Import sanitized HIS processing tools

2026-05-26 08:51:10 +08:00
commit 7e329f1d85
46 changed files with 19175 additions and 0 deletions
--- a/患者列表处理/数据处理工作区/01_科室分类规则.json
+++ b/患者列表处理/数据处理工作区/01_科室分类规则.json
@@ -0,0 +1,258 @@
+{
+  "说明": "每个具体子科室只归属一个大科室；aliases 用于把图片文件夹名归一到标准子科室名。",
+  "大科室列表": [
+    {
+      "大科室": "肝胆外科及肝移植相关",
+      "子科室": [
+        "肝胆外科1",
+        "肝胆外科2",
+        "肝胆外科3",
+        "肝胆外科4",
+        "肝胆外科5D",
+        "肝胆外科手术室",
+        "肝胆特种病区L",
+        "肝移植内",
+        "肝移植内N"
+      ]
+    },
+    {
+      "大科室": "普通外科及腹部外科",
+      "子科室": [
+        "普外科1",
+        "普外科2",
+        "普外科3",
+        "普外科4D",
+        "腹部外科L",
+        "普通腺体外科",
+        "普通胃肠外科"
+      ]
+    },
+    {
+      "大科室": "急诊医学科",
+      "子科室": [
+        "急诊中心",
+        "急诊中心L",
+        "急诊重症医学科L"
+      ]
+    },
+    {
+      "大科室": "重症医学科",
+      "子科室": [
+        "※重症医学1病区",
+        "重症医学2N病区",
+        "重症医学3病区",
+        "重症医学4D病区",
+        "外科ICU",
+        "肝胆ICU",
+        "肿瘤外科重症",
+        "感染重症"
+      ]
+    },
+    {
+      "大科室": "骨科",
+      "子科室": [
+        "骨科",
+        "骨科1",
+        "骨科2"
+      ]
+    },
+    {
+      "大科室": "泌尿外科",
+      "子科室": [
+        "泌尿外1",
+        "泌尿外2"
+      ]
+    },
+    {
+      "大科室": "呼吸内科",
+      "子科室": [
+        "呼吸内科3病区"
+      ]
+    },
+    {
+      "大科室": "耳鼻喉头颈外科",
+      "子科室": [
+        "耳鼻喉D",
+        "耳鼻喉头颈外科",
+        "耳鼻喉头颈外科L",
+        "耳鼻喉2病区"
+      ]
+    },
+    {
+      "大科室": "日间诊疗中心",
+      "子科室": [
+        "日间手术中心",
+        "日间中心病房L"
+      ]
+    },
+    {
+      "大科室": "乳腺外科",
+      "子科室": [
+        "乳腺外科1N",
+        "乳腺外科2N",
+        "乳腺外科2D"
+      ]
+    },
+    {
+      "大科室": "胸外科",
+      "子科室": [
+        "胸外1",
+        "胸外2",
+        "胸外3",
+        "胸外4D"
+      ]
+    },
+    {
+      "大科室": "肝病内科",
+      "子科室": [
+        "肝病内科"
+      ]
+    },
+    {
+      "大科室": "感染科",
+      "子科室": [
+        "感染1",
+        "感染2",
+        "感染3"
+      ]
+    },
+    {
+      "大科室": "肿瘤放疗科",
+      "子科室": [
+        "肿瘤放疗1",
+        "肿瘤放疗2",
+        "肿瘤放疗3",
+        "肿瘤放疗病区L",
+        "肿瘤放疗中心L【无人】",
+        "肿瘤放疗日间【无人】"
+      ]
+    },
+    {
+      "大科室": "特需/涉外病房",
+      "子科室": [
+        "健苑五涉外病房"
+      ]
+    },
+    {
+      "大科室": "老年外科",
+      "子科室": [
+        "老年外科"
+      ]
+    }
+  ],
+  "aliases": {
+    "呼吸内科3": "呼吸内科3病区",
+    "外科ICU": "外科ICU",
+    "急诊中心病房": "急诊中心",
+    "急诊中心": "急诊中心",
+    "急诊中心病房L": "急诊中心L",
+    "急诊中心L": "急诊中心L",
+    "急诊重症医学L": "急诊重症医学科L",
+    "急诊重症医学": "急诊重症医学科L",
+    "急诊重症L": "急诊重症医学科L",
+    "急诊重症医学科L": "急诊重症医学科L",
+    "感染科1": "感染1",
+    "感染科2": "感染2",
+    "感染科3": "感染3",
+    "感染1": "感染1",
+    "感染2": "感染2",
+    "感染3": "感染3",
+    "感染科重症": "感染重症",
+    "感染重症": "感染重症",
+    "肝病内科": "肝病内科",
+    "肝病内科N": "肝病内科",
+    "肝胆外科1": "肝胆外科1",
+    "肝胆外科2": "肝胆外科2",
+    "肝胆外科3": "肝胆外科3",
+    "肝胆外科4": "肝胆外科4",
+    "肝胆1": "肝胆外科1",
+    "肝胆2": "肝胆外科2",
+    "肝胆3": "肝胆外科3",
+    "肝胆4": "肝胆外科4",
+    "肝胆5": "肝胆外科5D",
+    "肝胆_5": "肝胆外科5D",
+    "肝胆5D": "肝胆外科5D",
+    "肝胆外科5病房D": "肝胆外科5D",
+    "肝胆特种L": "肝胆特种病区L",
+    "肝胆特种病区L": "肝胆特种病区L",
+    "肝胆移植内": "肝移植内",
+    "肝移植内": "肝移植内",
+    "肝移植内科": "肝移植内",
+    "肝移植内N": "肝移植内N",
+    "肝移植内科N": "肝移植内N",
+    "肿瘤放疗1": "肿瘤放疗1",
+    "肿瘤放疗2": "肿瘤放疗2",
+    "肿瘤放疗3": "肿瘤放疗3",
+    "肿放1": "肿瘤放疗1",
+    "肿放2": "肿瘤放疗2",
+    "肿放3": "肿瘤放疗3",
+    "肿瘤放疗L": "肿瘤放疗病区L",
+    "肿放L": "肿瘤放疗病区L",
+    "重症医学1": "※重症医学1病区",
+    "重症医学科1": "※重症医学1病区",
+    "重症1": "※重症医学1病区",
+    "重症医学2": "重症医学2N病区",
+    "重症医学科2": "重症医学2N病区",
+    "重症2": "重症医学2N病区",
+    "重症2N": "重症医学2N病区",
+    "重症医学3": "重症医学3病区",
+    "重症医学科3": "重症医学3病区",
+    "重症3": "重症医学3病区",
+    "重症医学4": "重症医学4D病区",
+    "重症医学科4": "重症医学4D病区",
+    "重症4": "重症医学4D病区",
+    "重症4D": "重症医学4D病区",
+    "胸外1": "胸外1",
+    "胸外2": "胸外2",
+    "胸外3": "胸外3",
+    "胸外4D": "胸外4D",
+    "普外1": "普外科1",
+    "普外2": "普外科2",
+    "普外3": "普外科3",
+    "普外4D": "普外科4D",
+    "普通外科1": "普外科1",
+    "普通外科2": "普外科2",
+    "普通外科3": "普外科3",
+    "普通外科4": "普外科4D",
+    "普通外科4D": "普外科4D",
+    "普通腺体外科": "普通腺体外科",
+    "普通胃肠": "普通胃肠外科",
+    "普通胃肠外科": "普通胃肠外科",
+    "腹部外科L": "腹部外科L",
+    "肝胆ICU": "肝胆ICU",
+    "日间手术": "日间手术中心",
+    "日间手术中心": "日间手术中心",
+    "日间手术L": "日间中心病房L",
+    "日间中心L": "日间中心病房L",
+    "日间中心病房L": "日间中心病房L",
+    "耳鼻喉": "耳鼻喉头颈外科",
+    "耳鼻喉D": "耳鼻喉D",
+    "耳鼻喉L": "耳鼻喉头颈外科L",
+    "耳鼻喉头颈外科": "耳鼻喉头颈外科",
+    "耳鼻喉头颈外科L": "耳鼻喉头颈外科L",
+    "耳鼻咽喉": "耳鼻喉头颈外科",
+    "耳鼻咽喉头颈外科": "耳鼻喉头颈外科",
+    "耳鼻喉2": "耳鼻喉2病区",
+    "耳鼻喉2D": "耳鼻喉2病区",
+    "耳鼻喉头颈2": "耳鼻喉2病区",
+    "乳腺外科": "乳腺外科1N",
+    "乳腺外科1": "乳腺外科1N",
+    "乳腺外科1N": "乳腺外科1N",
+    "乳腺外科2": "乳腺外科2N",
+    "乳腺外科2N": "乳腺外科2N",
+    "乳腺外科2D": "乳腺外科2D",
+    "乳腺1N": "乳腺外科1N",
+    "乳腺2N": "乳腺外科2N",
+    "乳腺2D": "乳腺外科2D",
+    "骨科": "骨科",
+    "骨科1": "骨科1",
+    "骨科2": "骨科2",
+    "骨科_1": "骨科1",
+    "骨科_2": "骨科2",
+    "泌尿1": "泌尿外1",
+    "泌尿2": "泌尿外2",
+    "健苑五涉外": "健苑五涉外病房",
+    "健苑五涉外病房": "健苑五涉外病房",
+    "老年外科": "老年外科"
