AIclinicalresearch/docs/03-业务模块/PKB-个人知识库/02-技术设计/01-数据库设计.md

PKB - 涓<>汉鐭ヨ瘑搴撴ā鍧楋細鏁版嵁搴撹<E690B4>璁?

*鐗堟湰锛? v1.0
*鏇存柊鏃堕棿锛? 2025-11-12
*鏁版嵁搴揝chema锛? pkb_schema
鐘舵€侊細 鉁?宸插疄鏂藉苟杩佺Щ

---

馃搵 鐩<>綍

1. 妯″潡姒傝堪
2. Schema淇℃伅
3. 鏁版嵁搴撹〃璁捐<EFBFBD>
4. 琛ㄥ叧绯诲浘
5. 绱㈠紩璁捐<EFBFBD>
6. Phase 3鍔熻兘璇存槑
7. 鍙樻洿鍘嗗彶

---

妯″潡姒傝堪

鍔熻兘瀹氫綅

**PKB锛圥ersonal Knowledge Base锛? 涓<>汉鐭ヨ瘑搴撴ā鍧?*鎻愪緵鏂囩尞绠＄悊鍜屾櫤鑳介棶绛旇兘鍔涳紝鏍稿績鍔熻兘锛?

1. *鐭ヨ瘑搴撶<EFBFBD>鐞? - 鍒涘缓鍜岀<E98D9C>鐞嗕釜浜虹煡璇嗗簱
2. 鏂囨。涓婁紶 - 鏀<>寔PDF/Word/TXT绛夋牸寮忔枃妗?
3. 鏅鸿兘闂<EFBFBD>瓟 - 鍩轰簬鐭ヨ瘑搴撶殑RAG锛堟<E9949B>绱㈠<E7BBB1>寮虹敓鎴愶級瀵硅瘽
4. *鎵瑰<EFBFBD>鐞嗕换鍔? - 鎵归噺澶勭悊鏂囩尞鎻愬彇锛圥hase 3锛?
5. 浠诲姟妯℃澘 - 棰勫畾涔夌殑鎵瑰<E98EB5>鐞嗕换鍔℃ā鏉匡紙Phase 3锛?

鏍稿績涓氬姟鍦烘櫙

• 鐢ㄦ埛鍒涘缓鐭ヨ瘑搴擄紙濡?CLL鐩稿叧鐭ヨ瘑搴?锛?
• 涓婁紶PDF鏂囩尞鍒扮煡璇嗗簱
• 鑷<EFBFBD>姩鎻愬彇鏂囨湰骞跺悜閲忓寲
• 鍩轰簬鐭ヨ瘑搴撹繘琛屾櫤鑳介棶绛?
• 鎵归噺鎻愬彇鏂囩尞涓<EFBFBD>殑缁撴瀯鍖栦俊鎭?

涓嶥ify骞冲彴闆嗘垚

PKB妯″潡娣卞害闆嗘垚Dify骞冲彴锛?

• 姣忎釜鐭ヨ瘑搴撳<EFBFBD>搴斾竴涓狣ify Dataset
• 姣忎釜鏂囨。瀵瑰簲涓€涓狣ify Document
• 浣跨敤Dify鐨勫悜閲忔<EFBFBD>绱㈠拰RAG鑳藉姏

---

Schema淇℃伅

Schema鍚嶇О

pkb_schema

鍒涘缓璇<EFBFBD>彞

CREATE SCHEMA IF NOT EXISTS pkb_schema;
GRANT ALL ON SCHEMA pkb_schema TO aiclinical_admin;

鏁版嵁杩佺Щ

• *杩佺Щ鏃堕棿锛? 2025-11-12
• *婧怱chema锛? public
• *杩佺Щ鑴氭湰锛? docs/09-鏋舵瀯瀹炴柦/migration-scripts/004-migrate-pkb.sql
• 鏁版嵁瀹屾暣鎬э細 鉁?100%杩佺Щ鎴愬姛

---

鏁版嵁搴撹〃璁捐<EFBFBD>

琛ㄥ垪琛?

