# AI智能文献模块 - 数据库设�?
> **文档版本�?* v3.0  
> **创建日期�?* 2025-10-29  
> **维护者：** AI智能文献开发团�? 
> **最后更新：** 2025-11-22（Day 4：全文复筛数据库设计�? 
> **更新说明�?* 新增全文复筛相关表（`AslLiterature`扩展、`AslFulltextScreeningTask`、`AslFulltextScreeningResult`�?
---

## 📋 文档说明

本文档描述AI智能文献模块的数据库设计，包括数据表结构、关系设计、索引设计等�?
**技术栈**:
- 数据库：PostgreSQL 16+
- ORM：Prisma
- Schema隔离：`asl_schema`
- 关联用户表：`platform_schema.users`

---

## 🏗�?Schema架构

ASL模块使用独立�?`asl_schema` 进行数据隔离，确保模块独立性和数据安全�?
```
platform_schema
  └── users (用户�?
       �?asl_schema
  ├── screening_projects (筛选项�?
  ├── literatures (文献条目)
  ├── screening_results (标题初筛结果)
  ├── screening_tasks (标题初筛任务)
  ├── fulltext_screening_tasks (全文复筛任务) �?Day 4新增
  └── fulltext_screening_results (全文复筛结果) �?Day 4新增
```

**v3.0 更新说明�?025-11-22�?*�?- �?扩展 `literatures` 表：支持全文生命周期管理、PDF存储、全文内容引�?- �?新增 `fulltext_screening_tasks` 表：管理全文复筛批处理任�?- �?新增 `fulltext_screening_results` 表：存储12字段评估结果
- �?符合云原生规范：全文内容存储引用而非直接存储

---

## 🗄�?核心数据�?
### 1. 筛选项目表 (screening_projects)

**Prisma模型�?*: `AslScreeningProject`  
**表名**: `asl_schema.screening_projects`

```prisma
model AslScreeningProject {
  id                String   @id @default(uuid())
  userId            String   @map("user_id")
  user              User     @relation("AslProjects", fields: [userId], references: [id], onDelete: Cascade)
  
  projectName       String   @map("project_name")
  
  // PICO标准
  picoCriteria      Json     @map("pico_criteria")
  // ⚠️ 格式兼容性说明：
  // 前端使用: { P, I, C, O, S }
  // 后端兼容: { P, I, C, O, S } �?{ population, intervention, comparison, outcome, studyDesign }
  // screeningService.ts 中有字段映射逻辑
  
  // 筛选标�?  inclusionCriteria String   @map("inclusion_criteria") @db.Text
  exclusionCriteria String   @map("exclusion_criteria") @db.Text
  
  // 状�?  status            String   @default("draft")
  // 可选�? draft, screening, completed
  
  // 筛选配�?  screeningConfig   Json?    @map("screening_config")
  // 结构: { models: ["DeepSeek-V3", "Qwen-Max"], style: "standard" }
  // ⚠️ 模型名称映射�?  // 前端展示�? DeepSeek-V3 �?API�? deepseek-chat
  // 前端展示�? Qwen-Max �?API�? qwen-max
  // screeningService.ts 中有模型名映射逻辑
  
  // 关联
  literatures       AslLiterature[]
  screeningTasks    AslScreeningTask[]
  screeningResults  AslScreeningResult[]
  
  createdAt         DateTime @default(now()) @map("created_at")
  updatedAt         DateTime @updatedAt @map("updated_at")
  
  @@map("screening_projects")
  @@schema("asl_schema")
  @@index([userId])
  @@index([status])
}
```

**SQL表结�?*:
```sql
CREATE TABLE asl_schema.screening_projects (
  id TEXT PRIMARY KEY,
  user_id TEXT NOT NULL,
  project_name TEXT NOT NULL,
  pico_criteria JSONB NOT NULL,
  inclusion_criteria TEXT NOT NULL,
  exclusion_criteria TEXT NOT NULL,
  status TEXT NOT NULL DEFAULT 'draft',
  screening_config JSONB,
  created_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  updated_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  CONSTRAINT fk_user FOREIGN KEY (user_id) 
    REFERENCES platform_schema.users(id) ON DELETE CASCADE
);

CREATE INDEX idx_screening_projects_user_id ON asl_schema.screening_projects(user_id);
CREATE INDEX idx_screening_projects_status ON asl_schema.screening_projects(status);
```

