feat(aia): Complete AIA V2.0 with universal streaming capabilities

Major Changes:
- Add StreamingService with OpenAI Compatible format
- Upgrade Chat component V2 with Ant Design X integration
- Implement AIA module with 12 intelligent agents
- Update API routes to unified /api/v1 prefix
- Update system documentation

Backend (~1300 lines):
- common/streaming: OpenAI Compatible adapter
- modules/aia: 12 agents, conversation service, streaming integration
- Update route versions (RVW, PKB to v1)

Frontend (~3500 lines):
- modules/aia: AgentHub + ChatWorkspace (100% prototype restoration)
- shared/Chat: AIStreamChat, ThinkingBlock, useAIStream Hook
- Update API endpoints to v1

Documentation:
- AIA module status guide
- Universal capabilities catalog
- System overview updates
- All module documentation sync

Tested: Stream response verified, authentication working
Status: AIA V2.0 core completed (85%)

docs/03-业务模块/ASL-AI智能文献/02-技术设计/07-文献处理技术选型.md

@@ -1,86 +1,86 @@
 # ASL <20><>讃憭<E8AE83><E686AD><EFBFBD><EFBFBD><EFBFBD>舫<EFBFBD>匧<EFBFBD>
 
-> **文档版本：** V1.0  
-> **创建日期：** 2025-11-15  
-> **适用模块：** AI 智能文献（ASL）  
-> **目标：** 定义初筛、全文复筛、全文提取的技术栈和实现路径
+> **<EFBFBD><EFBFBD>﹝<EFBFBD><EFBFBD>𧋦嚗?* V1.0  
+> **<EFBFBD>𥕦遣<EFBFBD>交<EFBFBD>嚗?* 2025-11-15  
+> **<EFBFBD><EFBFBD>鍂璅∪<EFBFBD>嚗?* AI <20>箄<EFBFBD><E7AE84><EFBFBD>讃嚗㇁SL嚗? 
+> **<EFBFBD>格<EFBFBD>嚗?* 摰帋<E691B0><E5B88B>萘<EFBFBD><E89098><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>蝑䜘<E89D91><E49C98><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>𣇉<EFBFBD><F0A38789><EFBFBD><EFBFBD>舀<EFBFBD><E88880><EFBFBD><EFBFBD><EFBFBD>啗楝敺?
 
 ---
 
 ## <20><> <20><>﹝璁<EFB99D>膩
 
-ASL 模块涉及三种不同的文献处理场景，每种场景有不同的技术特点和实现方案：
+ASL 璅∪<EFBFBD>瘨匧<EFBFBD>銝厩<EFBFBD>銝滚<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>桀<EFBFBD><EFBFBD><EFBFBD>㦤<EFBFBD>荔<EFBFBD>瘥讐<EFBFBD><EFBFBD>箸艶<EFBFBD>劐<EFBFBD><EFBFBD>𣬚<EFBFBD><EFBFBD><EFBFBD><EFBFBD>舐鸌<EFBFBD>孵<EFBFBD>摰䂿緵<EFBFBD>寞<EFBFBD>嚗?
 
-| 场景 | 输入格式 | 核心技术 | 主要挑战 |
+| <EFBFBD>箸艶 | 颲枏<E9A2B2><E69E8F>澆<EFBFBD> | <20>詨<EFBFBD><E8A9A8><EFBFBD><EFBFBD>?| 銝餉<E98A9D><E9A489>烐<EFBFBD> |
 |------|---------|---------|---------|
-| **标题摘要初筛** | Excel 文件 | Excel 解析 + LLM 筛选 | 批量处理效率 |
-| **全文复筛** | PDF 全文 | PDF 提取 + LLM 筛选 | PDF 解析准确率 |
-| **全文数据提取** | PDF 全文 | PDF 提取 + LLM 结构化提取 | 表格、公式准确提取 |
+| **<EFBFBD><EFBFBD><EFBFBD><EFBFBD>䁅<EFBFBD><EFBFBD>萘<EFBFBD>** | Excel <EFBFBD><EFBFBD>辣 | Excel 閫<EFBFBD><EFBFBD> + LLM 蝑偦<EFBFBD>?| <20>寥<EFBFBD>憭<EFBFBD><E686AD><EFBFBD><EFBFBD><EFBFBD> |
+| **<EFBFBD>冽<EFBFBD>憭滨<EFBFBD>** | PDF <EFBFBD>冽<EFBFBD> | PDF <EFBFBD>𣂼<EFBFBD> + LLM 蝑偦<EFBFBD>?| PDF 閫<EFBFBD><EFBFBD><EFBFBD><EFBFBD>＆<EFBFBD>?|
+| **<EFBFBD>冽<EFBFBD><EFBFBD>唳旿<EFBFBD>𣂼<EFBFBD>** | PDF <EFBFBD>冽<EFBFBD> | PDF <EFBFBD>𣂼<EFBFBD> + LLM 蝏𤘪<EFBFBD><EFBFBD>𡝗<EFBFBD><EFBFBD>?| 銵冽聢<E586BD><E881A2><EFBFBD>撘誩<E69298>蝖格<E89D96><E6A0BC>?|
 
 ---
 
 ## <20>㴓 <20><><EFBFBD>舀沲<E88880><E6B2B2><EFBFBD>餉<EFBFBD>
 
 ```
-┌─────────────────────────────────────────────────────────┐
-│                    ASL 文献处理流程                        │
-└─────────────────────────────────────────────────────────┘
-           │
+<EFBFBD>𢞖<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+<EFBFBD>?                   ASL <EFBFBD><EFBFBD>讃憭<EFBFBD><EFBFBD>瘚<EFBFBD><EFBFBD>                        <EFBFBD>?
+<EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+           <EFBFBD>?
            <20>鎿<EFBFBD> <20>箸艶 1: <20><><EFBFBD><EFBFBD>䁅<EFBFBD><E48185>萘<EFBFBD>
-           │   └─ 用户上传 Excel → 解析 → LLM 批量筛选 → 导出结果
-           │
+           <EFBFBD>?  <20>婙<EFBFBD> <20>冽<EFBFBD>銝𠹺<E98A9D> Excel <20>?閫<><E996AB> <20>?LLM <20>寥<EFBFBD>蝑偦<E89D91>?<3F>?撖澆枂蝏𤘪<E89D8F>
+           <EFBFBD>?
            <20>鎿<EFBFBD> <20>箸艶 2: <20>冽<EFBFBD>憭滨<E686AD>
-           │   └─ 用户上传 PDF → PDF 提取 → LLM 筛选 → 复核
-           │
+           <EFBFBD>?  <20>婙<EFBFBD> <20>冽<EFBFBD>銝𠹺<E98A9D> PDF <EFBFBD>?PDF <EFBFBD>𣂼<EFBFBD> <20>?LLM 蝑偦<E89D91>?<3F>?憭齿瓲
+           <EFBFBD>?
            <20>婙<EFBFBD> <20>箸艶 3: <20>冽<EFBFBD><E586BD>唳旿<E594B3>𣂼<EFBFBD>
-               └─ PDF → 提取 + 结构化 → LLM 提取数据 → 人工复核
+               <EFBFBD>婙<EFBFBD> PDF <EFBFBD>?<3F>𣂼<EFBFBD> + 蝏𤘪<E89D8F><F0A498AA>?<3F>?LLM <20>𣂼<EFBFBD><F0A382BC>唳旿 <20>?鈭箏極憭齿瓲
 
-┌─────────────────────────────────────────────────────────┐
-│               技术栈分层架构（共享）                        │
-├─────────────────────────────────────────────────────────┤
-│  前端层: React 19 + Ant Design 5 + xlsx/exceljs          │
-├─────────────────────────────────────────────────────────┤
-│  后端层: Node.js (Fastify) + TypeScript                  │
-├─────────────────────────────────────────────────────────┤
-│  文档处理层: Python 微服务 (extraction_service)           │
-│    ├─ PyMuPDF: 快速 PDF 提取                             │
-│    ├─ Nougat: 英文科学文献高质量提取 ⭐                   │
-│    └─ Language Detector: 自动语言检测                     │
-├─────────────────────────────────────────────────────────┤
-│  LLM 层: DeepSeek-V3 + Qwen3 / GPT-5 + Claude-4.5        │
-├─────────────────────────────────────────────────────────┤
-│  数据库: PostgreSQL 15 (asl_schema)                      │
-└─────────────────────────────────────────────────────────┘
+<EFBFBD>𢞖<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+<EFBFBD>?              <EFBFBD><EFBFBD><EFBFBD>舀<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>嗆<EFBFBD>嚗<EFBFBD><EFBFBD>鈭恬<EFBFBD>                        <EFBFBD>?
+<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+<EFBFBD>? <20>滨垢撅? React 19 + Ant Design 5 + xlsx/exceljs          <EFBFBD>?
+<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+<EFBFBD>? <20>𡒊垢撅? Node.js (Fastify) + TypeScript                  <EFBFBD>?
+<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+<EFBFBD>? <20><>﹝憭<EFB99D><E686AD>撅? Python 敺格<EFBFBD><EFBFBD>?(extraction_service)           <EFBFBD>?
+<EFBFBD>?   <EFBFBD>鎿<EFBFBD> PyMuPDF: 敹恍<EFBFBD>?PDF <EFBFBD>𣂼<EFBFBD>                             <EFBFBD>?
+<EFBFBD>?   <EFBFBD>鎿<EFBFBD> Nougat: <EFBFBD>望<EFBFBD>蝘穃郎<EFBFBD><EFBFBD>讃擃䁅捶<EFBFBD>𤩺<EFBFBD><EFBFBD>?潃?                  <EFBFBD>?
+<EFBFBD>?   <EFBFBD>婙<EFBFBD> Language Detector: <EFBFBD>芸𢆡霂剛<EFBFBD>璉<EFBFBD>瘚?                    <EFBFBD>?
+<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+<EFBFBD>? LLM 撅? DeepSeek-V3 + Qwen3 / GPT-5 + Claude-4.5        <EFBFBD>?
+<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+<EFBFBD>? <20>唳旿摨? PostgreSQL 15 (asl_schema)                      <EFBFBD>?
+<EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
 ```
 
