Intelligent semantic retrieval method based on cultural relic knowledge graph

Abstract

The invention discloses an intelligent semantic retrieval method based on a cultural relic knowledge graph. The method comprises the following steps: (1) entity mapping of retrieval statements: identifying an recognition entity of a user retrieval statement by utilizing an entity recognition model, describing and normalizing the recognition entity through synonym poeia, and positioning the recognition entity in a cultural relic knowledge graph, namely determining a corresponding entity corresponding to the recognition entity in the cultural relic knowledge graph; (2) relationship mapping of retrieval statements: according to the entity type of the corresponding entity, performing knowledge graph relationship mapping of user retrieval intention on the corresponding entity by adopting a relationship mapping model corresponding to the entity type, and determining a mapping relationship; and (3) generating a statement meeting a knowledge graph query mode according to the corresponding entity and the mapping relationship, and retrieving the cultural relic knowledge graph by using the query mode statement. Compared with keyword matching retrieval, the intelligent semantic retrieval method can better meet the retrieval requirements of users.

Description

technical field [0001] The invention relates to the technical fields of natural language processing, semantic analysis, information extraction, etc., and specifically relates to an intelligent semantic retrieval method based on a cultural relic knowledge map. Background technique [0002] With the rapid development of information technology, the amount of information on the Internet is also exponentially increasing. The massive amount of data in the Internet provides a natural data foundation for big data analysis, and also provides users with a rich and extensive information query source. In a large amount of data, people often need the help of search engines to retrieve the information they need. However, the current retrieval effect of search engines is not good, and a large number of relevant results will be returned to users. The screening cannot meet the increasing standards of users and the request of intelligent retrieval. This is especially true for professional k...

AI Technical Summary

Problems solved by technology

However, this method does not perform deep semantic analysis on the search sentences entered by the user, and cannot understand the user's query intent, and the query method is relatively rigid.

Images