Multi-agent based internet search

Abstract

In this paper, we present a multi-agent system for searching the internet. The search for interesting documents on the internet is becoming more and more difficult. The main problem is not that we do not have the needed information to build or use knowledge, the problem is that we have too much information, mostly irrelevant. A proof of this is that inference engines are largely outperformed by the expansion of the internet and the results of queries are often of very poor quality. To improve the search process, intelligent individual agents were developed. We believe that multi-agent systems can give more accurate results than the individual agents because in a multi-agent system, agents can be specialised in different tasks and can share information. We implemented such an approach using an open multi-agent system containing personal assistants, library agents, filter agents, and search agents. In this paper, we study the models of internet multi-agent systems and propose an architecture to do intelligent web search. The application is based on an AUML protocol (slightly extended) to allow interoperability and yields more accurate results than standard search engines.