Defining Business Process Models with Natural Language Processing and Speech Recognition

Abstract

Proposed approaches for modeling unstructured business processes include declarative, constraint-based solutions, which meet halfway between support and flexibility. A noteworthy example is the Declare framework, which is equipped with a graphical declarative language whose semantics can be expressed with multiple logic-based formalisms. So far, the practical use of Declare constraints has been mostly hampered by the difficulty of modeling them: the formal notation of Declare represents a steep learning curve for users lacking an understanding of temporal logic, while the graphical notation has proven to be unintuitive. As such, this work presents and assesses an analysis toolkit which tries to circumvent this issue by providing the user with a possibility to model Declare constraints by using their own way of expression. The toolkit includes a Declare modeler supplied with a speech recognition mechanism, which accepts a user’s vocal statement as input and converts it into the closest Declare constraint(s) by combining voice recognition, natural language processing and business rule extraction technologies. The constraints cover the entire Multi-Perspective extension of Declare (MP-Declare), complementing control-flow constraints with data and temporal perspectives. Even though this thesis focuses on Declare, it represents the first attempt at testing the practicability of speech recognition in business process modeling altogether.