Information aggregation and agent interaction patterns in InfoSleuth

The MCC InfoSleuth/sup TM/ Project is an agent-based system for information gathering and analysis tasks performed over networks of autonomous information sources. A key motivation of the InfoSleuth system is that real information gathering applications require long-running monitoring and integration of information at various levels of abstraction. To this end, InfoSleuth agents enable a loose integration of technologies allowing: (1) extraction of semantic concepts from autonomous information sources; (2) registration and integration of semantically annotated information from diverse sources; and (3) temporal monitoring, information routing, and identification of trends appearing across sources in the information network. In this paper we discuss the agents in InfoSleuth applications and the goal-driven interaction patterns that enable them to dynamically organize and cooperate to perform integrated and temporal information-gathering tasks.

[1]  Peter Schwarz,et al.  A Wrapper Architecture for Legacy Data Sources1 , 1997, VLDB 1997.

[2]  Wei-Min Shen,et al.  Using Carnot for enterprise information integration , 1993, [1993] Proceedings of the Second International Conference on Parallel and Distributed Information Systems.

[3]  Nicholas Kushmerick,et al.  Wrapper induction: Efficiency and expressiveness , 2000, Artif. Intell..

[4]  Keith Decker,et al.  Unified Information and Control Flow in Hierarchical Task Networks , 1996 .

[5]  Marian H. Nodine,et al.  Facilitating Open Communication in Agent Systems: The InfoSleuth Infrastructure , 1997, ATAL.

[6]  Stefano Spaccapietra,et al.  Issues and approaches of database integration , 1998, CACM.

[7]  Marian H. Nodine,et al.  Active Information Gathering in InfoSleuth , 1999, CODAS.

[8]  Anne H. H. Ngu,et al.  Semantic brokering over dynamic heterogeneous data sources in InfoSleuth/sup TM/ , 1999, Proceedings 15th International Conference on Data Engineering (Cat. No.99CB36337).

[9]  James A. Hendler,et al.  UMCP: A Sound and Complete Procedure for Hierarchical Task-network Planning , 1994, AIPS.

[10]  Patrick Valduriez,et al.  A Methodology for Query Reformulation in CIS Using Semantic Knowledge , 1996, Int. J. Cooperative Inf. Syst..

[11]  Marian H. Nodine,et al.  Experience with the InfoSleuth Agent Architecture , 1998 .

[12]  Craig A. Knoblock,et al.  Flexible and Scalable Query Planning in Distributed and Heterogeneous Environments , 1998, AIPS.

[13]  Craig A. Knoblock,et al.  STALKER: Learning Extraction Rules for Semistructured, Web-based Information Sources * , 1998 .

[14]  Mihai Barbuceanu,et al.  Coordinating Agents by Role Based Social Constraints and Conversation Plans , 1997, AAAI/IAAI.

[15]  Joann J. Ordille,et al.  Query-Answering Algorithms for Information Agents , 1996, AAAI/IAAI, Vol. 1.

[16]  Craig A. Knoblock.  Planning, Executing, Sensing, and Replanning for Information Gathering , 1995, IJCAI.

[17]  Carlo Zaniolo,et al.  LDL: A Logic-Based Data Language , 1986, VLDB.

[18]  Vipul Kashyap,et al.  InfoSleuth: agent-based semantic integration of information in open and dynamic environments , 1997, SIGMOD '97.

[19]  J. Fowler,et al.  Collaboration and knowledge sharing of environmental information: the EDEN project , 1998, Proceedings of the 1998 IEEE International Symposium on Electronics and the Environment. ISEE - 1998 (Cat. No.98CH36145).