The Research Of Query Optimization Technology In Information Retrieval

With the rapid development of computer network technology, the issuance and sharing of information no longer subject to the constraints of time and space, information on the Internet inflates rapidly, it has also brought the "information overload" problem while provided the massive information for the users. The contradiction between the huge digital information and the ability of people to gain the information which they need has become increasingly prominent. How to retrieve relevant information quickly and accurately has been an important area of research nowadays.The constitution of query is an important factor affects the effect of information retrieval. As most search engine users are ordinary internet users, they lack the necessary knowledge about the retrieval strategies and skills, the query which are input by users for the first time usually to be short and can not describe their query intention exactly. This problem results in the users' search results deviate their information needs. Therefore, the research of query optimization technology becomes a hotspot in information retrieval.Based on extensive and deep review of literature, a thorough analysis and research on many theoretical and application oriented problems is presented. The main contents follow:This thesis presents the development of information retrieval firstly, the general pattern and the basic model of information retrieval, as well as the basic theory and methods of the query optimization technology are systematically and thoroughly introduced. By analyzing on the classical methods, the thesis points out their special applying areas and shortcomings.This thesis presents the basic concept and implementation steps of the genetic algorithm, concludes the application of genetic algorithm in information retrieval, and shows that algorithm is practical. By improving the genetic algorithm, a query optimization based on genetic algorithm is proposed. Finally, we probe into the effect of the combination of genetic algorithm and local co-occurrence on query optimization. We utilize co-occurrence with the query terms in the relevant documents to expand the query, then used genetic algorithms to reweight the expand query vector, propose a new query optimization method based on genetic algorithm and local co-occurrence.