How Accounts Payable Operations integration with Document Intelligence works

  • Release version: Yokohama
  • Updated January 30, 2025
  • 4 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of How Accounts Payable Operations integration with Document Intelligence works

    The Accounts Payable Operations integration with Document Intelligence automates invoice processing by extracting data from invoice documents received as email attachments. This integration creates invoice records within Accounts Payable Operations, populates them with extracted data, and initiates the invoice processing workflow. It supports handling invoices with varying levels of data extraction confidence and includes error handling for transformation failures.

    Show full answer Show less

    Invoice Ingestion Process

    When an invoice is received as an email attachment, an invoice case is created in Accounts Payable Operations under the category Invoice automation and subcategory Invoice processing. The workflow varies based on the confidence level of data extraction by Document Intelligence:

    • High extraction confidence: Invoice data is automatically extracted and stored in staging tables. The system creates a draft invoice linked to the case, verifies required fields, and either auto-submits the invoice or requires manual input from an Accounts Payable Specialist if fields are missing or incomplete. Currency codes are resolved using purchase order data or user locale if unavailable. Once submitted, the invoice state changes to Received, and processing continues.
    • Low extraction confidence: Data is not automatically extracted. The Accounts Payable Specialist must review the invoice in Document Intelligence, manually enter missing data, and submit the invoice. After submission, the same verification and currency resolution steps apply as in the high-confidence scenario.
    • Transformation failure: If the entire data transformation fails, an error message prompts contacting the administrator to resolve the issue.

    Key Validation and Processing Details

    • The system ensures all required fields on the invoice and invoice lines are populated before submission. Missing fields require manual entry.
    • Invoices must have at least one invoice line record; if absent, the specialist must add one.
    • Currency codes are validated and defaulted if necessary, using purchase order information or the user’s locale.
    • After submission, the invoice enters the Received state, marking the start of further processing.

    Localization and Language Support

    Accounts Payable Operations supports multiple languages, but the out-of-the-box Document Intelligence model is trained only for English invoice extraction. For multi-language invoice processing, customers must train their own Document Intelligence models accordingly.

    Practical Implications for ServiceNow Customers

    • This integration streamlines invoice processing by reducing manual data entry via automated extraction, improving efficiency.
    • Customers should be prepared to handle low-confidence extraction cases with manual review and data correction workflows.
    • Understanding the required fields and currency handling logic is critical to ensure smooth invoice submission and processing.
    • Administrators should monitor for transformation failures and coordinate resolution when errors occur.
    • For non-English invoices, customers need to invest in training Document Intelligence models to maintain automation benefits.

    Accounts Payable Operations integration with Document Intelligence uses automated workflows to extract the required information from the invoice document received as an email attachment, creates an invoice record in Accounts Payable Operations, and adds the extracted information into the newly created invoice record.

    Invoice ingestion process flow when extraction confidence is high

    When you receive an invoice as an attachment via email from a supplier or an employee, the following occurs:
    1. An invoice case is created with category Invoice automation and subcategory Invoice processing in Accounts Payable Operations.
    2. If Document Intelligence determines that the extraction confidence is higher than the threshold value, it extracts the invoice data and stores the data in temporary staging tables.
    3. The Document Intelligence transformation process imports the invoice data from the staging tables, creates an invoice in the Draft state, and associates the invoice with the invoice processing case.
    4. The application verifies the following:
      • The required fields are populated on the invoice.
        • If the required fields aren’t populated on the invoice, the Accounts Payable Specialist is required to open the invoice, manually enter the required values in the required fields, and submit the invoice.
        • If the required fields are populated on the invoice, the invoice is auto-submitted.
      • At least one invoice line record exists for the invoice. If not, the Accounts Payable Specialist must add an invoice line record and submit the invoice.
      • If a unique currency code isn’t identified during currency transformation, the process uses the currency mentioned in the purchase order. If the currency is missing in the purchase order, the transformation process uses the session currency based on the user's locale. In this case, the Accounts Payable Specialist is required to open the invoice processing case, and enter the correct currency code in the invoice fields and submit the invoice. For more information, see Invoice data transformation logic.

      For more information about the required fields for invoice and invoice lines, see Required fields for creating an invoice.

      After the invoice is submitted, its state changes to Received. The invoice processing begins from this point. For more information, see Work on an invoice processing case.

    Invoice ingestion process flow when extraction confidence is low

    When you receive an invoice as an attachment via email from a supplier or an employee, the following occurs:
    1. An invoice case is created with category Invoice automation and subcategory Invoice processing in Accounts Payable Operations.
    2. If Document Intelligence determines that the extraction confidence is lower than the threshold value, it doesn’t extract the invoice data and as a consequence an invoice isn’t created.
    3. In this scenario, the Accounts Payable Specialist must do the following:
      1. Open the invoice processing case created in step 1.

        The case displays the following error message: Invoice has a data extraction error. Review invoice with automation to continue processing.

      2. Select Review invoice, which opens Document Intelligence and displays the invoice fields.
      3. Enter the required values into the invoice fields, and select Submit.
    4. The Document Intelligence transformation process imports the invoice data from the staging tables, creates an invoice in the Draft state, and associates the invoice with the invoice processing case.
    5. The application verifies the following:
      • The required fields are populated on the invoice.
        • If the required fields aren’t populated on the invoice, the Accounts Payable Specialist is required to open the invoice, manually enter the required values in the required fields, and submit the invoice.
        • If the required fields are populated on the invoice, the invoice is auto-submitted.
      • At least one invoice line record exists for the invoice. If not, the Accounts Payable Specialist must add an invoice line record and submit the invoice.
      • A unique currency code exists on the invoice. If a unique currency code isn’t identified during currency transformation, the process uses the currency mentioned in the purchase order. If the currency is missing in the purchase order, then the transformation process uses the session currency based on the user's locale. In this case, the Accounts Payable Specialist is required to open the invoice processing case and enter the correct currency code in the invoice fields and submit the invoice. For more information, see Invoice data transformation logic.

      For more information about the required fields for invoice and invoice lines, see Required fields for creating an invoice.

      After the invoice is submitted, its state changes to Received. The invoice processing begins from this point. For more information, see Work on an invoice processing case.

    Invoice ingestion process flow when the entire transformation process fails

    When the Document Intelligence transformation process fails entirely, the following error message is displayed on the invoice processing case:

    Invoice automation is experiencing issues. Please contact the administrator.

    You must collaborate with the administrator to resolve this issue.

    Localization information

    Accounts Payable Operations supports multiple languages. The current DocIntel model is trained to extract invoices in the English language only. If you want to process the invoice in multi-lingual languages supported by DocIntel, you must train the DocIntel model on your own.

    For more information on Document Intelligence, see Document Intelligence.