---

### 2. 文献条目�?(literatures) �?v3.0更新

**Prisma模型�?*: `AslLiterature`  
**表名**: `asl_schema.literatures`

**v3.0 更新说明**�?- �?新增 `stage` 字段：追踪文献生命周期（imported �?title_screened �?pdf_acquired �?fulltext_screened �?data_extracted�?- �?新增 PDF存储字段：支持Dify/OSS双适配（`pdfStorageType`, `pdfStorageRef`, `pdfStatus`�?- �?新增 全文存储字段�?*符合云原生规范，存储引用而非内容**（`fullTextStorageRef`, `fullTextUrl`�?- �?新增索引：`stage`, `hasPdf`, `pdfStatus` 提升查询性能

```prisma
model AslLiterature {
  id                String   @id @default(uuid())
  projectId         String   @map("project_id")
  project           AslScreeningProject @relation(fields: [projectId], references: [id], onDelete: Cascade)
  
  // 文献基本信息
  pmid              String?
  title             String   @db.Text
  abstract          String   @db.Text
  authors           String?
  journal           String?
  publicationYear   Int?     @map("publication_year")
  doi               String?
  
  // �?v3.0 新增：文献阶段（生命周期管理�?  stage             String   @default("imported") @map("stage")
  // imported | title_screened | title_included | pdf_acquired | fulltext_screened | data_extracted
  
  // 云原生存储字段（V1.0 阶段使用，MVP阶段预留�?  pdfUrl            String?  @map("pdf_url")        // PDF访问URL
  pdfOssKey         String?  @map("pdf_oss_key")    // OSS存储Key（用于删除）
  pdfFileSize       Int?     @map("pdf_file_size")  // 文件大小（字节）
  
  // �?v3.0 新增：PDF存储（Dify/OSS双适配�?  hasPdf            Boolean  @default(false) @map("has_pdf")
  pdfStorageType    String?  @map("pdf_storage_type")  // "dify" | "oss"
  pdfStorageRef     String?  @map("pdf_storage_ref")   // Dify: document_id, OSS: object_key
  pdfStatus         String?  @map("pdf_status")        // "uploading" | "ready" | "failed"
  pdfUploadedAt     DateTime? @map("pdf_uploaded_at")
  
  // �?v3.0 新增：全文内容存储（云原生：存储引用而非内容�?  fullTextStorageType String?  @map("full_text_storage_type")  // "dify" | "oss"
  fullTextStorageRef  String?  @map("full_text_storage_ref")   // document_id �?object_key
  fullTextUrl         String?  @map("full_text_url")           // 访问URL
  fullTextFormat      String?  @map("full_text_format")        // "markdown" | "plaintext"
  fullTextSource      String?  @map("full_text_source")        // "nougat" | "pymupdf"
  fullTextTokenCount  Int?     @map("full_text_token_count")
  fullTextExtractedAt DateTime? @map("full_text_extracted_at")
  
  // 关联
  screeningResults  AslScreeningResult[]
  fulltextScreeningResults AslFulltextScreeningResult[] // �?v3.0 新增
  
  createdAt         DateTime @default(now()) @map("created_at")
  updatedAt         DateTime @updatedAt @map("updated_at")
  
  @@map("literatures")
  @@schema("asl_schema")
  @@index([projectId])
  @@index([doi])
  @@index([stage])          // �?v3.0 新增
  @@index([hasPdf])         // �?v3.0 新增
  @@index([pdfStatus])      // �?v3.0 新增
  @@unique([projectId, pmid])
}
```

**SQL表结�?*（v3.0�?
```sql
CREATE TABLE asl_schema.literatures (
  id TEXT PRIMARY KEY,
  project_id TEXT NOT NULL,
  
  -- 文献基本信息
  pmid TEXT,
  title TEXT NOT NULL,
  abstract TEXT NOT NULL,
  authors TEXT,
  journal TEXT,
  publication_year INTEGER,
  doi TEXT,
  
  -- 文献阶段
  stage TEXT NOT NULL DEFAULT 'imported',
  
  -- PDF存储（旧字段，V1.0预留�?  pdf_url TEXT,
  pdf_oss_key TEXT,
  pdf_file_size INTEGER,
  
  -- PDF存储（新字段，Dify/OSS双适配�?  has_pdf BOOLEAN NOT NULL DEFAULT false,
  pdf_storage_type TEXT,
  pdf_storage_ref TEXT,
  pdf_status TEXT,
  pdf_uploaded_at TIMESTAMP(3),
  
  -- 全文内容存储（引用）
  full_text_storage_type TEXT,
  full_text_storage_ref TEXT,
  full_text_url TEXT,
  full_text_format TEXT,
  full_text_source TEXT,
  full_text_token_count INTEGER,
  full_text_extracted_at TIMESTAMP(3),
  
  created_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  updated_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  
  CONSTRAINT fk_project FOREIGN KEY (project_id) 
    REFERENCES asl_schema.screening_projects(id) ON DELETE CASCADE,
  CONSTRAINT unique_project_pmid UNIQUE (project_id, pmid)
);

CREATE INDEX idx_literatures_project_id ON asl_schema.literatures(project_id);
CREATE INDEX idx_literatures_doi ON asl_schema.literatures(doi);
CREATE INDEX idx_literatures_stage ON asl_schema.literatures(stage);
CREATE INDEX idx_literatures_has_pdf ON asl_schema.literatures(has_pdf);
CREATE INDEX idx_literatures_pdf_status ON asl_schema.literatures(pdf_status);
```

**字段说明**�?
| 字段 | 类型 | 说明 | 设计理由 |
|------|------|------|----------|
| `stage` | String | 文献阶段 | 追踪文献在整个流程中的位�?|
| `pdfStorageType` | String | PDF存储类型 | "dify"\|"oss"，支持双适配�?|
| `pdfStorageRef` | String | PDF存储引用 | Dify的document_id或OSS的object_key |
| `fullTextStorageType` | String | 全文存储类型 | 云原生：不直接存全文，存引用 �?|
| `fullTextStorageRef` | String | 全文存储引用 | 指向Dify或OSS中的全文文档 �?|
| `fullTextUrl` | String | 全文访问URL | 直接访问全文的URL |
| `fullTextTokenCount` | Int | Token数量 | 用于成本估算和LLM调用优化 |

