End-user development (EUD) and model-driven engineering (MDE) are particularly valuable for building classical intelligent systems that rely on declarative knowledge bases. In these knowledge bases, the key dependencies of the domain can be described in the form of logical rules. The general-purpose modeling language used in MDE, specifically UML, enables modeling of static data structures and the dynamics of object behavior; however, it does not primarily support the modeling logical rules. In this paper, we propose a rule visual modeling language inspired by UML—Rule Visual Modeling Language (RVML)—which expands the capabilities of MDE in terms of using domain-specific visual languages. This approach substantially supports end-users in constructing declarative knowledge bases. We present the formal semantics, visual syntax, and features of RVML, along with two industrial case studies. We empirically evaluate the effectiveness of RVML in development compared to other graphic notations used for modeling logical rules. Our evaluation demonstrates that RVML provides superior expressiveness and better preservation of semantic integrity.
Yurin et al. (Mon,) studied this question.