论文部分内容阅读
Generally a database encompasses various kinds of knowledge and is sharedby many users. Different users may prefer different kinds of knowledge. So it is importantfor a data mining algorithm to output specific knowledge according to users’ current require-ments (preference). We call this kind of data mining requirement-oriented knowledge discovery(ROKD). When the rough set theory is used in data mining, the ROKD problem is how to finda reduct and corresponding rules interesting for the user. Since reducts and rules are generatedin the same way, this paper only concs with how to find a particular reduct. The user’srequirement is described by an order of attributes, called attribute order, which implies the im-portance of attributes for the user. In the order, more important attributes are located beforeless important ones. Then the problem becomes how to find a reduct including those attributesanterior in the attribute order. An approach to dealing with such a problem is proposed. Andits completeness for reduct is proved. After that, three kinds of attribute order are developedto describe various user requirements.