**云原生设计亮�?* ⭐：
- �?全文内容存储在OSS/Dify，数据库只存引用（符合云原生规范�?- �?支持Dify �?OSS无缝迁移（只需切换storageType�?- �?数据库轻量，避免大量TEXT字段

---

### 3. 筛选结果表 (screening_results)

**Prisma模型�?*: `AslScreeningResult`  
**表名**: `asl_schema.screening_results`

**设计亮点**：支持双模型（DeepSeek + Qwen）并行验证，包含完整的判断、证据和冲突检测�?
```prisma
model AslScreeningResult {
  id                String   @id @default(uuid())
  projectId         String   @map("project_id")
  project           AslScreeningProject @relation(fields: [projectId], references: [id], onDelete: Cascade)
  literatureId      String   @map("literature_id")
  literature        AslLiterature @relation(fields: [literatureId], references: [id], onDelete: Cascade)
  
  // DeepSeek模型判断
  dsModelName       String   @map("ds_model_name") // "deepseek-chat"
  dsPJudgment       String?  @map("ds_p_judgment") // "match" | "partial" | "mismatch"
  dsIJudgment       String?  @map("ds_i_judgment")
  dsCJudgment       String?  @map("ds_c_judgment")
  dsSJudgment       String?  @map("ds_s_judgment")
  dsConclusion      String?  @map("ds_conclusion") // "include" | "exclude" | "uncertain"
  dsConfidence      Float?   @map("ds_confidence") // 0-1
  
  // DeepSeek模型证据
  dsPEvidence       String?  @map("ds_p_evidence") @db.Text
  dsIEvidence       String?  @map("ds_i_evidence") @db.Text
  dsCEvidence       String?  @map("ds_c_evidence") @db.Text
  dsSEvidence       String?  @map("ds_s_evidence") @db.Text
  dsReason          String?  @map("ds_reason") @db.Text
  
  // Qwen模型判断
  qwenModelName     String   @map("qwen_model_name") // "qwen-max"
  qwenPJudgment     String?  @map("qwen_p_judgment")
  qwenIJudgment     String?  @map("qwen_i_judgment")
  qwenCJudgment     String?  @map("qwen_c_judgment")
  qwenSJudgment     String?  @map("qwen_s_judgment")
  qwenConclusion    String?  @map("qwen_conclusion")
  qwenConfidence    Float?   @map("qwen_confidence")
  
  // Qwen模型证据
  qwenPEvidence     String?  @map("qwen_p_evidence") @db.Text
  qwenIEvidence     String?  @map("qwen_i_evidence") @db.Text
  qwenCEvidence     String?  @map("qwen_c_evidence") @db.Text
  qwenSEvidence     String?  @map("qwen_s_evidence") @db.Text
  qwenReason        String?  @map("qwen_reason") @db.Text
  
  // 冲突状�?  conflictStatus    String   @default("none") @map("conflict_status")
  // 可选�? none, conflict, resolved
  conflictFields    Json?    @map("conflict_fields")
  // 示例: ["P", "I", "conclusion"]
  
  // 最终决策（Week 4 混合方案使用�?  finalDecision     String?  @map("final_decision") // "include" | "exclude" | null
  // �?Week 4 说明：人工复核后设置此字段，作为最终决�?  // - include: 人工决定纳入（可能推翻AI建议�?  // - exclude: 人工决定排除（可能推翻AI建议�?  // - null: 未复核，使用AI决策
  
  finalDecisionBy   String?  @map("final_decision_by") // userId
  finalDecisionAt   DateTime? @map("final_decision_at")
  
  exclusionReason   String?  @map("exclusion_reason") @db.Text
  // �?Week 4 说明：人工填写的排除原因（优先级高于AI提取�?  // - 如果finalDecision=exclude，此字段存储人工填写的原�?  // - 如果为null，前端自动从AI判断中提取（dsPJudgment/dsIJudgment等）
  // - Week 4 初筛结果页使用此字段显示排除原因
  
  // AI处理状�?  aiProcessingStatus String  @default("pending") @map("ai_processing_status")
  // 可选�? pending, processing, completed, failed
  aiProcessedAt     DateTime? @map("ai_processed_at")
  aiErrorMessage    String?  @map("ai_error_message") @db.Text
  
  // 可追溯信�?  promptVersion     String   @default("v1.0.0") @map("prompt_version")
  rawOutput         Json?    @map("raw_output") // 原始LLM输出（备份）
  
  createdAt         DateTime @default(now()) @map("created_at")
  updatedAt         DateTime @updatedAt @map("updated_at")
  
  @@map("screening_results")
  @@schema("asl_schema")
  @@index([projectId])
  @@index([literatureId])
  @@index([conflictStatus])
  @@index([finalDecision])
  @@unique([projectId, literatureId])  // 一篇文献在一个项目中只有一个筛选结�?}
```

