AIclinicalresearch/docs/03-业务模块/ASL-AI智能文献/05-开发记录/2025-11-21-字段映射问题修复.md

# 字段映射问题修å¤<C3A5>报告

**日期**: 2025-11-21  
**问题**: 真实LLM筛选失败（æˆ<C3A6>功ï¼?/20ï¼? 
**原因**: 字段å<C2B5><C3A5>ä¸<C3A4>匹é…<C3A9>  
**状�*: �已修� 

---

## ðŸ”<C5B8> 问题诊断

### 症状
```
任务状� completed
进度: 20/20
æˆ<EFBFBD>功: 0 â<>?
筛选结果数: 0
```

**表现**�
- 任务瞬间完æˆ<C3A6>ï¼?秒）
- 所有文献处ç<E2809E>†å¤±è´?
- 没有ä¿<C3A4>存任何筛选结æž?

---

## 🎯 根本原因

### 问题1: PICOS字段å<C2B5><C3A5>ä¸<C3A4>匹é…<C3A9>

**å‰<C3A5>端/æ•°æ<C2B0>®åº“æ ¼å¼?* (`TitleScreeningSettings.tsx`):
```typescript
picoCriteria: {
  P: '2型糖尿病患�..',
  I: 'SGLT2抑制�..',
  C: '安慰剂或常规治疗...',
  O: '心血管结局...',
  S: 'RCT'
}
```

**LLMæœ<C3A6>务期望格å¼<C3A5>** (`llmScreeningService.ts`):
```typescript
// 实际上支æŒ<C3A6>两ç§<C3A7>æ ¼å¼<C3A5>，但优先使用短格å¼<C3A5>
picoCriteria: {
  P: '...',  // �
  I: '...',  // �
  C: '...',  // �
  O: '...',  // �
  S: '...'   // �
}
```

**诊断**：å‰<C3A5>端使ç”?P/I/C/O/S æ ¼å¼<C3A5>，但 `screeningService.ts` 直接传递了数æ<C2B0>®åº“的原始格å¼<C3A5>，未å<C2AA>šæ˜ å°„ã€?

---

### 问题2: 模型å<E280B9><C3A5>æ ¼å¼<C3A5>ä¸<C3A4>匹é…<C3A9>

**å‰<C3A5>端格å¼<C3A5>** (`TitleScreeningSettings.tsx`):
```typescript
models: ['DeepSeek-V3', 'Qwen-Max']
```

**LLMæœ<C3A6>务期望格å¼<C3A5>** (`llmScreeningService.ts`):
```typescript
models: ['deepseek-chat', 'qwen-max']
```

**原因**：å‰<C3A5>端使用展示å<C2BA><C3A5>称，å<C592>Žç«¯éœ€è¦<C3A8>APIå<49><C3A5>称ã€?

---

### 问题3: 缺少字段验è¯<C3A8>

文献å<EFBFBD>¯èƒ½ç¼ºå°‘ `title` æˆ?`abstract`，导致LLM调用失败ã€?

---

## âœ?ä¿®å¤<C3A5>方案

### ä¿®å¤<C3A5>1: 添加PICOS字段映射

**文件**: `backend/src/modules/asl/services/screeningService.ts`

```typescript
// 🔧 ä¿®å¤<C3A5>：字段å<C2B5><C3A5>映射（数æ<C2B0>®åº“æ ¼å¼<C3A5> â†?LLMæœ<C3A6>务格å¼<C3A5>ï¼?
const rawPicoCriteria = project.picoCriteria as any;
const picoCriteria = {
  P: rawPicoCriteria?.P || rawPicoCriteria?.population || '',
  I: rawPicoCriteria?.I || rawPicoCriteria?.intervention || '',
  C: rawPicoCriteria?.C || rawPicoCriteria?.comparison || '',
  O: rawPicoCriteria?.O || rawPicoCriteria?.outcome || '',
  S: rawPicoCriteria?.S || rawPicoCriteria?.studyDesign || '',
};
```