琛ㄥ悕	鐢ㄩ€?	琛屾暟锛堜及璁★級	鐘舵€?
knowledge_bases	鐭ヨ瘑搴?	5-50/鐢ㄦ埛	鉁?宸查儴缃?
documents	鏂囨。	10-1000/鐭ヨ瘑搴?	鉁?宸查儴缃?
batch_tasks	鎵瑰<EFBFBD>鐞嗕换鍔?	1-100/鐭ヨ瘑搴?	鉁?Phase 3
batch_results	鎵瑰<EFBFBD>鐞嗙粨鏋?	N鏉?浠诲姟	鉁?Phase 3
task_templates	浠诲姟妯℃澘	10-50/鐢ㄦ埛	鉁?Phase 3锛堥<E9949B>鐣欙級

*鎬昏<EFBFBD>锛? 5涓<35>〃锛?涓<>牳蹇冭〃 + 3涓狿hase 3琛<33>級

---

1. knowledge_bases - 鐭ヨ瘑搴撹〃

鐢ㄩ€旓細 瀛樺偍鐢ㄦ埛鍒涘缓鐨勪釜浜虹煡璇嗗簱

琛ㄧ粨鏋?

瀛楁<EFBFBD>鍚?	鏁版嵁绫诲瀷	绾︽潫	璇存槑
id	TEXT	PRIMARY KEY	鐭ヨ瘑搴撳敮涓€鏍囪瘑锛圲UID锛?
user_id	TEXT	NOT NULL, FK	鎵€灞炵敤鎴稩D
name	TEXT	NOT NULL	鐭ヨ瘑搴撳悕绉?
description	TEXT	NULL	鐭ヨ瘑搴撴弿杩?
dify_dataset_id	TEXT	NOT NULL, UNIQUE	Dify骞冲彴鐨凞ataset ID
file_count	INTEGER	NOT NULL, DEFAULT 0	鏂囦欢鏁伴噺
total_size_bytes	BIGINT	NOT NULL, DEFAULT 0	鎬绘枃浠跺ぇ灏忥紙瀛楄妭锛?
created_at	TIMESTAMPTZ	NOT NULL, DEFAULT now()	鍒涘缓鏃堕棿
updated_at	TIMESTAMPTZ	NOT NULL	鏇存柊鏃堕棿

Prisma Model

model KnowledgeBase {
  id             String   @id @default(uuid())
  userId         String   @map("user_id")
  name           String
  description    String?
  difyDatasetId  String   @map("dify_dataset_id")
  fileCount      Int      @default(0) @map("file_count")
  totalSizeBytes BigInt   @default(0) @map("total_size_bytes")
  
  createdAt      DateTime @default(now()) @map("created_at")
  updatedAt      DateTime @updatedAt @map("updated_at")
  
  user           User     @relation(fields: [userId], references: [id], onDelete: Cascade)
  documents      Document[]
  batchTasks     BatchTask[]
  
  @@index([userId])
  @@index([difyDatasetId])
  @@map("knowledge_bases")
  @@schema("pkb_schema")
}

涓氬姟瑙勫垯

1. Dify缁戝畾 - 姣忎釜鐭ヨ瘑搴撳<E690B4>搴斿敮涓€鐨凞ify Dataset
2. 缁熻<EFBFBD>瀛楁<EFBFBD> - file_count鍜宍total_size_bytes`闇€瀹炴椂鏇存柊
3. 鐢ㄦ埛闅旂<EFBFBD> - 閫氳繃user_id瀹炵幇鏁版嵁闅旂<EFBFBD>
4. 绾ц仈鍒犻櫎 - 鍒犻櫎鐭ヨ瘑搴撴椂锛屾枃妗ｅ拰浠诲姟涔熻<E6B694>鍒犻櫎

---

2. documents - 鏂囨。琛?

鐢ㄩ€旓細 瀛樺偍鐭ヨ瘑搴撲腑鐨勬枃妗ｄ俊鎭?

琛ㄧ粨鏋?