**SQL表结�?*（简化版�?
```sql
CREATE TABLE asl_schema.screening_results (
  id TEXT PRIMARY KEY,
  project_id TEXT NOT NULL,
  literature_id TEXT NOT NULL,
  
  -- DeepSeek判断
  ds_model_name TEXT NOT NULL,
  ds_p_judgment TEXT,
  ds_i_judgment TEXT,
  ds_c_judgment TEXT,
  ds_s_judgment TEXT,
  ds_conclusion TEXT,
  ds_confidence DOUBLE PRECISION,
  ds_p_evidence TEXT,
  ds_i_evidence TEXT,
  ds_c_evidence TEXT,
  ds_s_evidence TEXT,
  ds_reason TEXT,
  
  -- Qwen判断
  qwen_model_name TEXT NOT NULL,
  qwen_p_judgment TEXT,
  qwen_i_judgment TEXT,
  qwen_c_judgment TEXT,
  qwen_s_judgment TEXT,
  qwen_conclusion TEXT,
  qwen_confidence DOUBLE PRECISION,
  qwen_p_evidence TEXT,
  qwen_i_evidence TEXT,
  qwen_c_evidence TEXT,
  qwen_s_evidence TEXT,
  qwen_reason TEXT,
  
  -- 冲突状�?  conflict_status TEXT NOT NULL DEFAULT 'none',
  conflict_fields JSONB,
  
  -- 最终决�?  final_decision TEXT,
  final_decision_by TEXT,
  final_decision_at TIMESTAMP(3),
  exclusion_reason TEXT,
  
  -- AI处理状�?  ai_processing_status TEXT NOT NULL DEFAULT 'pending',
  ai_processed_at TIMESTAMP(3),
  ai_error_message TEXT,
  
  -- 可追溯信�?  prompt_version TEXT NOT NULL DEFAULT 'v1.0.0',
  raw_output JSONB,
  
  created_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  updated_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  
  CONSTRAINT fk_project_result FOREIGN KEY (project_id) 
    REFERENCES asl_schema.screening_projects(id) ON DELETE CASCADE,
  CONSTRAINT fk_literature FOREIGN KEY (literature_id) 
    REFERENCES asl_schema.literatures(id) ON DELETE CASCADE,
  CONSTRAINT unique_project_literature UNIQUE (project_id, literature_id)
);

CREATE INDEX idx_screening_results_project_id ON asl_schema.screening_results(project_id);
CREATE INDEX idx_screening_results_literature_id ON asl_schema.screening_results(literature_id);
CREATE INDEX idx_screening_results_conflict_status ON asl_schema.screening_results(conflict_status);
CREATE INDEX idx_screening_results_final_decision ON asl_schema.screening_results(final_decision);
```

---

### 4. 筛选任务表 (screening_tasks)

**Prisma模型�?*: `AslScreeningTask`  
**表名**: `asl_schema.screening_tasks`

```prisma
model AslScreeningTask {
  id                String   @id @default(uuid())
  projectId         String   @map("project_id")
  project           AslScreeningProject @relation(fields: [projectId], references: [id], onDelete: Cascade)
  
  taskType          String   @map("task_type") // "title_abstract" | "full_text"
  status            String   @default("pending")
  // 可选�? pending, running, completed, failed
  
  // 进度统计
  totalItems        Int      @map("total_items")
  processedItems    Int      @default(0) @map("processed_items")
  successItems      Int      @default(0) @map("success_items")
  failedItems       Int      @default(0) @map("failed_items")
  conflictItems     Int      @default(0) @map("conflict_items")
  
  // 时间信息
  startedAt         DateTime? @map("started_at")
  completedAt       DateTime? @map("completed_at")
  estimatedEndAt    DateTime? @map("estimated_end_at")
  
  // 错误信息
  errorMessage      String?  @map("error_message") @db.Text
  
  createdAt         DateTime @default(now()) @map("created_at")
  updatedAt         DateTime @updatedAt @map("updated_at")
  
  @@map("screening_tasks")
  @@schema("asl_schema")
  @@index([projectId])
  @@index([status])
}
```

**SQL表结�?*:
```sql
CREATE TABLE asl_schema.screening_tasks (
  id TEXT PRIMARY KEY,
  project_id TEXT NOT NULL,
  task_type TEXT NOT NULL,
  status TEXT NOT NULL DEFAULT 'pending',
  total_items INTEGER NOT NULL,
  processed_items INTEGER NOT NULL DEFAULT 0,
  success_items INTEGER NOT NULL DEFAULT 0,
  failed_items INTEGER NOT NULL DEFAULT 0,
  conflict_items INTEGER NOT NULL DEFAULT 0,
  started_at TIMESTAMP(3),
  completed_at TIMESTAMP(3),
  estimated_end_at TIMESTAMP(3),
  error_message TEXT,
  created_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  updated_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  CONSTRAINT fk_project_task FOREIGN KEY (project_id) 
    REFERENCES asl_schema.screening_projects(id) ON DELETE CASCADE
);

CREATE INDEX idx_screening_tasks_project_id ON asl_schema.screening_tasks(project_id);
CREATE INDEX idx_screening_tasks_status ON asl_schema.screening_tasks(status);
```