 ---
 
 ## <20><> <20>箸艶 1: <20><><EFBFBD><EFBFBD>䁅<EFBFBD><E48185>萘<EFBFBD>
 
-### 1.1 技术特点
+### 1.1 <EFBFBD><EFBFBD><EFBFBD>舐鸌<EFBFBD>?
 
 - **颲枏<E9A2B2><E69E8F>澆<EFBFBD>**: Excel <20><>辣 (`.xlsx` / `.xls`)
-- **数据规模**: 50-500 篇文献/批次
-- **主要字段**: 标题、摘要、DOI、作者、发表年份、期刊
+- **<EFBFBD>唳旿閫<EFBFBD>芋**: 50-500 蝭<EFBFBD><EFBFBD><EFBFBD>?<3F>寞活
+- **銝餉<EFBFBD>摮埈挾**: <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>閬<EFBFBD><E996AC><EFBFBD>OI<4F><49><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>銵典僑隞賬<E99A9E><E8B3AC><EFBFBD><EFBFBD>?
 - **憭<><E686AD><EFBFBD>滨<EFBFBD>**: <20>寥<EFBFBD>擃䀹<E69383>憭<EFBFBD><E686AD>嚗峕<E59A97><E5B395><EFBFBD> PDF 閫<><E996AB>
 
 ### 1.2 <20><><EFBFBD>舫<EFBFBD>匧<EFBFBD>
 
-#### 前端：Excel 上传与解析
+#### <EFBFBD>滨垢嚗鍃xcel 銝𠹺<E98A9D>銝舘圾<E88898>?
 
-| 技术 | 库 | 用途 | 优势 |
+| <EFBFBD><EFBFBD><EFBFBD>?| 摨?| <20>券<EFBFBD>?| 隡睃飵 |
 |------|-----|------|------|
 | **Excel 銝𠹺<E98A9D>** | `antd Upload` | <20><>辣銝𠹺<E98A9D>蝏<EFBFBD>辣 | <20>𡝗嗻銝𠹺<E98A9D><F0A0B9BA><EFBFBD><EFBFBD>摨行辺 |
-| **Excel 解析** | `xlsx` / `exceljs` | 前端解析 Excel | 纯前端处理，快速预览 |
-| **模板验证** | 自定义逻辑 | 校验列名和数据格式 | 提前发现格式错误 |
+| **Excel 閫<EFBFBD><EFBFBD>** | `xlsx` / `exceljs` | <EFBFBD>滨垢閫<EFBFBD><EFBFBD> Excel | 蝥臬<EFBFBD>蝡臬<EFBFBD><EFBFBD><EFBFBD><EFBFBD>敹恍<EFBFBD>罸<EFBFBD>閫?|
+| **璅⊥踎撉諹<EFBFBD>** | <EFBFBD>芸<EFBFBD>銋厰<EFBFBD>餉<EFBFBD> | <20>⊿<EFBFBD><E28ABF>堒<EFBFBD><E5A092>峕㺭<E5B395>格聢撘?| <20>𣂼<EFBFBD><F0A382BC>𤑳緵<F0A491B3>澆<EFBFBD><E6BE86>躰秤 |
 
-**推荐方案：`xlsx` 库（SheetJS）**
-- ✅ 支持 `.xlsx` 和 `.xls` 格式
-- ✅ 纯 JavaScript，前端直接解析
-- ✅ 体积小（~600KB），性能好
-- ✅ 支持大文件（1000+ 行）
+**<EFBFBD>刻<EFBFBD><EFBFBD>寞<EFBFBD>嚗䫤xlsx` 摨橒<EFBFBD>SheetJS嚗?*
+- <20>?<3F>舀<EFBFBD> `.xlsx` <20>?`.xls` <20>澆<EFBFBD>
+- <20>?蝥?JavaScript嚗<EFBFBD><EFBFBD>蝡舐凒<EFBFBD>亥圾<EFBFBD>?
+- <20>?雿梶妖撠𧶏<E692A0>~600KB嚗㚁<E59A97><E39A81>扯<EFBFBD>憟?
+- <20>?<3F>舀<EFBFBD>憭扳<E686AD>隞塚<E99A9E>1000+ 銵䕘<EFBFBD>
 
-**代码示例：**
+**隞<><E99A9E>蝷箔<E89DB7>嚗?*
 ```typescript
 import * as XLSX from 'xlsx';
 
@@ -97,15 +97,15 @@ function parseExcel(file: File): Promise<Literature[]> {
         const sheetName = workbook.SheetNames[0];
         const worksheet = workbook.Sheets[sheetName];
         
-        // 转换为 JSON
+        // 頧祆揢銝?JSON
         const jsonData = XLSX.utils.sheet_to_json(worksheet);
         
-        // 映射为标准格式
+        // <EFBFBD>惩<EFBFBD>銝箸<EFBFBD><EFBFBD><EFBFBD>聢撘?
         const literatures = jsonData.map((row: any) => ({
           title: row['Title'] || row['<27><><EFBFBD>'],
           abstract: row['Abstract'] || row['<27>䁅<EFBFBD>'],
           doi: row['DOI'],
-          authors: row['Authors'] || row['作者'],
+          authors: row['Authors'] || row['雿𡏭<E99BBF>?],
           year: row['Year'] || row['撟港遢'],
           journal: row['Journal'] || row['<27>笔<EFBFBD>'],
         }));
@@ -122,20 +122,20 @@ function parseExcel(file: File): Promise<Literature[]> {
 }
 ```
 
-#### 后端：批量筛选处理
+#### <EFBFBD>𡒊垢嚗𡁏鸌<EFBFBD>讐<EFBFBD><EFBFBD>匧<EFBFBD><EFBFBD>?
 
-**处理流程：**
+**憭<><E686AD>瘚<EFBFBD><E7989A>嚗?*
 ```
-Excel 数据 → 批量分组（10-20 篇/组）→ 并行调用 LLM → 汇总结果
+Excel <EFBFBD>唳旿 <20>?<3F>寥<EFBFBD><E5AFA5><EFBFBD><EFBFBD>嚗?0-20 蝭?蝏<><E89D8F><EFBFBD>?撟嗉<E6929F>靚<EFBFBD>鍂 LLM <20>?瘙<><E79899>餌<EFBFBD><E9A48C>?
 ```
 
-**关键技术点：**
-1. **批量分组**：避免单次请求过大，10-20 篇/组最优
-2. **并行处理**：使用 `Promise.all` 并行调用 LLM
-3. **进度推送**：WebSocket 实时推送处理进度
+**<EFBFBD>喲睸<EFBFBD><EFBFBD><EFBFBD>舐<EFBFBD>嚗?*
+1. **<2A>寥<EFBFBD><E5AFA5><EFBFBD><EFBFBD>**嚗𡁻<E59A97><F0A181BB>滚<EFBFBD>甈∟窈瘙<E7AA88><E79899>憭改<E686AD>10-20 蝭?蝏<><E89D8F>隡?
+2. **撟嗉<E6929F>憭<EFBFBD><E686AD>**嚗帋蝙<E5B88B>?`Promise.all` 撟嗉<E6929F>靚<EFBFBD>鍂 LLM
+3. **餈𥕦漲<F0A595A6>券<EFBFBD>?*嚗阳ebSocket 摰墧𧒄<E5A2A7>券<EFBFBD><E588B8><EFBFBD><EFBFBD><EFBFBD><EFBFBD>摨?
 4. **<2A>剔<EFBFBD>蝏凋<E89D8F>**嚗𡁏𣈲<F0A1818F><F0A388B2>遙<EFBFBD>∩葉<E288A9>剖<EFBFBD>蝏抒賒
 
