Automatic Generation of a Business Process Model Diagram Based on Natural Language Processing

Business Process Management is essential for businesses to adapt to changing requirements and stay relevant in the market. It manages chains of activities, the people involved, systems, artifacts, and information to support business processes. A Business Process Model is a visual representation of a business process. Business Process Model and Notation Version 2.0 (BPMN 2.0) is one of the most commonly used specifications. Thus, it is used in this paper. The manual gathering of information about business processes and the following modeling phase, usually conducted by experts, is very time-consuming. This work presents a software-based tool to support generating business process models based on a narrative in natural language. Natural Language Processing (NLP) methods are applied to create the corresponding process model in BPMN 2.0. NLP deals with the automated processing of human language, allowing machines to analyze and understand the meaning of natural language. This paper presents the first results of the evaluation of this prototype. Two different business processes have been automatically generated based on the description of persons who execute these processes. These results show that this approach accelerates the process modeling phase differently.