2006 | OriginalPaper | Chapter
ACP2P: Agent-Community-Based Peer-to-Peer Information Retrieval – An Evaluation
Authors : Tsunenori Mine, Akihiro Kogo, Makoto Amamiya
Published in: Agents and Peer-to-Peer Computing
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
The Agent-Community-based Peer-to-Peer Information Retrieval
(ACP2P)
method [1],[2] uses agent communities to manage and look up information of interest to users. An agent works as a delegate of its user and searches for information that the user wants by communicating with other agents. The communication between agents is carried out in a peer-to-peer computing architecture. Retrieving information relevant to a user query is performed with content files which consist of original and retrieved documents, and two histories: a query/retrieved document history and a query/sender agent history. The
ACP2P
is implemented using the Multi-Agent
Kodama
framework.
In this paper, we present some mathematical aspects of the
ACP2P
method with respect to the relationships between communication loads and the number of records that are stored both in the two histories and retrieved document content files, and discuss the experimental results, for which illustrate the validity of this approach. The results confirm the mathematical conjectures we presented and show that the two histories are more useful for reducing the communication load than a naive method employing ’multicast’ techniques, and lead to a higher retrieval accuracy than the naive method.