-**代码示例：**
+**隞<><E99A9E>蝷箔<E89DB7>嚗?*
 ```typescript
 async function batchScreening(
   literatures: Literature[],
@@ -156,7 +156,7 @@ async function batchScreening(
     
     results.push(...batchResults);
     
-    // 推送进度
+    // <EFBFBD>券<EFBFBD><EFBFBD><EFBFBD>摨?
     const progress = Math.round(((i + 1) / batches.length) * 100);
     progressCallback(progress);
   }
@@ -165,55 +165,55 @@ async function batchScreening(
 }
 ```
 
-### 1.3 数据流
+### 1.3 <EFBFBD>唳旿瘚?
 
 ```
 <EFBFBD>冽<EFBFBD><EFBFBD>滢<EFBFBD>             <20>滨垢憭<E59EA2><E686AD>              <20>𡒊垢憭<E59EA2><E686AD>            LLM 憭<><E686AD>
-   │                    │                     │                   │
-   ├─ 上传 Excel        │                     │                   │
-   │    └──────────────→│                     │                   │
-   │                    ├─ 解析 Excel         │                   │
-   │                    ├─ 验证格式           │                   │
-   │                    ├─ 显示预览           │                   │
-   │                    │                     │                   │
-   │                    ├─ 提交筛选任务       │                   │
-   │                    │    └───────────────→│                   │
-   │                    │                     ├─ 保存任务         │
-   │                    │                     ├─ 分组（15 篇/组） │
-   │                    │                     │                   │
-   │                    │                     ├─ 批次 1           │
-   │                    │                     │    └──────────────→│
-   │                    │                     │                   ├─ DeepSeek 筛选
-   │                    │                     │                   ├─ Qwen3 筛选
-   │                    │                     │                   ├─ 对比结果
-   │                    │                     │    ←──────────────┘
-   │                    │                     ├─ 保存结果         │
-   │                    │                     │                   │
-   │                    │                     ├─ 批次 2...        │
-   │                    │                     │                   │
-   │                    │    ←───────────────┤ 返回完整结果       │
-   │    ←──────────────┤ 显示结果            │                   │
-   └─ 人工复核          │                     │                   │
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>鎿<EFBFBD> 銝𠹺<E98A9D> Excel        <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>?   <EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>圝<EFBFBD>                     <20>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>鎿<EFBFBD> 閫<><E996AB> Excel         <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>鎿<EFBFBD> 撉諹<E69289><E8ABB9>澆<EFBFBD>           <20>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>鎿<EFBFBD> <20>曄內憸<E585A7><E686B8>           <20>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>鎿<EFBFBD> <20>𣂷漱蝑偦<E89D91>劐遙<E58A90>?      <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?   <20>婙<EFBFBD><E5A999><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>圝<EFBFBD>                   <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>鎿<EFBFBD> 靽嘥<E99DBD>隞餃𦛚         <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>鎿<EFBFBD> <20><><EFBFBD>嚗?5 蝭?蝏<><E89D8F> <20>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>鎿<EFBFBD> <20>寞活 1           <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?   <20>婙<EFBFBD><E5A999><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>圝<EFBFBD>
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>鎿<EFBFBD> DeepSeek 蝑偦<EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>鎿<EFBFBD> Qwen3 蝑偦<EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>鎿<EFBFBD> 撖寞<E69296>蝏𤘪<E89D8F>
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?   <20>鐥<EFBFBD><E990A5><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>鎿<EFBFBD> 靽嘥<E99DBD>蝏𤘪<E89D8F>         <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>鎿<EFBFBD> <20>寞活 2...        <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?                    <EFBFBD>?                  <EFBFBD>?
+   <EFBFBD>?                   <EFBFBD>?   <20>鐥<EFBFBD><E990A5><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?餈𥪜<E9A488>摰峕㟲蝏𤘪<E89D8F>       <EFBFBD>?
+   <EFBFBD>?   <EFBFBD>鐥<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?<3F>曄內蝏𤘪<E89D8F>            <EFBFBD>?                  <EFBFBD>?
+   <20>婙<EFBFBD> 鈭箏極憭齿瓲          <EFBFBD>?                    <20>?                  <EFBFBD>?
 ```
 
 ---
 
-## 📌 场景 2 & 3: 全文复筛与数据提取
+## <EFBFBD><EFBFBD> <20>箸艶 2 & 3: <EFBFBD>冽<EFBFBD>憭滨<EFBFBD>銝擧㺭<EFBFBD>格<EFBFBD><EFBFBD>?
 
-### 2.1 技术特点
+### 2.1 <EFBFBD><EFBFBD><EFBFBD>舐鸌<EFBFBD>?
 
 - **颲枏<E9A2B2><E69E8F>澆<EFBFBD>**: PDF <20><>辣嚗<E8BEA3>㘚<EFBFBD><E3989A>龫摮行<E691AE><E8A18C>殷<EFBFBD>
 - **<2A><>辣<EFBFBD>寧<EFBFBD>**: 
   - 蝘穃郎霈箸<E99C88><E7AEB8>澆<EFBFBD>嚗<EFBFBD><E59A97>憸塩<E686B8><E5A1A9><EFBFBD>閬<EFBFBD><E996AC><EFBFBD><EFBFBD>閮<EFBFBD><E996AE><EFBFBD>䲮瘜𨰻<E7989C><F0A8B0BB><EFBFBD><EFBFBD>栶<EFBFBD><E6A0B6>悄霈箝<E99C88><E7AE9D><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>殷<EFBFBD>
-  - 包含复杂表格、公式、图表
-  - 通常 10-30 页
+  - <20><>鉄憭齿<E686AD>銵冽聢<E586BD><E881A2><EFBFBD>撘譌<E69298><E8AD8C>㦛銵?
+  - <20>𡁜虜 10-30 憿?
 - **憭<><E686AD><EFBFBD>滨<EFBFBD>**: 擃睃<E69383>蝖桃<E89D96><E6A183>𣂼<EFBFBD>嚗䔶<E59A97><E494B6>嗵<EFBFBD><E597B5><EFBFBD><EFBFBD><EFBFBD>澆<EFBFBD>
 
 ### 2.2 <20><><EFBFBD>舫<EFBFBD>匧<EFBFBD>嚗䥪DF <20>𣂼<EFBFBD>
 
-#### 核心方案：Nougat + PyMuPDF 顺序降级策略 ⭐
+#### <EFBFBD>詨<EFBFBD><EFBFBD>寞<EFBFBD>嚗鐭ougat + PyMuPDF 憿箏<EFBFBD><EFBFBD>滨漣蝑𣇉裦 潃?
 
-**现有架构**（已实现，位于 `extraction_service/`）：
+**<EFBFBD>唳<EFBFBD><EFBFBD>嗆<EFBFBD>**嚗<>歇摰䂿緵嚗䔶<E59A97>鈭?`extraction_service/`嚗㚁<E59A97>
 
 ```python
 # 憿箏<E686BF><E7AE8F>滨漣蝑𣇉裦
@@ -221,75 +221,75 @@ def extract_pdf(file_path: str):
     # Step 1: 璉<>瘚贝祗閮<E7A597>
     language = detect_language(file_path)
     
-    # Step 2: 中文 PDF → PyMuPDF（快速）
+    # Step 2: 銝剜<EFBFBD> PDF <EFBFBD>?PyMuPDF嚗<EFBFBD>翰<EFBFBD><EFBFBD><EFBFBD>
     if language == 'chinese':
         return extract_pdf_pymupdf(file_path)
     
-    # Step 3: 英文 PDF → 尝试 Nougat
+    # Step 3: <EFBFBD>望<EFBFBD> PDF <EFBFBD>?撠肽<E692A0> Nougat
     if check_nougat_available():
         result = extract_pdf_nougat(file_path)
         
-        # 质量检查（阈值 0.7）
+        # 韐券<EFBFBD>璉<EFBFBD><EFBFBD>伐<EFBFBD><EFBFBD><EFBFBD><EFBFBD>?0.7嚗?
         if result['quality_score'] >= 0.7:
-            return result  # ✅ Nougat 成功
+            return result  # <EFBFBD>?Nougat <EFBFBD>𣂼<EFBFBD>
     
-    # Step 4: 降级到 PyMuPDF
+    # Step 4: <EFBFBD>滨漣<EFBFBD>?PyMuPDF
     return extract_pdf_pymupdf(file_path)
 ```
 
-#### 技术对比
+#### <EFBFBD><EFBFBD><EFBFBD>臬笆瘥?
 
