TSG Suggester：树结构知识图谱检索用于云事件故障排查指南推荐
原标题：TSG Suggester: Tree-Structured Knowledge-Graph Retrieval for Troubleshooting Guide Recommendation in Cloud Incident Management
AI 摘要
该论文提出 TSG Suggester，一个面向云事件管理的故障排查指南（TSG）推荐检索系统，可直接从事件描述中推荐相关 TSG。系统将指南解析为保留原生章节层级的树结构，为内部节点附加 LLM 生成的问题抽象，并抽取每份指南的实体知识图谱，在查询时融合嵌入相似度与实体级匹配。在来自 18 个服务团队的 314 个真实事件和 112 份 TSG 上，Tree + KG 取得 54.78% Top-1 和 82.48% Top-5 准确率，优于所有基线，比纯文本 RAG 的 Top-1 高 8.58 个百分点。研究还发现结构对齐主导效果，而多模态图像描述反而使 Top-5 下降 22.64 个百分点。
正文节选
TSG Suggester: Tree-Structured Knowledge-Graph Retrieval for Troubleshooting Guide Recommendation in Cloud Incident Management Abstract On-call engineers in large-scale cloud services work under intense time pressure, yet locating the correct Troubleshooting Guide (TSG) for an incident remains a largely manual, keyword-driven process—and prior empirical work finds that guide search consumes a substantial fraction of total mitigation time. We present TSG Suggester, a retrieval system that recomme