Vol. 62 | no. 3 | July - September 2014 Article 14

A multi-Agent Information Retrieval System
(full text in English)

Weiwei JIAO
This paper is a survey of the recent work in the field of information retrieval systems (e.g., web search engines). Information retrieval systems are critical for overcoming information overload. A major deficiency of existing retrieval systems is that they generally lack user modeling and are not adaptive to individual users. According to the defect of current search engines, this paper presents a model of information retrieval system based on multi-agent, which can realize individuation and intelligence of information retrieval according to user interested knowledge via multi-Agent collaboration. When a user submits a query keyword to the information retrieval system, it can automatically locate the current user’s implicit search intention according to the current user’s interest profile. This paper gives a working principle of the model and discusses about the abstract technology of the model. Experimental results show that the multi-Agent information retrieval system can improve search accuracy.
Keywords: personalized search, user interest model, multi-agent system, information retrieval system, web search, intelligent agent