Text retrieval method based on word vector and association pattern intersection expansion

Abstract

The invention provides a text retrieval method based on word vector and association pattern intersection expansion. The method comprises the following steps: firstly, inquiring and retrieving a Chinese document set by a user to obtain an initial document set; then, carrying out rule extension word mining and word vector semantic learning training on the initial inspection document set to respectively obtain a rule extension word set and a word vector extension word set;, the rule extension words contain feature word association information based on statistical analysis and the word vector extension words contain rich context semantic information; and performing intersection fusion on the rule extension word set and the word vector extension word set to obtain a final extension word set toimprove the extension word quality and realizing query extension. Experimental results show that the method can solve the problems of query topic drifting and word mismatching in information retrievaland improve the information retrieval performance, the retrieval performance is higher than that of similar comparison methods in recent years, and the method has good application value and popularization prospects.

Description

technical field [0001] The invention relates to a text retrieval method based on the intersection of word vector and association pattern expansion, and belongs to the technical field of information retrieval. Background technique [0002] In the face of the massive information resources of the Internet in the era of big data, how to accurately and efficiently query more required information from network big data information has always been a concern of researchers in the field of information retrieval in academia and industry. Query expansion is one of the core key technologies to solve the problem of information retrieval word mismatch and query topic drift. Query expansion refers to adding other feature words related to the original query semantics, making up for the lack of semantic information caused by the original query being too simple, and achieving improvement. Purpose of Information Retrieval Performance. The information retrieval method based on query expansion h...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a text retrieval method based on the intersection and expansion of word vectors and association patterns, which can be used in the field of information retrieval, such as Chinese web information retrieval systems or search engines, to improve and enhance the query performance of information retrieval systems , to reduce query subject drift and word mismatch problems in information retrieval

Images