---

### 5. 全文复筛任务�?(fulltext_screening_tasks) �?v3.0新增

**Prisma模型�?*: `AslFulltextScreeningTask`  
**表名**: `asl_schema.fulltext_screening_tasks`

**设计目标**：管理全文复筛的批处理任务，支持双模型并行调用、成本追踪、降级模�?
```prisma
model AslFulltextScreeningTask {
  id                String   @id @default(uuid())
  projectId         String   @map("project_id")
  project           AslScreeningProject @relation(fields: [projectId], references: [id], onDelete: Cascade)
  
  // 任务配置
  modelA            String   @map("model_a")          // "deepseek-v3"
  modelB            String   @map("model_b")          // "qwen-max"
  promptVersion     String   @default("v1.0.0") @map("prompt_version")
  
  // 任务状�?  status            String   @default("pending")
  // "pending" | "running" | "completed" | "failed" | "cancelled"
  
  // 进度统计
  totalCount        Int      @map("total_count")
  processedCount    Int      @default(0) @map("processed_count")
  successCount      Int      @default(0) @map("success_count")
  failedCount       Int      @default(0) @map("failed_count")
  degradedCount     Int      @default(0) @map("degraded_count")  // 单模型成�?  
  // 成本统计
  totalTokens       Int      @default(0) @map("total_tokens")
  totalCost         Float    @default(0) @map("total_cost")
  
  // 时间信息
  startedAt         DateTime? @map("started_at")
  completedAt       DateTime? @map("completed_at")
  estimatedEndAt    DateTime? @map("estimated_end_at")
  
  // 错误信息
  errorMessage      String?  @map("error_message") @db.Text
  errorStack        String?  @map("error_stack") @db.Text
  
  // 关联
  results           AslFulltextScreeningResult[]
  
  createdAt         DateTime @default(now()) @map("created_at")
  updatedAt         DateTime @updatedAt @map("updated_at")
  
  @@map("fulltext_screening_tasks")
  @@schema("asl_schema")
  @@index([projectId])
  @@index([status])
  @@index([createdAt])
}
```

**SQL表结�?*:
```sql
CREATE TABLE asl_schema.fulltext_screening_tasks (
  id TEXT PRIMARY KEY,
  project_id TEXT NOT NULL,
  
  -- 任务配置
  model_a TEXT NOT NULL,
  model_b TEXT NOT NULL,
  prompt_version TEXT NOT NULL DEFAULT 'v1.0.0',
  
  -- 任务状�?  status TEXT NOT NULL DEFAULT 'pending',
  
  -- 进度统计
  total_count INTEGER NOT NULL,
  processed_count INTEGER NOT NULL DEFAULT 0,
  success_count INTEGER NOT NULL DEFAULT 0,
  failed_count INTEGER NOT NULL DEFAULT 0,
  degraded_count INTEGER NOT NULL DEFAULT 0,
  
  -- 成本统计
  total_tokens INTEGER NOT NULL DEFAULT 0,
  total_cost DOUBLE PRECISION NOT NULL DEFAULT 0,
  
  -- 时间信息
  started_at TIMESTAMP(3),
  completed_at TIMESTAMP(3),
  estimated_end_at TIMESTAMP(3),
  
  -- 错误信息
  error_message TEXT,
  error_stack TEXT,
  
  created_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  updated_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  
  CONSTRAINT fk_project_fulltext_task FOREIGN KEY (project_id) 
    REFERENCES asl_schema.screening_projects(id) ON DELETE CASCADE
);

CREATE INDEX idx_fulltext_screening_tasks_project_id ON asl_schema.fulltext_screening_tasks(project_id);
CREATE INDEX idx_fulltext_screening_tasks_status ON asl_schema.fulltext_screening_tasks(status);
CREATE INDEX idx_fulltext_screening_tasks_created_at ON asl_schema.fulltext_screening_tasks(created_at);
```

**字段说明**�?
| 字段 | 类型 | 说明 |
|------|------|------|
| `modelA / modelB` | String | 双模型名称（deepseek-v3 + qwen-max�?|
| `degradedCount` | Int | 单模型成功的任务数（容错机制�?|
| `totalTokens` | Int | 累计Token使用�?|
| `totalCost` | Float | 累计成本（元�?|
| `promptVersion` | String | Prompt版本（可追溯�?|