瀛楁<EFBFBD>鍚?	鏁版嵁绫诲瀷	绾︽潫	璇存槑
id	TEXT	PRIMARY KEY	鏂囨。鍞<EFBFBD>竴鏍囪瘑锛圲UID锛?
kb_id	TEXT	NOT NULL, FK	鎵€灞炵煡璇嗗簱ID
user_id	TEXT	NOT NULL, FK	鎵€灞炵敤鎴稩D
filename	TEXT	NOT NULL	鏂囦欢鍚?
file_type	TEXT	NOT NULL	鏂囦欢绫诲瀷锛坧df/doc/txt绛夛級
file_size_bytes	BIGINT	NOT NULL	鏂囦欢澶у皬锛堝瓧鑺傦級
file_url	TEXT	NOT NULL	鏂囦欢瀛樺偍URL
dify_document_id	TEXT	NOT NULL	Dify骞冲彴鐨凞ocument ID
status	TEXT	NOT NULL, DEFAULT 'uploading'	鐘舵€侊紙uploading/processing/completed/failed锛?
progress	INTEGER	NOT NULL, DEFAULT 0	澶勭悊杩涘害锛?-100锛?
error_message	TEXT	NULL	閿欒<EFBFBD>淇℃伅
segments_count	INTEGER	NULL	鍒囩墖鏁伴噺
tokens_count	INTEGER	NULL	Token鏁伴噺
extraction_method	TEXT	NULL	鎻愬彇鏂规硶锛坅uto/ocr/parse锛?
Phase 2瀛楁<E7809B>			鍏ㄦ枃闃呰<EFBFBD>鍔熻兘
full_text	TEXT	NULL	瀹屾暣鏂囨湰鍐呭<EFBFBD>
full_text_length	INTEGER	NULL	鏂囨湰闀垮害
metadata	JSONB	NULL	鍏冩暟鎹<EFBFBD>紙浣滆€呫€佹爣棰樸€佹憳瑕佺瓑锛?
created_at	TIMESTAMPTZ	NOT NULL, DEFAULT now()	鍒涘缓鏃堕棿
updated_at	TIMESTAMPTZ	NOT NULL	鏇存柊鏃堕棿

Prisma Model

model Document {
  id              String   @id @default(uuid())
  kbId            String   @map("kb_id")
  userId          String   @map("user_id")
  filename        String
  fileType        String   @map("file_type")
  fileSizeBytes   BigInt   @map("file_size_bytes")
  fileUrl         String   @map("file_url")
  difyDocumentId  String   @map("dify_document_id")
  status          String   @default("uploading")
  progress        Int      @default(0)
  errorMessage    String?  @map("error_message")
  segmentsCount   Int?     @map("segments_count")
  tokensCount     Int?     @map("tokens_count")
  extractionMethod String? @map("extraction_method")
  
  // Phase 2: 鍏ㄦ枃闃呰<E99783>鍔熻兘
  fullText        String?  @map("full_text") @db.Text
  fullTextLength  Int?     @map("full_text_length")
  metadata        Json?
  
  createdAt       DateTime @default(now()) @map("created_at")
  updatedAt       DateTime @updatedAt @map("updated_at")
  
  knowledgeBase   KnowledgeBase @relation(fields: [kbId], references: [id], onDelete: Cascade)
  user            User     @relation(fields: [userId], references: [id], onDelete: Cascade)
  batchResults    BatchResult[]
  
  @@index([kbId])
  @@index([userId])
  @@index([status])
  @@index([difyDocumentId])
  @@index([extractionMethod])
  @@map("documents")
  @@schema("pkb_schema")
}

涓氬姟瑙勫垯

1. 鐘舵€佹満 - status瀛楁<EFBFBD>绠＄悊鏂囨。澶勭悊娴佺▼
   • uploading 鈫?processing 鈫?completed
   • 澶辫触鏃惰浆涓篳failed`
2. Dify鍚屾<EFBFBD> - 姣忎釜鏂囨。瀵瑰簲Dify涓<79>殑涓€涓狣ocument
3. 鎻愬彇鏂规硶 - 鏀<>寔鑷<E5AF94>姩璇嗗埆銆丱CR銆佽В鏋愪笁绉嶆柟寮?
4. Phase 2鎵╁睍 - full_text瀛楁<EFBFBD>鐢ㄤ簬鍏ㄦ枃闃呰<EFBFBD>鍜屾繁搴﹀垎鏋?

---

3. batch_tasks - 鎵瑰<E98EB5>鐞嗕换鍔¤〃 (Phase 3)

鐢ㄩ€旓細 鎵归噺澶勭悊鏂囩尞锛屾彁鍙栫粨鏋勫寲淇℃伅

琛ㄧ粨鏋?