+  }
+}
--- a/患者列表处理/数据处理工作区/02_患者列表OCR归档.py
+++ b/患者列表处理/数据处理工作区/02_患者列表OCR归档.py
--- a/患者列表处理/数据处理工作区/03_人工复核修正.template.json
+++ b/患者列表处理/数据处理工作区/03_人工复核修正.template.json
@@ -0,0 +1 @@
+[]
--- a/患者列表处理/数据处理工作区/04_合并批次结果.py
+++ b/患者列表处理/数据处理工作区/04_合并批次结果.py
@@ -0,0 +1,247 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Consolidate patient archive result folders."""
+
+from __future__ import annotations
+
+import csv
+import json
+from collections import Counter
+from pathlib import Path
+from typing import Any
+
+
+ROOT = Path("数据处理结果区")
+RESULT_SUFFIX = "-列表归档结果"
+INFO_DIR_NAME = "信息记录"
+
+
+def write_json(path: Path, data: Any) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
+
+
+def write_jsonl(path: Path, records: list[dict[str, Any]]) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", encoding="utf-8") as file:
+        for record in records:
+            file.write(json.dumps(record, ensure_ascii=False) + "\n")
+
+
+def flatten_record(batch_name: str, record: dict[str, Any]) -> dict[str, Any]:
+    patient = record["患者信息"]
+    image = record["图片信息"]
+    review = record["复核"]
+    return {
+        "处理批次": batch_name,
+        "大科室": record["大科室"],
+        "子科室": record["子科室"],
+        "来源文件夹": record["来源文件夹"],
+        "图片路径": image["图片路径"],
+        "图片名": image["图片名"],
+        "图片内行号": image["图片内行号"],
+        "拼接组序号": image["拼接组序号"],
+        "OCR请求ID": image.get("OCR请求ID", ""),
+        "姓名": patient["姓名"],
+        "性别": patient["性别"],
+        "年龄": patient["年龄"],
+        "住院号": patient["住院号"],
+        "诊断": patient["诊断"],
+        "入院时间": patient["入院时间"],
+        "最后书写时间": patient["最后书写时间"],
+        "住院天数": patient["住院天数"],
+        "出院时间": patient["出院时间"],
+        "手术后天数": patient["手术后天数"],
+        "复核状态": review["状态"],
+        "复核提示": review_note_text(review),
+        "人工修正": bool(review.get("人工修正")),
+    }
+
+
+def review_note_text(review: dict[str, Any]) -> str:
+    notes = [str(item) for item in review.get("提示", []) if str(item) and str(item) != "缺少出院时间"]
+    if review.get("人工备注"):
+        notes.append(f"人工备注: {review['人工备注']}")
+    return "；".join(notes)
+
+
+def record_quality_rank(record: dict[str, Any]) -> tuple[int, int, int, int]:
+    patient = record["患者信息"]
+    review = record["复核"]
+    review_ok = 0 if review.get("状态") == "需人工复核" else 1
+    manual_corrected = 1 if review.get("人工修正") else 0
+    date_count = int(bool(patient.get("入院时间"))) + int(bool(patient.get("出院时间")))
+    filled_count = sum(1 for value in patient.values() if value not in ("", None))
+    return (review_ok, manual_corrected, date_count, filled_count)
+
+
+def summarize_record_for_duplicate(record: dict[str, Any]) -> dict[str, Any]:
+    patient = record["患者信息"]
+    image = record["图片信息"]
+    review = record["复核"]
+    return {
+        "处理批次": record["处理批次"],
+        "大科室": record["大科室"],
+        "子科室": record["子科室"],
+        "来源文件夹": record["来源文件夹"],
+        "图片路径": image["图片路径"],
+        "图片名": image["图片名"],
+        "图片内行号": image["图片内行号"],
+        "姓名": patient.get("姓名", ""),
+        "住院号": patient.get("住院号", ""),
+        "入院时间": patient.get("入院时间", ""),
+        "出院时间": patient.get("出院时间", ""),
+        "复核状态": review.get("状态", ""),
+    }
+
+
+def deduplicate_records_by_inpatient_no(
+    records: list[dict[str, Any]],
+) -> tuple[list[dict[str, Any]], list[dict[str, Any]], list[dict[str, Any]]]:
+    kept_by_no: dict[str, dict[str, Any]] = {}
+    kept_order: list[str] = []
+    duplicates: list[dict[str, Any]] = []
+    missing_inpatient_no_records: list[dict[str, Any]] = []
+    for record in records:
+        inpatient_no = str(record["患者信息"].get("住院号", "")).strip()
+        if not inpatient_no:
+            missing_inpatient_no_records.append(
+                {
+                    "剔除记录": summarize_record_for_duplicate(record),
+                    "规则": "住院号为空，未纳入合并总表和数据库",
+                }
+            )
+            continue
+        if inpatient_no not in kept_by_no:
+            kept_order.append(inpatient_no)
+        else:
+            previous = kept_by_no[inpatient_no]
+            duplicates.append(
+                {
+                    "住院号": inpatient_no,
+                    "保留记录": summarize_record_for_duplicate(record),
+                    "剔除记录": summarize_record_for_duplicate(previous),
+                    "规则": "住院号重复，后出现记录覆盖先出现记录",
+                }
+            )
+        kept_by_no[inpatient_no] = record
+    return [kept_by_no[inpatient_no] for inpatient_no in kept_order], duplicates, missing_inpatient_no_records
+
+
+def slim_department_summary(batch_name: str, item: dict[str, Any]) -> dict[str, Any]:
+    raw_tips = item.get("提示", [])
+    if isinstance(raw_tips, list):
+        tips = "；".join(str(tip) for tip in raw_tips)
+    else:
+        tips = str(raw_tips)
+    return {
+        "处理批次": batch_name,
+        "来源文件夹": item["来源文件夹"],
+        "大科室": item["大科室"],
+        "子科室": item["子科室"],
