基于概念格的异构数据知识发现方法-计算机科学.pdfVIP

Vo1. 44 No. 9 第 44 卷第9 期 计算机科学 2017 年 9 月 COMPUTER SCIENCE Sep.2017 基于概念格的异构数据知识发现方法 牛娇娇范敏李金海殷允强 (昆明理工大学理学院 昆明 650500) 摘 要 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采。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。 关键词 概念格，异构形式背景，异构决策形式背景，知识发现 中固法分类号 TP18 文献标识码 A DOI 10. 11896/j. issn. 1002-137X. 2017. 09. 012 Knowledge Discovery Method for Heterogeneous Data ßased on Concept Lattice NIU Jiaσjiao FAN Min LI Jin-hai YIN Yun-qiang (Faculty of Science ,Kunming University of Science and Technology ,Kunming 650500 ,China) Abstract 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