**优势**�
- âœ?兼容两ç§<C3A7>æ ¼å¼<C3A5>（P/I/C/O/S æˆ?population/intervention/...ï¼?
- âœ?防御性编程，é<C592>¿å…<C3A5>undefined

---

### ä¿®å¤<C3A5>2: 添加模型å<E280B9><C3A5>映å°?

```typescript
// 🔧 ä¿®å¤<C3A5>：模型å<E280B9><C3A5>映射（å‰<C3A5>端格å¼?â†?APIæ ¼å¼<C3A5>ï¼?
const MODEL_NAME_MAP: Record<string, string> = {
  'DeepSeek-V3': 'deepseek-chat',
  'Qwen-Max': 'qwen-max',
  'GPT-4o': 'gpt-4o',
  'Claude-4.5': 'claude-sonnet-4.5',
  'deepseek-chat': 'deepseek-chat',  // 兼容直接使用APIå<49>?
  'qwen-max': 'qwen-max',
  // ... 更多映射
};

const rawModels = screeningConfig?.models || ['deepseek-chat', 'qwen-max'];
const models = rawModels.map((m: string) => MODEL_NAME_MAP[m] || m);
```

**映射�*�
| å‰<C3A5>端展示å<C2BA>?| APIå<49><C3A5>称 |
|-----------|---------|
| DeepSeek-V3 | deepseek-chat |
| Qwen-Max | qwen-max |
| GPT-4o | gpt-4o |
| Claude-4.5 | claude-sonnet-4.5 |

---

### ä¿®å¤<C3A5>3: 添加文献验è¯<C3A8>

```typescript
// 🔧 验è¯<C3A8>：必须有标题和摘è¦?
if (!literature.title || !literature.abstract) {
  logger.warn('Skipping literature without title or abstract', {
    literatureId: literature.id,
    hasTitle: !!literature.title,
    hasAbstract: !!literature.abstract,
  });
  console.log(`âš ï¸<EFBFBD>  跳过文献 ${processedCount + 1}: 缺少标题或摘è¦<C3A8>`);
  processedCount++;
  continue;
}
```

---

### ä¿®å¤<C3A5>4: 增强调试日志

```typescript
console.log('\n🚀 开始真实LLM筛�');
console.log('  任务ID:', taskId);
console.log('  项目ID:', projectId);
console.log('  文献�', literatures.length);
console.log('  模型（映射å<E2809E>Žï¼?', models);  // â­?显示映射å<E2809E>Žçš„å€?
console.log('  PICOS-P:', picoCriteria.P?.substring(0, 50) || '(ç©?');
console.log('  PICOS-I:', picoCriteria.I?.substring(0, 50) || '(ç©?');
console.log('  PICOS-C:', picoCriteria.C?.substring(0, 50) || '(ç©?');
console.log('  纳入标准:', inclusionCriteria?.substring(0, 50) || '(�');
console.log('  排除标准:', exclusionCriteria?.substring(0, 50) || '(�');
```

---

## 🧪 测试步骤

### 1. é‡<C3A9>å<EFBFBD>¯å<C2AF>Žç«¯ï¼ˆå¿…é¡»ï¼<C3AF>ï¼?

```bash
# å<>œæ­¢å½“å‰<C3A5>å<EFBFBD>Žç«¯ï¼ˆCtrl+Cï¼?
cd D:\MyCursor\AIclinicalresearch\backend
npm run dev
```

### 2. 测试（å°<C3A5>规模ï¼?

1. 访问å‰<C3A5>端
2. 填写PICOS
3. **上传5篇文çŒ?*（先测试å°<C3A5>规模）
4. 点击"开始AIåˆ<C3A5>ç­›"

