摘要： 针对具有上界约束的关联规则问题进行了研究，给出了上界约束的定义，分析了满足上界约束频繁集的性质，并给出了相关的证明。在此基础上，提出了基于FP-Tree的上界约束算法，采用了预先测试的方法，降低了测试项集的成本，提高了计算效率，实验结果证明该算法具有较高的效率。

关键词: 数据挖掘, 关联规则, 约束

Abstract: This paper discusses algorithms for association rules with upper bound constraints. The definition of upper bound constraints is presented, property of frequent item sets which satisfy upper bound constraints is analyzed and proved. And an algorithm of association rules with upper bound constraint is presented, which is based on FP-Tree. In this algorithm, the method of test in advance is adopted, which can reduce the cost of item set test, boost the performance. Experimental test show the algorithm is quite efficient.

Key words: Data mining, Association rules, Constraints