基于增量队列的在全置信度下的关联挖掘

摘要

关联挖掘是一种重要的数据分析方法, 提出了一种在全置信度下的增量队列关联挖掘算法模型, 在传统的 FP-Growth 及 PF-Tree 算法的关联挖掘中使用了全置信度规则, 算法的适应性得到提升, 由此提出FP4W-Growth 算法并运用到对文本数据的关联计算以及对增量式的数据进行关联性挖掘的研究中, 通过实验验证了此算法及模型的可行性与优化性, 为在庞大的文本数据中发现隐藏着的先前未知的并潜在有用的新信息和新模式, 提供了科学的决策方法.%Association mining is an important data analysis method, this article proposes an incremental queue association mining algorithm model under full confidence,using the full confidence rules in the traditional FP-Growth and PF-Tree association mining algorithm can improve the algorithm adaptability. Thus, the article proposes FP4W-Growth algorithm, and applies this algotithm to the association calculation of text data and association mining of incremental data. Then this paper conducted verification experiment. The experimental results show the feasibility of this algorithm and model. The article provides a scientific approach to finding hidden but useful information and patterns from large amount of text data.