Develop/AIclinicalresearch
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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%)
This commit is contained in:
HaHafeng
2026-01-14 19:15:01 +08:00
parent 3d35e9c58b
commit 1b53ab9d52
386 changed files with 52096 additions and 65238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

164
docs/03-业务模块/ASL-AI智能文献/04-开发计划/全文复筛开发计划-更新说明.md
View File

@@ -1,27 +1,27 @@
# 全文复筛开发计划 - 更新说明
# <EFBFBD>冽<EFBFBD>憭滨<EFBFBD>撘<EFBFBD><EFBFBD>𤏸恣<EFBFBD>?- <20>湔鰵霂湔<E99C82>
> **更新日期**：2025-11-22
> **<EFBFBD>湔鰵<EFBFBD>交<EFBFBD>**嚗?025-11-22
> **<2A><>𧋦**嚗间1.1
> **更新原因**：基于质量保障策略讨论，优化技术方案
> **<EFBFBD>湔鰵<EFBFBD>笔<EFBFBD>**嚗𡁜抅鈭舘捶<E88898>譍<EFBFBD><E8AD8D>𦦵<EFBFBD><F0A6A6B5>亥悄霈綽<E99C88>隡睃<E99AA1><E79D83><EFBFBD><EFBFBD>舀䲮獢?
---
## <20><> <20>詨<EFBFBD><E8A9A8>䀹凒<E480B9>餌<EFBFBD>
### 1️⃣ **提取策略：全文一次性 + Prompt工程优化**
### 1儭謿<EFBFBD> **<2A>𣂼<EFBFBD>蝑𣇉裦嚗𡁜<E59A97><F0A1819C><EFBFBD><EFBFBD>甈⊥<E79488>?+ Prompt撌亦<EFBFBD>隡睃<EFBFBD>**
**<EFBFBD>喟<EFBFBD>**嚗𡁻<E59A97><F0A181BB>典<EFBFBD><E585B8><EFBFBD><EFBFBD>甈⊥<E79488>扯<EFBFBD><E689AF>亦<EFBFBD><E4BAA6>伐<EFBFBD><E4BC90>屸<EFBFBD><E5B1B8><EFBFBD>挾<EFBFBD>𣂼<EFBFBD>
**理由**：
- ✅ 实现复杂度低（2周 vs 3周）
- ✅ 快速验证可行性
- ✅ Nougat结构化已降低大模型负担
- ✅ 先进的Prompt工程可以减轻Lost in the Middle
**<EFBFBD><EFBFBD>眏**嚗?
- <EFBFBD>?摰䂿緵憭齿<E686AD>摨虫<E691A8>嚗?<3F>?vs 3<EFBFBD>剁<EFBFBD>
- <EFBFBD>?敹恍<E695B9>罸<EFBFBD>霂<EFBFBD>虾銵峕<E98AB5>?
- <EFBFBD>?Nougat蝏𤘪<EFBFBD><EFBFBD>硋歇<EFBFBD>滢<EFBFBD>憭扳芋<EFBFBD>贝<EFBFBD><EFBFBD>?
- <EFBFBD>?<3F><><EFBFBD><EFBFBD><EFBFBD>rompt撌亦<E6928C><E4BAA6>臭誑<E887AD>讛蝠Lost in the Middle
**核心优化**：
1. **Nougat优先**：英文论文用Nougat提取（结构化Markdown）
2. **Section-Aware Prompting**：引导LLM逐章节处理
3. **Few-shot案例库**：特别强调"信息在中间位置"的案例
**<EFBFBD>詨<EFBFBD>隡睃<EFBFBD>**嚗?
1. **Nougat隡睃<EFBFBD>**嚗朞㘚<E69C9E><E3989A>捏<EFBFBD><E68D8F>鍂Nougat<61>𣂼<EFBFBD>嚗<EFBFBD><E59A97><EFBFBD><EFBFBD><EFBFBD>Markdown嚗?
2. **Section-Aware Prompting**嚗𡁜<E59A97>撖嘴LM<4C>鞟<EFBFBD><E99E9F><EFBFBD><EFBFBD><EFBFBD>?
3. **Few-shot獢<EFBFBD><EFBFBD>摨?*嚗𡁶鸌<F0A181B6>怠撩靚?靽⊥<E99DBD><E28AA5>其葉<E585B6>港<EFBFBD>蝵?<3F><><EFBFBD>靘?
