基于大语言模型的碰撞叙事引导的对策推荐：面向交叉口安全的检索增强生成框架
Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety
浏览论文内容
中文总结 AI 辅助
提出一种碰撞叙事引导的检索增强生成框架，利用大语言模型将非结构化碰撞叙事转化为交叉口安全对策建议，在佛罗里达州数据上实现0.82的F1分数，验证了其可解释性和可扩展性。
中文摘要 AI 辅助
提高交叉口安全性需要识别碰撞机制并推荐适当的对策。然而，这一过程传统上依赖专家判断，导致其劳动密集、难以规模化，并且依赖于经验丰富的交通安全工程师的可用性。尽管碰撞叙事包含了对碰撞机制的丰富描述，但这一非结构化信息在安全分析中仍未得到充分利用。本研究提出了一种碰撞叙事引导的检索增强生成（RAG）框架，将源自叙事的碰撞机制转化为针对具体地点的对策建议。从碰撞叙事中提取了关键机制属性，包括交通控制、信号指示、驾驶员过错、车辆运动和行驶方向，并将其与FHWA Proven Safety Countermeasures和CMF Clearinghouse中的循证治疗措施相关联。该框架整合了基于嵌入的历史相似交叉口检索、关联规则挖掘、关于预期相关对策数量的统计指导，以及工程推理指导，后者引导大语言模型在选择对策前经历符合领域规范的决策过程。在佛罗里达州莱克县和萨姆特县115个交叉口的312起致命和严重伤害碰撞中，使用五折交叉验证进行评估，该框架实现了0.82的精确率、0.85的召回率和0.82的F1分数，同时每个地点平均推荐3.91项对策，其中3.14项匹配，与实际平均值（3.86）非常接近。总体而言，所提出的框架展示了检索增强大语言模型作为交通机构可解释且可扩展的决策支持工具的潜力，可将碰撞叙事转化为对策建议。
英文摘要
Improving safety at intersections requires identifying crash mechanisms and recommending appropriate countermeasures. However, this process traditionally relies on expert judgment, making it labor-intensive, difficult to scale, and dependent on the availability of experienced traffic safety engineers. Although crash narratives contain rich description of crash mechanisms, this unstructured information remains largely underutilized in safety analyses. This study presents a crash narrative-guided retrieval-augmented generation (RAG) framework that translates narrative-derived crash mechanisms into site-specific countermeasure recommendations. Key mechanism attributes including traffic control, signal indication, driver fault, vehicle movement, and travel direction were extracted from crash narratives and linked to evidence-based treatments from the FHWA Proven Safety Countermeasures and the CMF Clearinghouse. The framework integrates embedding-based retrieval of historically similar intersections, association-rule mining, statistical guidance on the expected number of relevant countermeasures, and an engineering reasoning guidance that directs LLM through a domain-consistent decision process before selecting countermeasures. Evaluated on 312 fatal and serious-injury crashes across 115 intersections in Lake and Sumter Counties, Florida, using five-fold cross-validation, the framework achieved a precision of 0.82, recall of 0.85, and F1-score of 0.82, while recommending an average of 3.91 countermeasures per location with 3.14 matching, closely matching the actual average (3.86). Overall, the proposed framework demonstrates the potential of retrieval-augmented LLMs as an interpretable and scalable decision-support tool for transportation agencies for translating crash narratives into countermeasure recommendations.
发表机构
- University of Central Florida（中佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。
