AI-driven intelligent hazard monitoring for major petroleum projects under the Belt and Road Initiative: construction of an indicator system based on DPGT and RAG-HLLM

• Proposes a novel Dual-Path Grounded Theory (DPGT) framework for human-AI collaborative analysis. • Develops a hybrid LLM architecture (RAG-HLLM) balancing data privacy and reasoning power. • Constructs a comprehensive hazard monitoring system for major petroleum projects. • The AI-aided indicator system achieves a 92.61% recall rate on an industry database. • Offers a generalizable framework for intelligent safety management in major engineering projects. The major petroleum projects under the Belt and Road Initiative (BRI) encounter intricate hazard problems. Establishing a comprehensive and scientific hazard monitoring indicator system is important to realize early identification and proactive warning of risks. Therefore, this study innovatively proposes the “Dual-Path Grounded Theory” (DPGT) as a new paradigm for human–machine collaborative qualitative research. The paradigm combines the depth of human analysis with the broadness of LLMs’ processing through a system that allows for parallel coding, cross-validation, and complementary integration between human and LLM paths. It overcomes the limitations of depending merely on ineffective manual analysis or unreliable fully automatic methods. In implementation, the human-driven path utilizes the KeyBERT model and K-means clustering algorithm to help complete the three stages of coding. The LLM-driven path assesses the performance of DeepSeek-R1, Llama3, and Qwen3 models at various coding stages and chooses DeepSeek-R1 as the main engine. This is combined with Retrieval-Augmented Generation (RAG) to build a hybrid LLM deployment architecture (RAG-HLLM), making full use of superior cloud-based reasoning abilities and protecting local data privacy. According to the DPGT framework, after several rounds of integration and screening, a hazard monitoring indicator system including 2 major categories, 8 first-level indicators, 27 second-level indicators, and 109 specific factors was finally established. Validation indicates that this system has passed the theoretical saturation test and has achieved a recall rate of 92.61% on the International Association of Oil and Gas Producers (IOGP) standard database, which greatly surpasses the results obtained from single-path methods. Methodologically, this study pioneers a new paradigm for human–machine collaborative qualitative research. Technologically, the proposed hybrid architecture balances privacy concerns with processing efficiency. Practically, it provides a dependable tool for safety management in major energy projects, exhibiting significant theoretical value and broad engineering applicability.