Create custom models in Document Automation using Standard Forms

Standard Forms are fixed format document types that have a defined template, with little or no variation in the overall layout, and are typically official or legal forms, such as a W-4 (Employee Withholding Certificate) form, income tax form, or a sale deed.

With enhanced accuracy, this feature enables you to extract data from densely structured forms including those with handwritten input in the following languages: English, Dutch, French, German, Italian, Portuguese, and Spanish.

The following overview provides an end-to-end process you can use to create the Standard Forms data model, configure the learning instance, and publish the learning instance to process documents autonomously, all within the Document Automation interface.
Note: Set up your Document Automation environment, which includes configuring users, roles, and devices, and connecting the Control Room with the Automation Co-Pilot for Business Users: Set up your Document Automation environment.
  1. Evaluate your use case for Standard Forms.

    Evaluate your use case

  2. Review extraction service.

    Review extraction service

  3. Set up and configure an extraction service.

    Set up extraction service

  4. Configure Document Automation for the selected extraction service.

    Configure Document Automation with Azure AI Document Intelligence

  5. Build a data extraction model.

    Create a custom extraction model using Standard Forms

  6. Create a learning instance with the Standard Forms data model.

    Create a learning instance for standard forms

  7. Upload documents to the learning instance to test the model, fix validation errors, and verify the extracted data.

    Process documents

  8. Build a bot that uploads documents from a source folder to Document Automation.

    Build a bot to upload documents to Document Automation

  9. Transfer the Standard Forms learning instance across different Document Automation environments.

    Transfer standard forms learning instance

  10. Check the learning instance assets (process, form, and bots) into the public repository. Then, deploy the process and bots to unattended Bot Runner devices to begin processing documents in real time.

    Publish the learning instance to production

  11. Validate the processed documents for the Standard Forms learning instance.

    Validate the uploaded documents