Description: In this paper a method for forming logic rules of the knowledge base of an expert system has been considered based on rough sets theory. This method is based on the analysis of the importance of the features included in a cover. The most informative feature is placed on the right side of the logic rule, and the rough set reduct built on the basis of the remaining features is placed on the left side. Thus the logic rules of the knowledge base of an expert system can be ordered by the importance of target features.
Keywords: consulting model, associative dependence, logical rules, close great numbers