Abstract: According to the connective characteristic of data and demands within data space, the principle of ontology is introduced into the process of cluster analysis. The pinpoint existence modality and dynamic distribution of data are described on the definition of ontic kernel and object data. Interrelation among the data can be studied with weak ontic kernel and strong ontic kernel. The cluster analysis histogram is constructed on the time of object data and different value on the same time. For different histogram statement, the algorithm that can process the limited gate value with rational function of controlling cluster is presented to determine the ultimate generic cluster. An application illustration is used to demonstrate feasibility and validity of the cluster preprocessing on ontic kernel and histogram (CPOKH). 

Key words: cluster preprocessing, histogram, rational function, ontic kernel