Service classification method based on symbiotic attention representation learning

Abstract

The invention relates to a service classification method based on symbiotic attention representation learning. The method specifically comprises the following steps: selecting a web service, wherein the web service comprises a service description and a service name; constructing a description service matrix by using the service description; extracting information words from the service description, and constructing a service information word feature matrix; constructing a service name feature matrix by using the service names; fusing the information word feature matrix and the name feature matrix to obtain an enhanced data feature matrix; establishing a service feature correlation matrix by using the enhanced data feature matrix and the service description feature matrix; and calculating the correlation matrix to obtain a required vector parameter, and finally obtaining the service category of the web service according to the vector parameter and the feature matrix. According to the method, the service description is extracted as the additional service feature, and the extracted information word and the service name are combined to form the service enhancement feature for service classification, so that the classification accuracy is improved.

Description

Technical field[0001]The present invention relates to the field of service classification methods, and more particularly to a service classification method based on symbiotic attention representation.Background technique[0002]With a wide range of applications (SOA), web services become more popular in web platforms and mobile applications. So far, there have been many jobs related to service classification. Most of them focus on using keywords to match keywords in other service descriptions to measure the semantic distance between different services. The classification results will have similar The functional service classification is the same category; these keyword-based methods mainly depends on the quality of the keywords in the service description, and these keywords are managed by the service provider, but because the service provider has different services The degree understanding, providers choose the best keyword for service, which will lead to semantic gatches between diff...

AI Technical Summary

Problems solved by technology

However, these deep learning models still have some problems in service classification: first, these models usually only extract features from service descriptions to classify Web services; second, these models cannot solve the problems of data sparsity and context irrelevance

Although ServeNet-BERT has advantages in service classification, it still has limitations: ServeNet-BERT just combines features with service names and service descriptions, without fully exploiting the potential semantic correlation between service names and service descriptions

Images