pipexerp/ai-proj-helper
8
0
Fork 0
Code Issues Pull Requests 3 Actions 9 Packages Projects Releases Wiki Activity

chore(skill): 清理全部 23 条历史校验警告

Browse Source 
- 11 个超 20KB 的 SKILL.md 拆分，大章节移入 references/details.md
- 7 处非标准字段（arguments/user_invocable）移入 metadata
- 修 req-dev 4 条相对链接；validate 跳过行内代码避免 ![](...) 误报
- validate-skills.py: 23 warns -> 0 warns，0 errors
This commit is contained in:
johnQ
2026-10-31 22:21:07 +08:00
parent 7d47762303
commit 237631147a
29 changed files with 4013 additions and 3928 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills-biz/finance-plugin/skills/SKILL.md
+6 -454
View File
@@ -5,9 +5,6 @@ metadata:
invocation: user-invoked
disable-model-invocation: true
---
# 财务对账技能
## 功能概述
- **银行对账**: 银行流水 vs 系统收付款记录匹配
@@ -481,457 +478,6 @@ def export_reconciliation_to_excel(
---
## 常见对账场景
### 场景1: 月末银行对账
```python
# 1. 加载数据
bank_df = load_bank_statement('银行流水_202601.xlsx')
system_df = load_system_records('收付款记录_202601.xlsx')
# 2. 执行对账
result = reconcile(bank_df, system_df)
# 3. 查看汇总
print(f"已匹配: {result['summary']['matched_count']} 笔")
print(f"银行未达: {result['summary']['bank_only_count']} 笔, 金额 {result['summary']['bank_only_amount']:,.2f}")
print(f"企业未达: {result['summary']['system_only_count']} 笔, 金额 {result['summary']['system_only_amount']:,.2f}")
# 4. 生成调节表
report = generate_bank_reconciliation_report(
bank_balance=150000.00, # 银行对账单余额
book_balance=145000.00, # 企业账面余额
bank_only=result['bank_only'],
system_only=result['system_only'],
as_of_date='2026-01-31'
)
print(report)
# 5. 导出 Excel
export_reconciliation_to_excel(result, '银行对账_202601.xlsx', '2026-01-31')
```
### 场景2: 客户对账
```python
# 加载客户交易明细
ar_transactions = pd.read_excel('应收明细.xlsx')
# 筛选特定客户
customer_data = ar_transactions[ar_transactions['customer'] == '深圳XX公司']
# 生成对账单
statement = generate_ar_statement(
customer_name='深圳XX公司',
transactions=customer_data,
as_of_date='2026-01-31'
)
print(statement)
```
### 场景3: 账龄分析
```python
# 加载未收款数据
receivables = pd.read_excel('应收账款.xlsx')
# 账龄分析
aging = aging_analysis(
receivables=receivables,
as_of_date='2026-01-31',
aging_buckets=[30, 60, 90, 180, 365]
)
print(aging)
# 导出
aging.to_excel('账龄分析_202601.xlsx')
```
### 场景4: 扫描单据OCR识别与对账匹配（诉讼证据核对）
适用于：承运商/供应商提供扫描件作为诉讼证据，需要与我司对账单进行匹配核对。
```python
from pdf2image import convert_from_path
import pytesseract
import pandas as pd
import re
def ocr_pdf_extract_orders(pdf_path: str, dpi: int = 150) -> pd.DataFrame:
"""
从 PDF 扫描件中 OCR 提取订单信息
Args:
pdf_path: PDF 文件路径
dpi: 图像分辨率，越高识别越准但速度越慢
Returns:
DataFrame 包含 order_no, page, tc_no 等字段
"""
print(f"正在转换 PDF...")
images = convert_from_path(pdf_path, dpi=dpi)
print(f"共 {len(images)} 页，开始 OCR 识别...")
