Automated reasoning for regulatory compliance checking in the construction domain

Automating the process of compliance checking is expected to reduce the time and cost of the process, as well as reduce the probability of making compliance assessment errors. Automated reasoning is essential for enabling the automation of compliance checking. Among the different types of formally defined logic, which has varying degrees of descriptive capability, first order logic (FOL) is the most widely used for logical inference making. In this paper, we present our FOL-based representation method for supporting automated regulatory compliance checking in construction. The expressivity of FOL is leveraged to describe various concepts and their relations in construction regulations. Prolog is the most widely used logic programming language and reasoner. We used B-Prolog (an implementation of Prolog) for implementing our proposed method. We tested the method on representing and reasoning about quantitative requirements in Chapter 12 of the 2006 edition of the International Building Code. We developed 109 instances of project information as the test set. We tested the performance of our proposed method in detecting noncompliance instances. Using automatically extracted and transformed regulatory information (and represented in the form of logic clauses), we achieved 0.929 and 0.981 for precision and recall in detecting noncompliance instances, respectively. We also compared automated checking to manual checking in terms of the time efficiency. Automated checking takes a time shorter than 1/10,000 of that for manual checking.