TravelPlan: A MultiAgent System to Solve Web Electronic Travel Problems

ABSTRACT This paper presents TravelPlan, a multiagent ar hite ture to o-operative work between di erent elements (human and/or software) whose main goal is to re ommend useful solutions in the ele troni tourism domain to system users. The system uses di erent types of intelligent autonomous agents whose main hara teristi s are ooperation, negotiation, learning, planning and knowledge sharing. The information used by the intelligent agents is heterogeneous and geographi ally distributed. The main information sour e of the system is Internet (the web). Other information sour es are distributed knowledge bases in the own system.. The pro ess to obtain, lter, and store the information is performed automati ally by agents. This information is translated into a homogeneous format for high-level reasoning in order to obtain di erent partial solutions. Partial solutions are re onstru ted into a general solution (or solutions) to be presented to the user. The system will re ommend di erent solutions to the users analyzing his/her preferen es, and learning them from the intera tion.