all_records = []
for i, img in enumerate(images, 1):
if i % 10 == 0:
print(f" 处理进度: {i}/{len(images)}")
text = pytesseract.image_to_string(img, lang='chi_sim+eng')
# 提取多种订单号格式（根据实际业务调整）
hm_orders = re.findall(r'(HM\d{12,15})(?:-\d+)?', text) # 华住订单
hpo_orders = re.findall(r'(HPO-\d{8}-\d+)', text) # 华住采购订单
fy_orders = re.findall(r'(FY\d{9,})', text) # 凤悦订单
phgco_orders = re.findall(r'(PHGCO\d{9,})', text) # 锦江订单
tc_orders = re.findall(r'(TC\d{8,})', text) # 运单号
# 提取日期
dates = re.findall(r'(\d{4}-\d{2}-\d{2})', text)
all_orders = hm_orders + hpo_orders + fy_orders + phgco_orders
for order in all_orders:
all_records.append({
'order_no': order,
'page': i,
'tc_no': tc_orders[0] if tc_orders else None,
'date': dates[0] if dates else None,
'raw_text': text[:500] # 保留部分原文用于核查
})
df = pd.DataFrame(all_records)
df = df.drop_duplicates(subset=['order_no'])
print(f"提取完成，共 {len(df)} 条唯一订单")
return df
def extract_base_order_no(order_no: str) -> str:
"""
提取基础订单号（移除后缀如 -1, -2）
例如: HM202505227320-1 -> HM202505227320
"""
if pd.isna(order_no):
return None
order_str = str(order_no)
match = re.match(r'(HM\d{12,15}|HPO-\d{8}-\d+|FY\d{9,}|PHGCO\d{9,})', order_str)
return match.group(1) if match else order_str
def reconcile_scanned_with_excel(
scanned_df: pd.DataFrame,
excel_path: str,
main_sheet: str,
pending_sheet: str = None,
order_column: str = '华住/锦江订单号'
) -> dict:
"""
扫描单据与 Excel 对账单匹配
Args:
scanned_df: OCR 提取的订单 DataFrame
excel_path: Excel 对账单路径
main_sheet: 主数据 Sheet 名称
pending_sheet: 待结算/次月结 Sheet 名称（可选）
order_column: 订单号列名
Returns:
{
'matched_main': 在主表中匹配的订单,
'matched_pending': 在待结算表中匹配的订单,
'not_found': 未找到的订单,
'summary': 汇总统计
}
"""
# 加载主表
df_main = pd.read_excel(excel_path, sheet_name=main_sheet)
# 处理表头（如果第一行是表头）
if df_main.iloc[0].astype(str).str.contains(order_column).any():
df_main.columns = df_main.iloc[0]
df_main = df_main.iloc[1:].reset_index(drop=True)
# 提取基础订单号
main_orders = set(df_main[order_column].apply(extract_base_order_no).dropna())
# 加载待结算表（如有）
pending_orders = set()
df_pending = None
if pending_sheet:
try:
df_pending = pd.read_excel(excel_path, sheet_name=pending_sheet)
pending_orders = set(df_pending[order_column].apply(extract_base_order_no).dropna())
except:
pass
all_excel_orders = main_orders | pending_orders
# 扫描件订单号
scan_orders = set(scanned_df['order_no'].apply(extract_base_order_no).dropna())
# 匹配分析
matched_main = scan_orders & main_orders
matched_pending = scan_orders & pending_orders
not_found = scan_orders - all_excel_orders
# 汇总
summary = {
'scan_total': len(scan_orders),
'matched_main_count': len(matched_main),
'matched_pending_count': len(matched_pending),
'not_found_count': len(not_found),
'match_rate': (len(matched_main) + len(matched_pending)) / len(scan_orders) * 100 if scan_orders else 0
}
return {
'matched_main': matched_main,
'matched_pending': matched_pending,
'not_found': not_found,
'summary': summary,
'df_main': df_main,
'df_pending': df_pending
}
def generate_litigation_reconciliation_report(
result: dict,
scanned_df: pd.DataFrame,
output_path: str
):
"""
生成诉讼对账分析报告
"""
summary = result['summary']
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Sheet1: 汇总
summary_df = pd.DataFrame({
'项目': [
'扫描件订单数',
'在主对账单中找到',
'在待结算表中找到',
'完全未找到',
'匹配率'
],
'数值': [
summary['scan_total'],
summary['matched_main_count'],
summary['matched_pending_count'],
summary['not_found_count'],
f"{summary['match_rate']:.1f}%"
]
})
summary_df.to_excel(writer, sheet_name='对账汇总', index=False)
