Before starting any construction work, providing workers with awareness about past similar accident cases is effective in preventing mishaps. Based on construction accident reports, this study developed two models to identify past accidents at sites with similar site information. The site information includes 16 parameters, such as type of work, type of accident, the work in which the accident occurred, weather conditions, contract conditions, type of work, etc. The first model, the site information classification model, uses named entity recognition tasks to classify site information, which is extracted from accident reports. The second model, the similar-site accident retrieval model, which finds the most similar accidents that occurred in the past from input site information, uses a semantic textual similarity task to match the classified information with it. A total of 17,707 accident reports from South Korean construction sites were found; these models were trained to use Korean Language Understanding Evaluation–Bidirectional Encoder Representations from Transformers (KLUE-BERT) for processing. The first model achieved an average accuracy of 0.928, and the second model was precisely matched, with a mean cosine similarity score exceeding 0.90. These models could identify and provide workers with similar past accidents, enabling proactive safety measures, such as site-specific hazard identification and worker education, thereby allowing recognition of construction safety risks before starting work. By integrating site information with historical data, the models offer an effective approach to improving construction safety.

This study aimed to develop the accident mechanism of fatal accidents taking place in multiple processes at the workplace. Multiple processes were defined as the existence of multiple work types and work processes in the same workspace. Recently, various processes are frequently conducted simultaneously in one workplace with the participation of several companies, and more workers are increasingly experiencing industrial accidents while working in multiple processes. To prevent accidents in the multiple processes caused by the sameness of work period and space, the accident process was investigated by analyzing the investigation reports on serious industrial accidents in South Korea, and then the accident mechanism model was developed. By utilizing the developed model, the major safety measures to be taken by the contractor for each of the 8 types of accidents caused by the multiple processes were drawn. The roles and responsibilities of the contractor to be implemented in order to prevent accident occurrence in multiple processes were proposed through the accident mechanism of each type of fatal accident. It is expected that the accidents taking place in the multiple processes can be prevented with the drawn results.

This study developed a safety control structure model to analyze stakeholder interactions to improve safety in Korean building demolition projects. Legal stakeholders and safety measures were systematically incorporated into the System Theoretic Accident Model and Processes (STAMP). The novelty of this safety model is that it provides the first systematic application of STAMP to Korean building demolition, with a specific focus on legal stakeholders and their safety interactions. The results revealed that unsystematic reviews by licensing agencies, the absence of expert reviewers, and the inadequate role of supervisors were key factors contributing to accidents. In particular, the inspection and corrective action of safety measures performed by demolition supervisors directly impacted on-site safety. Furthermore, licensing agencies were identified as key players in determining the overall safety level of demolition projects. The proposed model provides a framework for effectively understanding the roles and responsibilities of stakeholders and supports the identification of non-compliance with safety measures. The use of the proposed model is expected to strengthen the interaction between stakeholders, enhance on-site safety, and contribute to the development of accident prevention strategies for future demolition projects.