A Multiagent Approach for Electronic Travel Planning

Abstract

In the last years, the amount of information stored in Internet has grown exponentially. This article presents a new approach to cooperative problem solving that uses the Web as a source of data. The architecture has been designed using two main Artificial Intelligence techniques: Multiagent System design, and classical resolution problem solving (planning). Both are used to obtain a new architecture that is tested with knowledge obtained dynamically from Internet. The system uses two different types of agents: planning agents and web agents. Planning agents pay attention to the user's queries and solve his/her problems at a high level of abstraction, web agents fill in the details obtaining the required information from Internet. Different partial solutions given by the web agents are combined by the planning agent to obtain a detailed solution (or solutions) to the user queries.