Semantic Service Clustering With Lightweight BERT-Based Service Embedding Using Invocation Sequences

Service clustering is an efficient method for facilitating service discovery and composition. Traditional approaches based on the self-description documents services usually utilize signatures. In Web composition, can also be performed by invocation relationship between services. Therefore, successful development of several embedding techniques words in contexts, a novel deep learning-based using sequences devised clustering. Moreover, many microservices are being created because rapid Internet Things (IoT), edge, fog computing. Following these developments, composition environments has emerged abundance. More lightweight to analyze large numbers necessary Consequently, approach semantic presented address requirements. this paper, we first propose concept capture information from sequences. Second, suggest state-of-the-art neural language sequence models develop corresponding Bidirectional Encoder Representations Transformers (BERT)-based model. Next, combined with K-means clustering, evaluated. Finally, experimental results show that process effectively BERT-based