Retrieval-augmented generation in home construction calculation : developing an intelligent assistance system
Abstract
This thesis develops and evaluates a prototype retrieval-augmented generation (RAG)–based chatbot assistant that supports non-expert users in completing the complex input process of a home construction calculation. While existing cost calculation tools primarily target professional users, private homebuilders often struggle with technical terminology, interdependencies, and normative requirements, which undermines planning security and decision quality. To ease this process, the chatbot is integrated into an existing web-based cost calculation workflow and provides context-sensitive explanations and guidance during data entry. Following the Action Design Research (ADR) methodology, the thesis proceeds in four steps: (1) requirement analysis via a standardized survey to identify typical comprehension problems, (2) design of an intelligent assistance concept, (3) technical implementation of the RAG chatbot using LangChain, LangGraph, ChromaDB, FastAPI, and Google GenAI, and (4) empirical evaluation of user acceptance. The prototype assistant provides context-sensitive, natural-language help on demand, grounded in a curated knowledge base focused on high-friction topics such as efficiency classes and funding, roof parameters, wall materials and thicknesses, and storey dimensions. User acceptance was assessed in a controlled study (n = 12), in which participants completed a realistic planning task and then rated the system using an extended Technology Acceptance Model (TAM)…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.