Multi-agent Paradigm and Conceptual Graphs in Information Retrieval Model

With the growing amount of on-line information and its dynamic nature, users' burden of retrieving information has become heavier and existing passive working is too inefficient to meet users' needs. An intelligent information retrieval model based on multi-agent paradigm and conceptual graphs is proposed. The model (IIR agent) has two layers of group agent and personal agent. Subagents of the IIR agent are also identified so that they can be designed and implemented separately. The system represents queries and documents in conceptual graph (CG), which brings semantic in some functions, such as intelligent search, auto-notification, navigation guide and personal information management. CG-based model improves ranking of documents returned from WWW search engines and makes passive working mode more efficient