 | <20>寞<EFBFBD> | 隡睃飵 | <20><>飵 | <20><>鍂<EFBFBD>箸艶 |
 |------|------|------|---------|
-| **Nougat** ⭐ | • 专为科学文献设计<br>• 公式、表格准确率高<br>• 输出 Markdown 格式<br>• 保留文档结构 | • 速度慢（1-2 分钟/20 页）<br>• 需要 GPU 加速<br>• 内存占用大（~4GB） | 英文医学文献全文提取 |
-| **PyMuPDF** | • 速度快（秒级）<br>• 内存占用低<br>• 部署简单 | • 公式、表格易丢失<br>• 纯文本输出<br>• 布局易混乱 | 中文文献、快速预览 |
-| **Adobe API** | • 商业级准确率<br>• 云端处理 | • 需付费<br>• 网络依赖<br>• 隐私风险 | 不推荐（成本高） |
-| **Tesseract OCR** | • 开源免费<br>• 支持多语言 | • 需要图像预处理<br>• 准确率不稳定 | 扫描版 PDF（备选） |
+| **Nougat** 潃?| <20>?銝㮖蛹蝘穃郎<E7A983><E9838E>讃霈曇恣<br><3E>?<3F>砍<EFBFBD><E7A08D><EFBFBD>”<EFBFBD>澆<EFBFBD>蝖桃<E89D96>擃?br><3E>?颲枏枂 Markdown <EFBFBD>澆<EFBFBD><br><EFBFBD>?靽萘<E99DBD><E89098><EFBFBD>﹝蝏𤘪<E89D8F> | <20>?<3F>笔漲<E7AC94>ｇ<EFBFBD>1-2 <EFBFBD><EFBFBD><EFBFBD>/20 憿蛛<EFBFBD><br><EFBFBD>?<3F><>閬?GPU <20>𣳇<EFBFBD>?br><3E>?<3F><><EFBFBD><EFBFBD>删鍂憭改<E686AD>~4GB嚗?| <20>望<EFBFBD><E69C9B>餃郎<E9A483><E9838E>讃<EFBFBD>冽<EFBFBD><E586BD>𣂼<EFBFBD> |
+| **PyMuPDF** | <EFBFBD>?<3F>笔漲敹恬<E695B9>蝘垍漣嚗?br><3E>?<3F><><EFBFBD><EFBFBD>删鍂雿?br><3E>?<3F>函蔡蝞<E894A1><E89D9E>?| <20>?<3F>砍<EFBFBD><E7A08D><EFBFBD>”<EFBFBD>潭<EFBFBD>銝Ｗ仃<br><3E>?蝥舀<E89DA5><E88880>祈<EFBFBD><E7A588>?br><3E>?撣<><E692A3><EFBFBD>𤘪毽銋?| 銝剜<E98A9D><E5899C><EFBFBD>讃<EFBFBD><E8AE83>翰<EFBFBD>罸<EFBFBD>閫?|
+| **Adobe API** | <EFBFBD>?<3F><><EFBFBD>蝥批<E89DA5>蝖桃<E89D96><br><3E>?鈭𤑳垢憭<E59EA2><E686AD> | <20>?<3F><>隞䁅晶<br><3E>?蝵𤑳<E89DB5>靘肽<E99D98><br><3E>?<3F>鞟<EFBFBD>憌𡡞埯 | 銝齿綫<E9BDBF>琜<EFBFBD><E7909C>鞉𧋦擃矋<E69383> |
+| **Tesseract OCR** | <EFBFBD>?撘<>皞𣂼<E79A9E>韐?br><3E>?<3F>舀<EFBFBD>憭朞祗閮<E7A597> | <20>?<3F><>閬<EFBFBD>㦛<EFBFBD>誯<EFBFBD>憭<EFBFBD><E686AD><br><3E>?<3F><>＆<EFBFBD><EFBC86><EFBFBD>蝔喳<E89D94> | <20>急<EFBFBD><E680A5>?PDF嚗<46><E59A97><EFBFBD>㚁<EFBFBD> |
 
-**推荐方案：Nougat（主） + PyMuPDF（降级） ⭐**
+**<EFBFBD>刻<EFBFBD><EFBFBD>寞<EFBFBD>嚗鐭ougat嚗<EFBFBD>蜓嚗?+ PyMuPDF嚗<46><E59A97>蝥改<E89DA5> 潃?*
 
 #### Nougat <20>詨<EFBFBD>隡睃飵嚗<E9A3B5>龫摮行<E691AE><E8A18C>桀㦤<E6A180>荔<EFBFBD>
 
 ```
-✅ 专为科学文献设计
+<EFBFBD>?銝㮖蛹蝘穃郎<E7A983><E9838E>讃霈曇恣
    <20>鎿<EFBFBD> 霈剔<E99C88><E58994>唳旿嚗惨rXiv 霈箸<E99C88> + 蝘穃郎<E7A983>笔<EFBFBD>
    <20>鎿<EFBFBD> <20>砍<EFBFBD>霂<EFBFBD><E99C82>嚗匁aTeX <20>澆<EFBFBD>颲枏枂
    <20>鎿<EFBFBD> 銵冽聢靽萘<E99DBD>嚗鐝arkdown 銵冽聢<E586BD>澆<EFBFBD>
-   └─ 结构化输出：章节、段落清晰
+   <EFBFBD>婙<EFBFBD> 蝏𤘪<E89D8F><F0A498AA>𤥁<EFBFBD><F0A4A581>綽<EFBFBD>蝡㰘<E89DA1><E3B098><EFBFBD>挾<EFBFBD>賣<EFBFBD><E8B3A3>?
 
-✅ 输出格式：Markdown
-   ├─ 标题层级：# ## ###
+<EFBFBD>?颲枏枂<E69E8F>澆<EFBFBD>嚗鐝arkdown
+   <EFBFBD>鎿<EFBFBD> <20><><EFBFBD>撅<EFBFBD>漣嚗? ## ###
    <20>鎿<EFBFBD> 銵冽聢嚗𡯂 Header | Data |
-   ├─ 公式：$$ formula $$
+   <EFBFBD>鎿<EFBFBD> <20>砍<EFBFBD>嚗?$ formula $$
    <20>婙<EFBFBD> 撘閧鍂嚗靀1] [2] [3]
 
-✅ 质量评估机制
-   ├─ 自动质量评分（0-1）
-   ├─ 低质量自动降级 PyMuPDF
-   └─ 保证提取成功率
+<EFBFBD>?韐券<E99F90>霂<EFBFBD>摯<EFBFBD>箏<EFBFBD>
+   <EFBFBD>鎿<EFBFBD> <20>芸𢆡韐券<E99F90>霂<EFBFBD><E99C82>嚗?-1嚗?
+   <EFBFBD>鎿<EFBFBD> 雿舘捶<E88898>讛䌊<E8AE9B>券<EFBFBD>蝥?PyMuPDF
+   <EFBFBD>婙<EFBFBD> 靽肽<E99DBD><E882BD>𣂼<EFBFBD><F0A382BC>𣂼<EFBFBD><F0A382BC>?
 ```
 
 #### 摰䂿緵蝏<E7B7B5><E89D8F>
 
-**服务架构：**
+**<2A>滚𦛚<E6BB9A>嗆<EFBFBD>嚗?*
 ```
 Node.js Backend (Port 3001)
-    │
+    <EFBFBD>?
     <20>鎿<EFBFBD> 靚<>鍂 ExtractionClient.ts
-    │   └─ HTTP 请求 → Python 微服务
-    │
+    <EFBFBD>?  <20>婙<EFBFBD> HTTP 霂瑟<E99C82> <20>?Python 敺格<E695BA><E6A0BC>?
+    <EFBFBD>?
 Python Extraction Service (Port 8000)
-    │
+    <EFBFBD>?
     <20>鎿<EFBFBD> /api/extract/pdf
-    │   ├─ detect_language()
-    │   ├─ extract_pdf_nougat() → Nougat Model
-    │   └─ extract_pdf_pymupdf() → PyMuPDF
-    │
+    <EFBFBD>?  <20>鎿<EFBFBD> detect_language()
+    <EFBFBD>?  <20>鎿<EFBFBD> extract_pdf_nougat() <EFBFBD>?Nougat Model
+    <EFBFBD>?  <20>婙<EFBFBD> extract_pdf_pymupdf() <EFBFBD>?PyMuPDF
+    <EFBFBD>?
     <20>婙<EFBFBD> /api/health
-        └─ 检查 Nougat 可用性
+        <EFBFBD>婙<EFBFBD> 璉<><E79289>?Nougat <20>舐鍂<E88890>?
 ```
 
-**Node.js 调用代码：**
+**Node.js 靚<EFBFBD>鍂隞<EFBFBD><EFBFBD>嚗?*
 ```typescript
 import { extractionClient } from '@common/document/ExtractionClient';
 
@@ -320,7 +320,7 @@ async function extractLiteraturePDF(file: Buffer, filename: string) {
 }
 ```
 
-**Python 提取代码：**
+**Python <EFBFBD>𣂼<EFBFBD>隞<EFBFBD><EFBFBD>嚗?*
 ```python
 # extraction_service/services/nougat_extractor.py
 
@@ -336,14 +336,14 @@ def extract_pdf_nougat(file_path: str) -> Dict[str, Any]:
         file_path,
         '-o', output_dir,
         '--markdown',      # 颲枏枂 Markdown <20>澆<EFBFBD>
-        '--no-skipping'    # 不跳过任何页面
+        '--no-skipping'    # 銝滩歲餈<EFBFBD>遙雿閖△<EFBFBD>?
     ]
     
-    # 执行 Nougat（超时 5 分钟）
+    # <EFBFBD>扯<EFBFBD> Nougat嚗<EFBFBD><EFBFBD><EFBFBD>?5 <20><><EFBFBD>嚗?
     process = subprocess.Popen(cmd, ...)
     stdout, stderr = process.communicate(timeout=300)
     
-    # 读取输出文件（.mmd）
+    # 霂餃<EFBFBD>颲枏枂<EFBFBD><EFBFBD>辣嚗?mmd嚗?
     markdown_text = read_output_file()
     
     # 韐券<E99F90>霂<EFBFBD>摯
@@ -362,9 +362,9 @@ def extract_pdf_nougat(file_path: str) -> Dict[str, Any]:
     }
 ```
 
-### 2.3 文本后处理
+### 2.3 <EFBFBD><EFBFBD>𧋦<EFBFBD>𤾸<EFBFBD><EFBFBD>?
 
