大数据环境下相容数据集的关联规则数据挖掘
Data Mining Algorithm of Association Rules Among Compatible Datasets in Big Data Environment
-
摘要: 在对不可连接数据集充分分析的基础上, 给出基于不可连接数据集的相容数据集和不相容数据集2个定义, 给出相容数据集的一些基本理论, 在这些理论基础上给出一个基于相容数据集的关联规则挖掘方案, 实现每个相容数据集挖掘的关联规则直接合并, 生成整个相容数据集的关联规则, 实现普通数据挖掘算法无法实现的关联规则挖掘.方案扩展了关联规则算法的应用领域, 提高了数据挖掘效率, 在一定程度上也实现了隐私保护.Abstract: On the basis of the data set which can not be connecteel, the definitions of the compatible data set and incompatible data set 2 based on the data sets not to be connected are given, some basic theories about compatible data set are presented, an association rule mining programme based on compatible data set is proposed. It is realized that association rules of compatible data set mining merge directly, so that association rules of the whole compatible data set are generated and the algorithm can realize an association rule mining which cannot be realized by the common data mining. The algorithm expands the application field of association rule algorithm and improves the efficiency of data mining, meanwhile, it realized the privacy protection in a certain extent.
下载:
