关联规则发现是数据库中知识发现研究中的热点课题,有着广泛的应用领域.在现有的研究中,数据库中的各个项目是按平等一致的方式加以处理的.然而,在现实世界数据库中却并非如此,不同的项目往往有着不同的重要性.为了将它们反映出来,对项目引入权值,从而提出了新的加权关联规则问题.由于项目权值的引入,频繁项目集的子集不再一定是频繁的.为此,又提出了项目的k-支持期望概念,并由此提出了加权关联规则的发现算法.

Discovery of association rules is a very hot topic in data mining research, which has been found applicable and useful in many areas. In the current researches, all the items in a databases are treated in a uniform way. However, it is not true in the real world databases, in which different items usually have different importances. In order to represent the importance of individual items, the weight value for items is introduced, and a new problem of discovery of weighted association rules is put forward. Due to the introduction of weight for items, it is not sure that any subset of a frequent itemset is also frequent. Thus, a concept of k-support bound of itemsets is set forth, and an algorithm to discover weighted association rules is proposed.

国家自然科学基金资助项目(69975001)