# Sheet2: 未找到的订单
if result['not_found']:
not_found_df = scanned_df[
scanned_df['order_no'].apply(extract_base_order_no).isin(result['not_found'])
][['order_no', 'page', 'tc_no', 'date']]
not_found_df.columns = ['订单号', 'PDF页码', '运单号', '日期']
not_found_df.to_excel(writer, sheet_name='未找到订单', index=False)
# Sheet3: 待结算订单详情
if result['matched_pending'] and result['df_pending'] is not None:
pending_detail = result['df_pending'][
result['df_pending']['华住/锦江订单号'].apply(extract_base_order_no).isin(result['matched_pending'])
]
pending_detail.to_excel(writer, sheet_name='待结算订单', index=False)
print(f"报告已保存: {output_path}")
```
#### 使用示例
```python
# 1. 从 PDF 扫描件提取订单
pdf_path = "承运商证据_6月业务.pdf"
scanned_df = ocr_pdf_extract_orders(pdf_path, dpi=150)
# 2. 与 Excel 对账单匹配
result = reconcile_scanned_with_excel(
scanned_df=scanned_df,
excel_path="对账单_2025年6月.xlsx",
main_sheet="2025.6",
pending_sheet="次月结",
order_column="华住/锦江订单号"
)
# 3. 查看匹配结果
print(f"匹配率: {result['summary']['match_rate']:.1f}%")
print(f"未找到: {result['summary']['not_found_count']} 条")
if result['not_found']:
print("\n未找到的订单:")
for order in result['not_found']:
print(f" {order}")
# 4. 生成报告
generate_litigation_reconciliation_report(
result=result,
scanned_df=scanned_df,
output_path="诉讼对账分析报告.xlsx"
)
```
#### OCR 识别注意事项
1. **环境依赖**:
```bash
# macOS
brew install tesseract tesseract-lang poppler
pip install pdf2image pytesseract pandas openpyxl
```
2. **识别精度**:
- DPI 150 适合快速扫描，DPI 200-250 适合精确识别
- 中文识别需要 `chi_sim` 语言包
3. **订单号格式差异**:
- PDF 中可能是 `HM202505227320`
- Excel 中可能是 `HM202505227320-1`、`HM202505227320-2`（带后缀）
- 匹配时应使用基础订单号
4. **常见问题**:
- 空白页（签收单背面）会被自动跳过
- OCR 可能误识别字符（如 5→S, 0→O），建议人工抽查
- 大 PDF 处理较慢，可先用低 DPI 预览
5. **"次月结"/"待结算" 订单**:
- 这类订单通常标记为"没有报价"、"未建单"等
- 虽然在系统中有记录，但可能未计入正式结算金额
- 诉讼中需特别关注这类订单的状态
6. **多承运商订单归属校验（重要风险点）**:
- 承运商可能将其他公司的订单混入证据，企图多收运费
- 必须检查PDF订单是否出现在其他承运商的对账单中
- 如果订单同时出现在多个承运商对账单中，则为异常订单
#### 多承运商订单归属校验
```python
def check_order_ownership(
scanned_df: pd.DataFrame,
my_company_excel: str,
other_carrier_excels: list[str],
order_column: str = '华住/锦江订单号'
) -> dict:
"""
检查订单归属，识别是否有其他承运商的订单被混入
Args:
scanned_df: OCR 提取的订单 DataFrame
my_company_excel: 我司对账单路径
other_carrier_excels: 其他承运商对账单路径列表
order_column: 订单号列名
Returns:
{
'my_orders': 属于我司的订单,
'other_carrier_orders': 属于其他承运商的订单（异常）,
'disputed_orders': 同时出现在多处的争议订单,
'summary': 汇总
}
"""
# 提取PDF订单
scan_orders = set(scanned_df['order_no'].apply(extract_base_order_no).dropna())
# 加载我司对账单订单
my_orders = set()
try:
xl = pd.ExcelFile(my_company_excel)
for sheet in xl.sheet_names:
df = pd.read_excel(my_company_excel, sheet_name=sheet)
for col in df.columns:
if '订单' in str(col):
orders = df[col].apply(extract_base_order_no).dropna()
my_orders.update(orders)
except Exception as e:
print(f"加载我司对账单失败: {e}")
# 加载其他承运商对账单订单
other_orders = {} # {carrier_name: set of orders}
for excel_path in other_carrier_excels:
carrier_name = excel_path.split('/')[-1]
carrier_orders = set()
try:
xl = pd.ExcelFile(excel_path)
for sheet in xl.sheet_names:
df = pd.read_excel(excel_path, sheet_name=sheet)
for col in df.columns:
if '订单' in str(col):
orders = df[col].apply(extract_base_order_no).dropna()
carrier_orders.update(orders)
other_orders[carrier_name] = carrier_orders
except:
pass
# 分析订单归属
all_other_orders = set()
for orders in other_orders.values():
all_other_orders.update(orders)
# 分类
only_mine = scan_orders & my_orders - all_other_orders # 仅在我司
only_others = scan_orders & all_other_orders - my_orders # 仅在其他承运商（异常！）