-**Nougat 输出优化：**
+**Nougat 颲枏枂隡睃<EFBFBD>嚗?*
 ```typescript
 function postProcessNougatOutput(markdown: string): ProcessedText {
   return {
@@ -380,10 +380,10 @@ function postProcessNougatOutput(markdown: string): ProcessedText {
     // <20>砍<EFBFBD><E7A08D>𣂼<EFBFBD>
     formulas: extractFormulas(markdown),
     
-    // 纯文本（去除格式）
+    // 蝥舀<EFBFBD><EFBFBD>穿<EFBFBD><EFBFBD>駁膄<EFBFBD>澆<EFBFBD>嚗?
     plainText: markdownToPlainText(markdown),
     
-    // 结构化数据（用于 LLM）
+    // 蝏𤘪<EFBFBD><EFBFBD>𡝗㺭<EFBFBD>殷<EFBFBD><EFBFBD>其<EFBFBD> LLM嚗?
     structured: {
       title: extractTitle(markdown),
       abstract: extractAbstract(markdown),
@@ -398,13 +398,13 @@ function postProcessNougatOutput(markdown: string): ProcessedText {
 
 ## <20><> <20>箸艶 4: <20><>讃銝贝蝸嚗㇎npaywall API嚗争<E59A97>
 
-### 3.1 技术背景
+### 3.1 <EFBFBD><EFBFBD><EFBFBD>航<EFBFBD><EFBFBD>?
 
-**Unpaywall** 是一个免费的开放获取（Open Access）文献 API，可以：
-- ✅ 通过 DOI 查询文献是否有免费全文
-- ✅ 获取合法的 PDF 下载链接
-- ✅ 完全免费，无需付费
-- ✅ 数据库覆盖 3000+ 万篇文献
+**Unpaywall** <20>臭<EFBFBD>銝芸<E98A9D>韐寧<E99F90>撘<EFBFBD><E69298>曇繮<E69B87>吔<EFBFBD>Open Access嚗㗇<E59A97><E39787>?API嚗<49>虾隞伐<E99A9E>
+- <20>?<3F>朞<EFBFBD> DOI <20>亥砭<E4BAA5><E7A0AD>讃<EFBFBD>臬炏<E887AC>匧<EFBFBD>韐孵<E99F90><E5ADB5>?
+- <20>?<3F>瑕<EFBFBD><E79195><EFBFBD><EFBFBD><EFBFBD>?PDF 銝贝蝸<E8B49D>暹𦻖
+- <20>?摰<><E691B0><EFBFBD>滩晶嚗峕<E59A97><E5B395><EFBFBD>隞䁅晶
+- <20>?<3F>唳旿摨栞<E691A8><E6A09E>?3000+ 銝<><E98A9D><EFBFBD><EFBFBD>讃
 
 **摰条<E691B0>**: https://unpaywall.org/products/api
 
@@ -412,18 +412,18 @@ function postProcessNougatOutput(markdown: string): ProcessedText {
 
 #### API 靚<>鍂<EFBFBD>孵<EFBFBD>
 
-**基础信息：**
+**<2A>箇<EFBFBD>靽⊥<E99DBD>嚗?*
 - **API 蝡舐<E89DA1>**: `https://api.unpaywall.org/v2/{doi}?email={your_email}`
 - **霂瑟<E99C82><E7919F>寞<EFBFBD>**: GET
 - **霈方<E99C88><E696B9>孵<EFBFBD>**: <20>𣳇<EFBFBD> API Key嚗䔶<E59A97><E494B6><EFBFBD><EFBFBD>𣂷<EFBFBD><F0A382B7>桃拳
-- **速率限制**: 100,000 次/天（免费）
+- **<2A>毺<EFBFBD><E6AFBA>𣂼<EFBFBD>**: 100,000 甈?憭抬<E686AD><E68AAC>滩晶嚗?
 
-**示例请求：**
+**蝷箔<E89DB7>霂瑟<E99C82>嚗?*
 ```bash
 curl "https://api.unpaywall.org/v2/10.1038/nature12373?email=YOUR_EMAIL"
 ```
 
-**响应示例：**
+**<2A>滚<EFBFBD>蝷箔<E89DB7>嚗?*
 ```json
 {
   "doi": "10.1038/nature12373",
@@ -443,7 +443,7 @@ curl "https://api.unpaywall.org/v2/10.1038/nature12373?email=YOUR_EMAIL"
 
 #### Node.js 摰䂿緵
 
-**服务封装：**
+**<2A>滚𦛚撠<F0A69B9A><E692A0>嚗?*
 ```typescript
 // backend/src/common/literature/UnpaywallClient.ts
 
@@ -453,7 +453,7 @@ import { config } from '../../config/env';
 export interface UnpaywallResult {
   doi: string;
   title: string;
-  isOA: boolean;              // 是否开放获取
+  isOA: boolean;              // <EFBFBD>臬炏撘<EFBFBD><EFBFBD>曇繮<EFBFBD>?
   oaStatus: string;           // "gold" | "green" | "hybrid" | "bronze" | "closed"
   pdfUrl: string | null;      // PDF 銝贝蝸<E8B49D>暹𦻖
   landingPageUrl: string;     // <20><>讃憿菟𢒰<E88F9F>暹𦻖
@@ -476,12 +476,12 @@ class UnpaywallClient {
     try {
       const url = `${this.baseUrl}/${doi}?email=${this.email}`;
       const response = await axios.get(url, {
-        timeout: 10000,  // 10 秒超时
+        timeout: 10000,  // 10 蝘坿<EFBFBD><EFBFBD>?
       });
 
       const data = response.data;
 
-      // 获取最佳下载位置
+      // <EFBFBD>瑕<EFBFBD><EFBFBD><EFBFBD>雿喃<EFBFBD>頧賭<EFBFBD>蝵?
       const bestOA = data.best_oa_location;
 
       return {
@@ -505,7 +505,7 @@ class UnpaywallClient {
   }
 
   /**
-   * 批量查询（带速率限制）
+   * <EFBFBD>寥<EFBFBD><EFBFBD>亥砭嚗<EFBFBD>蒂<EFBFBD>毺<EFBFBD><EFBFBD>𣂼<EFBFBD>嚗?
    */
   async getBatch(dois: string[]): Promise<UnpaywallResult[]> {
     const results = [];
@@ -515,7 +515,7 @@ class UnpaywallClient {
         const result = await this.getByDoi(doi);
         results.push(result);
         
-        // 速率限制：100ms/请求
+        // <EFBFBD>毺<EFBFBD><EFBFBD>𣂼<EFBFBD>嚗?00ms/霂瑟<EFBFBD>
         await new Promise(resolve => setTimeout(resolve, 100));
       } catch (error) {
         console.error(`Failed to fetch ${doi}:`, error.message);
@@ -547,7 +547,7 @@ class UnpaywallClient {
 export const unpaywallClient = new UnpaywallClient();
 ```
 
-**环境变量配置：**
+**<EFBFBD>臬<EFBFBD><EFBFBD>㗛<EFBFBD><EFBFBD>滨蔭嚗?*
 ```env
 # .env
 UNPAYWALL_EMAIL=your-email@example.com
@@ -560,7 +560,7 @@ UNPAYWALL_EMAIL=your-email@example.com
 async function checkLiteratureAvailability(literatures: Literature[]) {
   const dois = literatures
     .map(lit => lit.doi)
-    .filter(doi => doi);  // 过滤空 DOI
+    .filter(doi => doi);  // 餈<EFBFBD>誘蝛?DOI
 
   const results = await unpaywallClient.getBatch(dois);
 
@@ -572,7 +572,7 @@ async function checkLiteratureAvailability(literatures: Literature[]) {
 }
 ```
 