+        "图片数": item["图片数"],
+        "记录数": item["记录数"],
+        "拼接组数": item["拼接组数"],
+        "提示": tips,
+    }
+
+
+def write_csv(path: Path, rows: list[dict[str, Any]]) -> None:
+    if not rows:
+        return
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", encoding="utf-8-sig", newline="") as file:
+        writer = csv.DictWriter(file, fieldnames=list(rows[0].keys()))
+        writer.writeheader()
+        writer.writerows(rows)
+
+
+def main() -> None:
+    ROOT.mkdir(exist_ok=True)
+    raw_records: list[dict[str, Any]] = []
+    batch_summaries: list[dict[str, Any]] = []
+
+    for result_dir in sorted(ROOT.rglob(f"*{RESULT_SUFFIX}")):
+        archive_path = result_dir / "患者列表_结构化.json"
+        review_path = result_dir / "复核报告.json"
+        if not archive_path.exists():
+            continue
+        batch_name = result_dir.name[: -len(RESULT_SUFFIX)]
+        archive = json.loads(archive_path.read_text(encoding="utf-8"))
+        review = json.loads(review_path.read_text(encoding="utf-8")) if review_path.exists() else {}
+        department_summaries = [
+            slim_department_summary(batch_name, item) for item in archive.get("科室汇总", [])
+        ]
+        summary = {
+            "处理批次": batch_name,
+            "结果目录": str(result_dir),
+            **archive.get("汇总", {}),
+            "科室归类": archive.get("科室归类", []),
+            "科室汇总": department_summaries,
+            "需人工复核记录数": len(review.get("需人工复核记录", [])),
+            "人工修正记录数": len(review.get("人工修正记录", [])),
+        }
+        batch_summaries.append(summary)
+
+        summary_dir = result_dir / INFO_DIR_NAME
+        write_json(summary_dir / "汇总.json", {**summary, "科室汇总": department_summaries})
+        write_csv(summary_dir / "科室汇总.csv", department_summaries)
+
+        for record in archive.get("患者记录", []):
+            enriched = {"处理批次": batch_name, **record}
+            raw_records.append(enriched)
+
+    all_records, duplicate_records, missing_inpatient_no_records = deduplicate_records_by_inpatient_no(raw_records)
+    flat_records = [flatten_record(record["处理批次"], record) for record in all_records]
+    kept_by_batch = Counter(record["处理批次"] for record in all_records)
+    dropped_by_batch = Counter(item["剔除记录"]["处理批次"] for item in duplicate_records)
+    missing_by_batch = Counter(item["剔除记录"]["处理批次"] for item in missing_inpatient_no_records)
+    batch_level_duplicate_count = sum(int(item.get("重复住院号剔除记录数", 0)) for item in batch_summaries)
+    batch_level_raw_count = sum(
+        int(item.get("去重前患者记录数", int(item.get("患者记录数", 0)) + int(item.get("重复住院号剔除记录数", 0))))
+        for item in batch_summaries
+    )
+
+    for summary in batch_summaries:
+        batch_name = summary["处理批次"]
+        original_count = int(summary.get("患者记录数", 0))
+        summary["原始患者记录数"] = original_count
+        summary["合并阶段重复住院号剔除记录数"] = int(dropped_by_batch.get(batch_name, 0))
+        summary["合并阶段缺少住院号剔除记录数"] = int(missing_by_batch.get(batch_name, 0))
+        summary["患者记录数"] = int(kept_by_batch.get(batch_name, 0))
+        write_json(Path(summary["结果目录"]) / INFO_DIR_NAME / "汇总.json", summary)
+
+    global_summary = {
+        "批次数": len(batch_summaries),
+        "总图片数": sum(int(item.get("图片数", 0)) for item in batch_summaries),
+        "批次内去重前患者记录数": batch_level_raw_count,
+        "批次内重复住院号剔除记录数": batch_level_duplicate_count,
+        "合并前患者记录数": len(raw_records),
+        "总患者记录数": len(all_records),
+        "合并阶段重复住院号剔除记录数": len(duplicate_records),
+        "合并阶段缺少住院号剔除记录数": len(missing_inpatient_no_records),
+        "重复住院号剔除记录数": batch_level_duplicate_count + len(duplicate_records),
+        "需人工复核记录数": sum(int(item.get("需人工复核记录数", 0)) for item in batch_summaries),
+        "人工修正记录数": sum(int(item.get("人工修正记录数", 0)) for item in batch_summaries),
+        "批次汇总": batch_summaries,
+    }
+    write_json(ROOT / INFO_DIR_NAME / "全局汇总.json", global_summary)
+    write_csv(ROOT / INFO_DIR_NAME / "批次汇总.csv", batch_summaries)
+    write_json(
+        ROOT / "合并_患者列表_结构化.json",
+        {
+            "汇总": global_summary,
+            "重复住院号剔除记录": duplicate_records,
+            "缺少住院号剔除记录": missing_inpatient_no_records,
+            "患者记录": all_records,
+        },
+    )
+    write_jsonl(ROOT / "合并_患者列表_记录.jsonl", all_records)
+    write_csv(ROOT / "合并_患者列表_记录.csv", flat_records)
+    write_json(ROOT / INFO_DIR_NAME / "重复住院号报告.json", duplicate_records)
+    write_json(ROOT / INFO_DIR_NAME / "缺少住院号报告.json", missing_inpatient_no_records)
+    print(json.dumps(global_summary, ensure_ascii=False, indent=2))
+
+
+if __name__ == "__main__":
+    main()
--- a/患者列表处理/数据处理工作区/05_同步PostgreSQL单表.py
+++ b/患者列表处理/数据处理工作区/05_同步PostgreSQL单表.py
@@ -0,0 +1,233 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Sync consolidated HIS patient records into PostgreSQL single table.
+
+Database credentials are read from environment variables by default:
+HIS_DB_HOST, HIS_DB_PORT, HIS_DB_NAME, HIS_DB_USER, HIS_DB_PASSWORD.