in_both = scan_orders & my_orders & all_other_orders # 同时出现（争议）
nowhere = scan_orders - my_orders - all_other_orders # 哪里都没有
# 识别异常订单属于哪个承运商
abnormal_details = []
for order in only_others:
for carrier, orders in other_orders.items():
if order in orders:
page = scanned_df[scanned_df['order_no'].apply(extract_base_order_no) == order]['page'].values
abnormal_details.append({
'order_no': order,
'belongs_to': carrier,
'pdf_page': page[0] if len(page) > 0 else None
})
summary = {
'scan_total': len(scan_orders),
'my_orders_count': len(only_mine),
'other_carrier_count': len(only_others), # 异常订单数
'disputed_count': len(in_both),
'not_found_count': len(nowhere)
}
return {
'my_orders': only_mine,
'other_carrier_orders': only_others,
'abnormal_details': abnormal_details,
'disputed_orders': in_both,
'not_found': nowhere,
'summary': summary
}
```
#### 使用示例（多承运商校验）
```python
# 检查订单归属
result = check_order_ownership(
scanned_df=scanned_df,
my_company_excel="智慧云彩对账单_2025年6月.xlsx",
other_carrier_excels=[
"友利速运对账单_2025年6月.xlsx",
"其他承运商对账单.xlsx"
]
)
# 检查是否有异常订单
if result['summary']['other_carrier_count'] > 0:
print(f"⚠️ 发现 {result['summary']['other_carrier_count']} 个异常订单！")
print("这些订单属于其他承运商，不应由我司支付：")
for item in result['abnormal_details']:
print(f" {item['order_no']} -> 属于 {item['belongs_to']} (PDF第{item['pdf_page']}页)")
else:
print("✓ 未发现异常订单，所有订单归属正确")
```
---
## 注意事项
1. **数据格式统一**: 确保日期、金额格式一致后再对账
@@ -949,3 +495,9 @@ else:
- **data-excel**: 处理复杂的 Excel 数据转换
- **feishu**: 将对账报告保存到飞书云文档
- **siyuan**: 记录对账工作日志到思源笔记
## 详细内容
以下章节已移到 [references/details.md](references/details.md)：
- 常见对账场景
skills-biz/finance-plugin/skills/references/details.md
+453
View File
@@ -0,0 +1,453 @@
# skills 详细内容
## 常见对账场景
### 场景1: 月末银行对账
```python
# 1. 加载数据
bank_df = load_bank_statement('银行流水_202601.xlsx')
system_df = load_system_records('收付款记录_202601.xlsx')
# 2. 执行对账
result = reconcile(bank_df, system_df)
# 3. 查看汇总
print(f"已匹配: {result['summary']['matched_count']} 笔")
print(f"银行未达: {result['summary']['bank_only_count']} 笔, 金额 {result['summary']['bank_only_amount']:,.2f}")
print(f"企业未达: {result['summary']['system_only_count']} 笔, 金额 {result['summary']['system_only_amount']:,.2f}")
# 4. 生成调节表
report = generate_bank_reconciliation_report(
bank_balance=150000.00, # 银行对账单余额
book_balance=145000.00, # 企业账面余额
bank_only=result['bank_only'],
system_only=result['system_only'],
as_of_date='2026-01-31'
)
print(report)
# 5. 导出 Excel
export_reconciliation_to_excel(result, '银行对账_202601.xlsx', '2026-01-31')
```
### 场景2: 客户对账
```python
# 加载客户交易明细
ar_transactions = pd.read_excel('应收明细.xlsx')
# 筛选特定客户
customer_data = ar_transactions[ar_transactions['customer'] == '深圳XX公司']
# 生成对账单
statement = generate_ar_statement(
customer_name='深圳XX公司',
transactions=customer_data,
as_of_date='2026-01-31'
)
print(statement)
```
### 场景3: 账龄分析
```python
# 加载未收款数据
receivables = pd.read_excel('应收账款.xlsx')
# 账龄分析
aging = aging_analysis(
receivables=receivables,
as_of_date='2026-01-31',
aging_buckets=[30, 60, 90, 180, 365]
)
print(aging)
# 导出
aging.to_excel('账龄分析_202601.xlsx')
```
### 场景4: 扫描单据OCR识别与对账匹配（诉讼证据核对）
适用于：承运商/供应商提供扫描件作为诉讼证据，需要与我司对账单进行匹配核对。
```python
from pdf2image import convert_from_path
import pytesseract
import pandas as pd
import re
def ocr_pdf_extract_orders(pdf_path: str, dpi: int = 150) -> pd.DataFrame:
"""
从 PDF 扫描件中 OCR 提取订单信息
Args:
pdf_path: PDF 文件路径
dpi: 图像分辨率，越高识别越准但速度越慢
Returns:
DataFrame 包含 order_no, page, tc_no 等字段
"""
print(f"正在转换 PDF...")
