Digital Decision Support in Construction: Analysis of Information Requirements and Data Provision for AI-based Selection of Sustainable Building Products

Abstract: The construction industry is increasingly adopting sustainable, resource-efficient practices requiring data-driven decisions. However, manual data preparation and lack of standardisation impede this transition. Certification systems like DGNB, quality seals like QNG and classification systems like the EU Taxonomy incorporate measurable sustainability criteria, highlighting the need for reliable data. This study utilises LLMs to extract data from product data sheets and Environmental Product Declarations, converting it to standardised JSON schema. By integrating Python and knowledge graphs, the structured data can be matched against sustainability criteria, serving as foundation for planners, contractors, and clients to make AI-based decisions for sustainable building products.