Abstract: The theory of rough sets is a prevalent way for data processing at present, and the granular computing has been a hot spot of the theory of rough sets. In this paper, the theory of granular computing is applied to the process of rough sets in knowledge discovery, the existing knowledge reduction algorithm is improved, and a new method is put forward to increase the speed of knowledge reduction. This paper does a research on the way of reduction in data application by the theory of rough sets and granular computing.

Key words: granular computing, rough set, knowledge discovery