images = convert_from_path(pdf_path, dpi=dpi)
print(f"共 {len(images)} 页，开始 OCR 识别...")
all_records = []
for i, img in enumerate(images, 1):
if i % 10 == 0:
print(f" 处理进度: {i}/{len(images)}")
text = pytesseract.image_to_string(img, lang='chi_sim+eng')
# 提取多种订单号格式（根据实际业务调整）
hm_orders = re.findall(r'(HM\d{12,15})(?:-\d+)?', text) # 华住订单
hpo_orders = re.findall(r'(HPO-\d{8}-\d+)', text) # 华住采购订单
fy_orders = re.findall(r'(FY\d{9,})', text) # 凤悦订单
phgco_orders = re.findall(r'(PHGCO\d{9,})', text) # 锦江订单
tc_orders = re.findall(r'(TC\d{8,})', text) # 运单号
# 提取日期
dates = re.findall(r'(\d{4}-\d{2}-\d{2})', text)
all_orders = hm_orders + hpo_orders + fy_orders + phgco_orders
for order in all_orders:
all_records.append({
'order_no': order,
'page': i,
'tc_no': tc_orders[0] if tc_orders else None,
'date': dates[0] if dates else None,
'raw_text': text[:500] # 保留部分原文用于核查
})
df = pd.DataFrame(all_records)
df = df.drop_duplicates(subset=['order_no'])
print(f"提取完成，共 {len(df)} 条唯一订单")
return df
def extract_base_order_no(order_no: str) -> str:
"""
提取基础订单号（移除后缀如 -1, -2）
例如: HM202505227320-1 -> HM202505227320
"""
if pd.isna(order_no):
return None
order_str = str(order_no)
match = re.match(r'(HM\d{12,15}|HPO-\d{8}-\d+|FY\d{9,}|PHGCO\d{9,})', order_str)
return match.group(1) if match else order_str
def reconcile_scanned_with_excel(
scanned_df: pd.DataFrame,
excel_path: str,
main_sheet: str,
pending_sheet: str = None,
order_column: str = '华住/锦江订单号'
) -> dict:
"""
扫描单据与 Excel 对账单匹配
Args:
scanned_df: OCR 提取的订单 DataFrame
excel_path: Excel 对账单路径
main_sheet: 主数据 Sheet 名称
pending_sheet: 待结算/次月结 Sheet 名称（可选）
order_column: 订单号列名
Returns:
{
'matched_main': 在主表中匹配的订单,
'matched_pending': 在待结算表中匹配的订单,
'not_found': 未找到的订单,
'summary': 汇总统计
}
"""
# 加载主表
df_main = pd.read_excel(excel_path, sheet_name=main_sheet)
# 处理表头（如果第一行是表头）
if df_main.iloc[0].astype(str).str.contains(order_column).any():
df_main.columns = df_main.iloc[0]
df_main = df_main.iloc[1:].reset_index(drop=True)
# 提取基础订单号
main_orders = set(df_main[order_column].apply(extract_base_order_no).dropna())
# 加载待结算表（如有）
pending_orders = set()
df_pending = None
if pending_sheet:
try:
df_pending = pd.read_excel(excel_path, sheet_name=pending_sheet)
pending_orders = set(df_pending[order_column].apply(extract_base_order_no).dropna())
except:
pass
all_excel_orders = main_orders | pending_orders
# 扫描件订单号
scan_orders = set(scanned_df['order_no'].apply(extract_base_order_no).dropna())
# 匹配分析
matched_main = scan_orders & main_orders
matched_pending = scan_orders & pending_orders
not_found = scan_orders - all_excel_orders
# 汇总
summary = {
'scan_total': len(scan_orders),
'matched_main_count': len(matched_main),
'matched_pending_count': len(matched_pending),
'not_found_count': len(not_found),
