Files
AIclinicalresearch/docs/01-平台基础层/[AI对接] 平台层快速上下文.md
HaHafeng beb7f7f559 feat(asl): Implement full-text screening core LLM service and validation system (Day 1-3)
Core Components:
- PDFStorageService with Dify/OSS adapters
- LLM12FieldsService with Nougat-first + dual-model + 3-layer JSON parsing
- PromptBuilder for dynamic prompt assembly
- MedicalLogicValidator with 5 rules + fault tolerance
- EvidenceChainValidator for citation integrity
- ConflictDetectionService for dual-model comparison

Prompt Engineering:
- System Prompt (6601 chars, Section-Aware strategy)
- User Prompt template (PICOS context injection)
- JSON Schema (12 fields constraints)
- Cochrane standards (not loaded in MVP)

Key Innovations:
- 3-layer JSON parsing (JSON.parse + json-repair + code block extraction)
- Promise.allSettled for dual-model fault tolerance
- safeGetFieldValue for robust field extraction
- Mixed CN/EN token calculation

Integration Tests:
- integration-test.ts (full test)
- quick-test.ts (quick test)
- cached-result-test.ts (fault tolerance test)

Documentation Updates:
- Development record (Day 2-3 summary)
- Quality assurance strategy (full-text screening)
- Development plan (progress update)
- Module status (v1.1 update)
- Technical debt (10 new items)

Test Results:
- JSON parsing success rate: 100%
- Medical logic validation: 5/5 passed
- Dual-model parallel processing: OK
- Cost per PDF: CNY 0.10

Files: 238 changed, 14383 insertions(+), 32 deletions(-)
Docs: docs/03-涓氬姟妯″潡/ASL-AI鏅鸿兘鏂囩尞/05-寮€鍙戣褰?2025-11-22_Day2-Day3_LLM鏈嶅姟涓庨獙璇佺郴缁熷紑鍙?md
2025-11-22 22:21:12 +08:00

146 lines
2.6 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# [AI对接] 平台层快速上下文
> **阅读时间:** 2-3分钟 | **Token消耗** ~1500 tokens
> **层级:** L1 | **前置阅读:** 00-系统总体设计/[AI对接] 快速上下文.md
---
## 📋 平台层定位
**平台基础层是所有业务模块的地基,提供通用的基础设施能力。**
**核心原则:**
- ✅ 全局唯一(整个平台只有一套)
- ✅ 业务无关(不涉及具体业务逻辑)
- ✅ 强依赖性(所有业务模块都必须依赖)
- ✅ 高稳定性(很少变动)
---
## 🎯 5个核心模块
### 1. 用户与权限中心UAM⭐ P0优先级
**职责:**
- 用户注册、登录、认证JWT
- 角色与权限管理RBAC
- Feature Flag功能开关 ⭐ 商业模式核心
- 多租户管理
**为什么重要:**
```
Feature Flag = 商业模式技术基础
专业版 → 只能用基础功能 + DeepSeek
高级版 → 更多功能 + Qwen3
旗舰版 → 全部功能 + Claude
通过Feature Flag控制
```
**数据表platform_schema**
```sql
- users #
- roles #
- permissions #
- feature_flags # Feature Flag配置
- tenants # SaaS多租户
```
---
### 2. 存储服务 - P1
**职责:**
- 文件上传、下载、删除
- 对象存储MinIO/阿里云OSS
- 本地文件系统(单机版)
---
### 3. 通知服务 - P2
**职责:**
- 站内消息
- 邮件通知
- WebSocket实时推送
---
### 4. 监控与日志 - P1
**职责:**
- 操作日志记录
- 错误日志监控
- 审计日志(合规要求)
**数据表:**
```sql
- admin_logs #
- error_logs #
- audit_logs #
```
---
### 5. 系统配置 - P1
**职责:**
- 系统级配置管理
- 多环境配置(开发、测试、生产)
- 动态配置更新
---
## 📊 依赖关系
**所有业务模块都依赖平台层:**
```
业务模块层AIA、ASL、PKB、DC、SSA、ST、RVW、ADMIN
↓ 全部依赖
平台基础层UAM、存储、通知、监控、配置
```
---
## 🔗 快速导航
**详细设计文档:**
- [用户与权限中心](./01-用户与权限中心(UAM)/README.md)
- [存储服务](./02-存储服务/README.md)
- [通知服务](./03-通知服务/README.md)
- [监控与日志](./04-监控与日志/README.md)
- [系统配置](./05-系统配置/README.md)
**相关文档:**
- [系统架构分层设计](../00-系统总体设计/01-系统架构分层设计.md)
---
**最后更新:** 2025-11-06
**维护人:** 技术架构师