Semantic modeling for automated compliance checking

Automated compliance checking of construction projects remains to be a challenge. Existing computer-supported compliance checking methods are mainly rule-checking systems (utilizing if-then-else logic statements) that assess building designs based on a set of well-defined criteria. However, laws and regulations are normally complex to interpret and implement; and thus if-then-else rule-checking does not provide the level of knowledge representation and reasoning that is needed to efficiently interpret applicable laws and regulations and check conformance of designs and operations to those interpretations. In this paper, we explore a new approach to automated regulatory compliance checking - we propose to apply theoretical and computational developments in the fields of deontology, deontic logic, and Natural Language Processing (NLP) to the problem of regulatory compliance checking in construction. Deontology is a theory of rights and obligations; and deontic logic is a branch of modal logic that deals with obligations, permissions, etc. The paper starts by discussing the need for automated compliance checking of construction operations and analyzing the limitations of existing compliance checking efforts in this regard. The paper, then, provides an overview of the proposed approach for automated compliance checking; and follows by an introduction of deontology and deontic logic and their applications in other domains (e.g. computational law). Finally, the paper presents the initial deontic modeling efforts towards automated compliance checking.