'match_rate': (len(matched_main) + len(matched_pending)) / len(scan_orders) * 100 if scan_orders else 0
}
return {
'matched_main': matched_main,
'matched_pending': matched_pending,
'not_found': not_found,
'summary': summary,
'df_main': df_main,
'df_pending': df_pending
}
def generate_litigation_reconciliation_report(
result: dict,
scanned_df: pd.DataFrame,
output_path: str
):
"""
生成诉讼对账分析报告
"""
summary = result['summary']
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Sheet1: 汇总
summary_df = pd.DataFrame({
'项目': [
'扫描件订单数',
'在主对账单中找到',
'在待结算表中找到',
'完全未找到',
'匹配率'
],
'数值': [
summary['scan_total'],
summary['matched_main_count'],
summary['matched_pending_count'],
summary['not_found_count'],
f"{summary['match_rate']:.1f}%"
]
})
summary_df.to_excel(writer, sheet_name='对账汇总', index=False)
# Sheet2: 未找到的订单
if result['not_found']:
not_found_df = scanned_df[
scanned_df['order_no'].apply(extract_base_order_no).isin(result['not_found'])
][['order_no', 'page', 'tc_no', 'date']]
not_found_df.columns = ['订单号', 'PDF页码', '运单号', '日期']
not_found_df.to_excel(writer, sheet_name='未找到订单', index=False)
# Sheet3: 待结算订单详情
if result['matched_pending'] and result['df_pending'] is not None:
pending_detail = result['df_pending'][
result['df_pending']['华住/锦江订单号'].apply(extract_base_order_no).isin(result['matched_pending'])
]
pending_detail.to_excel(writer, sheet_name='待结算订单', index=False)
print(f"报告已保存: {output_path}")
```
#### 使用示例
```python
# 1. 从 PDF 扫描件提取订单
pdf_path = "承运商证据_6月业务.pdf"
scanned_df = ocr_pdf_extract_orders(pdf_path, dpi=150)
# 2. 与 Excel 对账单匹配
result = reconcile_scanned_with_excel(
scanned_df=scanned_df,
excel_path="对账单_2025年6月.xlsx",
main_sheet="2025.6",
pending_sheet="次月结",
order_column="华住/锦江订单号"
)
# 3. 查看匹配结果
print(f"匹配率: {result['summary']['match_rate']:.1f}%")
print(f"未找到: {result['summary']['not_found_count']} 条")
if result['not_found']:
print("\n未找到的订单:")
for order in result['not_found']:
print(f" {order}")
# 4. 生成报告
generate_litigation_reconciliation_report(
result=result,
scanned_df=scanned_df,
output_path="诉讼对账分析报告.xlsx"
)
```
#### OCR 识别注意事项
1. **环境依赖**:
```bash
# macOS
brew install tesseract tesseract-lang poppler
pip install pdf2image pytesseract pandas openpyxl
```
2. **识别精度**:
- DPI 150 适合快速扫描，DPI 200-250 适合精确识别
- 中文识别需要 `chi_sim` 语言包
3. **订单号格式差异**:
- PDF 中可能是 `HM202505227320`
- Excel 中可能是 `HM202505227320-1`、`HM202505227320-2`（带后缀）
- 匹配时应使用基础订单号
4. **常见问题**:
- 空白页（签收单背面）会被自动跳过
- OCR 可能误识别字符（如 5→S, 0→O），建议人工抽查
- 大 PDF 处理较慢，可先用低 DPI 预览
5. **"次月结"/"待结算" 订单**:
- 这类订单通常标记为"没有报价"、"未建单"等
- 虽然在系统中有记录，但可能未计入正式结算金额
- 诉讼中需特别关注这类订单的状态
6. **多承运商订单归属校验（重要风险点）**:
- 承运商可能将其他公司的订单混入证据，企图多收运费
- 必须检查PDF订单是否出现在其他承运商的对账单中
- 如果订单同时出现在多个承运商对账单中，则为异常订单
#### 多承运商订单归属校验
```python
def check_order_ownership(
scanned_df: pd.DataFrame,
my_company_excel: str,
other_carrier_excels: list[str],
order_column: str = '华住/锦江订单号'
