gradual development of knowledge graph technology, more and more industries have begun to establish business knowledge graphs. The current development of big data technology has brought more and more data to knowledge graphs. How to store, search, and reason and apply them has become a waiting The problem solved by mutual balance is currently only based on the structural characteristics of the knowledge map, using the path relationship between entities for reasoning. For multi-path and long-path reasoning problems, the current application performance is limited to a certain extent. This is because each time the node is positioned. It is necessary to traverse the large-scale nodes of the knowledge graph, so the structure of the knowledge graph becomes larger and more complex, and the calculation and processing speed becomes slower and slower, resulting in low operating efficiency of the knowledge graph

Images