将工厂维修流程图转为可查询的结构化知识图谱
FlowExtract: Procedural Knowledge Extraction from Maintenance Flowcharts
- 分两步提取：先识别节点，再通过箭头方向追溯连接关系
- 节点识别准确率高，边提取性能显著优于视觉语言模型
- 适合需要数字化维护流程的企业和工业AI系统开发者
制造设施中的维护流程常以静态PDF或扫描图像中的流程图形式存在，虽蕴含资产全生命周期管理的关键流程知识，却难以被现代运维系统使用。当前主流的视觉语言模型在从这类图表中重建连接拓扑方面表现不佳。本文提出FlowExtract，一种从符合ISO 5807标准的流程图中提取有向图的流水线方法。系统将元素检测与连通性重建分离：采用YOLOv8和EasyOCR进行领域对齐的节点检测与文本提取；设计新型边检测方法，通过分析箭头朝向并反向追踪连线至源节点实现连接关系还原。在工业故障排查指南数据集上的评估显示，该方法在节点检测上表现优异，在边提取上显著优于视觉语言模型基线，为组织构建可查询的流程知识表示提供了实用路径。代码已开源：https://github.com/guille-gil/FlowExtract。
原文摘要 · Abstract (English)
Maintenance procedures in manufacturing facilities are often documented as flowcharts in static PDFs or scanned images. They encode procedural knowledge essential for asset lifecycle management, yet inaccessible to modern operator support systems. Vision-language models, the dominant paradigm for image understanding, struggle to reconstruct connection topology from such diagrams. We present FlowExtract, a pipeline for extracting directed graphs from ISO 5807-standardized flowcharts. The system separates element detection from connectivity reconstruction, using YOLOv8 and EasyOCR for standard domain-aligned node detection and text extraction, combined with a novel edge detection method that analyzes arrowhead orientations and traces connecting lines backward to source nodes. Evaluated on industrial troubleshooting guides, FlowExtract achieves very high node detection and substantially outperforms vision-language model baselines on edge extraction, offering organizations a practical path toward queryable procedural knowledge representations. The implementation is available athttps://github.com/guille-gil/FlowExtract.
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。