Description:
Abstract The cores of granular computing are the granule, the granule layer and the granule structure. In this paper the concepts “Ontology granule” and “Compatible granule” were defined, applying the granular computing ideas and an ontology model, an Ontology granular set; and thus ontology tree generation algorithms were proposed. These algorithms produce an initial ontology granular set with a compatible class, and extend the other ontology granules by the vector of intension IG, building a lattice hierarchy and a conception tree model of ontology with the vector of relation RG. The empirical research of the traditional Chinese medicine ontology shows that these algorithms are correct and efficient, and provide a good technical way for ontology learning.