AIR Agent—A GPT-Based Subway Construction Accident Investigation Report Analysis Chatbot
Open Access
Abstract
Subway construction accident reports often take a lot of time and personnel to analyze and contain a large amount of data that require professional identification, which increases the difficulty of the analysis. This study aims to use Generative Pre-trained Transformer (GPT) models for the automated analysis of subway construction accident investigation reports, with the goal of improving the efficiency of accident identification and analysis. By analyzing a dataset of 50 subway reports, this study developed the Accident Investigation Report (AIR) Agent, which utilizes GPTs to automatically identify accident types and extract key details from the reports. The chatbot is composed of three core modules: a conversation module, an instruction module, and a knowledge module. Ablation studies were performed to validate the AIR Agent’s efficiency, and the validation results show that the AIR Agent achieves an accuracy of 80.32% when analyzing new reports with a brief conclusion, demonstrating the AIR Agent’s ability to automatically format and structure reports in a consistent and correct manner. These findings suggest that the AIR Agent can significantly reduce the manual effort involved in accident investigation report analysis and enhance the overall efficiency of analyzing subway construction accident investigation reports, thereby improving the effectiveness of accident investigation and management.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFC3014103)
This publication has 21 references indexed in Scilit:
- AI-Generated Medical Advice—GPT and BeyondJAMA, 2023
- Accident pattern recognition in subway construction for the provision of customized safety measuresTunnelling and Underground Space Technology, 2023
- ChatGPT for good? On opportunities and challenges of large language models for educationLearning and Individual Differences, 2023
- Development of a database exclusively for subway construction accidents and corresponding analysesTunnelling and Underground Space Technology, 2021
- Assessment of tunnel face stability subjected to an adjacent tunnelReliability Engineering & System Safety, 2021
- Text mining-based construction site accident classification using hybrid supervised machine learningAutomation in Construction, 2020
- Root causes of coal mine accidents: Characteristics of safety culture deficiencies based on accident statisticsProcess Safety and Environmental Protection, 2020
- Risk assessment for construction of urban rail transit projectsSafety Science, 2019
- Analysis of excessive deformations in tunnels for safety evaluationTunnelling and Underground Space Technology, 2015
- Strategies for dealing with resistance to recommendations from accident investigationsAccident Analysis & Prevention, 2011