-**场景 2：用户点击下载全文**
+**<EFBFBD>箸艶 2嚗𡁶鍂<F0A181B6>瑞<EFBFBD><E7919E>颱<EFBFBD>頧賢<E9A0A7><E8B3A2>?*
 ```typescript
 async function downloadLiteratureFullText(doi: string) {
   // Step 1: <20>亥砭 Unpaywall
@@ -588,7 +588,7 @@ async function downloadLiteratureFullText(doi: string) {
   
   await unpaywallClient.downloadPdf(unpaywallResult.pdfUrl, outputPath);
 
-  // Step 3: 提取文本（调用 extraction_service）
+  // Step 3: <EFBFBD>𣂼<EFBFBD><EFBFBD><EFBFBD>𧋦嚗<EFBFBD><EFBFBD><EFBFBD>?extraction_service嚗?
   const extractionResult = await extractionClient.extractPdf(
     fs.readFileSync(outputPath),
     filename,
@@ -605,9 +605,9 @@ async function downloadLiteratureFullText(doi: string) {
 
 ### 3.3 <20>滨垢<E6BBA8><E59EA2><EFBFBD>
 
-**批量下载按钮：**
+**<EFBFBD>寥<EFBFBD>銝贝蝸<EFBFBD>厰僼嚗?*
 ```typescript
-// 批量检查可下载性
+// <20>寥<EFBFBD>璉<EFBFBD><E79289>亙虾銝贝蝸<E8B49D>?
 async function checkDownloadable(selectedRows: Literature[]) {
   setLoading(true);
   
@@ -631,7 +631,7 @@ async function downloadFullText(literature: Literature) {
     const result = await api.downloadLiteratureFullText(literature.doi);
     message.success('銝贝蝸<E8B49D>𣂼<EFBFBD>');
     
-    // 打开 PDF 查看器
+    // <EFBFBD>枏<EFBFBD> PDF <EFBFBD>亦<EFBFBD><EFBFBD>?
     openPdfViewer(result.pdfPath);
   } catch (error) {
     message.error(`銝贝蝸憭梯揖: ${error.message}`);
@@ -645,23 +645,23 @@ async function downloadFullText(literature: Literature) {
 
 ### 4.1 <20>冽<EFBFBD><E586BD>啁<EFBFBD><E59581><EFBFBD><EFBFBD>舐<EFBFBD><E88890>餌<EFBFBD>
 
-| 技术点 | 状态 | 说明 |
+| <EFBFBD><EFBFBD><EFBFBD>舐<EFBFBD> | <20>嗆<EFBFBD>?| 霂湔<E99C82> |
 |--------|------|------|
-| ✅ Nougat 模型 | 已实现 | `extraction_service/services/nougat_extractor.py` |
-| ✅ PyMuPDF | 已实现 | `extraction_service/services/pdf_extractor.py` |
-| ✅ 顺序降级策略 | 已实现 | 英文→Nougat，中文→PyMuPDF |
-| 🆕 Unpaywall API | 需新增 | 本文档提供实现方案 |
-| ✅ Excel 解析 | 需新增 | 使用 `xlsx` 库（前端） |
+| <EFBFBD>?Nougat 璅∪<EFBFBD> | 撌脣<E6928C><E884A3>?| `extraction_service/services/nougat_extractor.py` |
+| <EFBFBD>?PyMuPDF | 撌脣<EFBFBD><EFBFBD>?| `extraction_service/services/pdf_extractor.py` |
+| <EFBFBD>?憿箏<E686BF><E7AE8F>滨漣蝑𣇉裦 | 撌脣<E6928C><E884A3>?| <20>望<EFBFBD><E69C9B>𩦝ougat嚗䔶葉<E494B6><E89189><EFBFBD>PyMuPDF |
+| <EFBFBD><EFBFBD> Unpaywall API | <EFBFBD><EFBFBD><EFBFBD>啣<EFBFBD> | <20>祆<EFBFBD>獢<EFBFBD><E78DA2>靘𥕦<E99D98><F0A595A6>唳䲮獢?|
+| <EFBFBD>?Excel 閫<EFBFBD><EFBFBD> | <20><><EFBFBD>啣<EFBFBD> | 雿輻鍂 `xlsx` 摨橒<E691A8><E6A992>滨垢嚗?|
 
-### 4.2 可能遗漏的技术点 ⭐
+### 4.2 <EFBFBD>航<EFBFBD><EFBFBD>埈<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>舐<EFBFBD> 潃?
 
-#### （1）表格提取增强
+#### 嚗?嚗㕑”<E39591>潭<EFBFBD><E6BDAD>硋<EFBFBD>撘?
 
-**问题**：Nougat 虽然保留表格结构，但 LLM 直接处理 Markdown 表格可能不准确。
+**<EFBFBD>桅<EFBFBD>**嚗鐭ougat <20>賜<EFBFBD>靽萘<E99DBD>銵冽聢蝏𤘪<E89D8F>嚗䔶<E59A97> LLM <20>湔𦻖憭<F0A6BB96><E686AD> Markdown 銵冽聢<E586BD>航<EFBFBD>銝滚<E98A9D>蝖柴<E89D96>?
 
 **閫<><E996AB><EFBFBD>寞<EFBFBD>嚗関able Transformer**
 ```python
-# 使用微软的 Table Transformer 模型
+# 雿輻鍂敺株蔓<E6A0AA>?Table Transformer 璅∪<EFBFBD>
 # https://github.com/microsoft/table-transformer
 
 from transformers import TableTransformerForObjectDetection
@@ -675,7 +675,7 @@ def extract_tables_enhanced(pdf_path: str):
         "microsoft/table-transformer-detection"
     )
     
-    # 检测表格位置
+    # 璉<EFBFBD>瘚贝”<EFBFBD>潔<EFBFBD>蝵?
     tables = model.detect_tables(pdf_path)
     
     # <20>𣂼<EFBFBD>瘥譍葵銵冽聢
@@ -686,22 +686,22 @@ def extract_tables_enhanced(pdf_path: str):
     return structured_tables
 ```
 
-**优先级：V2.0**（MVP 阶段 Nougat 足够）
+**隡睃<EFBFBD>蝥改<EFBFBD>V2.0**嚗㇈VP <20>嗆挾 Nougat 頞喳<EFBFBD>嚗?
 
-#### （2）引用解析与链接
+#### 嚗?嚗匧<E59A97><E58CA7>刻圾<E588BB>𣂷<EFBFBD><F0A382B7>暹𦻖
 
-**问题**：科学文献包含大量引用 `[1] [2] [3]`，需要解析并链接到参考文献。
+**<EFBFBD>桅<EFBFBD>**嚗𡁶<E59A97>摮行<E691AE><E8A18C>桀<EFBFBD><E6A180>怠之<E680A0>誩<EFBFBD><E8AAA9>?`[1] [2] [3]`嚗屸<E59A97>閬<EFBFBD>圾<EFBFBD>𣂼僎<F0A382BC>暹𦻖<E69AB9>啣<EFBFBD><E595A3><EFBFBD><EFBFBD><EFBFBD>柴<EFBFBD>?
 
 **閫<><E996AB><EFBFBD>寞<EFBFBD>嚗鎭ROBID**
 ```python
-# GROBID: 开源科学文献解析工具
+# GROBID: 撘<EFBFBD>皞鞟<EFBFBD>摮行<EFBFBD><EFBFBD>株圾<EFBFBD>𣂼極<EFBFBD>?
 # https://github.com/kermitt2/grobid
 
 import requests
 
 def parse_references(pdf_path: str):
     """
-    使用 GROBID 解析参考文献
+    雿輻鍂 GROBID 閫<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>?
     """
     with open(pdf_path, 'rb') as f:
         files = {'input': f}
@@ -714,11 +714,11 @@ def parse_references(pdf_path: str):
     return response.json()['references']
 ```
 
-**优先级：V2.0**（非核心功能）
+**隡睃<EFBFBD>蝥改<EFBFBD>V2.0**嚗<><E59A97><EFBFBD>詨<EFBFBD><E8A9A8>蠘<EFBFBD>嚗?
 
-#### （3）公式识别与渲染
+#### 嚗?嚗匧<E59A97>撘讛<E69298><E8AE9B>思<EFBFBD>皜脫<E79A9C>
 
-**问题**：Nougat 输出 LaTeX 公式，前端需要渲染。
+**<EFBFBD>桅<EFBFBD>**嚗鐭ougat 颲枏枂 LaTeX <EFBFBD>砍<EFBFBD>嚗<EFBFBD><EFBFBD>蝡舫<EFBFBD>閬<EFBFBD>葡<EFBFBD>瓐<EFBFBD>?
 
