BDI planning approach to distributed multiagent based semantic search engine

Abstract

This paper proposes a distributed multiagent architecture based on philosophical model of human practical reasoning for web search engine. The paper handles incompletely specified goals using Belief Desire and Intention model of practical reasoning in two stages. In the first stage deliberation cycle begins by accepting input query from the user and then presents the user with a set of semantically identified relevant topics obtained by exploring the surface and deep web. The chosen topic becomes the intention of the user. In the next stage, a set of partially ordered sequence of actions with respect to this intention are presented to the user using means-ends reasoning .This leads to incremental satisfaction of a user's request via multiple iterations. © 2009 Springer Berlin Heidelberg.