Distributed Knowledge Integration Based on Intelligent Topic Map

摘要

We propose a novel concept of Intelligent Topic Map, which extends the conventional topic map in structure and enhances the reasoning functions. With the Intelligent Topic Map as infrastructure, a mechanism of distributed knowledge integration is designed. The structure is divided into three layers: local Intelligent Topic Map layer, similarity measure layer and global Intelligent Topic Map layer. It provides a uniform query interface to a multitude of knowledge sources and lays the foundation for high-quality knowledge services. Moreover, we propose a new similarity measure algorithm based on comprehensive information theory and merging rules for knowledge integration. The experimental results show that our method is feasible and it has the significance of reference and value of further study for the distributed knowledge integration.