Personal Agents on the Semantic Web
Monday, January 26, 2004, 9:30am - Monday, January 26, 2004, 11:30am
We describe an architecture for persistent personal agents (PPAs) designed to work on the Semantic Web and actively interact with various other entities. Our Personal Agents assists its user with everyday activities, such as maintaining a calendar, coordinating activities with other people, and answering simple queries on their behalf. They use the semantic web languages RDF and DAML+OIL to define and use ontologies, to understand markup on web resources, and to encode the content in ACL messages exchanged with other PAs. The Agents store their knowledge in Jess and use FIPA languages, protocols and infrastructure to communicate with other agents. We demonstrate the feasibility of our approach through a prototype, which receives event recommendations, infers whether or not to add events to its user's calendar, interacts and shares information with peers. A discovery mechanism has been developed that allows PPAs to find and negotiate information exchange with peer PPAs. An extension to the FIPA framework allows the DAML Query Language to be used to query other agents. A reasoning approach designed to facilitate the Agents to reason about the trust-worthiness of a query is also illustrated.