Multi-Agents Systems for Information Retrieval on the WWW

This Diploma thesis describes the implementation of a prototype multi-agent system. The system consists of four different types of agents and is based on the Java Agent Template, an agent framework freely available from Stanford University.

The purpose of the multi-agent system is to aid users in searching and retrieving information available on the WorldWideWeb. Information is categorized in concepts and the different agents share and exchange the knowledge about concepts and documents on the WWW that matches these concepts.

This thesis presents how the information is modeled and how it is communicated between the agents of the system. It also includes prototypes of the agents that demonstrate a working implementation of the approach.

Please see the CEMAS home page for further details at http://www.informatik.uni-ulm.de/abt/ki/Students/mb/cemas/

Online Copy

Available as gzipped Postscript (1.38 MB)  

BibTeX Entry

@mastersthesis{Ble98,
author = {Michael Bleyer},
title  = {Multi-Agent Systems for {I}nformation {R}etrieval on the 
{W}orld {W}ide {W}eb},
month = {Mar},
year = {1998},
school = {University of Ulm, Germany},
url = {http://www.informatik.uni-ulm.de/abt/ki/Students/mb/cemas/Diplomarbeit.ps.gz},
note = {Diploma Thesis, additional information at
        {\tt http://www.informatik.uni-ulm.de/abt/ki/Students/mb/cemas/}}
}