摘要： 通过数据库和Web 日志构建概念层次树，在继承FP 算法思想的基础上，提出了由概念层次树挖掘多层包括交叉层次的关联规则算法。实验结果表明，该算法在性能上比传统算法有了较大的改善，能为客户提供多层次的关联推荐和电子商务的个性化服务。

关键词: 关联规则；数据挖掘；概念层次树

Abstract: Based on the idea of FP algorithm, this paper proposes an association rule algorithm of the crossover level by application the interval support. The simulation result shows the high optimization efficiency of this algorithm and it gives the multilevel individuation recommendation for the online consumers.

Key words: Association rule; Data mining; Concept level tree