+"""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import json
+import os
+import subprocess
+import tempfile
+from pathlib import Path
+from typing import Any
+
+
+DEFAULT_RESULT_JSON = Path("数据处理结果区/合并_患者列表_结构化.json")
+DEFAULT_SCHEMA_SQL = Path("数据处理工作区/06_PostgreSQL建表结构.sql")
+
+TABLE_NAME = '"Patient_Lists"'
+
+PATIENT_FIELDS = [
+    "batch_name",
+    "major_department",
+    "sub_department",
+    "source_folder",
+    "image_path",
+    "image_name",
+    "image_row_no",
+    "patient_name",
+    "gender",
+    "age",
+    "inpatient_no",
+    "diagnosis",
+    "admission_time",
+    "last_write_time",
+    "hospital_days",
+    "discharge_time",
+    "postoperative_days",
+    "review_status",
+    "review_notes",
+    "manual_corrected",
+]
+
+
+def scalar(value: Any) -> str:
+    if value is None:
+        return ""
+    if isinstance(value, bool):
+        return "true" if value else "false"
+    return str(value)
+
+
+def clean_integer(value: Any) -> tuple[str, str]:
+    text = scalar(value).strip()
+    if not text:
+        return "", ""
+    if text.isdigit():
+        return text, ""
+    return "", f"住院天数非数字，原识别值: {text}"
+
+
+def review_note_items(review: dict[str, Any]) -> list[str]:
+    tips = review.get("提示", [])
+    if isinstance(tips, list):
+        note_items = [str(tip) for tip in tips if str(tip) and str(tip) != "缺少出院时间"]
+    else:
+        note_items = [str(tips)] if str(tips) else []
+    if review.get("人工备注"):
+        note_items.append(f"人工备注: {review['人工备注']}")
+    return note_items
+
+
+def psql_quote(path: Path) -> str:
+    return "'" + str(path.resolve()).replace("'", "''") + "'"
+
+
+def flatten_patient_record(record: dict[str, Any]) -> dict[str, Any]:
+    patient = record["患者信息"]
+    image = record["图片信息"]
+    review = record["复核"]
+    note_items = review_note_items(review)
+    hospital_days, hospital_days_note = clean_integer(patient["住院天数"])
+    if hospital_days_note:
+        note_items.append(hospital_days_note)
+    review_notes = "；".join(note_items)
+    return {
+        "batch_name": record["处理批次"],
+        "major_department": record["大科室"],
+        "sub_department": record["子科室"],
+        "source_folder": record["来源文件夹"],
+        "image_path": image["图片路径"],
+        "image_name": image["图片名"],
+        "image_row_no": image["图片内行号"],
+        "patient_name": patient["姓名"],
+        "gender": patient["性别"],
+        "age": patient["年龄"],
+        "inpatient_no": patient["住院号"],
+        "diagnosis": patient["诊断"],
+        "admission_time": patient["入院时间"],
+        "last_write_time": patient["最后书写时间"],
+        "hospital_days": hospital_days,
+        "discharge_time": patient["出院时间"],
+        "postoperative_days": patient["手术后天数"],
+        "review_status": review["状态"],
+        "review_notes": review_notes,
+        "manual_corrected": bool(review.get("人工修正")),
+    }
+
+
+def prepare_unique_rows(rows: list[dict[str, Any]]) -> tuple[list[dict[str, Any]], list[str], list[str]]:
+    kept_by_no: dict[str, dict[str, Any]] = {}
+    kept_order: list[str] = []
+    replacements: list[str] = []
+    invalid: list[str] = []
+    for row in rows:
+        inpatient_no = str(row.get("inpatient_no", "")).strip()
+        location = f"{row['batch_name']} / {row['image_path']} / 第{row['image_row_no']}行"
+        if not inpatient_no:
+            invalid.append(f"{location}: 空")
+            continue
+        if inpatient_no not in kept_by_no:
+            kept_order.append(inpatient_no)
+        else:
+            previous = kept_by_no[inpatient_no]
+            replacements.append(
+                f"{inpatient_no}: {previous['batch_name']} / {previous['image_path']} / 第{previous['image_row_no']}行 -> {location}"
+            )
+        kept_by_no[inpatient_no] = row
+    return [kept_by_no[inpatient_no] for inpatient_no in kept_order], replacements, invalid
+
+
+def load_rows(result_json: Path) -> tuple[list[dict[str, Any]], list[str], list[str]]:
+    merged = json.loads(result_json.read_text(encoding="utf-8"))
+    rows = [flatten_patient_record(record) for record in merged.get("患者记录", [])]
+    return prepare_unique_rows(rows)
+
+
+def write_temp_csv(rows: list[dict[str, Any]]) -> Path:
+    temp_file = tempfile.NamedTemporaryFile(
+        mode="w",
+        encoding="utf-8",
+        newline="",
+        suffix="_his_patient_lists.csv",
+        delete=False,
+    )
+    with temp_file:
+        writer = csv.DictWriter(temp_file, fieldnames=PATIENT_FIELDS)
+        writer.writeheader()
+        for row in rows:
+            writer.writerow({field: scalar(row.get(field, "")) for field in PATIENT_FIELDS})
+    return Path(temp_file.name)
+
+
+def sync_to_postgres(args: argparse.Namespace, csv_path: Path, row_count: int) -> None:
+    sql = f"""\\set ON_ERROR_STOP on
+\\i {psql_quote(Path(args.schema))}
+TRUNCATE TABLE {TABLE_NAME} RESTART IDENTITY;
