Document

Available in Classic and VPC

In NAVER Cloud Platform console's CLOVA OCR > Domain, you can create and manage Document domains equipped with a specialized model engine that understands document's semantic structure based on machine learning, and automatically extracts entered information (key values). Document OCR is provided after an advance request and approval process as personal and sensitive information may be included in receipts, IDs, and business cards. We provide guidance about how to process personal and sensitive information (Reference Architecture, etc.) through the advance approval process.
This guide describes how to create and use Document-type domains. For more information on viewing, deleting, and copying a domain list, as well as integrating with API Gateway, see Domain.

Create domain

The following describes how to create a domain whose service type is Template.

1. From the NAVER Cloud Platform console's Region menu, click and select the region you're using.
2. From the Platform menu, click to select between VPC and Classic.
3. Click the Services > AI Services > CLOVA OCR menu in order.
4. Click the Domain menu.
5. Click the [Create domain] button, and then click the [Specialized model] button.
6. When the Create domain pop-up window appears, enter the required information.
   • Domain name: enter a name between 1 to 50 characters using Korean letters, English uppercase and lowercase letters, Chinese letters, Japanese letters, numbers, and full/half-width special characters (& 。_ - × 々), and click the [Check] button to check for duplicates.
   • Domain code: enter a code between 1 to 50 characters excluding spaces using English uppercase and lowercase letters and special characters (.?&。_-×々), and then click the [Check] button to check for duplicates.
   • Service type: check for Document.
   • Recognition model (Specific): click to select the specialized model to be recognized by the domain.
     • Business registration certificate (KR): recognizes (individual/corporate) business registration certificate, proof of business registration, mail order distributor registration certificate, business declaration certificate, and certificate of registered seal
     • Credit card (Global): extracts card numbers and expiration date, supports recognition of vertical format credit card
     • Receipt (KR): extracts key information such as store information, payment details, payment method, amount, etc.
     • ID (KR): recognizes resident registration certificate, driver's license, and passport (KR and Global)
     • Business card (KR/EN/JP): extracts information such as name, company name, department, phone number, address, email, etc.
   • Service plan: click to select the service plan applicable for the domain.
7. Click the [Create domain] button.

Set specialized model

To create Document-type domains, you need to subscribe to specialized models. You can subscribe to specialized models in the NAVER Cloud Platform console. The request for business collaboration received through the console will be reviewed by the NAVER Cloud Platform personnel in charge, and then you will receive a response with additional information to be confirmed or necessary tasks afterward. It may take NAVER Cloud Platform a certain period (days) to complete the approval of the subscription request. The following describes how to subscribe to a specialized model.

1. From the NAVER Cloud Platform console's Region menu, click and select the region you're using.
2. From the Platform menu, click to select between VPC and Classic.
3. Click the Services > AI Services > CLOVA OCR menu in order.
4. Click the Domain menu.
5. Click the [Set specialized model] button.
6. When the list of specialized models appears, check the content and status of each specialized model.
   • Specialized model: specialized model type
   • Supported language: types of languages that can be recognized in the specialized model
   • Detailed description: description of the specialized model
   • Request status: specialized model availability status
     • Available: status where the subscription request of the specialized model has been completed and domains whose service type is Document can be created
     • Approval pending: status where the approval status of the specialized model subscription request is being reviewed by the personnel in charge
     • Approval rejected: status where the approval of the specialized model subscription request has been rejected
     • Not requested: status where a specialized model subscription request is required
7. Click the [Request specialized model] button.
8. When the agreement for technical and administrative levels for CLOVA OCR (specialized model) service pop-up window appears, click Read and agree to the CLOVA OCR Terms of service.
9. Click the [OK] button.
10. When the Set specialized model pop-up window appears, enter the required information.
    • Specialized model: click to select the specialized model you want to request.
    • Purpose of use: purpose of subscribing to the specialized model <example> services using specialized models (shopping mall, bookkeeping, etc.), internal document management, consignment of document management, reselling, software and hardware mounting, others
    • Usage time: usage period of specialized model <example> 00/00
    • Estimated usage: estimated usage of the specialized model <example> Specialized model for business registration certificate (KR) 30,000 monthly API calls
    • Details: enter focusing on actual usage scenarios. <example> Operating a shopping mall, using specialized model for credit cards when registering customer credit cards
11. Click the [OK] button.

Integrating with API Gateway

The following shows how to integrate the API Gateway to set the Invoke URL for Document OCR.

1. From the NAVER Cloud Platform console's Region menu, click and select the region you're using.
2. From the Platform menu, click to select between VPC and Classic.
3. Click the Services > AI Services > CLOVA OCR menu in order.
4. Click the Domain menu.
5. Click the [API Gateway integration] button of a Document domain.
6. When the Document OCR pop-up window appears, set up the required information.
   • For detailed integration methods, see Integrating with API Gateway of Domain.

Call API

Once you complete the invoke URL settings of Document OCR, you can enter images by calling the API provided by CLOVA OCR, and get the recognized value. For more information on calling the API, see the following guide.

• CLOVA OCR API guide