4. **JSON Schema蝥行<E89DA5>**嚗𡁜撩<F0A1819C>嗉<EFBFBD><E59789>桅曎 + 憭<><E686AD><EFBFBD>亙<EFBFBD> + <20>芣<EFBFBD>撉諹<E69289>
---
@@ -30,104 +30,104 @@
**<EFBFBD>䀹凒**嚗帋<E59A97> GPT-4o + Claude-4.5 <20>嫣蛹 DeepSeek-V3 + Qwen3-Max
**理由**：
- ✅ 成本友好：¥0.06/篇 vs ¥0.10/篇（节省40%）
- ✅ 通用能力层已支持
- ✅ 中文文献友好
- ✅ MVP阶段优先验证可行性，而非追求极致准确率
**<EFBFBD><EFBFBD>眏**嚗?
- <EFBFBD>?<3F>鞉𧋦<E99E89>见末嚗块?.06/蝭?vs 瞼0.10/蝭<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>40%嚗?
- <EFBFBD>?<3F>𡁶鍂<F0A181B6>賢<EFBFBD>撅<EFBFBD>歇<EFBFBD>舀<EFBFBD>
- <EFBFBD>?銝剜<E98A9D><E5899C><EFBFBD>讃<EFBFBD>见末
- <EFBFBD>?MVP<EFBFBD>嗆挾隡睃<EFBFBD>撉諹<EFBFBD><EFBFBD>航<EFBFBD><EFBFBD>改<EFBFBD><EFBFBD>屸<EFBFBD>餈賣<EFBFBD><EFBFBD><EFBFBD>稲<EFBFBD><EFBFBD>＆<EFBFBD>?
---
### 3儭謿<E584AD> **韐券<E99F90>靽嗪<E99DBD>嚗鋴ochrane<6E><65><EFBFBD> + <20>餃郎<E9A483>餉<EFBFBD>撉諹<E69289>**
**新增服务**：
1. **MedicalLogicValidator**（医学逻辑验证）
**<EFBFBD>啣<EFBFBD><EFBFBD>滚𦛚**嚗?
1. **MedicalLogicValidator**嚗<>龫摮阡<E691AE>餉<EFBFBD>撉諹<E69289>嚗?
- RCT敹<54>◆<EFBFBD>厰<EFBFBD><E58EB0>箏<EFBFBD>
- <20>𣬚𤩅<F0A3AC9A>𠉛弦敹<E5BCA6>◆霂湔<E99C82><E6B994>脫<EFBFBD>
- 样本量与基线数据一致性
- 等...共5条规则
- <EFBFBD>瑟𧋦<EFBFBD>譍<EFBFBD><EFBFBD>箇瑪<EFBFBD>唳旿銝<EFBFBD><EFBFBD>湔<EFBFBD>?
- 蝑?..<2E>?<3F>∟<EFBFBD><E2889F>?
2. **EvidenceChainValidator**（证据链验证）
2. **EvidenceChainValidator**嚗<><E59A97><EFBFBD>桅曎撉諹<E69289>嚗?
- 撘箏<E69298><E7AE8F><EFBFBD><EFBFBD>撘閧鍂嚗<E98D82>竉50摮梹<E691AE>
- 雿滨蔭靽⊥<E99DBD>嚗<EFBFBD><E59A97><EFBFBD><EFBFBD><EFBFBD><EFBFBD>挾<EFBFBD>踝<EFBFBD>
- 憭<><E686AD><EFBFBD>亙<EFBFBD>撉諹<E69289>
3. **ConflictDetectionService**嚗<><E59A97>撘綽<E69298>
- 基于Cochrane标准的严重程度分级
- <EFBFBD>箔<EFBFBD>Cochrane<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>艇<EFBFBD>滨<EFBFBD>摨血<EFBFBD>蝥?
- <20>喲睸摮埈挾<E59F88>寞<EFBFBD>憭<EFBFBD><E686AD>
---
### 4儭謿<E584AD> **Prompt璅⊥踎嚗𡁶<E59A97><F0A181B6><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>**
**新目录结构**：
**<EFBFBD>啁𤌍敶閧<EFBFBD><EFBFBD>?*嚗?
```
prompts/
├── system_prompt.md # System Prompt（Section-Aware）
<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD> system_prompt.md # System Prompt嚗𠄎ection-Aware嚗?