+\\copy {TABLE_NAME}({','.join(PATIENT_FIELDS)}) FROM {psql_quote(csv_path)} WITH (FORMAT csv, HEADER true, NULL '')
+"""
+    env = os.environ.copy()
+    password = args.password or env.get("HIS_DB_PASSWORD")
+    if password:
+        env["PGPASSWORD"] = password
+    command = [
+        "psql",
+        "-h",
+        args.host,
+        "-p",
+        str(args.port),
+        "-U",
+        args.user,
+        "-d",
+        args.dbname,
+        "-v",
+        "ON_ERROR_STOP=1",
+    ]
+    completed = subprocess.run(command, input=sql, text=True, env=env, capture_output=True)
+    print(completed.stdout, end="")
+    if completed.returncode != 0:
+        print(completed.stderr, end="")
+        completed.check_returncode()
+    print(json.dumps({"synced_table": "Patient_Lists", "records": row_count}, ensure_ascii=False))
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--input", default=str(DEFAULT_RESULT_JSON), help="合并后的患者记录 JSON")
+    parser.add_argument("--schema", default=str(DEFAULT_SCHEMA_SQL), help="单表建表 SQL")
+    parser.add_argument("--host", default=os.getenv("HIS_DB_HOST", "DB_HOST"))
+    parser.add_argument("--port", default=os.getenv("HIS_DB_PORT", "5432"))
+    parser.add_argument("--dbname", default=os.getenv("HIS_DB_NAME", "DB_NAME"))
+    parser.add_argument("--user", default=os.getenv("HIS_DB_USER", "DB_USER"))
+    parser.add_argument("--password", default="", help="数据库密码；建议改用 HIS_DB_PASSWORD 环境变量")
+    return parser.parse_args()
+
+
+def main() -> None:
+    args = parse_args()
+    rows, replacements, invalid = load_rows(Path(args.input))
+    csv_path = write_temp_csv(rows)
+    try:
+        sync_to_postgres(args, csv_path, len(rows))
+        if invalid:
+            print(
+                json.dumps(
+                    {
+                        "skipped_empty_inpatient_no": len(invalid),
+                        "empty_examples": invalid[:20],
+                    },
+                    ensure_ascii=False,
+                )
+            )
+        if replacements:
+            print(
+                json.dumps(
+                    {
+                        "deduplicated_by_inpatient_no": len(replacements),
+                        "replacement_examples": replacements[:20],
+                    },
+                    ensure_ascii=False,
+                )
+            )
+    finally:
+        csv_path.unlink(missing_ok=True)
+
+
+if __name__ == "__main__":
+    main()
--- a/患者列表处理/数据处理工作区/06_PostgreSQL建表结构.sql
+++ b/患者列表处理/数据处理工作区/06_PostgreSQL建表结构.sql
@@ -0,0 +1,84 @@
+DROP TABLE IF EXISTS patient_records CASCADE;
+
+CREATE TABLE IF NOT EXISTS "Patient_Lists" (
+  record_id bigserial PRIMARY KEY,
+  batch_name text NOT NULL,
+  major_department text NOT NULL,
+  sub_department text NOT NULL,
+  source_folder text NOT NULL,
+  image_path text NOT NULL,
+  image_name text NOT NULL,
+  image_row_no integer NOT NULL,
+  patient_name text NOT NULL,
+  gender text,
+  age text,
+  inpatient_no text NOT NULL,
+  diagnosis text,
+  admission_time text,
+  last_write_time text,
+  hospital_days integer,
+  discharge_time text,
+  postoperative_days text,
+  review_status text NOT NULL,
+  review_notes text,
+  manual_corrected boolean NOT NULL DEFAULT false,
+  imported_at timestamptz NOT NULL DEFAULT now(),
+  audit_result text,
+  audit_ai_feedback text,
+  audit_manual_feedback text,
+  audit_machine_verdict text,
+  audit_source text,
+  audit_checked_by text,
+  audit_checked_at timestamptz,
+  CONSTRAINT uq_patient_lists_inpatient_no UNIQUE (inpatient_no),
+  CONSTRAINT ck_patient_lists_inpatient_no_present CHECK (btrim(inpatient_no) <> ''),
+  CONSTRAINT ck_patient_lists_admission_before_discharge CHECK (
+    COALESCE(discharge_time, '') = ''
+    OR COALESCE(admission_time, '') = ''
+    OR admission_time !~ '^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$'
+    OR discharge_time !~ '^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$'
+    OR admission_time <= discharge_time
+    OR review_status = '需人工复核'
+  )
+);
+
+CREATE INDEX IF NOT EXISTS idx_patient_lists_batch_name ON "Patient_Lists"(batch_name);
+CREATE INDEX IF NOT EXISTS idx_patient_lists_department ON "Patient_Lists"(major_department, sub_department);
+CREATE INDEX IF NOT EXISTS idx_patient_lists_source_folder ON "Patient_Lists"(source_folder);
+CREATE INDEX IF NOT EXISTS idx_patient_lists_patient_name ON "Patient_Lists"(patient_name);
+CREATE INDEX IF NOT EXISTS idx_patient_lists_review_status ON "Patient_Lists"(review_status);
+CREATE INDEX IF NOT EXISTS idx_patient_lists_audit_result ON "Patient_Lists"(audit_result);
+
+COMMENT ON TABLE "Patient_Lists" IS 'HIS患者列表图片OCR归档后的正式患者记录单表';
+COMMENT ON COLUMN "Patient_Lists".record_id IS '患者记录主键，数据库自动生成';
+COMMENT ON COLUMN "Patient_Lists".batch_name IS '处理批次名称，通常为原始图片集群文件夹名';
+COMMENT ON COLUMN "Patient_Lists".major_department IS '归类后的大科室';