瀛楁<EFBFBD>鍚?	鏁版嵁绫诲瀷	绾︽潫	璇存槑
id	TEXT	PRIMARY KEY	浠诲姟鍞<EFBFBD>竴鏍囪瘑锛圲UID锛?
user_id	TEXT	NOT NULL, FK	鎵€灞炵敤鎴稩D
kb_id	TEXT	NOT NULL, FK	鎵€灞炵煡璇嗗簱ID
task_name	TEXT	NOT NULL	浠诲姟鍚嶇О
task_type	TEXT	NOT NULL	浠诲姟绫诲瀷锛坋xtract_info/summarize绛夛級
prompt_template	TEXT	NOT NULL	Prompt妯℃澘
model_name	TEXT	NOT NULL, DEFAULT 'gpt-4'	浣跨敤鐨凩LM妯″瀷
status	TEXT	NOT NULL, DEFAULT 'pending'	鐘舵€侊紙pending/running/completed/failed锛?
total_documents	INTEGER	NOT NULL, DEFAULT 0	鎬绘枃妗ｆ暟
processed_count	INTEGER	NOT NULL, DEFAULT 0	宸插<EFBFBD>鐞嗘暟
success_count	INTEGER	NOT NULL, DEFAULT 0	鎴愬姛鏁?
failed_count	INTEGER	NOT NULL, DEFAULT 0	澶辫触鏁?
error_message	TEXT	NULL	閿欒<EFBFBD>淇℃伅
created_at	TIMESTAMPTZ	NOT NULL, DEFAULT now()	鍒涘缓鏃堕棿
updated_at	TIMESTAMPTZ	NOT NULL	鏇存柊鏃堕棿

Prisma Model

model BatchTask {
  id              String   @id @default(uuid())
  userId          String   @map("user_id")
  kbId            String   @map("kb_id")
  taskName        String   @map("task_name")
  taskType        String   @map("task_type")
  promptTemplate  String   @map("prompt_template") @db.Text
  modelName       String   @default("gpt-4") @map("model_name")
  status          String   @default("pending")
  totalDocuments  Int      @default(0) @map("total_documents")
  processedCount  Int      @default(0) @map("processed_count")
  successCount    Int      @default(0) @map("success_count")
  failedCount     Int      @default(0) @map("failed_count")
  errorMessage    String?  @map("error_message") @db.Text
  
  user            User     @relation(fields: [userId], references: [id], onDelete: Cascade)
  knowledgeBase   KnowledgeBase @relation(fields: [kbId], references: [id], onDelete: Cascade)
  results         BatchResult[]
  
  createdAt       DateTime @default(now()) @map("created_at")
  updatedAt       DateTime @updatedAt @map("updated_at")
  
  @@index([userId])
  @@index([kbId])
  @@index([status])
  @@index([createdAt])
  @@map("batch_tasks")
  @@schema("pkb_schema")
}

涓氬姟瑙勫垯

1. 浠诲姟绫诲瀷 - 鏀<>寔澶氱<E6BEB6>鎵瑰<E98EB5>鐞嗙被鍨?
   • extract_info - 鎻愬彇缁撴瀯鍖栦俊鎭?
   • summarize - 鎵归噺鎽樿<E98EBD>
   • classify - 鏂囩尞鍒嗙被
2. 鐘舵€佹満 - status绠＄悊浠诲姟鎵ц<EFBFBD>鐘舵€?
3. 杩涘害璺熻釜 - 瀹炴椂鏇存柊璁℃暟鍣ㄥ瓧娈?
4. 妯″瀷閫夋嫨 - 鏀<>寔澶氱<E6BEB6>LLM妯″瀷

---

4. batch_results - 鎵瑰<E98EB5>鐞嗙粨鏋滆〃 (Phase 3)

鐢ㄩ€旓細 瀛樺偍鎵瑰<E98EB5>鐞嗕换鍔＄殑姣忕瘒鏂囩尞缁撴灉

琛ㄧ粨鏋?

