Mutidimensinal Association Rules Algorithm Mining Research And System Actualizatio

In order to support the applications of OLAP and data mining simultaneously,we gave the orientation that the multidimensional data model become the common data basic of OLAP and data mining,.In this thesis, we research on the character of multi-dimensional cube and the association mining algorithm of Apriori, synthesize the technology of data warehouse, OLAP and the association mining algorithm, propose and develop an association mining algorithm base on multi-dimensional data, including intra-dimensional association, inter-dimensional association, hybrid association. This algorithm has changed the way that the old algorithm computed the support through scan the transaction database, instead of scan multi- dimensional the data cube. In addition, aim at the construction of data cube and the opertion of OLAP, we propose an algorithm base on the conception of hiberarchy, select the reasonable dimension and mine the association in it. While it generating the associations, we propose the conception of interest and constraint mine the interesting and reasonable multi-dimensional hiberarchy associations that satisfy the constraint that the people specified. The research shows this multi-dimensional association mining algorithm base on the technology of OLAP can judge whether the dimensional hiberarchy high or not, and adjust the dimensional hiberarchy through drill-up and drill-down, with high efficiency.