 **閫<><E996AB><EFBFBD>寞<EFBFBD>嚗鐗aTeX / MathJax**
 ```typescript
@@ -736,9 +736,9 @@ function renderFormula(latex: string) {
 
 **隡睃<E99AA1>蝥改<E89DA5>MVP**嚗<><E59A97><EFBFBD><EFBFBD>鍂<EFBFBD>瑚<EFBFBD>撉䕘<E69289>
 
-#### （4）PDF 预览与标注
+#### 嚗?嚗侨DF 憸<><E686B8>銝擧<E98A9D>瘜?
 
-**问题**：人工复核时需要查看原文，并高亮标注。
+**<EFBFBD>桅<EFBFBD>**嚗帋犖撌亙<E6928C><E4BA99>豢𧒄<E8B1A2><F0A79284>閬<EFBFBD>䰻<EFBFBD>见<EFBFBD><E8A781><EFBFBD><EFBFBD>撟園<E6929F>鈭格<E988AD>瘜具<E7989C>?
 
 **閫<><E996AB><EFBFBD>寞<EFBFBD>嚗䥪DF.js + Annotator.js**
 ```typescript
@@ -762,11 +762,11 @@ function PdfViewer({ pdfUrl, annotations }) {
 
 **隡睃<E99AA1>蝥改<E89DA5>MVP**嚗<>瓲敹<E793B2><E695B9><EFBFBD>踝<EFBFBD>
 
-#### （5）文献去重
+#### 嚗?嚗㗇<E59A97><E39787>桀縧<E6A180>?
 
-**问题**：Excel 上传可能包含重复文献（同一篇文献不同版本）。
+**<EFBFBD>桅<EFBFBD>**嚗鍃xcel 銝𠹺<E98A9D><F0A0B9BA>航<EFBFBD><E888AA><EFBFBD>鉄<EFBFBD>滚<EFBFBD><E6BB9A><EFBFBD>讃嚗<E8AE83><E59A97>銝<EFBFBD>蝭<EFBFBD><E89DAD><EFBFBD>桐<EFBFBD><E6A190>𣬚<EFBFBD><F0A3AC9A>穿<EFBFBD><E7A9BF>?
 
-**解决方案：基于 DOI 和标题的去重**
+**閫<EFBFBD><EFBFBD><EFBFBD>寞<EFBFBD>嚗𡁜抅鈭?DOI <20>峕<EFBFBD>憸条<E686B8><E69DA1>駁<EFBFBD>**
 ```typescript
 function deduplicateLiteratures(literatures: Literature[]) {
   const seen = new Set();
@@ -791,16 +791,16 @@ function normalizeTitle(title: string): string {
   return title
     .toLowerCase()
     .replace(/[^\w\s]/g, '')  // <20>駁膄<E9A781><E88684><EFBFBD>
-    .replace(/\s+/g, ' ')      // 规范化空格
+    .replace(/\s+/g, ' ')      // 閫<EFBFBD><EFBFBD><EFBFBD>𣇉征<EFBFBD>?
     .trim();
 }
 ```
 
 **隡睃<E99AA1>蝥改<E89DA5>MVP**嚗<><E59A97>憿餃<E686BF><E9A483>踝<EFBFBD>
 
-#### （6）文献元数据补全
+#### 嚗?嚗㗇<E59A97><E39787>桀<EFBFBD><E6A180>唳旿銵亙<E98AB5>
 
-**问题**：Excel 上传的数据可能不完整（缺 DOI、年份等）。
+**<EFBFBD>桅<EFBFBD>**嚗鍃xcel 銝𠹺<E98A9D><F0A0B9BA><EFBFBD>㺭<EFBFBD>桀虾<E6A180>賭<EFBFBD>摰峕㟲嚗<E39FB2>撩 DOI<4F><49>僑隞賜<E99A9E>嚗剹<E59A97>?
 
 **閫<><E996AB><EFBFBD>寞<EFBFBD>嚗鋴rossref API**
 ```typescript
@@ -826,9 +826,9 @@ async function enrichMetadata(literature: Literature) {
 
 **隡睃<E99AA1>蝥改<E89DA5>V1.0**嚗<><E59A97>撘箏<E69298><E7AE8F>踝<EFBFBD>
 
-#### （7）批处理进度持久化
+#### 嚗?嚗㗇鸌憭<E9B88C><E686AD>餈𥕦漲<F0A595A6><E6BCB2><EFBFBD><EFBFBD>?
 
-**问题**：批量筛选耗时长（1000 篇 > 10 分钟），需支持断点续传。
+**<EFBFBD>桅<EFBFBD>**嚗𡁏鸌<F0A1818F>讐<EFBFBD><E8AE90>㕑<EFBFBD>埈𧒄<E59F88>選<EFBFBD>1000 蝭?> 10 <EFBFBD><EFBFBD><EFBFBD>嚗㚁<EFBFBD><EFBFBD><EFBFBD><EFBFBD>舀<EFBFBD><EFBFBD>剔<EFBFBD>蝏凋<EFBFBD><EFBFBD>?
 
 **閫<><E996AB><EFBFBD>寞<EFBFBD>嚗鑹edis + 隞餃𦛚<E9A483>笔<EFBFBD>**
 ```typescript
@@ -862,11 +862,11 @@ screeningQueue.process(async (job) => {
 
 **隡睃<E99AA1>蝥改<E89DA5>V1.0**嚗<><E59A97>撉䔶<E69289><E494B6>吔<EFBFBD>
 
-#### （8）错误处理与重试
+#### 嚗?嚗厰<E59A97>霂臬<E99C82><E887AC><EFBFBD><EFBFBD><EFBFBD>滩<EFBFBD>
 
-**问题**：LLM 调用可能失败（网络、超时、限流）。
+**<EFBFBD>桅<EFBFBD>**嚗匁LM 靚<>鍂<EFBFBD>航<EFBFBD>憭梯揖嚗<E68F96><E59A97>蝏栶<E89D8F><E6A0B6><EFBFBD><EFBFBD>嗚<EFBFBD><E5979A><EFBFBD>瘚<EFBFBD><E7989A><EFBFBD>?
 
-**解决方案：指数退避重试**
+**閫<EFBFBD><EFBFBD><EFBFBD>寞<EFBFBD>嚗𡁏<EFBFBD><EFBFBD>圈<EFBFBD><EFBFBD><EFBFBD>輸<EFBFBD>霂?*
 ```typescript
 async function retryWithBackoff<T>(
   fn: () => Promise<T>,
@@ -892,30 +892,30 @@ async function retryWithBackoff<T>(
 
 ## <20><> <20><><EFBFBD>舫<EFBFBD>匧<EFBFBD><E58CA7>餌<EFBFBD>
 
-### MVP 阶段必选技术
+### MVP <EFBFBD>嗆挾敹<EFBFBD><EFBFBD>㗇<EFBFBD><EFBFBD>?
 
-| 层级 | 技术 | 用途 |
+| 撅<EFBFBD>漣 | <20><><EFBFBD>?| <20>券<EFBFBD>?|
 |------|------|------|
 | **<2A>滨垢** | `xlsx` | Excel 閫<><E996AB> |
 | **<2A>滨垢** | `PDF.js` | PDF 憸<><E686B8> |
 | **<2A>滨垢** | `KaTeX` | <20>砍<EFBFBD>皜脫<E79A9C> |
-| **后端** | `ExtractionClient` | 调用 Python 微服务 |
+| **<EFBFBD>𡒊垢** | `ExtractionClient` | 靚<EFBFBD>鍂 Python 敺格<EFBFBD><EFBFBD>?|
 | **<2A>𡒊垢** | `UnpaywallClient` | <20><>讃銝贝蝸 |
 | **Python** | `Nougat` | <20>望<EFBFBD> PDF <20>𣂼<EFBFBD> |
-| **Python** | `PyMuPDF` | 快速 PDF 提取 |
-| **数据库** | `asl_schema` | 数据存储 |
+| **Python** | `PyMuPDF` | 敹恍<EFBFBD>?PDF <EFBFBD>𣂼<EFBFBD> |
+| **<EFBFBD>唳旿摨?* | `asl_schema` | <EFBFBD>唳旿摮睃<EFBFBD> |
 
-### V1.0 增强技术
+### V1.0 憓𧼮撩<EFBFBD><EFBFBD><EFBFBD>?
 
-| 技术 | 用途 |
+| <EFBFBD><EFBFBD><EFBFBD>?| <20>券<EFBFBD>?|
 |------|------|
-| Crossref API | 元数据补全 |
+| Crossref API | <EFBFBD><EFBFBD>㺭<EFBFBD>株‘<EFBFBD>?|
 | Bull Queue | 隞餃𦛚<E9A483>笔<EFBFBD> |
-| Redis | 进度持久化 |
+| Redis | 餈𥕦漲<EFBFBD><EFBFBD><EFBFBD><EFBFBD>?|
 
-### V2.0 高级技术
+### V2.0 擃条漣<EFBFBD><EFBFBD><EFBFBD>?
 
-| 技术 | 用途 |
+| <EFBFBD><EFBFBD><EFBFBD>?| <20>券<EFBFBD>?|
 |------|------|
 | Table Transformer | 銵冽聢蝎曄＆<E69B84>𣂼<EFBFBD> |
 | GROBID | 撘閧鍂閫<E98D82><E996AB> |
@@ -932,63 +932,63 @@ AIclinicalresearch/docs/03-业务模块/ASL-AI智能文献/
 <EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD> 05-瘚贝<E7989A><E8B49D><EFBFBD>﹝/
     <20>鎿<EFBFBD><E98EBF><EFBFBD> 01-瘚贝<E7989A>霈∪<E99C88>.md
     <20>鎿<EFBFBD><E98EBF><EFBFBD> 02-<2D><><EFBFBD><EFBFBD>䁅<EFBFBD><E48185>萘<EFBFBD>瘚贝<E7989A><E8B49D>其<EFBFBD>.md
-    └── 03-测试数据/  ← 新建文件夹
-        ├── README.md  ← 说明文档
+    <EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD> 03-瘚贝<E7989A><E8B49D>唳旿/  <20>?<3F>啣遣<E595A3><E981A3>辣憭?
+        <EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD> README.md  <EFBFBD>?霂湔<E99C82><E6B994><EFBFBD>﹝
         <20>鎿<EFBFBD><E98EBF><EFBFBD> screening-test-data/
-        │   ├── literature-list-199.xlsx  ← 199 篇文献列表
-        │   ├── picos-criteria.txt        ← PICOS 标准
-        │   └── expected-results.json     ← 预期结果（金标准）
+        <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> literature-list-199.xlsx  <EFBFBD>?199 蝭<EFBFBD><EFBFBD><EFBFBD>桀<EFBFBD>銵?
+        <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> picos-criteria.txt        <EFBFBD>?PICOS <EFBFBD><EFBFBD><EFBFBD>
+        <EFBFBD>?  <20>婙<EFBFBD><E5A999><EFBFBD> expected-results.json     <EFBFBD>?憸<><E686B8>蝏𤘪<E89D8F>嚗<EFBFBD><E59A97><EFBFBD><EFBFBD><EFBFBD>嚗?
         <20>鎿<EFBFBD><E98EBF><EFBFBD> pdf-samples/
-        │   ├── sample-rct-01.pdf
-        │   ├── sample-cohort-01.pdf
-        │   └── README.md
+        <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> sample-rct-01.pdf
+        <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> sample-cohort-01.pdf
+        <EFBFBD>?  <20>婙<EFBFBD><E5A999><EFBFBD> README.md
         <20>婙<EFBFBD><E5A999><EFBFBD> extraction-test-data/
             <20>婙<EFBFBD><E5A999><EFBFBD> README.md
 ```
 
