NLP-based Data-Enrichment for Building Management

Abstract: One of the main challenges in building management is dealing with the large amount of unstructured data produced in the asset’s life cycle, including design and construction, and extracting the information needed in the operational phase. At handover, Building Information Models often provide low-quality, incomplete data, necessitating extensive manual re-work to elicit information from many sources. So, this study proposes an automated Information Extraction procedure, applied to the design and construction documents to extract information and enrich a COBie format. The proposed approach is based on Natural Language Processing, adopts Transformer-based Named Entity Recognition and Relation Extraction methods for IE.