<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD> user_prompt_template.md # User Prompt璅⊥踎
├── cochrane_standards/ # Cochrane标准描述（分字段）
│ ├── 随机化方法.md
│ ├── 盲法.md
│ ├── 结果完整性.md
│ └── ...（共12个）
└── few_shot_examples/ # Few-shot医学案例库
<EFBFBD>鎿<EFBFBD><EFBFBD><EFBFBD> cochrane_standards/ # Cochrane<EFBFBD><EFBFBD><EFBFBD><EFBFBD>讛膩嚗<EFBFBD><EFBFBD>摮埈挾嚗?
<EFBFBD>? <20>鎿<EFBFBD><E98EBF><EFBFBD> <20>𤩺㦤<F0A4A9BA>𡝗䲮瘜?md
<EFBFBD>? <20>鎿<EFBFBD><E98EBF><EFBFBD> <20>脫<EFBFBD>.md
<EFBFBD>? <20>鎿<EFBFBD><E98EBF><EFBFBD> 蝏𤘪<E89D8F>摰峕㟲<E5B395>?md
<EFBFBD>? <20>婙<EFBFBD><E5A999><EFBFBD> ...嚗<><E59A97>12銝迎<E98A9D>
<EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD> few_shot_examples/ # Few-shot<EFBFBD>餃郎獢<EFBFBD><EFBFBD>摨?
<20>鎿<EFBFBD><E98EBF><EFBFBD> 擃䁅捶<E48185>嗬CT.md
<20>鎿<EFBFBD><E98EBF><EFBFBD> 韐券<E99F90>銝滩雲獢<E99BB2><E78DA2>.md
└── 信息在中间位置案例.md # ← 特别重要
<EFBFBD>婙<EFBFBD><EFBFBD><EFBFBD> 靽⊥<E99DBD><E28AA5>其葉<E585B6>港<EFBFBD>蝵格<E89DB5>靘?md # <EFBFBD>?<3F>孵<EFBFBD><E5ADB5>滩<EFBFBD>
```
---
### 5️⃣ **开发周期：2周 + MVP验证3天**
### 5儭謿<EFBFBD> **撘<><E69298>穃𪂹<E7A983><F0AA82B9><EFBFBD>2<EFBFBD>?+ MVP撉諹<E69289>3憭?*
**调整**：
**靚<EFBFBD>㟲**嚗?
- Week 1-2嚗𡁜<E59A97><F0A1819C>𡢅<EFBFBD>靽脲<E99DBD>2<EFBFBD>剁<EFBFBD>
- Week 3嚗㇄ay 11-13嚗㚁<E59A97>MVP撉諹<E69289> + <20>∩辣<E288A9><E8BEA3>漣<EFBFBD>喟<EFBFBD>
**MVP验证关键**：
- 测试10-15篇人工标注论文
- 评估准确率（目标≥85%）
**MVP撉諹<EFBFBD><EFBFBD>喲睸**嚗?
- 瘚贝<EFBFBD>10-15蝭<EFBFBD>犖撌交<EFBFBD>瘜刻捏<EFBFBD>?
- 霂<EFBFBD>摯<EFBFBD><EFBFBD>＆<EFBFBD><EFBFBD><EFBFBD><EFBFBD>格<EFBFBD><EFBFBD>?5%嚗?
- 憒<><E68692><80%嚗<><E59A97>蝥找蛹瘛瑕<E7989B>蝑𣇉裦嚗<E8A3A6><E59A97><EFBFBD>桀<EFBFBD>畾萄<E795BE>畾菜<E795BE><E88F9C>吔<EFBFBD>
---
### 6️⃣ **数据库设计增强**
### 6儭謿<EFBFBD> **<2A>唳旿摨栞挽霈∪<E99C88>撘?*
**新增字段**：
- `promptVersion`：Prompt版本号
- `extractionMethod`：'nougat' | 'pymupdf'
- `structuredFormat`：是否为结构化格式
**<EFBFBD>啣<EFBFBD>摮埈挾**嚗?
- `promptVersion`嚗䥪rompt<EFBFBD><EFBFBD>𧋦<EFBFBD>?
- `extractionMethod`嚗?nougat' | 'pymupdf'
- `structuredFormat`嚗𡁏糓<EFBFBD>虫蛹蝏𤘪<EFBFBD><EFBFBD>𡝗聢撘?
