Question Answering for Decisionmaking in Green Building Design: A Multimodal Data Reasoning Method Driven by Large Language Models

TL;DR

The paper tackles the high learning costs and inefficiencies in green building design decision-making by integrating large language models with a multimodal knowledge base in GreenQA. It deploys Retrieval Augmented Generation, Chain of Thought, and Function Call to enable multimodal QA across weather data, case retrieval, and knowledge queries, demonstrated via a web platform and a user study. Key contributions include a 3.8-million-word KB with 1,200 cases, a multimodal QA pipeline, and evidence of improved design efficiency (96% of users) along with identified limitations and future work. This work offers a practical AI-assisted design workflow that enhances knowledge access, reasoning, and data-driven decisions in green building design.

Abstract

In recent years, the critical role of green buildings in addressing energy consumption and environmental issues has become widely acknowledged. Research indicates that over 40% of potential energy savings can be achieved during the early design stage. Therefore, decision-making in green building design (DGBD), which is based on modeling and performance simulation, is crucial for reducing building energy costs. However, the field of green building encompasses a broad range of specialized knowledge, which involves significant learning costs and results in low decision-making efficiency. Many studies have already applied artificial intelligence (AI) methods to this field. Based on previous research, this study innovatively integrates large language models with DGBD, creating GreenQA, a question answering framework for multimodal data reasoning. Utilizing Retrieval Augmented Generation, Chain of Thought, and Function Call methods, GreenQA enables multimodal question answering, including weather data analysis and visualization, retrieval of green building cases, and knowledge query. Additionally, this study conducted a user survey using the GreenQA web platform. The results showed that 96% of users believed the platform helped improve design efficiency. This study not only effectively supports DGBD but also provides inspiration for AI-assisted design.

Figures (16)

• Figure 1: Conceptual illustration of the question answering platform GreenQA for decision-making in green building design.
• Figure 2: Research framework.
• Figure 3: Multimodal green building knowledge base.
• Figure 4: Implementation of cases and knowledge base retrieval.
• Figure 5: Comparison of results with/without using zero-shot CoT.