瀛楁<EFBFBD>鍚?	鏁版嵁绫诲瀷	绾︽潫	璇存槑
id	TEXT	PRIMARY KEY	缁撴灉鍞<EFBFBD>竴鏍囪瘑锛圲UID锛?
task_id	TEXT	NOT NULL, FK	鎵€灞炰换鍔<EFBFBD>D
document_id	TEXT	NOT NULL, FK	鎵€灞炴枃妗<EFBFBD>D
status	TEXT	NOT NULL, DEFAULT 'pending'	鐘舵€侊紙pending/processing/completed/failed锛?
result_data	JSONB	NULL	鎻愬彇鐨勭粨鏋勫寲鏁版嵁
raw_output	TEXT	NULL	LLM鍘熷<EFBFBD>杈撳嚭
tokens_used	INTEGER	NULL	浣跨敤鐨凾oken鏁?
error_message	TEXT	NULL	閿欒<EFBFBD>淇℃伅
created_at	TIMESTAMPTZ	NOT NULL, DEFAULT now()	鍒涘缓鏃堕棿

Prisma Model

model BatchResult {
  id              String   @id @default(uuid())
  taskId          String   @map("task_id")
  documentId      String   @map("document_id")
  status          String   @default("pending")
  resultData      Json?    @map("result_data")
  rawOutput       String?  @map("raw_output") @db.Text
  tokensUsed      Int?     @map("tokens_used")
  errorMessage    String?  @map("error_message") @db.Text
  
  task            BatchTask @relation(fields: [taskId], references: [id], onDelete: Cascade)
  document        Document @relation(fields: [documentId], references: [id], onDelete: Cascade)
  
  createdAt       DateTime @default(now()) @map("created_at")
  
  @@index([taskId])
  @@index([documentId])
  @@index([status])
  @@map("batch_results")
  @@schema("pkb_schema")
}

涓氬姟瑙勫垯

1. 缁撴灉瀛樺偍 - result_data瀛樺偍JSON鏍煎紡鐨勭粨鏋勫寲鏁版嵁
2. 鍘熷<EFBFBD>杈撳嚭 - raw_output淇濈暀LLM鍘熷<EFBFBD>杈撳嚭锛屼究浜庤皟璇?
3. Token缁熻<EFBFBD> - 璁板綍姣忕瘒鏂囩尞鐨凾oken娑堣€?

---

5. task_templates - 浠诲姟妯℃澘琛?(Phase 3, 鏆備笉瀹炵幇)

鐢ㄩ€旓細 瀛樺偍棰勫畾涔夌殑鎵瑰<E98EB5>鐞嗕换鍔℃ā鏉?

琛ㄧ粨鏋?

瀛楁<EFBFBD>鍚?	鏁版嵁绫诲瀷	绾︽潫	璇存槑
id	TEXT	PRIMARY KEY	妯℃澘鍞<EFBFBD>竴鏍囪瘑锛圲UID锛?
user_id	TEXT	NOT NULL, FK	鎵€灞炵敤鎴稩D
template_name	TEXT	NOT NULL	妯℃澘鍚嶇О
task_type	TEXT	NOT NULL	浠诲姟绫诲瀷
prompt_template	TEXT	NOT NULL	Prompt妯℃澘
output_fields	JSONB	NOT NULL, DEFAULT '{}'	杈撳嚭瀛楁<EFBFBD>瀹氫箟
model_name	TEXT	NOT NULL, DEFAULT 'gpt-4'	榛樿<EFBFBD>妯″瀷
created_at	TIMESTAMPTZ	NOT NULL, DEFAULT now()	鍒涘缓鏃堕棿
updated_at	TIMESTAMPTZ	NOT NULL	鏇存柊鏃堕棿

Prisma Model

model TaskTemplate {
  id              String   @id @default(uuid())
  userId          String   @map("user_id")
  templateName    String   @map("template_name")
  taskType        String   @map("task_type")
  promptTemplate  String   @map("prompt_template") @db.Text
  outputFields    Json     @default("{}") @map("output_fields")
  modelName       String   @default("gpt-4") @map("model_name")
  
  user            User @relation(fields: [userId], references: [id], onDelete: Cascade)
  
  createdAt       DateTime @default(now()) @map("created_at")
  updatedAt       DateTime @updatedAt @map("updated_at")
  
  @@index([userId])
  @@map("task_templates")
  @@schema("pkb_schema")
}

涓氬姟瑙勫垯

1. 妯℃澘澶嶇敤 - 鐢ㄦ埛鍙<E59F9B>繚瀛樺父鐢ㄧ殑浠诲姟閰嶇疆
2. 瀛楁<EFBFBD>瀹氫箟 - output_fields瀹氫箟鏈熸湜鐨勮緭鍑虹粨鏋?
3. 鏆備笉瀹炵幇 - Phase 3棰勭暀锛屽悗缁<E68297>紑鍙?