- `processingLog`嚗𡁜<EFBFBD><EFBFBD><EFBFBD>𠯫敹梹<EFBFBD>撉諹<EFBFBD><EFBFBD>鞟<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
- `logicValidation`嚗𡁜龫摮阡<EFBFBD>餉<EFBFBD>撉諹<EFBFBD>蝏𤘪<EFBFBD>
- `evidenceComplete`嚗朞<EFBFBD><EFBFBD>桅曎<EFBFBD>臬炏摰峕㟲
- `conflictSeverity`：冲突严重程度
- `conflictSeverity`嚗𡁜<EFBFBD>蝒<EFBFBD>艇<EFBFBD>滨<EFBFBD>摨?
- `reviewPriority`嚗𡁜<EFBFBD><EFBFBD>訾<EFBFBD><EFBFBD><EFBFBD>漣
---
## 🎯 关键技术要点
## <EFBFBD>㴓 <20>喲睸<E596B2><E79DB8><EFBFBD>航<EFBFBD><E888AA>?
### Prompt撌亦<E6928C><E4BAA6>詨<EFBFBD>蝑𣇉裦
#### 1. Section-Aware Prompting
```markdown
⚠️ 重要：本文是完整全文（约20,000字），请按章节逐步处理。
<EFBFBD>𩤃<EFBFBD> <20>滩<EFBFBD>嚗𡁏𧋦<F0A1818F><F0A78BA6>糓摰峕㟲<E5B395>冽<EFBFBD>嚗<EFBFBD>漲20,000摮梹<E691AE>嚗諹窈<E8ABB9>厩<EFBFBD><E58EA9><EFBFBD><EFBFBD>鞉郊憭<E9838A><E686AD><EFBFBD>?
## 处理流程（必须遵守）：
## 憭<EFBFBD><EFBFBD>瘚<EFBFBD><EFBFBD>嚗<EFBFBD><EFBFBD>憿駁<EFBFBD>摰<EFBFBD><EFBFBD>嚗?
### Step 1: 蝡㰘<E89DA1>摰帋<E691B0>
快速浏览全文，识别关键章节（Abstract、Methods、Results...）
敹恍<EFBFBD><EFBFBD><EFBFBD>閫<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>霂<EFBFBD><EFBFBD><EFBFBD>喲睸蝡㰘<EFBFBD>嚗㇁bstract<EFBFBD><EFBFBD>ethods<EFBFBD><EFBFBD>esults...嚗?
### Step 2: 分字段提取
对于每个字段：
### Step 2: <EFBFBD><EFBFBD><EFBFBD>畾菜<EFBFBD><EFBFBD>?
撖嫣<EFBFBD>瘥譍葵摮埈挾嚗?
1. <20><>釣憸<E987A3><E686B8>雿滨蔭
2. 定位到章节
2. 摰帋<EFBFBD><EFBFBD>啁<EFBFBD><EFBFBD>?
3. **<EFBFBD>鞉挾隞𠉛<EFBFBD><EFBFBD><EFBFBD>粉**嚗<><E59A97>閬<EFBFBD>歲餈<E6ADB2>葉<EFBFBD>湛<EFBFBD>
4. <20>𣂼<EFBFBD>靽⊥<E99DBD>
5. 记录引用和位置
5. 霈啣<EFBFBD>撘閧鍂<EFBFBD>䔶<EFBFBD>蝵?
⚠️ 特别注意：
<EFBFBD>𩤃<EFBFBD> <20>孵<EFBFBD>瘜冽<E7989C>嚗?