---

### 6. 全文复筛结果�?(fulltext_screening_results) �?v3.0新增

**Prisma模型�?*: `AslFulltextScreeningResult`  
**表名**: `asl_schema.fulltext_screening_results`

**设计目标**：存�?2字段详细评估结果，支持双模型对比、验证结果、冲突检�?
**设计亮点**�?- �?完整的双模型结果（fields + overall + logs�?- �?医学逻辑验证和证据链验证结果
- �?冲突检测和复核优先�?- �?降级模式支持（单模型成功�?- �?JSON存储12字段评估（符合云原生规范�?
```prisma
model AslFulltextScreeningResult {
  id                String   @id @default(uuid())
  taskId            String   @map("task_id")
  task              AslFulltextScreeningTask @relation(fields: [taskId], references: [id], onDelete: Cascade)
  projectId         String   @map("project_id")
  project           AslScreeningProject @relation(fields: [projectId], references: [id], onDelete: Cascade)
  literatureId      String   @map("literature_id")
  literature        AslLiterature @relation(fields: [literatureId], references: [id], onDelete: Cascade)
  
  // ====== 模型A结果（DeepSeek-V3�?=====
  modelAName        String   @map("model_a_name")
  modelAStatus      String   @map("model_a_status")      // "success" | "failed"
  modelAFields      Json     @map("model_a_fields")      // 12字段评估 { field1: {...}, field2: {...}, ... }
  modelAOverall     Json     @map("model_a_overall")     // 总体评估 { decision, confidence, keyIssues }
  modelAProcessingLog Json?  @map("model_a_processing_log")
  modelAVerification Json?   @map("model_a_verification")
  modelATokens      Int?     @map("model_a_tokens")
  modelACost        Float?   @map("model_a_cost")
  modelAError       String?  @map("model_a_error") @db.Text
  
  // ====== 模型B结果（Qwen-Max�?=====
  modelBName        String   @map("model_b_name")
  modelBStatus      String   @map("model_b_status")
  modelBFields      Json     @map("model_b_fields")
  modelBOverall     Json     @map("model_b_overall")
  modelBProcessingLog Json?  @map("model_b_processing_log")
  modelBVerification Json?   @map("model_b_verification")
  modelBTokens      Int?     @map("model_b_tokens")
  modelBCost        Float?   @map("model_b_cost")
  modelBError       String?  @map("model_b_error") @db.Text
  
  // ====== 验证结果 ======
  medicalLogicIssues Json?   @map("medical_logic_issues")  // MedicalLogicValidator输出
  evidenceChainIssues Json?  @map("evidence_chain_issues") // EvidenceChainValidator输出
  
  // ====== 冲突检�?======
  isConflict        Boolean  @default(false) @map("is_conflict")
  conflictSeverity  String?  @map("conflict_severity")        // "high" | "medium" | "low"
  conflictFields    String[] @map("conflict_fields")          // ["field1", "field9", "overall"]
  conflictDetails   Json?    @map("conflict_details")
  reviewPriority    Int?     @map("review_priority")          // 0-100复核优先�?  reviewDeadline    DateTime? @map("review_deadline")
  
  // ====== 最终决�?======
  finalDecision     String?  @map("final_decision")           // "include" | "exclude" | null
  finalDecisionBy   String?  @map("final_decision_by")
  finalDecisionAt   DateTime? @map("final_decision_at")
  exclusionReason   String?  @map("exclusion_reason") @db.Text
  reviewNotes       String?  @map("review_notes") @db.Text
  
  // ====== 处理状�?======
  processingStatus  String   @default("pending") @map("processing_status")
  // "pending" | "processing" | "completed" | "failed" | "degraded"
  isDegraded        Boolean  @default(false) @map("is_degraded")
  degradedModel     String?  @map("degraded_model")               // "modelA" | "modelB"
  
  processedAt       DateTime? @map("processed_at")
  
  // ====== 可追溯信�?======
  promptVersion     String   @default("v1.0.0") @map("prompt_version")
  rawOutputA        Json?    @map("raw_output_a")
  rawOutputB        Json?    @map("raw_output_b")
  
  createdAt         DateTime @default(now()) @map("created_at")
  updatedAt         DateTime @updatedAt @map("updated_at")
  
  @@map("fulltext_screening_results")
  @@schema("asl_schema")
  @@index([taskId])
  @@index([projectId])
  @@index([literatureId])
  @@index([isConflict])
  @@index([finalDecision])
  @@index([reviewPriority])
  @@unique([projectId, literatureId])  // 一篇文献只有一个全文复筛结�?}
```

