摘要： 提出一种自动标签提取(ATE)构件表示方法，并设计基于ATE的模糊聚类方法。ATE表示能够包含比刻面分类更多的有效信息，并克服构件刻面分类可能产生的主观因素影响。模糊聚类使构件摆脱传统聚类的硬划分模式，可分别隶属于不同的簇，对构件检索提供更好的支持。在原型构件库中的对比实验证明该方法的可行性与有效性。
关键词:
软件构件,
构件聚类,
构件检索,
自动标签提取算法,
刻面分类,
模糊聚类
Abstract: An Automatic Tags Extraction(ATE) component expression is proposed, and a fuzzy clustering method of components is designed based on the ATE. The ATE expression which contains more effective information can overcome the effect of subjective factors in faceted classification. The ATE clustering, breaking the rigid division mode with permitting a component to be classified into more than one cluster, can provide better support for components retrieval than traditional components clustering. Through the experiment in prototype component repository, the feasibility and efficiency of ATE clustering are validated.
Key words:
software component,
component clustering,
component retrieval,
Automatic Tags Extraction(ATE) algorithm,
faceted classification,
fuzzy clustering
中图分类号:
谢斌红, 陈立潮, 张雷, 潘理虎, 张英俊. 软件构件的ATE表示及其聚类方法[J]. 计算机工程, 2012, 38(11): 42-44,47.
XIE Bin-Gong, CHEN Li-Chao, ZHANG Lei, BO Li-Hu, ZHANG Yang-Dun. ATE Expression of Software Component and Its Clustering Method[J]. Computer Engineering, 2012, 38(11): 42-44,47.