Yizhong Fan and Susan Gauch
The expansion of information available on the Web has been explosive. The initial approach of collecting all Web pages into a single location and indexing them is limited in its ability to deal with this explosion. Different search engines provide access to different collections, requiring users to access multiple information sources to meet their needs. A scalable approach to information gathering from multiple sources is described which is based on the use of distributed information agents to route queries to the most appropriate sources and fuse information they provide. This paper describes an intelligent, adaptive Web search tool that can not only locate relevant information sources for the user, but also adapt to the frequent changes of the dynamic Web environment. We employ a multiple agent architecture to intelligently categorize and broker queries to remote search engines, learn and continuously update confidence factors for the quality of results provided by each search engine, and automatically detect and adapt to changes in the syntax used by the search engines. Our work is an extension of ProFusion thtto://www.orofusion.com) [Ganch 96b], a Web rectasearch engine developed at the University of Kansas which can currently broker information from nine remote search engines.