Rough set theory is a new mathematical tool dealing with vagueness and uncertainty knowledge which is introduced by Z.Pawlak in 1982. It has been widely used in the area of Artificial intelligence, Knowledge and Data Discovery, Pattern Recognition and Classification, Malfunction Detection, etc. Rough set theory has some particular viewpoint which can analyse data properly.The attribute reduction is a key technology in rough sets for data mining. Based on the research of the current reduction algorithm, we expand the classical rough set model. We propose the attribute reduction algorithm which is based on varied precision model. Repair the individuals through fixing the modify operator, optimize the modify operator. Ensure the variety of colony and the algorithm can constringe faster. At last, the validity of the algorithm in this paper is proved by an instance. |