---

琛ㄥ叧绯诲浘

erDiagram
    PLATFORM_USERS ||--o{ KNOWLEDGE_BASES : "owns"
    PLATFORM_USERS ||--o{ DOCUMENTS : "uploads"
    PLATFORM_USERS ||--o{ BATCH_TASKS : "creates"
    PLATFORM_USERS ||--o{ TASK_TEMPLATES : "defines"
    
    KNOWLEDGE_BASES ||--o{ DOCUMENTS : "contains"
    KNOWLEDGE_BASES ||--o{ BATCH_TASKS : "processes"
    
    BATCH_TASKS ||--o{ BATCH_RESULTS : "generates"
    DOCUMENTS ||--o{ BATCH_RESULTS : "analyzed_by"

    PLATFORM_USERS {
        text id PK
        text email
        text password
    }

    KNOWLEDGE_BASES {
        text id PK
        text user_id FK
        text name
        text dify_dataset_id
        int file_count
        bigint total_size_bytes
    }

    DOCUMENTS {
        text id PK
        text kb_id FK
        text user_id FK
        text filename
        text file_type
        text dify_document_id
        text status
        text full_text
        jsonb metadata
    }

    BATCH_TASKS {
        text id PK
        text user_id FK
        text kb_id FK
        text task_name
        text task_type
        text status
        int total_documents
        int processed_count
    }

    BATCH_RESULTS {
        text id PK
        text task_id FK
        text document_id FK
        text status
        jsonb result_data
        text raw_output
    }

    TASK_TEMPLATES {
        text id PK
        text user_id FK
        text template_name
        text task_type
        jsonb output_fields
    }

璺⊿chema寮曠敤

*澶栭敭鍏崇郴锛?

• knowledge_bases.user_id 鈫?platform_schema.users.id
• documents.user_id 鈫?platform_schema.users.id
• batch_tasks.user_id 鈫?platform_schema.users.id
• task_templates.user_id 鈫?platform_schema.users.id

*璇存槑锛? Prisma鑷<61>姩澶勭悊璺⊿chema澶栭敭锛屽簲鐢ㄤ唬鐮佹棤闇€鍏冲績Schema鍓嶇紑

---

绱㈠紩璁捐<EFBFBD>

涓婚敭绱㈠紩

鎵€鏈夎〃鐨刞id`瀛楁<E7809B>鑷<EFBFBD>姩鍒涘缓B-tree涓婚敭绱㈠紩銆?

澶栭敭绱㈠紩

琛ㄥ悕	绱㈠紩瀛楁<EFBFBD>	鐢ㄩ€?
knowledge_bases	user_id	鏌ヨ<EFBFBD>鐢ㄦ埛鐨勬墍鏈夌煡璇嗗簱
knowledge_bases	dify_dataset_id	Dify鏁版嵁鍚屾<EFBFBD>
documents	kb_id	鏌ヨ<EFBFBD>鐭ヨ瘑搴撶殑鎵€鏈夋枃妗?
documents	user_id	鏌ヨ<EFBFBD>鐢ㄦ埛鐨勬墍鏈夋枃妗?
documents	status	杩囨护鏂囨。鐘舵€?
documents	dify_document_id	Dify鏁版嵁鍚屾<EFBFBD>
documents	extraction_method	鎸夋彁鍙栨柟娉曡繃婊?
batch_tasks	user_id	鏌ヨ<EFBFBD>鐢ㄦ埛鐨勪换鍔?
batch_tasks	kb_id	鏌ヨ<EFBFBD>鐭ヨ瘑搴撶殑浠诲姟
batch_tasks	status	杩囨护浠诲姟鐘舵€?
batch_results	task_id	鏌ヨ<EFBFBD>浠诲姟鐨勬墍鏈夌粨鏋?
batch_results	document_id	鏌ヨ<EFBFBD>鏂囨。鐨勫<EFBFBD>鐞嗙粨鏋?
batch_results	status	杩囨护缁撴灉鐘舵€?
task_templates	user_id	鏌ヨ<EFBFBD>鐢ㄦ埛鐨勬ā鏉?

鏃堕棿绱㈠紩

琛ㄥ悕	绱㈠紩瀛楁<EFBFBD>	鐢ㄩ€?
batch_tasks	created_at	鎸夋椂闂存帓搴忎换鍔?

