摘要：Existing methods and technologies for Web services discovery mainly consist of two models: service matching based on grammar and based on semantics. With keywords service matching method, we introduce text information retrieval technology with vectors and concept lattice theory. Then a web service discovery algorithm using eigenvectors is put forward. It orders the Web services by correlation among the services in Web service subset. The services which have bigger correlation will get anterior places. According to this algorithm a Web service discovery system based on eigenvectors is designed. We give description to key modules of the system. At last the improved algorithm is compared to methods based on full-text retrieval and pure similarity retrieval. The results show it has better performance in accuracy and response.
关键词：Web services;text information retrieval;eigenvectors;clustering;correlation
