对粗糙集进行了相关研究,并提出了一种以粗糙集理论为基础的K-平均聚类算法,该算法以信息表中条件属性和决策属性的一致性原理为基础,应用粗糙集的属性约简算法消除冗余属性,利用各属性重要度确定其权值,在此基础上应用改进的K-平均算法进行聚类分析.该方法的优势在于消除了不重要的属性,赋予了各属性权值,使聚类更有效,更客观.实验结果表明,该方法是有效的. The research on rough sets is made and a K-means clustering algorithm based on rough set theory is proposed. Based on the consistency principle of condition attributes and decision attributes in the information table, the algorithm applies the attributes of rough sets Reduction algorithm to eliminate redundant attributes, the use of the importance of each attribute to determine its weight, based on the application of improved K-means clustering analysis. The advantage of this method is to eliminate the non-important attributes, given the attributes The weights make the clustering more efficient and objective.The experimental results show that this method is effective.