面向功能的Web服务分类系统研究与实现

Research and Implementation of Function-oriented Web Service Classification System

提出一种基于支持向量机方法依据Web服务的功能信息进行分类的服务分类系统,以UNSPSC作为Web服务的类别体系,并利用UNSPSC中各类别的描述信息作为其父类别的样本文档.在层次化分类体系中利用概念之间的语义层次关系判断出类别的主概念从而进行特征选择的方法,概念之间的语义层次关系通过计算概念在语义词汇网络WordNet中的语义相似度而建立.经过在实际数据和模拟数据集合上进行实验,结果证明服务分类系统分类效果理想.

A novel method based on support vector machine is presented to conduct service classification with a medium or big category set.It uses the descriptive information of categories in a large-scale taxonomy as sample data,so as to disengage from the dependence on sample service documents,and the functional information of the new service document is extracted for classification.A new feature selection method using semantic hierarchy relationship between words to determine the main concepts of the category is introduced to enable efficient classification using this new type of sample data.The semantic hierarchy relationship between words is built according to the semantic similarity between words which is calculated by semantic similarity methods based on WordNet.We demonstrate the effectiveness of our classification method through extensive experiments.