A DMSS for Sustainable Residential Interior Environmental Design Knowledge Management, Green-Material Ontologies, and Multi-Criteria Optimization

This article presents a decision-making support system for sustainable residential interior environmental design that links knowledge management with artificial intelligence-enabled multi-criteria optimization. The architecture integrates data capture, storage, and retrieval for layouts, green-material metrics, energy logs, and resident feedback; a knowledge base unifying organizational memory, best-practice repositories, and semantic ontologies of green materials; a model base with multi-criteria decision models, simulation-derived surrogates, and recommendation routines; dialog management for preference elicitation, constraint specification, and what-if analysis; and output presentation via explainable dashboards plus a feedback-control layer that learns from post-occupancy evaluations. Mixed methods populate and validate the data/knowledge/model bases across diverse housing typologies. Empirical analyses indicated faster green-material adoption, improved layout decisions via designer–resident collaboration, and measurable gains in energy-use intensity and indoor comfort.