基于概念格的异构数据知识发现方法

Knowledge Discovery Method for Heterogeneous Data Based on Concept Lattice

基于概念格的知识发现方法已被广泛关注,同时也吸引了众多学者的研究兴趣,特别是决策形式背景的知识发现,近年来取得了一些重要的研究成果。然而,现有的知识发现方法在面临大数据环境时,缺乏可行性与有效性。考虑到异构性是大数据的主要数据特征之一,针对异构数据,研究了基于概念格的知识发现方法。具体地,提出了异构形式背景及其概念格,通过异构形式背景定义了异构决策形式背景,进一步在异构决策形式背景上讨论了规则提取问题,并给出了挖掘非冗余决策规则的有效算法。

Recently,much attention has been paid to concept-lattice-based knowledge discovery methods. In the mean- while, this topic has attracted many research interests from the communities of formal concept analysis and rough set theory. Especially, in recent years, some substantial progresses have been made on studying formal decision contexts. However, the existing knowledge discovery methods are lack of feasibility and effectiveness when they are applied to big data. Considering that heterogeneity is one of the main characteristics of big data, this paper investigated concept-lattice based knowledge discovery methods for heterogeneous data. Specifically, the notion of a heterogeneous formal context was proposed as well as its corresponding concept lattice, heterogeneous formal contexts were further employed to de fine heterogeneous formal decision contexts, and rule acquisition was discussed. Moreover, an algorithm of mining non- redundant decision rules h＇om a heterogeneous formal decision context was explored.