Study On Granular Computing And Its Application To Ontology Learning

Granular computing is an emerging conceptual and computing paradigm in information processing. Just as a great umbrella, it may be regarded as a label of theories, methodologies, techniques, and tools that make use of granules.The content of granular computing contains two main aspects, one is how to construct information granule,the other is how to use granules computing to solve problems.The advance of ontology decreases and eliminates confusion of domain concept and terms, making base of systems, which communicate, share with and manipulate each other, and it solves the problem of knowledge's share and reuse. But ontology construction is very complicated, it needs experts' effort, in addition, its handworked construction is time-consuming, laborious, and tendentious mistakes are easy to come forth, besides, it is difficult to renew developments duly, so people put forward automatic or semiautomatic ways-ontology learning.Based on analysis of basical granular computing theory and technology, ontology concept, ontology sorts, the meaning of ontology research and ontology learning, granular computing is applied to ontology learning, and the model of ontology learning is put forward, which is based on granular computing, and the. arithmetic is also put forward, which is based on granular computing and makes ontology learning come true. Then, the ways are applied to domain of naval ships, and ontology in naval ships domain is constructed semiautomatically. Furthermore, we show ontology, namely concept and its relation, which is from naval ships learning by JSP, and then search the concept about domain of naval ships by chart matching technology.The last part of the thesis analyzes disadvantages of the scheme, and prospects farther study.