摘要： 现有服务发现方法大多按照统计概率方式计算服务相关度，不能较准确地反映查询和服务之间的语义关联。针对该不足，提出一种基于向量空间模型的Web服务发现方法。引入WordNet词典进行同义词向量建模，划分服务主题和服务内容，得到新的服务相关度计算公式，并实现Web服务发现原型系统。实验结果表明，该方法具有较高的查准率和查全率，其调和平均值始终保持在0.6以上。

关键词: Web服务发现, 向量空间模型, WordNet词典

Abstract: Existing service discovery methods calculate service relevance based on statistical probability mostly, which is not able to precisely reveal the semantic relevance between query and service. Aiming at this shortage, this paper presents a Web service discovery method based on Vector Space Model(VSM). WordNet is adopted to build synonym vector. Service description is segmented to service theme and service content. A new function is provided to compute the relevance between query and service. Prototype system based on this method is also realized. Experimental result shows that this method has higher precision and recall with harmonic mean remaining in 0.6 above.

Key words: Web service discovery, Vector Space Model(VSM), WordNet dictionary

中图分类号: 

• TP391.3