基于中文命名实体识别的查询扩充方法

In order to provide users with a convenient way to obtain information in the era of Internet big data and solve the problem of difficult understanding of query intention in retrieval service, this paper proposes a query expansion method based on Chinese named entity recognition, which helps the system expand the query words by identifying the entity category and part of speech in the query words, and improves the integrity and efficiency of the query results.Firstly, the current situation and difficulties of Chinese named entity recognition are analyzed; secondly, a named entity model based on vocabulary enhancement and relative coding is designed; finally, the query words are expanded by using the identified entity information and part of speech information. Through the analysis of the experimental results on the open data set MSRA, it is found that this method improves the accuracy of entity recognition, and the advantages of the new method are verified by ablation experiments.