论文部分内容阅读
概念格是一种有效的数据分析和知识提取的形式化工具.然而,随着要处理的数据量的剧增,基于原始形式背景构造出的概念格结点数目庞大,占用大的存储空间,同时概念格结点中一些属性集形成的内涵,用户并不都感兴趣,因而从中提取用户需求知识费时.为了降低概念格构造的时空复杂性,增强实用性和针对性,首先采用谓词逻辑描述用户感兴趣的背景知识,并将背景知识引入到概念格结构中,提出了一种新的概念格:约束概念格.在此基础上,提出了基于背景知识的约束概念格构造算法CCLA.理论分析表明,该算法能有效地减少概念格的存储空间和建格时间.最后,采用恒星天体光谱数据作为形式背景,实验验证了该算法的有效性.
Concept lattice is an effective formal tool for data analysis and knowledge extraction.However, as the amount of data to be processed increases sharply, the number of concept lattice nodes constructed based on the original formal context is huge and occupies a large amount of storage space, At the same time, the connotation formed by some attribute sets in the concept lattice node are not all interested by the users, so it takes time to extract knowledge from users’ needs.In order to reduce the space-time complexity of concept lattice structure and enhance its practicability and pertinence, Users are interested in the background knowledge, and the background knowledge is introduced into the concept lattice structure, a new concept lattice is proposed: Constraint concept lattice.On the basis of this, a constraint concept lattice construction algorithm based on background knowledge is proposed. The analysis shows that this algorithm can effectively reduce the storage space and time of lattice construction.Finally, using the stellar celestial body spectral data as the formal background, the experimental results show the effectiveness of the algorithm.