) -> dict:
"""
检查订单归属，识别是否有其他承运商的订单被混入
Args:
scanned_df: OCR 提取的订单 DataFrame
my_company_excel: 我司对账单路径
other_carrier_excels: 其他承运商对账单路径列表
order_column: 订单号列名
Returns:
{
'my_orders': 属于我司的订单,
'other_carrier_orders': 属于其他承运商的订单（异常）,
'disputed_orders': 同时出现在多处的争议订单,
'summary': 汇总
}
"""
# 提取PDF订单
scan_orders = set(scanned_df['order_no'].apply(extract_base_order_no).dropna())
# 加载我司对账单订单
my_orders = set()
try:
xl = pd.ExcelFile(my_company_excel)
for sheet in xl.sheet_names:
df = pd.read_excel(my_company_excel, sheet_name=sheet)
for col in df.columns:
if '订单' in str(col):
orders = df[col].apply(extract_base_order_no).dropna()
my_orders.update(orders)
except Exception as e:
print(f"加载我司对账单失败: {e}")
# 加载其他承运商对账单订单
other_orders = {} # {carrier_name: set of orders}
for excel_path in other_carrier_excels:
carrier_name = excel_path.split('/')[-1]
carrier_orders = set()
try:
xl = pd.ExcelFile(excel_path)
for sheet in xl.sheet_names:
df = pd.read_excel(excel_path, sheet_name=sheet)
for col in df.columns:
if '订单' in str(col):
orders = df[col].apply(extract_base_order_no).dropna()
carrier_orders.update(orders)
other_orders[carrier_name] = carrier_orders
except:
pass
# 分析订单归属
all_other_orders = set()
for orders in other_orders.values():
all_other_orders.update(orders)
# 分类
only_mine = scan_orders & my_orders - all_other_orders # 仅在我司
only_others = scan_orders & all_other_orders - my_orders # 仅在其他承运商（异常！）
in_both = scan_orders & my_orders & all_other_orders # 同时出现（争议）
nowhere = scan_orders - my_orders - all_other_orders # 哪里都没有
# 识别异常订单属于哪个承运商
abnormal_details = []
for order in only_others:
for carrier, orders in other_orders.items():
if order in orders:
page = scanned_df[scanned_df['order_no'].apply(extract_base_order_no) == order]['page'].values
abnormal_details.append({
'order_no': order,
'belongs_to': carrier,
'pdf_page': page[0] if len(page) > 0 else None
})
summary = {
'scan_total': len(scan_orders),
'my_orders_count': len(only_mine),
'other_carrier_count': len(only_others), # 异常订单数
'disputed_count': len(in_both),
'not_found_count': len(nowhere)
}
return {
'my_orders': only_mine,
'other_carrier_orders': only_others,
'abnormal_details': abnormal_details,
'disputed_orders': in_both,
'not_found': nowhere,
'summary': summary
}
```
#### 使用示例（多承运商校验）
```python
# 检查订单归属
result = check_order_ownership(
scanned_df=scanned_df,
my_company_excel="智慧云彩对账单_2025年6月.xlsx",
other_carrier_excels=[
"友利速运对账单_2025年6月.xlsx",
"其他承运商对账单.xlsx"
]
)
# 检查是否有异常订单
if result['summary']['other_carrier_count'] > 0:
print(f"⚠️ 发现 {result['summary']['other_carrier_count']} 个异常订单！")
print("这些订单属于其他承运商，不应由我司支付：")
for item in result['abnormal_details']:
print(f" {item['order_no']} -> 属于 {item['belongs_to']} (PDF第{item['pdf_page']}页)")
else:
print("✓ 未发现异常订单，所有订单归属正确")
```
---