Extension classification method and its application based on extensible set

Based on the definitions of extensible set and the constructing method of its dependent function, a sort of classification method under extension transformation, which is called extension classification method, is studied. It is different from the classification methods based on classical set, fuzzy set and rough set, and it is a sort of alterable classification method. According to a certain transformation, it can divide a universe of discourse into 5 parts: positive extension field, negative extension field, positive stable field, negative stable field and extension boundary. Moreover, the universe of discourse and the dependent function describing the degree that an object possesses certain character are alterable. It makes the classification more elaborate. The phenomenon that "there is a corresponding classification pattern for a given transformation" is illuminated from the angle of set theory. Taking the extension classification management on human resources as an example, its applied value will be explained. The classification method is a basic method of extension data mining. It makes the classification function of data mining richer.