Validating documents through Automation Co-Pilot validator

Document Automation uses Automation Co-Pilot for Business Users technology to manage the end-to-end document extraction process. Each incoming document creates a new request, which triggers the extraction process. If a document requires manual validation, Automation Co-Pilot creates a validation task and assigns it to a validation team.

When you click the Validate documents link on the Learning instances page, the Automation Co-Pilot Task Manager opens in a new tab, with the first failed document in queue.

Note: An empty page with a notification message appears in the following scenarios:
  • If you are not assigned to any validation teams, and thus do not have access to learning instances.
  • If there are no files that require validation in the learning instances to which you have access.
  • If another user is working on the remaining file in the validation queue.

Validator user interface

1. Filter the documents in your queue
The Validator opens with certain filters enabled by default to show only the documents from a specific learning instance that need validation.
2. Your task queue
The documents that match the parameters you specified in the filters pane appear here. You can switch between documents in the queue without completing validation for the current document.
3. Customize your view
Icons on the taskbar provides the following options:
  • Page: Use the forward arrow to go to the next page and the back arrow to go to the previous page. Use the page number field to enter a page number and select enter to go to the page.
  • Hide field regions: Use this option to hide the field regions so that you can review the document or section of the document without distractions.
  • Stacked View: Use this option to view documents that are in landscape mode so that you get enough room to review the field regions and values.
  • Fit to screen: Use this option to reset the page zoom level and to return to the default page zoom level.
  • Zoom in: Use this option to zoom in to a section of the document to mark, modify, or review a field region.
  • Zoom out: Use this option to zoom out of the document.
4. You can toggle between the Table and Detail views
Detail view: We recommend that you perform validation tasks in the Detail view because this view shows all the documents in the validation queue side by side with the document that you are currently validating. Additionally, when you finish validating a document, the next document in the queue automatically opens.
Note: You can search for specific documents (tasks) in Detail view only.
Table view: Use the Table view see learning instance history. When you open a document from this view, the history for the learning instance that is processing this document appears in a pane on the left. Click the empty text field, then select the blue-bounded box in the document that contains the data to extract. After you select a box, the data is highlighted in yellow and a green outline appears, which you can resize or reposition to include all the data that you want to extract.
5. Toggle between the fields views
Use the drop-down list to select between Show all fields to see all the document fields or Show fields that need validation to only show the fields that need your manual validation.
6. Fields awaiting validation
Fields that need validation are outlined in red. Click the field value and select the correct value for the field in the document. The value is automatically updated for the field. You can also select the field region and modify it in case the value was not selected correctly. In the sample screenshot, the Due Amount field value requires validation. A user can click the due amount field and click the due amount value in the document to automatically select the value for the field.
7. Add or delete a row
To insert or delete a row, hover over the ellipses to show the icons for adding or deleting table rows.
8. Advanced document options
  • Open in full screen: Provides a larger viewing area for validating documents.
  • Auto fill: Extracts multiple rows of data from multipage tables after you manually validate three cells in a column.
  • Skip: Skips a file without correcting the errors in the current document.
  • Reprocess: When you are training documents and if you edit the learning instance when the validation for the document is pending, you need to reprocess the documents to validate the updated fields.
  • Mark as invalid: Marks a document as invalid when the document is missing fields or includes incorrect values, or when you processed a wrong document.
  • Submit: Submit the document for reprocessing. This option is enabled only after all the fields are validated.
For documents processed in a connected learning instance:
The Validator shows the group number for the document. If you are unsatisfied with the extraction results, you can retrain the learning instance in Automation 360 IQ Bot.

Validating documents

Note:
  • The learning instance assets must be checked-in to the public repository.
  • If a document contains tables with large number of rows or data fields (>1000), there might be a delay in the initial validation and the corresponding response time.

In a window that is 1280 pixels or more, the panels are positioned side-by-side. Otherwise, the panel containing the fields and extracted data shifts below the panel containing the document, as demonstrated in this video:

  1. Log in as the Validator user.
  2. From the Control Room home page, navigate to AI > Document Automation.

    The Learning instances table displays details for each instance. The value in the Validate documents link indicates the number of documents awaiting manual validation.

  3. Click Validate documents.

    The Automation Co-Pilot Task Manager opens in a new tab, with the first failed document in queue.

  4. Provide correct values to the fields that need validation.

    The following video shows these steps:

    1. Select Show fields that need validation from the drop-down list in the right panel.
    2. Click the field to extract.
    3. In the document image, click the blue-bounded box containing the correct data or draw a box around the data you want to extract.
      • To skip a document without correcting its errors, click Skip to proceed to the next document in the validation queue.
      • To remove a document that cannot be processed, click Mark as Invalid.
  5. After you make the necessary corrections, click Submit so the document can be processed and the extracted data downloaded.

    The extracted values are saved to a file in the Success folder. The Validator shows the next document in queue. When all documents are corrected, the system displays a message stating that there are no more tasks available.