**SQL表结�?*（简化版，实际包含所有字段）:
```sql
CREATE TABLE asl_schema.fulltext_screening_results (
  id TEXT PRIMARY KEY,
  task_id TEXT NOT NULL,
  project_id TEXT NOT NULL,
  literature_id TEXT NOT NULL,
  
  -- 模型A结果
  model_a_name TEXT NOT NULL,
  model_a_status TEXT NOT NULL,
  model_a_fields JSONB NOT NULL,
  model_a_overall JSONB NOT NULL,
  model_a_processing_log JSONB,
  model_a_verification JSONB,
  model_a_tokens INTEGER,
  model_a_cost DOUBLE PRECISION,
  model_a_error TEXT,
  
  -- 模型B结果（同上）
  model_b_name TEXT NOT NULL,
  model_b_status TEXT NOT NULL,
  model_b_fields JSONB NOT NULL,
  model_b_overall JSONB NOT NULL,
  model_b_processing_log JSONB,
  model_b_verification JSONB,
  model_b_tokens INTEGER,
  model_b_cost DOUBLE PRECISION,
  model_b_error TEXT,
  
  -- 验证结果
  medical_logic_issues JSONB,
  evidence_chain_issues JSONB,
  
  -- 冲突检�?  is_conflict BOOLEAN NOT NULL DEFAULT false,
  conflict_severity TEXT,
  conflict_fields TEXT[],
  conflict_details JSONB,
  review_priority INTEGER,
  review_deadline TIMESTAMP(3),
  
  -- 最终决�?  final_decision TEXT,
  final_decision_by TEXT,
  final_decision_at TIMESTAMP(3),
  exclusion_reason TEXT,
  review_notes TEXT,
  
  -- 处理状�?  processing_status TEXT NOT NULL DEFAULT 'pending',
  is_degraded BOOLEAN NOT NULL DEFAULT false,
  degraded_model TEXT,
  processed_at TIMESTAMP(3),
  
  -- 可追溯信�?  prompt_version TEXT NOT NULL DEFAULT 'v1.0.0',
  raw_output_a JSONB,
  raw_output_b JSONB,
  
  created_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  updated_at TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
  
  CONSTRAINT fk_task FOREIGN KEY (task_id) 
    REFERENCES asl_schema.fulltext_screening_tasks(id) ON DELETE CASCADE,
  CONSTRAINT fk_project_fulltext_result FOREIGN KEY (project_id) 
    REFERENCES asl_schema.screening_projects(id) ON DELETE CASCADE,
  CONSTRAINT fk_literature_fulltext FOREIGN KEY (literature_id) 
    REFERENCES asl_schema.literatures(id) ON DELETE CASCADE,
  CONSTRAINT unique_project_literature_fulltext UNIQUE (project_id, literature_id)
);

CREATE INDEX idx_fulltext_screening_results_task_id ON asl_schema.fulltext_screening_results(task_id);
CREATE INDEX idx_fulltext_screening_results_project_id ON asl_schema.fulltext_screening_results(project_id);
CREATE INDEX idx_fulltext_screening_results_literature_id ON asl_schema.fulltext_screening_results(literature_id);
CREATE INDEX idx_fulltext_screening_results_is_conflict ON asl_schema.fulltext_screening_results(is_conflict);
CREATE INDEX idx_fulltext_screening_results_final_decision ON asl_schema.fulltext_screening_results(final_decision);
CREATE INDEX idx_fulltext_screening_results_review_priority ON asl_schema.fulltext_screening_results(review_priority);
```

**JSON字段示例**�?
**modelAFields (12字段评估)**:
```json
{
  "field1": {
    "present": true,
    "completeness": "完整",
    "extractable": true,
    "quote": "第一作者：Zhang et al., 发表�?JAMA 2023...",
    "location": "Title page, Methods section",
    "note": "文献来源信息完整"
  },
  "field2": { ... },
  // ... field3-field12
}
```

**modelAOverall (总体评估)**:
```json
{
  "decision": "include",
  "confidence": 0.92,
  "keyIssues": [
    "随机化方法描述完�?,
    "盲法实施清晰",
    "结局指标可提�?
  ]
}
```

**medicalLogicIssues (医学逻辑验证)**:
```json
{
  "hasIssues": false,
  "issues": []
}
```

**conflictDetails (冲突详情)**:
```json
{
  "field9": {
    "modelA": "完整",
    "modelB": "不完�?,
    "severity": "high"
  }
}
```

---

## 📊 数据关系图（v3.0更新�?
```
literature_screening_projects (1) ──< (N) literature_items
literature_screening_projects (1) ──< (N) title_abstract_screening_results
literature_items (1) ──< (1) title_abstract_screening_results
literature_screening_projects (1) ──< (N) screening_tasks
```

---

## 🔍 索引设计汇总（v3.0更新�?
| 表名 | 索引字段 | 索引类型 | 说明 |
|------|---------|---------|------|
| screening_projects | user_id | B-tree | 用户项目查询 |
| screening_projects | status | B-tree | 状态筛�?|
| literatures | project_id | B-tree | 项目文献查询 |
| literatures | doi | B-tree | DOI查重 |
| literatures | stage �?| B-tree | 文献阶段查询 v3.0 |
| literatures | has_pdf �?| B-tree | PDF获取状�?v3.0 |
| literatures | pdf_status �?| B-tree | PDF上传状�?v3.0 |
| literatures | (project_id, pmid) | Unique | 防止重复导入 |
| screening_results | project_id | B-tree | 项目结果查询 |
| screening_results | literature_id | B-tree | 文献结果查询 |
| screening_results | conflict_status | B-tree | 冲突筛�?|
| screening_results | final_decision | B-tree | 决策筛�?|
| screening_results | (project_id, literature_id) | Unique | 唯一性约�?|
| screening_tasks | project_id | B-tree | 项目任务查询 |
| screening_tasks | status | B-tree | 任务状态筛�?|
| fulltext_screening_tasks �?| project_id | B-tree | 全文任务查询 v3.0 |
| fulltext_screening_tasks �?| status | B-tree | 任务状态筛�?v3.0 |
| fulltext_screening_tasks �?| created_at | B-tree | 时间排序 v3.0 |
| fulltext_screening_results �?| task_id | B-tree | 任务结果查询 v3.0 |
| fulltext_screening_results �?| project_id | B-tree | 项目结果查询 v3.0 |
| fulltext_screening_results �?| literature_id | B-tree | 文献结果查询 v3.0 |
| fulltext_screening_results �?| is_conflict | B-tree | 冲突筛�?v3.0 |
| fulltext_screening_results �?| final_decision | B-tree | 决策筛�?v3.0 |
| fulltext_screening_results �?| review_priority | B-tree | 复核优先�?v3.0 |
| fulltext_screening_results �?| (project_id, literature_id) | Unique | 唯一性约�?v3.0 |

