基于LDA和模糊C均值的Web服务多功能聚类  

Web services clustering with multi-functionality based on LDA and fuzzy C-means algorithm

作　　者：张祥平 刘建勋 肖巧翔 石敏 曹步清 ZHAGN Xiangping;LIU Jianxun;XIAO Qiaoxiang;SHI Min;CAO Buqing(Key Laboratory of Knowledge Processing & Networked Manufacturing of Hunan Province,School of Computer Science and Engineering, Hunan University of Science & Technology, Xiangtan 411201, China)

机构地区：[1]湖南科技大学计算机科学与工程学院,知识处理与网络化制造湖南省普通高校重点实验室,湖南湘潭411201

出　　处：《中南大学学报（自然科学版）》2018年第12期2986-2992,共7页Journal of Central South University:Science and Technology

基　　金：国家自然科学基金资助项目(61872139,61873316,61572187,61702181);湖南省自然科学基金资助项目(2017JJ2098,2018JJ2136).

摘　　要：基于Web服务发现方法通常是将Web服务聚在某一个固定的功能类中,导致该Web服务的其余功能特性被忽略,Web服务的资源利用率降低的问题,提出一种基于LDA和模糊C均值的Web服务多功能聚类方法。首先,从ProgrammableWeb.com网站上爬取Web服务数据,并抽取Web服务描述文档;其次,使用LDA主题模型对Web服务描述文档进行建模,获得包含不同功能信息的文档主题矩阵;最后,在文档主题矩阵上使用模糊C均值算法将Web服务聚类到不同的功能类中,完成Web服务的多功能聚类。研究结果表明:Web服务的多功能特性切实提高了服务发现的精度。Considering that Web service discovery usually classifies Web service into one fixed cluster,which neglects other important function attributions of the Web service,a Web services clustering method with multi-functionality was proposed based on LDA and fuzzy c-means algorithm.The method firstly crawled Web services from ProgrammableWeb.com and extracted the description document of them.Then LDA was used to model the description documents of Web services,and the document-topic matrix which contained different functional information was obtained.Finally,they were clustered into various clusters with similar functionality by exploiting fuzzy C-means algorithm.The results show that the multifunctionality of Web services effectively improve the accuracy of Web services discovery.

关 键 词：WEB服务 模糊C均值算法 LDA主题模型 WEB服务发现 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]