-**推荐结构：**
+**<2A>刻<EFBFBD>蝏𤘪<E89D8F>嚗?*
 ```
 05-瘚贝<E7989A><E8B49D><EFBFBD>﹝/
 <EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD> 01-瘚贝<E7989A>霈∪<E99C88>.md
 <EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD> 02-<2D><><EFBFBD><EFBFBD>䁅<EFBFBD><E48185>萘<EFBFBD>瘚贝<E7989A><E8B49D>其<EFBFBD>.md
 <EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD> 03-瘚贝<E7989A><E8B49D>唳旿/
-    ├── README.md  ← 重要！说明测试数据来源、版权、使用方法
+    <EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD> README.md  <EFBFBD>?<3F>滩<EFBFBD>嚗<EFBFBD>秩<EFBFBD>擧<EFBFBD>霂閙㺭<E99699>格䔉皞僐<E79A9E><E58390><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>蝙<EFBFBD>冽䲮瘜?
     <20>鎿<EFBFBD><E98EBF><EFBFBD> screening/
-    │   ├── literature-list-199.xlsx
-    │   ├── picos-criteria.txt
-    │   ├── inclusion-criteria.txt
-    │   ├── exclusion-criteria.txt
-    │   └── gold-standard.json  ← 人工标注的正确答案
+    <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> literature-list-199.xlsx
+    <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> picos-criteria.txt
+    <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> inclusion-criteria.txt
+    <EFBFBD>?  <20>鎿<EFBFBD><E98EBF><EFBFBD> exclusion-criteria.txt
+    <EFBFBD>?  <20>婙<EFBFBD><E5A999><EFBFBD> gold-standard.json  <EFBFBD>?鈭箏極<E7AE8F><E6A5B5>釣<EFBFBD><E987A3>迤蝖桃<E89D96>獢?
     <20>婙<EFBFBD><E5A999><EFBFBD> pdf-extraction/
         <20>鎿<EFBFBD><E98EBF><EFBFBD> sample-01-high-quality.pdf
         <20>鎿<EFBFBD><E98EBF><EFBFBD> sample-02-with-tables.pdf
         <20>婙<EFBFBD><E5A999><EFBFBD> sample-03-chinese.pdf
 ```
 
-**README.md 示例：**
+**README.md 蝷箔<EFBFBD>嚗?*
 ```markdown
-# ASL 测试数据集
+# ASL 瘚贝<EFBFBD><EFBFBD>唳旿<EFBFBD>?
 
 ## <20><> <20>唳旿霂湔<E99C82>
 
 ### 1. <20><><EFBFBD><EFBFBD>䁅<EFBFBD><E48185>萘<EFBFBD>瘚贝<E7989A><E8B49D>唳旿
 - **<2A><>辣**: `literature-list-199.xlsx`
-- **数量**: 199 篇英文医学文献
-- **字段**: 标题、摘要、DOI、作者、年份、期刊
+- **<2A>圈<EFBFBD>**: 199 蝭<>㘚<EFBFBD><E3989A>龫摮行<E691AE><E8A18C>?
+- **摮埈挾**: <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>閬<EFBFBD><E996AC><EFBFBD>OI<4F><49><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>僑隞賬<E99A9E><E8B3AC><EFBFBD><EFBFBD>?
 - **<2A>交<EFBFBD>**: [<5B>讛膩<E8AE9B>唳旿<E594B3>交<EFBFBD>]
 - **<2A><><EFBFBD>**: [霂湔<E99C82><E6B994><EFBFBD><EFBFBD>靽⊥<E99DBD>]
 
 ### 2. PICOS <20><><EFBFBD>
 - **<2A><>辣**: `picos-criteria.txt`
 - **<2A><>捆**: Population, Intervention, Comparison, Outcome, Study Design
-- **纳入标准**: 5 条
-- **排除标准**: 8 条
+- **蝥喳<E89DA5><E596B3><EFBFBD><EFBFBD>**: 5 <EFBFBD>?
+- **<2A>㘾膄<E398BE><E88684><EFBFBD>**: 8 <EFBFBD>?
 
-### 3. 金标准（人工标注结果）
+### 3. <EFBFBD>烐<EFBFBD><EFBFBD><EFBFBD><EFBFBD>鈭箏極<EFBFBD><EFBFBD>釣蝏𤘪<EFBFBD>嚗?
 - **<2A><>辣**: `gold-standard.json`
-- **标注人**: [标注专家信息]
+- **<2A><>釣鈭?*: [<5B><>釣銝枏振靽⊥<E99DBD>]
 - **<2A><>釣<EFBFBD>園𡢿**: [<5B>園𡢿]
-- **预期准确率**: ≥ 90%
+- **憸<><E686B8><EFBFBD><EFBFBD>＆<EFBFBD>?*: <EFBFBD>?90%
 
 ## <20>㴓 雿輻鍂<E8BCBB>寞<EFBFBD>
 
@@ -997,15 +997,15 @@ AIclinicalresearch/docs/03-业务模块/ASL-AI智能文献/
 npm run test:asl:screening
 ```
 
-### 评估准确率
+### 霂<EFBFBD>摯<EFBFBD><EFBFBD>＆<EFBFBD>?
 ```bash
 npm run test:asl:evaluate -- --gold-standard gold-standard.json
 ```
 
 ## <20><> 憸<><E686B8>蝏𤘪<E89D8F>
-- 纳入: 45 篇
-- 排除: 132 篇
-- 不确定: 22 篇
+- 蝥喳<E89DA5>: 45 蝭?
+- <20>㘾膄: 132 蝭?
+- 銝滨＆摰? 22 蝭?
 ```
 
 ---
@@ -1013,13 +1013,13 @@ npm run test:asl:evaluate -- --gold-standard gold-standard.json
 ## <20><> <20>詨<EFBFBD><E8A9A8><EFBFBD>﹝
 
 - [韐券<EFBFBD>靽嗪<EFBFBD>銝𤾸虾餈賣滲蝑𣇉裦](./06-韐券<E99F90>靽嗪<E99DBD>銝𤾸虾餈賣滲蝑𣇉裦.md)
-- [数据库设计](./01-数据库设计.md)
+- [<EFBFBD>唳旿摨栞挽霈（(./01-<2D>唳旿摨栞挽霈?md)
 - [API 霈曇恣閫<E681A3><E996AB>](./02-API霈曇恣閫<E681A3><E996AB>.md)
 - [<5B><>﹝<EFBFBD>𣂼<EFBFBD>敺格<E695BA><E6A0BC>（(../../../../extraction_service/README.md)
 
 ---
 
-**更新日志**：
+**<EFBFBD>湔鰵<EFBFBD>亙<EFBFBD>**嚗?
 - 2025-11-15: <20>𥕦遣<F0A595A6><E981A3>﹝嚗<EFB99D><E59A97>銋匧<E98A8B>蝑䜘<E89D91><E49C98><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>桐<EFBFBD>頧賣<E9A0A7><E8B3A3>舫<EFBFBD>匧<EFBFBD>