Abstract: Rule extraction is an very important and difficult process for an intelligent information system. To deal with the problem, the paper proposed a method based on rough set theory, researched attribute reduction, attribute values reduction and so on. According to the indiscernible relation in rough set, discernible vector and its addition rule were defined to calculate the core attributes and all attributes' importance. The core attributes set was taken as the start point to obtain an attributes reduction set by using the attributes' importance as the heuristic information. Based on the attributes reduction set, attribute value reduction was realized through gradually deleting the redundant attribute values in every rule of the information table depending on the correlation of condition attributes and decision attributes. Finally,a concise rule set was obtained. The illustration and experiment results indicate that the method is effective and efficient for rule extraction.

Key words: Rough set, Information system, Rule extraction, Attribute reduction, Attribute value reduction