+COMMENT ON COLUMN "Patient_Lists".sub_department IS '归类后的子科室';
+COMMENT ON COLUMN "Patient_Lists".source_folder IS '原始第一层科室文件夹名';
+COMMENT ON COLUMN "Patient_Lists".image_path IS '原始患者列表图片路径，用于定位数据来源';
+COMMENT ON COLUMN "Patient_Lists".image_name IS '原始患者列表图片文件名';
+COMMENT ON COLUMN "Patient_Lists".image_row_no IS '患者记录在原始图片内的行号';
+COMMENT ON COLUMN "Patient_Lists".patient_name IS '患者姓名';
+COMMENT ON COLUMN "Patient_Lists".gender IS '患者性别';
+COMMENT ON COLUMN "Patient_Lists".age IS '患者年龄，保留原始岁数字符串';
+COMMENT ON COLUMN "Patient_Lists".inpatient_no IS '住院号，不能为空且全库唯一；不强制校验格式';
+COMMENT ON COLUMN "Patient_Lists".diagnosis IS '诊断，可能为空';
+COMMENT ON COLUMN "Patient_Lists".admission_time IS '入院时间，按OCR/清洗后的文本保存';
+COMMENT ON COLUMN "Patient_Lists".last_write_time IS '最后书写时间，按OCR/清洗后的文本保存';
+COMMENT ON COLUMN "Patient_Lists".hospital_days IS '住院天数';
+COMMENT ON COLUMN "Patient_Lists".discharge_time IS '出院时间，按OCR/清洗后的文本保存';
+COMMENT ON COLUMN "Patient_Lists".postoperative_days IS '手术后天数，可能为空';
+COMMENT ON COLUMN "Patient_Lists".review_status IS '自动复核或人工复核状态';
+COMMENT ON COLUMN "Patient_Lists".review_notes IS '复核提示信息';
+COMMENT ON COLUMN "Patient_Lists".manual_corrected IS '是否经过人工修正';
+COMMENT ON COLUMN "Patient_Lists".imported_at IS '导入数据库的时间';
+COMMENT ON COLUMN "Patient_Lists".audit_result IS '抽查人工核验结果';
+COMMENT ON COLUMN "Patient_Lists".audit_ai_feedback IS '抽查项AI反馈原文';
+COMMENT ON COLUMN "Patient_Lists".audit_manual_feedback IS '抽查项人工反馈';
+COMMENT ON COLUMN "Patient_Lists".audit_machine_verdict IS '抽查机器核验判断';
+COMMENT ON COLUMN "Patient_Lists".audit_source IS '抽查来源';
+COMMENT ON COLUMN "Patient_Lists".audit_checked_by IS '抽查操作用户';
+COMMENT ON COLUMN "Patient_Lists".audit_checked_at IS '抽查结果保存时间';
+COMMENT ON CONSTRAINT uq_patient_lists_inpatient_no ON "Patient_Lists" IS '保证同一个住院号只归档一条患者记录';
+COMMENT ON CONSTRAINT ck_patient_lists_inpatient_no_present ON "Patient_Lists" IS '住院号不能为空；格式不做强制校验';
+COMMENT ON CONSTRAINT ck_patient_lists_admission_before_discharge ON "Patient_Lists" IS '出院时间为空时放行；入院时间晚于出院时间时必须标记为需人工复核';
--- a/患者列表处理/数据处理工作区/07_处理程序说明.md
+++ b/患者列表处理/数据处理工作区/07_处理程序说明.md
@@ -0,0 +1,72 @@
+# 患者列表归档处理程序说明
+
+## 工作区文件
+
+1. `01_科室分类规则.json`：大科室、子科室、文件夹别名归类规则。
+2. `02_患者列表OCR归档.py`：单个图片集群的 OCR、字段清洗、去重、复核报告生成程序。
+3. `03_人工复核修正.json`：少量无法靠规则自动判断的人工修正项，可能包含患者信息，不提交到 Git。
+4. `04_合并批次结果.py`：合并所有 `*-列表归档结果`，生成全局 JSON/CSV 和 `信息记录`。
+5. `05_同步PostgreSQL单表.py`：把合并结果同步到 PostgreSQL 的 `"Patient_Lists"` 单表。
+6. `06_PostgreSQL建表结构.sql`：数据库单表结构、索引、表注释、字段注释。
+7. `07_处理程序说明.md`：当前说明。
+8. `08_PostgreSQL调整Patient_Lists列顺序.sql`：保留数据的前提下，把现有 `"Patient_Lists"` 物理列顺序调整为当前字段顺序。
+9. `09_PostgreSQL住院号非空唯一约束.sql`：删除住院号为空的记录，重复住院号保留最新一条，并让 PostgreSQL 强制住院号不能为空且唯一。
+
+## 智能体处理顺序
+
+1. 检查待处理批次目录和图片数量。
+2. 必要时更新 `01_科室分类规则.json` 的别名。
+3. 运行 `02_患者列表OCR归档.py` 处理一个批次。
+4. 查看 `复核报告.json` 和 `重复住院号报告.json`。
+5. 若有需人工复核项，优先补自动清洗规则；仍不能自动判断时，写入 `03_人工复核修正.json`。
+6. 用 `--rebuild-from-cache` 重建该批次结果，确认复核项和重复住院号符合预期。
+7. 运行 `04_合并批次结果.py` 更新全局 `信息记录`。
+8. 运行 `05_同步PostgreSQL单表.py` 同步到 PostgreSQL。
+9. 导入 PostgreSQL 后查询记录数、需复核记录数、重复住院号组数。
+
+## 人工复核网页端
+
+- 代码目录：`人工复核网页端/`。
+- 启动方式：`cd 人工复核网页端 && docker compose up -d --build`。
+- 登录配置从项目根目录 `.env` 读取：`REVIEW_APP_USERNAME`、`REVIEW_APP_PASSWORD`、`REVIEW_APP_SECRET_KEY`、`REVIEW_APP_PORT`。
+- 网页端读取各批次 `复核报告.json`，按原始图片路径与图片内行号裁剪截图；住院号不能为空且唯一，格式是否规范交由人工复核时判断。
+- 保存修订后写入 `数据处理工作区/03_人工复核修正.json`，并尽量同步 PostgreSQL；若 PostgreSQL 暂不可用，会保留待同步状态，之后可在网页端点击“提交待同步”。
+- 出院时间默认允许为空；确有出院时间时，网页端和处理程序会校验时间格式以及是否早于入院时间。
+- 页面包含概览、复核、抽查、抽查查看、设置区域；抽查功能可随机抽取患者行，调用 Kimi 多模态模型二次核验，并把 AI 反馈、机器判断、人工抽查结论写入 PostgreSQL。
+
+## 识别策略
+
+- OCR 接口：腾讯云 `RecognizeTableAccurateOCR` 表格识别 V3。
+- 新批次拼接图默认给每张原图上下各加 `24px` 白色边界，减少贴边表格行被裁掉或和相邻图片粘连的概率。
+- 正式处理优先用 6 张拼接；接口超时、失败或行数偏少时，程序会自动降到 4/3/2/单张。
+- 行数校验：按图片高度推断应有行数，返回行数偏少即判定该拼接档位不可靠。
+- 漏行不一定只发生在最上方或最下方两行；长拼接图中间也可能漏行，白边只能缓解贴边问题。
+- 同一科室内会记忆稳定回退档位；跨科室不共享该记忆，避免重建历史缓存时误用。
+- 只用缓存重建时，若前序回退策略需要的缓存不完整，会先尝试该组主缓存，避免因缓存形态不同造成少行。
+- 字段顺序固定为：姓名、性别、年龄、住院号、诊断、入院时间、最后书写时间、住院天数、出院时间、手术后天数。
+- 字段清洗包含日期规范化、住院号常见误识别修正、长诊断吞入入院时间、空时间字段导致列左移、`后XX天` 错位等。
+
+## 住院号核验规则
+
+- `住院号` 是唯一强制校验条件：不能为空且全库唯一。
+- 单批次、全局合并和 PostgreSQL 同步都会剔除住院号为空的记录；重复住院号按后出现记录覆盖先出现记录；格式异常但非空的住院号保留。
+- 网页端保存时优先按图片路径和图片内行号定位数据库记录；如果当前住院号已存在于另一条记录，会用当前修订覆盖既有住院号记录，并删除当前重复图片记录。
+- 数据库约束允许 `出院时间` 为空；若入院时间和出院时间均为标准格式且入院时间晚于出院时间，该记录必须标记为 `需人工复核`。
+
+## PostgreSQL 单表字段
+
+`"Patient_Lists"` 只保留正式查看和追溯需要的字段：
+
+- 数据定位：`batch_name`、`source_folder`、`image_path`、`image_name`、`image_row_no`
+- 科室信息：`major_department`、`sub_department`
+- 患者信息：姓名、性别、年龄、住院号、诊断、入院时间、最后书写时间、住院天数、出院时间、手术后天数
+- 复核信息：`review_status`、`review_notes`、`manual_corrected`
+- 抽查信息：`audit_result`、`audit_ai_feedback`、`audit_manual_feedback`、`audit_machine_verdict`、`audit_source`、`audit_checked_by`、`audit_checked_at`
+
+复核状态含义：
+
+- `自动复核通过`：OCR 结果经过程序规则校验后没有发现明显异常，`manual_corrected=false`。
+- `人工复核通过`：该行命中了 `03_人工复核修正.json` 中的人工修正项，修正后校验通过，`manual_corrected=true`。