### 3. 查看å<E280B9>Žç«¯æŽ§åˆ¶å<C2B6>?

**应该看到**�
```
🚀 开始真实LLM筛�
  任务ID: xxx
  文献� 5
  模型（映射å<E2809E>Žï¼? [ 'deepseek-chat', 'qwen-max' ]
  PICOS-P: 2型糖尿病患�..
  PICOS-I: SGLT2抑制�..
  PICOS-C: 安慰�..
  纳入标准: æˆ<C3A6>人2åž‹ç³–å°¿ç—…...
  排除标准: 综述ã€<C3A3>系统评ä»?..

[等待10-20秒]

âœ?文献 1/5 处ç<E2809E>†æˆ<C3A6>功
  DS: include / Qwen: include
  冲çª<C3A7>: å<>?

[等待10-20秒]

âœ?文献 2/5 处ç<E2809E>†æˆ<C3A6>功
  DS: exclude / Qwen: exclude
  冲çª<C3A7>: å<>?
...
```

---

## 📊 预期效果

### ä¿®å¤<C3A5>å‰?
- â<>±ï¸<C3AF> 1秒完æˆ?0ç¯?
- â<>?æˆ<C3A6>功ï¼?
- â<>?筛选结果数ï¼?

### ä¿®å¤<C3A5>å<EFBFBD>?
- â<>±ï¸<C3AF> 50-100秒完æˆ?篇（æ¯<C3A6>篇10-20秒）
- âœ?æˆ<C3A6>功ï¼?
- �筛选结果数�
- âœ?è¯<C3A8>æ<EFBFBD>®åŒ…å<E280A6>«çœŸå®žçš„AI分æž<C3A6>
- âœ?è¯<C3A8>æ<EFBFBD>®ä¸<C3A4>包å<E280A6>?模拟è¯<C3A8>æ<EFBFBD>®"

---

## 🔧 修改文件

- �`backend/src/modules/asl/services/screeningService.ts`
  - 添加PICOS字段映射
  - 添加模型å<E280B9><C3A5>映å°?
  - 添加文献验è¯<C3A8>
  - 增强调试日志

---

## 💡 ç»<C3A7>验教训

### 1. å‰<C3A5>å<EFBFBD>Žç«¯æ•°æ<C2B0>®æ ¼å¼<C3A5>一致æ€?
- å‰<C3A5>端使用的展示格å¼?â‰?å<>Žç«¯APIæ ¼å¼<C3A5>
- 需è¦<C3A8>在集æˆ<C3A6>层å<E2809A>šæ˜ å°„

### 2. 防御性编�
- 使用 `||` æ<><C3A6>供默认å€?
- 验è¯<C3A8>必需字段
- 兼容多ç§<C3A7>æ ¼å¼<C3A5>

### 3. 调试日志的é‡<C3A9>è¦<C3A8>æ€?
- 显示映射å<E2809E>Žçš„值（ä¸<C3A4>是原始值）
- 输出所有关键å<C2AE>‚æ•?
- 帮助快速定ä½<C3A4>é—®é¢?

---

## 🎯 å<>Žç»­ä¼˜åŒ–

### 短期
1. âœ?字段映射（已完æˆ<C3A6>ï¼?
2. âœ?模型å<E280B9><C3A5>映射（已完æˆ<C3A6>）
3. âœ?验è¯<C3A8>必需字段（已完æˆ<C3A6>ï¼?

### 中期
1. 统一å‰<C3A5>å<EFBFBD>Žç«¯æ•°æ<C2B0>®æ ¼å¼<C3A5>（使用 TypeScript 接å<C2A5>£ï¼?
2. 添加数æ<C2B0>®æ ¼å¼<C3A5>验è¯<C3A8>中间ä»?
3. 改进错误æ<C2AF><C3A6>示

### 长期
1. 使用 tRPC æˆ?GraphQL ç¡®ä¿<C3A4>类型安全
2. 自动化测试覆�
3. Schema验è¯<C3A8>

---

**报告�*: AI Assistant  
**日期**: 2025-11-21  
**版本**: v1.0.0