AI Resume Screening
Batch-parse resumes into structured talent pools: OCR, field extraction, skill taxonomy mapping, scoring, and Excel output — one pipeline, zero manual entry.
What does this workflow do?
System flow
PDF 版面分析与全文提取 → AI 语义解析（多维度简历信息提取）→ 技能标准化映射（LinkedIn 技能分类体系）→ 工作经历时间线校验与空档期检测 → 岗位匹配度评分（基于 JD 关键词相似度 + 经验权重）→ 重复候选人检测与合并 → 结构化 Excel 输出（可筛选/排序）
Pipeline breakdown
- PyPDF
pypdf— PDF text and metadata extraction, page-level splitting pdf → text - LLM Reasoning
llm— Large-language-model step that extracts, classifies, validates or writes structured output text → json - Pandas
pandas— Tabular compute — join, aggregate, validate and reshape the extracted records json → json - LLM Reasoning
llm— Large-language-model step that extracts, classifies, validates or writes structured output json → json - OpenPyXL
openpyxl— Writes a formatted, formula-ready Excel workbook as the deliverable json → xlsx
Workflow Reputation Score
Based on executions, success rate, update frequency, component quality, and user rating.
Based on executions, success rate, update frequency, component quality, and user rating.
Components used
Large-language-model step that extracts, classifies, validates or writes structured output
FlowSync proprietaryTabular compute — join, aggregate, validate and reshape the extracted records
pandas-dev/pandas ↗Writes a formatted, formula-ready Excel workbook as the deliverable
theorchard/openpyxl ↗How is this different from n8n or Zapier?
Unlike generic workflow builders, FlowSync workflows ship pre-configured with AI skills baked into every node — OCR, LLM reasoning, transcription, super-resolution — not just webhook triggers. Each node is white-box auditable: you see input, output, and config. Deployment is instant — no self-hosting, no API-key per node.
Use cases
- 校招/社招批量初筛
- 猎头候选人库建设
- 多岗位并行招聘
- 人才库数字化管理
Author & Source
Field notes
校招 5000 份简历，HireEZ 年费 $3000+。FlowSync Pro $19/月搞定，匹配度评分比 HireEZ 还准。
批量解析后按技能标签检索，候选人匹配效率提升 10 倍。
Data handling
FlowSync Workflow Marketplace · 76 reputation score · 30% execution · 100% success · 5-node white-box pipeline · maintained by FlowSync Official
Ready to run?
Batch-parse resumes into structured talent pools: OCR, field extraction, skill taxonomy mapping, scoring, and Excel output — one pipeline, zero manual entry.