A Multi-Agent System using Semantic Metadata for the Cooperation among Multiple Information Sources

We propose an agent architecture that enables actual cooperation among a set of autonomous and heterogeneous information sources. An object oriented descriptive layer is defined to insure an homogeneous view of the local accessible data. To preserve local autonomy and the architecture scalability, the descriptive layer is composed of two metadata object types : Data Descriptive Objects (DDO) represent the structural (data model) and terminological dimensions of local data whereas Semantic Links Objects implement various semantic relations among the DDO. Thus, a global object oriented semantic knowledge base is obtained and distributed to Agents involved in a cooperation protocol dedicated to global queries treatment. Conflict resolution and completeness of the answer are processed during a negotiation phase in the multi-agent protocol.

[1]  Peter Fankhauser,et al.  IRO-DB: Making Relational and Object-Oriented Database Systems Interoperable , 1996, EDBT.

[2]  Stéphane Bressan,et al.  Context Interchange: New Features and Formalisms for the Intelligent Integration of Information Context Interchange: New Features and Formalisms for the Intelligent Integration of Information , 1997 .

[3]  Yannis Papakonstantinou,et al.  Object Fusion in Mediator Systems , 1996, VLDB.

[4]  Amit P. Sheth,et al.  Logical information modeling of Web-accessible heterogeneous digital assets , 1998, Proceedings IEEE International Forum on Research and Technology Advances in Digital Libraries -ADL'98-.

[5]  Jennifer Widom,et al.  Object exchange across heterogeneous information sources , 1995, Proceedings of the Eleventh International Conference on Data Engineering.

[6]  Sibel Adali,et al.  A uniform framework for integrating knowledge in heterogeneous knowledge systems , 1995, Proceedings of the Eleventh International Conference on Data Engineering.

[7]  Timos K. Sellis,et al.  An Organizational Framework for Cooperating Intelligent Information Systems , 1992, Int. J. Cooperative Inf. Syst..

[8]  Joann J. Ordille,et al.  Querying Heterogeneous Information Sources Using Source Descriptions , 1996, VLDB.

[9]  Hector Garcia-Molina,et al.  Template-based wrappers in the TSIMMIS system , 1997, SIGMOD '97.

[10]  Reid G. Smith,et al.  The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver , 1980, IEEE Transactions on Computers.

[11]  Gio Wiederhold,et al.  Mediators in the architecture of future information systems , 1992, Computer.

[12]  Jennifer Widom,et al.  The TSIMMIS Project: Integration of Heterogeneous Information Sources , 1994, IPSJ.

[13]  Craig A. Knoblock,et al.  Retrieving and Integrating Data from Multiple Information Sources , 1993, Int. J. Cooperative Inf. Syst..

[14]  Sati S. Sian,et al.  Extending Learning to Multiple Agents: Issues and a Model for Multi-Agent Machine Learning (MA-ML) , 1991, EWSL.

[15]  Danielle Boulanger,et al.  Semantic cooperation of legacy information systems: an object-oriented framework , 1997, Database and Expert Systems Applications. 8th International Conference, DEXA '97. Proceedings.

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

[17]  Yves Demazeau,et al.  Using the active object model to implement multi-agent systems , 1993, Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93).

[18]  Craig A. Knoblock,et al.  Cooperating Agents for Information Retrieval , 1994, CoopIS.

[19]  Marian H. Nodine.  The InfoSleuth Agent System , 1998, CIA.

[20]  Danielle Boulanger,et al.  An Object Approach for Information System Cooperation , 1998, Inf. Syst..