(Національний технічний університет "Харківський політехнічний інститут", 2024) Rudskyi, Oleksandr Vadymovych; Kopp, Andrii Mykhailovych; Goncharenko, Tetiana Yevhenivna; Gamayun, Igor Petrovych
In this paper, we present a method for comparing business process models with their textual descriptions, using a semantic-based approach based on the SBERT (Sentence-Bidirectional Encoder Representations from Transformers) model. Business process models, especially those created with the BPMN (Business Process Model and Notation) standard, are crucial for optimizing organizational activities. Ensuring the alignment between these models and their textual descriptions is essential for improving business process accuracy and clarity. Traditional set similarity methods, which rely on tokenization and basic word matching, fail to capture deeper semantic relationships, leading to lower accuracy in comparison. Our approach addresses this issue by leveraging the SBERT model to evaluate the semantic similarity between the text description and the BPMN business process model. The experimental results demonstrate that the SBERT-based method outperforms traditional methods, based on similarity measures, by an average of 31%, offering more reliable and contextually relevant comparisons. The ability of SBERT to capture semantic similarity, including identifying synonyms and contextually relevant terms, provides a significant advantage over simple token-based approaches, which often overlook nuanced language variations.
