用少量样例让大模型从维修日志中提取关键故障模式
LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs
- 通过少样本提示学习，将非结构化日志转为可机读数据
- 基于6169条记录的测试，成功识别出关键故障模式
- 适合航空、工业维护等需要从文本中挖信息的场景
飞机维修日志包含宝贵的安全数据，但因格式非结构化而难以利用。本文提出LogSyn框架，借助大语言模型（LLM）将这些日志转化为结构化、机器可读的数据。该框架在6,169条记录上采用少样本上下文学习，执行受控抽象生成（CAG），对问题-解决过程进行摘要，并在详细的分层本体中分类事件。该方法能有效识别关键故障模式，为航空及关联行业提供一种可扩展的语义结构化与可操作洞察提取方案，助力改进维护流程与预测分析。
原文摘要 · Abstract (English)
Aircraft maintenance logs hold valuable safety data but remain underused due to their unstructured text format. This paper introduces LogSyn, a framework that uses Large Language Models (LLMs) to convert these logs into structured, machine-readable data. Using few-shot in-context learning on 6,169 records, LogSyn performs Controlled Abstraction Generation (CAG) to summarize problem-resolution narratives and classify events within a detailed hierarchical ontology. The framework identifies key failure patterns, offering a scalable method for semantic structuring and actionable insight extraction from maintenance logs. This work provides a practical path to improve maintenance workflows and predictive analytics in aviation and related industries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。