+- `AI修改-待确认`：网页端 Kimi 辅助生成的草稿状态，不会被待同步流程写入 PostgreSQL，需人工保存确认。
+
+OCR 请求号、OCR 缓存路径、拼接图路径、拼接组号等中间态字段不进入数据库正式表。
--- a/患者列表处理/数据处理工作区/08_PostgreSQL调整Patient_Lists列顺序.sql
+++ b/患者列表处理/数据处理工作区/08_PostgreSQL调整Patient_Lists列顺序.sql
@@ -0,0 +1,168 @@
+-- 保留现有数据，重建 "Patient_Lists" 的物理列顺序。
+-- 只调整列顺序，不交换 last_write_time/discharge_time 的值。
+-- 执行前建议先确认已备份数据库。
+
+BEGIN;
+
+LOCK TABLE "Patient_Lists" IN ACCESS EXCLUSIVE MODE;
+
+DROP TABLE IF EXISTS "Patient_Lists__reordered";
+
+CREATE TABLE "Patient_Lists__reordered" (
+  record_id bigint NOT NULL,
+  batch_name text NOT NULL,
+  major_department text NOT NULL,
+  sub_department text NOT NULL,
+  source_folder text NOT NULL,
+  image_path text NOT NULL,
+  image_name text NOT NULL,
+  image_row_no integer NOT NULL,
+  patient_name text NOT NULL,
+  gender text,
+  age text,
+  inpatient_no text NOT NULL,
+  diagnosis text,
+  admission_time text,
+  last_write_time text,
+  hospital_days integer,
+  discharge_time text,
+  postoperative_days text,
+  review_status text NOT NULL,
+  review_notes text,
+  manual_corrected boolean NOT NULL DEFAULT false,
+  imported_at timestamptz NOT NULL DEFAULT now(),
+  audit_result text,
+  audit_ai_feedback text,
+  audit_manual_feedback text,
+  audit_machine_verdict text,
+  audit_source text,
+  audit_checked_by text,
+  audit_checked_at timestamptz,
+  CONSTRAINT ck_patient_lists_inpatient_no_present CHECK (btrim(inpatient_no) <> ''),
+  CONSTRAINT ck_patient_lists_admission_before_discharge CHECK (
+    COALESCE(discharge_time, '') = ''
+    OR COALESCE(admission_time, '') = ''
+    OR admission_time !~ '^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$'
+    OR discharge_time !~ '^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$'
+    OR admission_time <= discharge_time
+    OR review_status = '需人工复核'
+  )
+);
+
+INSERT INTO "Patient_Lists__reordered" (
+  record_id,
+  batch_name,
+  major_department,
+  sub_department,
+  source_folder,
+  image_path,
+  image_name,
+  image_row_no,
+  patient_name,
+  gender,
+  age,
+  inpatient_no,
+  diagnosis,
+  admission_time,
+  last_write_time,
+  hospital_days,
+  discharge_time,
+  postoperative_days,
+  review_status,
+  review_notes,
+  manual_corrected,
+  imported_at,
+  audit_result,
+  audit_ai_feedback,
+  audit_manual_feedback,
+  audit_machine_verdict,
+  audit_source,
+  audit_checked_by,
+  audit_checked_at
+)
+SELECT
+  record_id,
+  batch_name,
+  major_department,
+  sub_department,
+  source_folder,
+  image_path,
+  image_name,
+  image_row_no,
+  patient_name,
+  gender,
+  age,
+  inpatient_no,
+  diagnosis,
+  admission_time,
+  last_write_time,
+  hospital_days,
+  discharge_time,
+  postoperative_days,
+  review_status,
+  review_notes,
+  manual_corrected,
+  imported_at,
+  audit_result,
+  audit_ai_feedback,
+  audit_manual_feedback,
+  audit_machine_verdict,
+  audit_source,
+  audit_checked_by,
+  audit_checked_at
+FROM "Patient_Lists";
+
+DROP TABLE "Patient_Lists";
+ALTER TABLE "Patient_Lists__reordered" RENAME TO "Patient_Lists";
+
+DROP SEQUENCE IF EXISTS "Patient_Lists_record_id_seq";
+CREATE SEQUENCE "Patient_Lists_record_id_seq";
+ALTER SEQUENCE "Patient_Lists_record_id_seq" OWNED BY "Patient_Lists".record_id;
+ALTER TABLE "Patient_Lists" ALTER COLUMN record_id SET DEFAULT nextval('"Patient_Lists_record_id_seq"'::regclass);
+SELECT setval('"Patient_Lists_record_id_seq"', COALESCE((SELECT max(record_id) FROM "Patient_Lists"), 1), true);
+
+ALTER TABLE "Patient_Lists" ADD CONSTRAINT "Patient_Lists_pkey" PRIMARY KEY (record_id);
+ALTER TABLE "Patient_Lists" ADD CONSTRAINT uq_patient_lists_inpatient_no UNIQUE (inpatient_no);
+
+CREATE INDEX idx_patient_lists_batch_name ON "Patient_Lists"(batch_name);
+CREATE INDEX idx_patient_lists_department ON "Patient_Lists"(major_department, sub_department);
+CREATE INDEX idx_patient_lists_source_folder ON "Patient_Lists"(source_folder);
+CREATE INDEX idx_patient_lists_patient_name ON "Patient_Lists"(patient_name);
+CREATE INDEX idx_patient_lists_review_status ON "Patient_Lists"(review_status);
+CREATE INDEX idx_patient_lists_audit_result ON "Patient_Lists"(audit_result);
+
+COMMENT ON TABLE "Patient_Lists" IS 'HIS患者列表图片OCR归档后的正式患者记录单表';
+COMMENT ON COLUMN "Patient_Lists".record_id IS '患者记录主键，数据库自动生成';
+COMMENT ON COLUMN "Patient_Lists".batch_name IS '处理批次名称，通常为原始图片集群文件夹名';
+COMMENT ON COLUMN "Patient_Lists".major_department IS '归类后的大科室';
+COMMENT ON COLUMN "Patient_Lists".sub_department IS '归类后的子科室';
+COMMENT ON COLUMN "Patient_Lists".source_folder IS '原始第一层科室文件夹名';
+COMMENT ON COLUMN "Patient_Lists".image_path IS '原始患者列表图片路径，用于定位数据来源';
+COMMENT ON COLUMN "Patient_Lists".image_name IS '原始患者列表图片文件名';
+COMMENT ON COLUMN "Patient_Lists".image_row_no IS '患者记录在原始图片内的行号';
+COMMENT ON COLUMN "Patient_Lists".patient_name IS '患者姓名';
+COMMENT ON COLUMN "Patient_Lists".gender IS '患者性别';
+COMMENT ON COLUMN "Patient_Lists".age IS '患者年龄，保留原始岁数字符串';
