Invoice Optical Character Recognition

Last updated: 2025-02-06 16:03:48

Introduction

Invoice Optical Character Recognition (Invoice OCR) is based on industry-leading deep learning technology, providing services such as VAT invoice recognition, train ticket recognition, taxi receipt recognition, flight itinerary recognition, and tax payment certificate recognition. It supports intelligent identification of text content in images into structured text, applicable to various scenarios like corporate invoice reimbursement, financial invoice recognition, and express bill entry, significantly improving information processing efficiency.

General Invoice Recognition (Advanced Edition)

For reimbursable invoices, it supports PDF multiple pages, single page with single or multiple invoices, and mixed-type invoice recognition. Supported invoice types include: VAT invoices (special, general, roll, blockchain, toll), fully electronic invoices (special, general), non-tax invoices (general receipts, unified payment slips), fixed amount invoices, general machine-printed invoices, vehicle purchase invoices (motor vehicle sales invoices, second-hand car invoices), train tickets, taxi receipts, flight itineraries, bus tickets, ship tickets, and toll invoices, covering 14 major types of standard reimbursable invoices. It also supports intelligent identification of other invoice types not listed above.

Value-Added Tax Invoice Verification (New Edition)

Supports the accuracy verification of VAT invoices. By entering key fields of the VAT invoice, you can provide the required verification information. The API returns the actual invoice-related information, including invoice code, invoice number, invoice date, currency, consumption type, buyer's name, buyer's taxpayer identification number, seller's name, seller's taxpayer identification number, and other common fields. It supports verification of various invoice types, including special VAT invoices, general VAT invoices (including electronic general invoices, roll invoices, toll invoices), fully electronic invoices, unified motor vehicle sales invoices, special VAT invoices for the transportation industry, unified second-hand car sales invoices, and general machine-printed electronic invoices (Guangdong and Zhejiang).

VAT Invoice Recognition

Supports the structured recognition of fields for VAT invoices (special, general) and fully electronic invoices (special, general), including invoice code, invoice number, printed invoice code, printed invoice number, invoice date, total currency, check code, tax rate, total tax amount, total amount including tax, buyer's identification number, verification, seller's identification number, issuer, password area 1, password area 2, password area 3, password area 4, invoice name, buyer's name, seller's name, service name, remark, specification, quantity, unit price, currency, tax amount, payee, and other fields.

OFD Invoice Recognition

Supports the structured recognition of VAT invoices (special, general) and fully electronic invoices (special, general) in OFD format, returning invoice code, invoice number, invoice date, verification code, machine number, password area, buyer and seller information including name, taxpayer identification number, address and phone number, bank of account and account, as well as total amount including tax, issuer, payee, verifier, tax amount, and amount excluding tax.

Bank Receipt Recognition

This API supports the recognition of all fields of bank receipts, including payer's bank, recipient's bank, payer's account number, recipient account number, receipt type, receipt number, currency type, serial number, voucher number, transaction institution, transaction amount, transaction fee, date, and other field information.

Tax Payment Certificate Recognition

Supports the structured recognition of general tax payment certificates for businesses and personal tax payment certificates, including key fields such as tax number, taxpayer identification number, taxpayer name, total amount in words, total amount in figures, issuance date, tax authority, and issuer.

Medical Invoice Recognition

Medical invoice recognition currently supports the recognition of national unified outpatient invoices, national unified inpatient invoices, and some local outpatient and inpatient invoices.

Waybill Recognition

Supports the recognition of mainstream electronic waybills on the market, including fields such as recipient and sender's name, phone, address, and waybill number.

Online Ride-Hailing Itinerary Recognition

Supports the recognition of key fields in online ride-hailing itineraries, including trip start and end dates, boarding time, starting point, end, mileage, and currency.

Insurance Document Recognition

Supports the recognition of fields in common insurance claim documents, including the first page of the medical record, expense list, settlement sheet, medical invoice's name, sex, date of birth, discharge diagnosis, disease code, admission condition, etc.

Advantages

Comprehensive Capability

Supports the recognition of all types of reimbursable documents, such as VAT invoices, quota invoices, car purchase invoices, train tickets, taxi invoices, flight itineraries, electronic waybills, etc., covering many fields and providing comprehensive information.

High Accuracy

The accuracy of each field is industry-leading. For example, the identification accuracy of VAT invoices for fields such as invoice code, total amount including tax, total amount, buyer's identification number, and invoice date exceeds 95%.

Support Verification

Supports the verification of various types of invoices, including VAT (special, general), fully electronic invoices (special, general), unified invoices for motor vehicle sales, and unified invoices for second-hand car sales.

Use Cases

Corporate Expense Control and Reimbursement Management

Suitable for corporate expense control and reimbursement management systems, enabling the rapid acquisition and verification of invoice information, achieving electronic archiving of financial invoices, and improving review efficiency for expense control and reimbursement.

Finance, Taxation, and Agency Accounting

Suitable for agency accounting firms, enabling the acquisition and verification of invoice information, achieving electronic management of financial invoices, reducing manual operation and the cost of lost invoices, and improving agency accounting management efficiency.