大语言模型驱动的城市轨道交通突发事件应急响应方法OA

[Background]Improper emergency management in rail transit systems can significantly disrupt train operations,thus potentially causing passenger injuries and substantial economic losses.[Objective]This study introduces a large language model(LLM)for emergency management(EM-LLM)that integrates a domain-specific local knowledge base.Its primary goal is to provide urban rail transit dispatchers with rapid and accurate decision support in complex environments,thereby safeguarding the operational safety and reliability of urban rail transit systems.[Method]Textual da-ta were obtained,segmented,and vectorized to construct a local knowledge base.A unified"prompt"was defined to serve as the global guiding instruction for model responses.The EM-LLM was devel-oped and deployed locally using the LangChain framework.To validate its effectiveness,a compara-tive human-machine evaluation experiment was designed.In this experiment,three approaches—ex-perienced dispatchers,a general-purpose LLM,and the proposed EM-LLM—were tested in 34 typi-cal emergency scenarios.The performance was evaluated across multiple dimensions,including the quality of the generated dispatch instructions,the response time,and the completeness of the generat-ed decision.[Data]A local knowledge base was constructed using approximately 10 million charac-ters from national,industrial,and enterprise standards related to train dispatching,along with histori-cal emergency-management data.[Result]Although the general-purpose LLM exhibited certain ad-vantages over human dispatchers in terms of fault-type classification,it underperformed in generat-ing comprehensive,long-form management decisions.By contrast,the EM-LLM demonstrated great-er effectiveness in responding to complex and unexpected emergency scenarios.[Conclusion]The EM-LLM offers valuable support for intelligent rail traffic management in complex emergency sce-narios,thus significantly enhancing the emergency response capabilities and operational efficiency of the system during unexpected disruptions.