Extending Building Information Models Semiautomatically Using Semantic Natural Language Processing Techniques

Automated compliance checking (ACC) of building designs requires automated extraction of information from building information models (BIMs). However, current industry foundation classes (IFC)-based BIMs provide limited support for ACC, because they lack the necessary information that is needed to perform compliance checking (CC). In this paper, the authors propose a new method for extending the IFC schema to incorporate CC-related information, in an objective and semiautomated manner. The method utilizes semantic natural language processing techniques and machine learning techniques to extract concepts from documents that are related to CC (e. g., building codes) and match the extracted concepts to concepts in the IFC class hierarchy. The proposed method includes a set of methods/algorithms that are combined into one computational platform: (1) a method for concept extraction that utilizes pattern-matching-based rules to extract regulatory concepts from CC-related regulatory documents; (2) a method for concept matching and semantic similarity assessment to select the most related IFC concepts to the extracted regulatory concepts; and (3) a machine learning classification method for predicting the relationship between the extracted regulatory concepts and their most related IFC concepts. The proposed method enables the extension of the IFC schema, in an objective way, using any construction regulatory document. To test and evaluate the proposed method, two chapters were randomly selected from the International Building Code (IBC) 2006 and 2009. Chapter 12 of IBC 2006 was used for training/development and Chapter 19 of IBC 2009 was used for testing and evaluation. Comparing to manually-developed gold standards, 91.7% F1-measure, 84.5% adoption rate, and 87.9% precision were achieved for regulatory concept extraction, IFC concept selection, and relationship classification, respectively. (C) 2016 American Society of Civil Engineers.