概念特化的概念格更新构造算法  

An improved algorithm based on concept specialization for constructing concept lattices

作　　者：杜秋香[1] 张继福[1] 张素兰[1] 

机构地区：[1]太原科技大学计算机科学与技术学院,山西太原030024

出　　处：《智能系统学报》2008年第5期443-448,共6页CAAI Transactions on Intelligent Systems

基　　金：山西省自然科学基金资助项目(2006011041)

摘　　要：概念格是形式概念分析中的核心数据结构,概念格应用的瓶颈之一是其构造效率.针对形式背景的某个属性分解为多个新属性得到更加特化的概念,给出了一种基于概念特化的渐进式更新构造算法.该算法利用分解后的新属性及其相应的形式背景,构造出的概念格与原概念格的某个子概念格作比较,来更新构造概念格,从而减少了比较次数,提高了更新构造的效率.以天体光谱数据作为形式背景,实验验证了该算法的正确性和有效性.Concept lattices are the core data structures in formal concept analysis. The widespread application of concept analysis is limited by the difficulty of constructing a concept lattice. An incrementally updating construction algorithm based on concept spcialization was developed after it was realized that the attributes in the formal context can be decomposed into several new attributes, or more specialized concepts. The algorithm, with decomposed attributes and a corresponding formal context, compares the concept lattice formed with the new attributes and one of the sub-lattices of the original concept lattice, then upgrades the concept lattice according to results from the comparisons. In this way the number of comparisons is reduced and the efficiency of constructing the concept lattice is improved. Experiment results, with celestial spectrum data as the formal context, verified the validity of the algorithm.

关 键 词：概念格 渐进式构造 概念特化 更新构造 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]