- Methods<64>朙esults<74>其葉<E585B6>港<EFBFBD>蝵殷<E89DB5><E6AEB7><EFBFBD>摰寞<E691B0><E5AF9E>埈<EFBFBD>
- 餈嗘<E9A488>蝡㰘<E89DA1>敺<EFBFBD>鵭嚗諹窈<E8ABB9><E7AA88>挾<EFBFBD><E68CBE>粉
@@ -141,15 +141,15 @@ prompts/
### 獢<><E78DA2>1嚗帋縑<E5B88B>臬銁Methods銝剝𡢿畾菔氜嚗<E6B09C><E59A97><EFBFBD>埈<EFBFBD>嚗争<E59A97>
<EFBFBD>冽<EFBFBD>19,500摮梹<E691AE>
- Methods（4,000字）
- 第1段：研究设计概述
- 第2段：入排标准
- **第3段：随机化方法** ← 关键！在中间
- 第4段：盲法
- Methods嚗?,000摮梹<EFBFBD>
- 蝚?畾蛛<E795BE><E89B9B>𠉛弦霈曇恣璁<E681A3>膩
- 蝚?畾蛛<E795BE><E89B9B>交<EFBFBD><E4BAA4><EFBFBD><EFBFBD>
- **蝚?畾蛛<E795BE><E89B9B>𤩺㦤<F0A4A9BA>𡝗䲮瘜?* <20>?<3F>喲睸嚗<E79DB8>銁銝剝𡢿
- 蝚?畾蛛<E795BE><E89B9B>脫<EFBFBD>
- ...
甇<EFBFBD>＆<EFBFBD>𡁏<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>鞉挾<EFBFBD><EFBFBD>粉嚗䔶<EFBFBD>頝唾<EFBFBD>
错误示例❌：只看开头和结尾，跳过中间
<EFBFBD>躰秤蝷箔<EFBFBD><EFBFBD>䕘<EFBFBD><EFBFBD>芰<EFBFBD>撘<EFBFBD>憭游<EFBFBD>蝏枏偏嚗諹歲餈<EFBFBD>葉<EFBFBD>?
```
#### 3. JSON Schema撘箏<E69298>蝥行<E89DA5>
@@ -159,15 +159,15 @@ prompts/
"processing_log": {
"sections_reviewed": ["Abstract", "Methods", "Results", "Tables"],
"paragraphs_read_per_section": {
"Methods": 7, // 必须≥3
"Results": 5 // 必须≥3
"Methods": 7, // 敹<EFBFBD>◆<EFBFBD>?
"Results": 5 // 敹<EFBFBD>◆<EFBFBD>?
},
"middle_sections_attention": true // 敹<>◆<EFBFBD>單釣銝剝𡢿
},
"verification": {
"keywords_searched": ["randomization", "blinding", "ITT"],
"reread_count": 2, // 至少重读1次
"reread_count": 2, // <EFBFBD>喳<EFBFBD><EFBFBD>滩粉1甈?
"found_missed_info": false
}
}
@@ -179,30 +179,30 @@ prompts/
| <20><><EFBFBD> | <20>格<EFBFBD> | 撉諹<E69289><E8ABB9>寞<EFBFBD> |
|------|------|----------|
| **准确率（MVP）** | ≥ 85% | 人工标注10-15篇测试 |
| **Methods章节准确率** | ≥ 83% | 分章节评估 |
| **Results章节准确率** | ≥ 83% | 分章节评估 |
| **证据链完整性** | 100% | 自动检查 |
| **医学逻辑验证** | 100% | 规则引擎检查 |
| **成本** | ≤ ¥0.06/篇 | 实际消耗统计 |
| **处理时间** | ≤ 3分钟/篇 | 性能测试 |
| **<EFBFBD><EFBFBD>＆<EFBFBD><EFBFBD><EFBFBD>MVP嚗?* | <EFBFBD>?85% | 鈭箏極<EFBFBD><EFBFBD>釣10-15蝭<35><E89DAD>霂?|
| **Methods蝡㰘<EFBFBD><EFBFBD><EFBFBD>＆<EFBFBD>?* | <EFBFBD>?83% | <EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>隡?|
| **Results蝡㰘<EFBFBD><EFBFBD><EFBFBD>＆<EFBFBD>?* | <EFBFBD>?83% | <EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>隡?|
| **霂<EFBFBD>旿<EFBFBD>曉<EFBFBD><EFBFBD>湔<EFBFBD>?* | 100% | <EFBFBD>芸𢆡璉<EFBFBD><EFBFBD>?|
| **<EFBFBD>餃郎<EFBFBD>餉<EFBFBD>撉諹<EFBFBD>** | 100% | 閫<EFBFBD><EFBFBD>撘閙<EFBFBD>璉<EFBFBD><EFBFBD>?|
| **<EFBFBD>鞉𧋦** | <EFBFBD>?瞼0.06/蝭?| 摰鮋<E691B0>瘨<EFBFBD><E798A8>㛖<EFBFBD>霈?|
| **憭<EFBFBD><EFBFBD><EFBFBD>園𡢿** | <EFBFBD>?3<><33><EFBFBD>/蝭?| <20>扯<EFBFBD>瘚贝<E7989A> |
---
## <20><> <20>∩辣<E288A9><E8BEA3>漣頝臬<E9A09D>
如果MVP准确率<80%，升级为**混合策略**：
憒<EFBFBD><EFBFBD>MVP<EFBFBD><EFBFBD>＆<EFBFBD>?80%嚗<><E59A97>蝥找蛹**瘛瑕<E7989B>蝑𣇉裦**嚗?
