Research And Application Of Query Expansion Technology Based On The Analysis Of User Characteristics

From the end of the 20th century to the present, search engine in gave some convenience for people to find information, but it cannot completely provide the satisfaction results to user. In the process of the use of search engines today. The user’s query statement is too short, results to the words don’t match, lost the information direction and information overload problem, become one of the main factors of restricting the retrieval quality. In addition, most of the search engines currently don’t take into account differences in characteristics of individual users that result in retrieval results contained more useless information, accuracy is lower. Therefore, information retrieval system should be able to differentiate between different user query requests, according to certain strategy for the original query word additional keywords, to solve the problem of incomplete information on user queries.This paper expounds the technical background and significance of thesis research the basic situation of domestic and foreign similar research, then introduces some related theory and key technology of knowledge, finally will query extension principle applied to paper retrieval system of colleges and universities, according to the experimental results verify the effectiveness of the proposed principle. The main work as follows:This paper proposes a model based on the user’s query expansion method, the paper use ontology to describe the user model, and according to the user model to extend the user query, in order to improve the user’s search satisfaction, according to user’s log file at the same time, considering the different characteristics of different users, the difference between the user’s query intention, to prevent "query drift" phenomenon.Draw lessons from the full text search tool Lucene index structure, the design against the database information of inverted index structure, building the full text database retrieval system based on Lucene (the database retrieval system-based-Lucene), through the experiment proves that the system significantly improved the efficiency of the database retrieval and recall, enables users to get a better search experience.The query expansion technology is applied to the full-text retrieval system based on the Lucene index. It can extend queries keywords based on user characteristics, and the retrieval results can be more in line with the user’s query intention, improve the satisfaction of users.