Knowledge representation and reasoning using interconnected uncertain rules for describing workflows in complex systems

Knowledge representation and reasoning (KRR) in complex systems (CSs) usually require facts from multiple experts having complementary backgrounds to fuse together. Consequently, such KRR methods should provide universal modeling languages close to human reasoning, with increased expressiveness and efficient capabilities to describe uncertainties. In this context, this paper introduces a new modeling formalism entitled Hybrid Logic-Algebraic Relational Modeling which is based on combining logic, probabilities, numerical information and network representations. The behavior, facts and workflows in a CS can be described using an environment of interconnected models enclosing sets of logical rules with attached probabilistic trust factors and links regarding logical attributes and numerical parameters. The logical and probabilistic inference applied to the modeling environment gives valuable knowledge to designers and decision-makers so that they can develop procedures or take actions in managing the CS. In this article, the proposed approach is completely formalized, from concept to definition and proofs and up to implementation, while its usage is illustrated within a complex economic, logistical, economical and technical scenario.