```
关键字段（3个）→ 分段提取
- 随机化方法（Methods）
- 盲法（Methods）
- 结果完整性（Results + Figures）
<EFBFBD>喲睸摮埈挾嚗?銝迎<E98A9D><E8BF8E>?<3F><>挾<EFBFBD>𣂼<EFBFBD>
- <EFBFBD>𤩺㦤<EFBFBD>𡝗䲮瘜𤏪<EFBFBD>Methods嚗?
- <EFBFBD>脫<EFBFBD>嚗㇈ethods嚗?
- 蝏𤘪<EFBFBD>摰峕㟲<EFBFBD>改<EFBFBD>Results + Figures嚗?
其他字段（9个）→ 保持全文提取
<EFBFBD>嗡<EFBFBD>摮埈挾嚗?銝迎<E98A9D><E8BF8E>?靽脲<E99DBD><E884B2>冽<EFBFBD><E586BD>𣂼<EFBFBD>
- <20>𠉛弦霈曇恣<E69B87><E681A3><EFBFBD>蝛嗡犖蝢扎<E89DA2><E6898E>僕憸<E58395>綳<EFBFBD>賜<EFBFBD>
开发增量：+1周
撘<EFBFBD><EFBFBD>穃<EFBFBD><EFBFBD>𧶏<EFBFBD>+1<>?
憸<EFBFBD><EFBFBD><EFBFBD><EFBFBD>＆<EFBFBD><EFBFBD><EFBFBD>90%+
```
@@ -210,15 +210,15 @@ prompts/
## <20><> <20>詨<EFBFBD><E8A9A8><EFBFBD>﹝
- [全文复筛质量保障策略](../02-技术设计/08-全文复筛质量保障策略.md)
- [标题摘要初筛质量保障策略](../02-技术设计/06-质量保障与可追溯策略.md)
- [数据库设计](../02-技术设计/01-数据库设计.md)
- [API设计规范](../02-技术设计/02-API设计规范.md)
- [<EFBFBD>冽<EFBFBD>憭滨<EFBFBD>韐券<EFBFBD>靽嗪<EFBFBD>蝑𣇉裦](../02-<2D><><EFBFBD>航挽霈?08-<2D>冽<EFBFBD>憭滨<E686AD>韐券<E99F90>靽嗪<E99DBD>蝑𣇉裦.md)
- [<EFBFBD><EFBFBD><EFBFBD><EFBFBD>䁅<EFBFBD><EFBFBD>萘<EFBFBD>韐券<EFBFBD>靽嗪<EFBFBD>蝑𣇉裦](../02-<2D><><EFBFBD>航挽霈?06-韐券<E99F90>靽嗪<E99DBD>銝𤾸虾餈賣滲蝑𣇉裦.md)
- [<EFBFBD>唳旿摨栞挽霈（(../02-<2D><><EFBFBD>航挽霈?01-<2D>唳旿摨栞挽霈?md)
- [API霈曇恣閫<EFBFBD><EFBFBD>](../02-<EFBFBD><EFBFBD><EFBFBD>航挽霈?02-API霈曇恣閫<E681A3><E996AB>.md)
---
**更新日志**：
- 2025-11-22: V1.1 - 基于质量保障讨论，确定全文一次性+Prompt优化策略
**<EFBFBD>湔鰵<EFBFBD>亙<EFBFBD>**嚗?
- 2025-11-22: V1.1 - <EFBFBD>箔<EFBFBD>韐券<EFBFBD>靽嗪<EFBFBD>霈刻捏嚗𣬚＆摰𡁜<EFBFBD><EFBFBD><EFBFBD><EFBFBD>甈⊥<EFBFBD>?Prompt隡睃<E99AA1>蝑𣇉裦
- 2025-11-22: V1.0 - <20>嘥<EFBFBD><E598A5><EFBFBD>𧋦