인터페이스는 현지화되어 있으며, Skill 소개와 설명 문서는 선택한 언어로 AI가 자동 번역합니다. 코드·명령어·경로·전문 용어는 원문을 유지하며 원작자 문서가 우선합니다.
Skills 둘러보기
문서 및 사무 · SKILL.md

china-kyc-doc-parse

china-kyc-doc-parse

Parse and extract data from Chinese identity documents for KYC (Know Your Customer) compliance. Adapts the original kyc-doc-parse skill for Chinese ID cards, business licenses, and domestic compliance requirements. Triggers on "A股KYC", "身份文件解析", "parse Chinese ID", "KYC document", "客户身份识别", or "extract [document type]".

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill 문서

GitHub

name: china-kyc-doc-parse description: Parse and extract data from Chinese identity documents for KYC (Know Your Customer) compliance. Adapts the original kyc-doc-parse skill for Chinese ID cards, business licenses, and domestic compliance requirements. Triggers on "A股KYC", "身份文件解析", "parse Chinese ID", "KYC document", "客户身份识别", or "extract [document type]".

china-kyc-doc-parse

Purpose

Parse 中国身份文件 — extract and verify data from Chinese KYC documents.

Data Sources

Tier 0 — 万得 Wind(最全面付费数据)

  • 覆盖:A股/港美股/基金/指数/债券/宏观/研报/分析(44个工具)
  • MCP 服务:wind-mcp(需 WIND_API_KEY 密钥,以 ak_ 开头)
  • 优势:全市场覆盖面最广、数据最全面、包含研报和量化分析
  • 密钥申请:https://aifinmarket.wind.com.cn/#/home

Tier 1 — 同花顺 iFind(付费精确数据)/ AkShare MCP(Tier-2 免费备选)

# Not typically used for KYC; for background checks:
get_stock_info(ticker)                    → Company verification (if applicable)

Secondary Sources

  • 国家企业信用信息公示系统 — business license verification
  • 天眼查 / 企查查 — corporate information
  • 公安部 — ID verification (via approved channels)

Document Types

1. 个人身份证 (Personal ID Card)

Front of ID card:

FieldLocationData Type
姓名Upper sectionText
性别Below name男/女
民族Below genderText (e.g., 汉)
出生日期Below ethnicityYYYY年MM月DD日
住址Lower sectionAddress
公民身份号码Lower section18-digit number

Back of ID card:

FieldDescription
签发机关Issuing authority
有效期限Validity period
证件签发Issue date
证件失效Expiry date

ID number structure:

PositionLengthContent
1-66 digitsAddress code (行政区划)
7-148 digitsBirth date (YYYYMMDD)
15-173 digitsOrder code + gender (odd=male, even=female)
181 digitCheck digit

2. 营业执照 (Business License)

Unified Social Credit Code (统一社会信用代码):

StructureLengthContent
登记管理部门代码1 digit9=工商, 1=机构编制, etc.
机构类别代码1 digit
登记管理机关行政区划码6 digits
主体标识码9 digitsOrg code
校验码1 digitCheck digit

Business license fields:

FieldContent
统一社会信用代码18-digit code
名称Company name
类型Entity type
法定代表人Legal representative
注册资本Registered capital
成立日期Establishment date
住所Registered address
经营范围Business scope
登记机关Registration authority
登记日期Registration date

3. 护照 (Passport)

FieldContent
护照号码Letter + 8 digits
姓名Chinese + Pinyin
国籍Nationality
出生日期DD/MM/YYYY
性别M/F
出生地点Place of birth
签发日期Issue date
有效期至Expiry date
签发机关Issuing authority

4. 港澳通行证 / 台湾通行证

FieldContent
证件号码HK/Macau/Taiwan travel permit number
姓名Name
出生日期DOB
性别Gender
有效期至Expiry date

5. 外国人居留许可证

FieldContent
姓名Name (native + Chinese)
国籍Nationality
出生日期DOB
性别Gender
有效期至Expiry date
签发机关Issuing authority

Parsing Workflow

Step 1: Document Intake

Document verification:

CheckPass Criteria
照片清晰Photo clear enough to read
文字清晰Text legible
无遮挡No obstruction of key fields
证件在有效期内Not expired
证件真实Genuine appearance

Step 2: Data Extraction

Extraction checklist:

DocumentFields to Extract
身份证Name, ID number, DOB, gender, address
营业执照Company name, USCC, legal rep, registered capital, scope
护照Passport number, name, nationality, DOB, expiry
其他As applicable

Step 3: ID Number Validation

ID number checks:

CheckMethodPass
Length18 digits✓
Birth dateValid date✓
GenderOdd/even check✓
Check digitMod 11 algorithm✓
Address codeValid code✓

Check digit algorithm:

Weights: 7, 9, 10, 5, 8, 4, 2, 1, 6, 3, 7, 9, 10, 5, 8, 4, 2
Remainder → 0-10 → Code: 10→X, 0→1, 1→0, 2→9, ...

Step 4: Address Code Decoding

Address code lookup:

CodeProvince/City
11北京
31上海
44广东
33浙江
32江苏
......

Step 5: Data Normalization

Normalization rules:

FieldNormalization
NameTrim whitespace, no middle dots
ID numberUppercase X for check digit
DOBYYYY-MM-DD format
AddressStandardize
Phone+86 format
Registered capitalConvert to 万元
DatesYYYY-MM-DD format

Step 6: Quality Checks

Extraction quality:

CheckPass
All required fields extracted✓
Data format correct✓
ID number validated✓
Dates valid✓
No OCR errors✓

China-Specific Considerations

Anti-Money Laundering (AML)

RequirementImplementation
客户身份识别Identify and verify customer
受益所有人Ultimate beneficial owner
持续识别Ongoing monitoring
风险分类Risk categorization
身份证明文件Minimum documents required

Required Documents by Customer Type

TypeRequired
中国个人身份证
外国个人护照 + 居留许可
中国企业营业执照 + 法人身份证
外国企业注册文件 + 授权代表证件

Common Issues

IssueResolution
照片模糊Request clearer copy
证件过期Request current document
信息矛盾Verify with other sources
扫描不全Request complete document

Quality Checks

Before completing:

  • All fields extracted
  • Data validated
  • Documents verified
  • AML checks performed
  • Records complete

Data Source Mode Switch: Set env var IFIND_DATA_SOURCE_MODE to control data source preference.

  • ifind-only (strict): Use iFind only, error if unavailable
  • ifind-fallback (default): iFind preferred, fallback to AkShare
  • akshare-only: Skip iFind, use AkShare only
  • wind-only: Wind only, error if unavailable
  • wind-fallback: Wind first, fallback to iFind → AkShare
저장한 Skills