A web service matching algorithm based on semantic similarity.

Purpose - The purpose of this paper is to obtain more accurate matching between the request and the release of web service. Design/methodology/approach - This paper adopts Levenshtein distance algorithm to calculate the name similarity between publishing service and request service, employs cosine theorem to compute the text similarity, and uses semantic distance to count the input-output similarity, then filters out the low similarity and bad reputation services to structure the candidate service set. Findings - The qualitative and quantitative analysis of the scheme is given in this paper. The experimental results show that the multi-level matching filtering algorithm can obviously improve the recall ratio and precision ratio of web service discovery. Originality/value - This paper proposes a similarity-based filtering algorithm for multi-level matching. [ABSTRACT FROM AUTHOR]