+COMMENT ON COLUMN "Patient_Lists".inpatient_no IS '住院号，不能为空且全库唯一；不强制校验格式';
+COMMENT ON COLUMN "Patient_Lists".diagnosis IS '诊断，可能为空';
+COMMENT ON COLUMN "Patient_Lists".admission_time IS '入院时间，按OCR/清洗后的文本保存';
+COMMENT ON COLUMN "Patient_Lists".last_write_time IS '最后书写时间，按OCR/清洗后的文本保存';
+COMMENT ON COLUMN "Patient_Lists".hospital_days IS '住院天数';
+COMMENT ON COLUMN "Patient_Lists".discharge_time IS '出院时间，按OCR/清洗后的文本保存';
+COMMENT ON COLUMN "Patient_Lists".postoperative_days IS '手术后天数，可能为空，格式通常为“后X天”';
+COMMENT ON COLUMN "Patient_Lists".review_status IS '自动复核或人工复核状态';
+COMMENT ON COLUMN "Patient_Lists".review_notes IS '复核提示信息';
+COMMENT ON COLUMN "Patient_Lists".manual_corrected IS '是否经过人工修正';
+COMMENT ON COLUMN "Patient_Lists".imported_at IS '导入数据库或人工同步更新的时间';
+COMMENT ON COLUMN "Patient_Lists".audit_result IS '抽查人工核验结果';
+COMMENT ON COLUMN "Patient_Lists".audit_ai_feedback IS '抽查项AI反馈原文';
+COMMENT ON COLUMN "Patient_Lists".audit_manual_feedback IS '抽查项人工反馈';
+COMMENT ON COLUMN "Patient_Lists".audit_machine_verdict IS '抽查机器核验判断';
+COMMENT ON COLUMN "Patient_Lists".audit_source IS '抽查来源';
+COMMENT ON COLUMN "Patient_Lists".audit_checked_by IS '抽查操作用户';
+COMMENT ON COLUMN "Patient_Lists".audit_checked_at IS '抽查结果保存时间';
+COMMENT ON CONSTRAINT uq_patient_lists_inpatient_no ON "Patient_Lists" IS '保证同一个住院号只归档一条患者记录';
+COMMENT ON CONSTRAINT ck_patient_lists_inpatient_no_present ON "Patient_Lists" IS '住院号不能为空；格式不做强制校验';
+COMMENT ON CONSTRAINT ck_patient_lists_admission_before_discharge ON "Patient_Lists" IS '出院时间为空时放行；入院时间晚于出院时间时必须标记为需人工复核';
+
+COMMIT;
--- a/患者列表处理/数据处理工作区/09_PostgreSQL住院号非空唯一约束.sql
+++ b/患者列表处理/数据处理工作区/09_PostgreSQL住院号非空唯一约束.sql
@@ -0,0 +1,102 @@
+-- 住院号为唯一定位条件：数据库强制“不能为空且唯一”。
+-- 不校验 ZY 位数格式；空住院号记录会先删除，重复住院号保留 id 最大/最新的一条。
+
+DELETE FROM "Patient_Lists"
+WHERE inpatient_no IS NULL OR btrim(inpatient_no) = '';
+
+DELETE FROM "Patient_Lists" p
+USING (
+  SELECT record_id
+  FROM (
+    SELECT record_id, row_number() OVER (PARTITION BY inpatient_no ORDER BY record_id DESC) AS rn
+    FROM "Patient_Lists"
+  ) ranked
+  WHERE rn > 1
+) duplicate_rows
+WHERE p.record_id = duplicate_rows.record_id;
+
+ALTER TABLE "Patient_Lists"
+  DROP CONSTRAINT IF EXISTS ck_patient_lists_inpatient_no_format;
+
+ALTER TABLE "Patient_Lists"
+  DROP CONSTRAINT IF EXISTS uq_patient_lists_inpatient_no;
+
+DROP INDEX IF EXISTS uq_patient_lists_inpatient_no;
+
+ALTER TABLE "Patient_Lists"
+  DROP CONSTRAINT IF EXISTS ck_patient_lists_inpatient_no_present;
+
+ALTER TABLE "Patient_Lists"
+  DROP CONSTRAINT IF EXISTS ck_patient_lists_inpatient_no_required;
+
+ALTER TABLE "Patient_Lists"
+  ALTER COLUMN inpatient_no SET NOT NULL;
+
+ALTER TABLE "Patient_Lists"
+  ADD CONSTRAINT ck_patient_lists_inpatient_no_present
+  CHECK (btrim(inpatient_no) <> '');
+
+ALTER TABLE "Patient_Lists"
+  ADD CONSTRAINT uq_patient_lists_inpatient_no UNIQUE (inpatient_no);
+
+COMMENT ON COLUMN "Patient_Lists".inpatient_no
+  IS '住院号，不能为空且全库唯一；不强制校验格式';
+
+COMMENT ON CONSTRAINT ck_patient_lists_inpatient_no_present ON "Patient_Lists"
+  IS '住院号不能为空；格式不做强制校验';
+
+COMMENT ON CONSTRAINT uq_patient_lists_inpatient_no ON "Patient_Lists"
+  IS '保证同一个住院号只归档一条患者记录';
+
+DELETE FROM "Patient_FrontPages"
+WHERE inpatient_no IS NULL OR btrim(inpatient_no) = '';
+
+DELETE FROM "Patient_FrontPages" p
+USING (
+  SELECT id
+  FROM (
+    SELECT id, row_number() OVER (PARTITION BY inpatient_no ORDER BY id DESC) AS rn
+    FROM "Patient_FrontPages"
+  ) ranked
+  WHERE rn > 1
+) duplicate_rows
+WHERE p.id = duplicate_rows.id;
+
+ALTER TABLE "Patient_FrontPages"
+  DROP CONSTRAINT IF EXISTS "ck_Patient_FrontPages_inpatient_no_format";
+
+ALTER TABLE "Patient_FrontPages"
+  DROP CONSTRAINT IF EXISTS ck_patient_frontpages_inpatient_no_format;
+
+ALTER TABLE "Patient_FrontPages"
+  DROP CONSTRAINT IF EXISTS uq_patient_frontpages_inpatient_no;
+
+DROP INDEX IF EXISTS uq_patient_frontpages_inpatient_no;
+
+ALTER TABLE "Patient_FrontPages"
+  DROP CONSTRAINT IF EXISTS ck_patient_frontpages_inpatient_no_present;
+
+ALTER TABLE "Patient_FrontPages"
+  DROP CONSTRAINT IF EXISTS "ck_Patient_FrontPages_inpatient_no_required";
+
+ALTER TABLE "Patient_FrontPages"
+  DROP CONSTRAINT IF EXISTS ck_patient_frontpages_inpatient_no_required;
+
+ALTER TABLE "Patient_FrontPages"
+  ALTER COLUMN inpatient_no SET NOT NULL;
+
+ALTER TABLE "Patient_FrontPages"
+  ADD CONSTRAINT ck_patient_frontpages_inpatient_no_present
+  CHECK (btrim(inpatient_no) <> '');
+
+ALTER TABLE "Patient_FrontPages"
+  ADD CONSTRAINT uq_patient_frontpages_inpatient_no UNIQUE (inpatient_no);
+
+COMMENT ON COLUMN "Patient_FrontPages".inpatient_no
+  IS '住院号，不能为空且全库唯一；不强制校验格式';
+
+COMMENT ON CONSTRAINT ck_patient_frontpages_inpatient_no_present ON "Patient_FrontPages"
+  IS '住院号不能为空；格式不做强制校验';
+
+COMMENT ON CONSTRAINT uq_patient_frontpages_inpatient_no ON "Patient_FrontPages"
+  IS '保证同一个住院号只保留一条首页记录';