**索引总数**: 25个（v3.0新增13个）  
**唯一约束**: 4个（v3.0新增1个）

**v3.0索引优化说明**�?- �?`literatures.stage`: 快速查询特定阶段的文献（如"pdf_acquired"待全文复筛）
- �?`fulltext_screening_results.review_priority`: 优化人工复核队列排序
- �?`fulltext_screening_tasks.created_at`: 任务历史查询优化

---

## 💾 数据字典

### PICO标准 (picoCriteria JSON)
```json
{
  "population": "研究人群，如�?型糖尿病成人患�?,
  "intervention": "干预措施，如：SGLT2抑制�?,
  "comparison": "对照，如：安慰剂或常规疗�?,
  "outcome": "结局指标，如：心血管结局",
  "studyDesign": "研究设计，如：随机对照试�?(RCT)"
}
```

### 筛选配�?(screeningConfig JSON)
```json
{
  "models": ["deepseek-chat", "qwen-max"],
  "temperature": 0,
  "maxRetries": 3
}
```

### 冲突字段 (conflictFields JSON)
```json
["P", "I", "C", "S", "conclusion"]
```

### 原始输出 (rawOutput JSON)
```json
{
  "deepseek": { "判断": {...}, "证据": {...} },
  "qwen": { "判断": {...}, "证据": {...} }
}
```

---

## 🔒 数据安全

### Schema隔离
- 使用 `asl_schema` 与其他模块数据隔�?- 用户表在 `platform_schema`，统一管理

### 级联删除
- 删除用户 �?自动删除所有筛选项目及关联数据
- 删除项目 �?自动删除文献、结果、任�?- 删除文献 �?自动删除筛选结�?
### 唯一性约�?- 同一项目中PMID唯一（允许无PMID�?- 同一项目中一篇文献只有一个筛选结�?
---

## 📈 数据量预�?
| 项目规模 | 文献�?| 筛选结�?| 存储空间 |
|---------|--------|---------|----------|
| 小型 | 100-500 | 100-500 | < 10 MB |
| 中型 | 500-2000 | 500-2000 | 10-50 MB |
| 大型 | 2000-5000 | 2000-5000 | 50-200 MB |
| 超大�?| 5000+ | 5000+ | 200 MB+ |

**单条记录大小估算**:
- 文献条目：~2-5 KB
- 筛选结果：~5-10 KB（含双模型判断和证据�?
---

## �?后续规划

### Phase 2 (全文复筛) �?v3.0已完�?- [x] 扩展 `literatures` 表（生命周期管理�?- [x] 添加 `fulltext_screening_tasks` �?- [x] 添加 `fulltext_screening_results` 表（12字段�?
### Phase 3 (数据提取) 待开�?- [ ] 复用 `fulltext_screening_tasks` 表（切换模式�?- [ ] 复用 `fulltext_screening_results` 表（存储提取数据�?- [ ] 或新�?`data_extraction_results` 表（如需独立�?
### Phase 4 (质量评估) 待规�?- [ ] 质量评估结果�?- [ ] 偏倚风险评估表
- [ ] GRADE证据质量�?
---

## 📝 v3.0 设计决策记录

### 决策1: 全文内容存储引用而非直接存储 �?
**问题**：全文内容是否存储在数据库？

**方案对比**�?| 方案 | 优点 | 缺点 |
|------|------|------|
| 存TEXT | LLM调用�?| 违背云原生规范，数据库臃�?|
| 存引�?| 符合规范，轻�?| LLM调用增加100-200ms |

**决策**：✅ 采用方案2（存引用�?- 符合云原生存储与计算分离原则
- 支持超大文献�?1MB�?- RDS存储成本是OSS�?-10�?
### 决策2: 12字段使用JSON存储 �?
**问题**�?2字段是拆分为列还是JSON存储�?
**决策**：✅ 使用PostgreSQL JSONB
- 不需要单独查询某个字段内�?- 字段结构复杂�?个子字段�?- JSONB性能优秀且支持GIN索引

### 决策3: 独立全文复筛结果�?�?
**问题**：是否复�?`screening_results` 表？

**决策**：✅ 新增独立�?`fulltext_screening_results`
- 数据结构完全不同（PICOS vs 12字段�?- 避免字段冗余和逻辑耦合
- 便于独立维护和优�?
---

**文档版本�?* v3.0  
**最后更新：** 2025-11-22（Day 4：全文复筛数据库设计�? 
**维护者：** AI智能文献开发团�?
**版本历史**�?- v3.0 (2025-11-22): 全文复筛数据库设计，新增3个表和相关字�?- v2.2 (2025-11-21): Week 4统计功能完成
- v2.0 (2025-11-18): 标题初筛数据库设�?- v1.0 (2025-10-29): 初始版本