SuperAPI AI Directory

china-kyc-doc-parse

Security & auditing

View repository

Updated 10-16 09:15

About this skill

china-kyc-doc-parse

Purpose

Parse Chinese Identity Documents — extract and verify data from Chinese KYC documents.

Data Sources

Tier 0 — Wind (most comprehensive paid data)

  • Coverage: A-shares/Hong Kong and US stocks/funds/indices/bonds/macroeconomics/research reports/analysis (44 tools)
  • MCP service:wind-mcp(requires WIND_API_KEY key, starting with ak_ )
  • Advantages: widest whole-market coverage, most comprehensive data, includes research reports and quantitative analysis
  • Key application:https://aifinmarket.wind.com.cn/#/home

Tier 1 — iFind (paid precise data) / AkShare MCP (Tier-2 free alternative)

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

Secondary Sources

  • National Enterprise Credit Information Publicity System — business license verification
  • Tianyancha / Qichacha — corporate information
  • Ministry of Public Security — ID verification (via approved channels)

Document Types

1. Personal ID Card (Personal ID Card)

Front of ID card:

Field Location Data Type
Name Upper section Text
Gender Below name Male/Female
Ethnicity Below gender Text (e.g., 汉)
Date of Birth Below ethnicity YYYY年MM月DD日
Address Lower section Address
Citizen ID Number Lower section 18-digit number

Back of ID card:

Field Description
Issuing Authority Issuing authority
Validity Period Validity period
Document Issuance Issue date
Document Expiry Expiry date

ID number structure:

Position Length Content
1-6 6 digits Address code (administrative division)
7-14 8 digits Birth date (YYYYMMDD)
15-17 3 digits Order code + gender (odd=male, even=female)
18 1 digit Check digit

2. Business License (Business License)

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

Structure Length Content
Registration Authority Code 1 digit 9=Industry and Commerce, 1=Institutional Organization, etc.
Institution Category Code 1 digit
Registration Authority Administrative Division Code 6 digits
Entity Identifier Code 9 digits Org code
Check Code 1 digit Check digit

Business license fields:

Field Content
Unified Social Credit Code 18-digit code
Name Company name
Type Entity type
Legal Representative Legal representative
Registered Capital Registered capital
Date of Establishment Establishment date
Address Registered address
Business Scope Business scope
Registration Authority Registration authority
Registration Date Registration date

3. Passport (Passport)

Field Content
Passport Number Letter + 8 digits
Name Chinese + Pinyin
Nationality Nationality
Date of Birth DD/MM/YYYY
Gender M/F
Place of Birth Place of birth
Date of Issuance Issue date
Valid Until Expiry date
Issuing Authority Issuing authority

4. Hong Kong and Macau Travel Permit / Taiwan Travel Permit

Field Content
Document Number HK/Macau/Taiwan travel permit number
Name Name
Date of Birth DOB
Gender Gender
Valid Until Expiry date

5. Foreigner Residence Permit

Field Content
Name Name (native + Chinese)
Nationality Nationality
Date of Birth DOB
Gender Gender
Valid Until Expiry date
Issuing Authority Issuing authority

Parsing Workflow

Step 1: Document Intake

Document verification:

Check Pass Criteria
Photo Clear Photo clear enough to read
Text Clear Text legible
Unobstructed No obstruction of key fields
Document Within Validity Period Not expired
Document Authentic Genuine appearance

Step 2: Data Extraction

Extraction checklist:

Document Fields to Extract
ID Card Name, ID number, DOB, gender, address
Business License Company name, USCC, legal rep, registered capital, scope
Passport Passport number, name, nationality, DOB, expiry
Other As applicable

Step 3: ID Number Validation

ID number checks:

Check Method Pass
Length 18 digits ✓
Birth date Valid date ✓
Gender Odd/even check ✓
Check digit Mod 11 algorithm ✓
Address code Valid 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:

Code Province/City
11 Beijing
31 Shanghai
44 Guangdong
33 Zhejiang
32 Jiangsu
... ...

Step 5: Data Normalization

Normalization rules:

Field Normalization
Name Trim whitespace, no middle dots
ID number Uppercase X for check digit
DOB YYYY-MM-DD format
Address Standardize
Phone +86 format
Registered capital Convert to 万元
Dates YYYY-MM-DD format

Step 6: Quality Checks

Extraction quality:

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

China-Specific Considerations

Anti-Money Laundering (AML)

Requirement Implementation
Customer Identity Verification Identify and verify customer
Beneficial owner Ultimate beneficial owner
Ongoing identification Ongoing monitoring
Risk classification Risk categorization
Identity document Minimum documents required

Required Documents by Customer Type

Type Required
Chinese individual ID card
Foreign individual Passport + residence permit
Chinese enterprise Business license + legal representative's ID card
Foreign enterprise Registration documents + authorized representative's identification

Common Issues

Issue Resolution
Blurry photo Request clearer copy
Expired document Request current document
Conflicting information Verify with other sources
Incomplete scan 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