The statutory provisions are crucial for safeguarding safety and productivity in mining and averting loss of life and property. Adherence to these rules is obligatory. The integration of artificial intelligence (AI), natural language processing (NLP), and large language models (LLMs) may improve safety, efficiency, and real-time decision-making in the mining industry. This research investigates the creation of a chatbot using the natural language toolkit (NLTK), cosine similarity, and subsequently, a retrieval-augmented generation (RAG) framework with transformer-based models, such as bi-directional encoder representation from transformers (BERT) and large language model meta AI 2 (LLaMA 2). The system analyses regulatory documents using pre-processing, tokenisation, chunking, embedding creation, and semantic search to provide precise, contextually relevant replies. By transforming legal documents into vector embeddings, the chatbot achieves a retrieval accuracy of 95% and reduces query response time by 70%. This approach demonstrates a scalable, machine learning-based compliance tool that enhances operational efficiency and decision-making by automating access to critical safety information.
Baske et al. (2026) studied this question.