Research On Optimization Of Multi-Agent Based Search Engine

In recent years, as the appearance of computers and networks, the Internet information go into the exponential growth, Search engine has become essential tools for the Internet. Traditional search engines advantage is informative, timely updates without manual intervention, but with the exponential growth of information, Massive search technology is increasingly obvious drawbacks, the return of information overload, coupled with a large number of redundant or irrelevant information. We must search results on its own or multiple secondary screening, virtually reduced the accuracy of the search. We need to have new technology to solve these problems. The research based on the optimization of multi-Agent search several key issues, from the second generation of search by the current problems and to conduct search engine optimization further.Undering matching the keywords search on the premise, through client and the server-Agent interaction, detailed analysis of user behavior's browsing web, How to judge the importance of web page increased user factor.By the client and the server-Agent interaction, search behavior with Multi-Agent System take the specific to a certain user, uncertainty and personality into account.This paper first introduces search engine technology and classifications. Then the Agent and the definition of system architecture and learning techniques of user interest. Then design my ownMulti-Agent-System-based search engine architecture and each Agent's functions. Finally simulate and implements of the client Agents of search Engine, and made a comparis on test.