---

Phase 3鍔熻兘璇存槑

鎵瑰<EFBFBD>鐞嗗伐浣滄祦绋?

sequenceDiagram
    participant User
    participant API
    participant BatchTask
    participant Document
    participant LLM
    participant BatchResult

    User->>API: 鍒涘缓鎵瑰<E98EB5>鐞嗕换鍔?
    API->>BatchTask: 鍒涘缓浠诲姟璁板綍
    API->>Document: 鏌ヨ<E98F8C>鐭ヨ瘑搴撴枃妗ｅ垪琛?
    
    loop 姣忕瘒鏂囨。
        BatchTask->>Document: 璇诲彇鏂囨。鍏ㄦ枃
        BatchTask->>LLM: 璋冪敤LLM鎻愬彇淇℃伅
        LLM-->>BatchTask: 杩斿洖缁撴瀯鍖栨暟鎹?
        BatchTask->>BatchResult: 淇濆瓨缁撴灉
        BatchTask->>BatchTask: 鏇存柊杩涘害
    end
    
    BatchTask->>API: 浠诲姟瀹屾垚
    API-->>User: 杩斿洖缁撴灉姹囨€?

鎵瑰<EFBFBD>鐞嗕换鍔＄被鍨嬬ず渚?

1. 淇℃伅鎻愬彇 (extract_info)

   • 鎻愬彇鐮旂┒鏂规硶銆佹牱鏈<EFBFBD>噺銆丳鍊肩瓑
   • 杈撳嚭JSON鏍煎紡鐨勭粨鏋勫寲鏁版嵁

2. 鏂囩尞鎽樿<EFBFBD> (summarize)

   • 鎵归噺鐢熸垚鏂囩尞鎽樿<EFBFBD>
   • 缁熶竴鏍煎紡鍜岄暱搴?

3. 鏂囩尞鍒嗙被 (classify)

   • 鏍规嵁鐮旂┒绫诲瀷鍒嗙被
   • 鏍囩<EFBFBD>鍖栫<EFBFBD>鐞?

---

鍙樻洿鍘嗗彶

v1.0 - 2025-11-12 - 鍒濆<E98D92>鐗堟湰 鉁?

*鍙樻洿鍐呭<EFBFBD>锛?

1. 浠巂public schema杩佺Щ鍒癭pkb_schema
2. 5涓<EFBFBD>〃鍏ㄩ儴杩佺Щ锛?
   • knowledge_bases
   • documents
   • batch_tasks
   • batch_results
   • task_templates
3. 鍦≒risma涓<EFBFBD>坊鍔燻@@schema("pkb_schema")`鏍囩<E98F8D>
4. 鎵€鏈夋暟鎹?00%瀹屾暣杩佺Щ

*杩佺Щ鑴氭湰锛? docs/09-鏋舵瀯瀹炴柦/migration-scripts/004-migrate-pkb.sql

楠岃瘉鐘舵€侊細 鉁?宸查獙璇侊紝鍔熻兘姝ｅ父

*鐗规畩澶勭悊锛?

• batch_results.rawOutput 鈫?raw_output锛堝垪鍚嶆槧灏勪慨姝ｏ級
• task_templates.outputFields 鈫?output_fields锛堝垪鍚嶆槧灏勪慨姝ｏ級

---

馃摎 鐩稿叧鏂囨。

• Schema闅旂<EFBFBD>鏋舵瀯璁捐<EFBFBD>
• Schema杩佺Щ瀹屾垚鎶ュ憡
• Prisma閰嶇疆瀹屾垚鎶ュ憡
• [蹇<>€熷姛鑳芥祴璇曟姤鍛奭(../../../09-鏋舵瀯瀹炴柦/蹇<>€熷姛鑳芥祴璇曟姤鍛?md)
• [AIA鏁版嵁搴撹<E690B4>璁℃枃妗<E69E83>(../../AIA-AI鏅鸿兘闂<E58598>瓟/02-鎶€鏈<E282AC><E98F88>璁?01-鏁版嵁搴撹<E690B4>璁?md)

---

鏂囨。缁存姢鑰咃細 AI鍔╂墜
鏈€鍚庢洿鏂帮細 2025-11-12
鏂囨。鐘舵€侊細 鉁?宸插畬鎴愬苟楠岃瘉