Construction safety reporting improved by conversational ai system
CARES: A Conversational AI System for Regulation-Grounded Safety Reporting in Construction Education
Human-Computer Interaction
Summary
Safety reports at construction sites often miss important rules because they rely on manual entries or fixed forms. The authors created CARES, a new chatbot that helps people write safety reports while showing the relevant safety rules. CARES uses smart techniques to find these rules and turns conversations into organized reports that users can review and fix. Early tests with students showed the system is pretty accurate and useful, although some parts that find information can be better. This study suggests chatbots could help people learn and follow safety rules better in construction work.
What this means in practice
- •For construction project managers: Use a conversational assistant to generate safety reports linked to relevant regulations during daily site activities.
- •For facility maintenance teams: Improve safety documentation by integrating conversational AI that references compliance rules during routine inspection reporting.
Authors
Fan Yang, Jiabin Wu, Yuan Tian, Jiansong Zhang
Abstract
Construction safety reporting often relies on manual logs and static templates that provide limited feedback and leave daily activities disconnected from relevant regulations. This paper introduces CARES (Conversational AI Reporting for Enhanced Safety), a conversational AI system that integrates regulatory guidance into daily reporting to support construction safety education. CARES combines proactive multi-agent dialogue, retrieval-augmented generation (RAG), and automated report generation. The system guides users through reporting tasks, retrieves relevant regulatory passages using hybrid retrieval, and converts conversations into structured daily reports. Regulatory sources and the evolving report are displayed alongside the dialogue to support user review and correction. A preliminary evaluation involving 15 construction management students assessed retrieval quality, response faithfulness, and conversational relevance. CARES achieved an overall faithfulness score of 0.74 and an answer relevance score of 1.00, while initial retrieval ranking remained an area for improvement. These results provide preliminary evidence of the technical feasibility of regulation-grounded conversational reporting. The study highlights opportunities to integrate regulatory knowledge into routine documentation, with future work needed to evaluate effects on report quality, safety awareness, and learning outcomes.