Using the Split Document action

Use the Split Document action to separate the input document into multiple documents based on the selected classification model.

Prerequisites

  • If not done already, use the Train Advanced Classifier action to create a model file.
  • Ensure the input files are in required format.

To split a document into multiple documents, do the following:

Procedure

  1. In the Actions palette, double-click or drag the Split Document action from the Advanced Classifier package.
    Note: The PDF and TIFF documents with multiple pages are the only valid inputs for the Split Document action.
  2. In the Input file path, select one of the following options to specify the location of the Input file:
    • Control Room file
    • Desktop file
    • Variable
  3. Use the Output folder path option to save the classification output documents.
    • Desktop folder
    • Variable
  4. In the License field, provide a license credential.
  5. If you select Credential option, click Pick to provide a license from the credential vault.
  6. Use the Save split output variable option to save the classification output documents. Save the classification results as a list of dictionaries with the following keys:
    • fileName: Name of file that you want to process
    • documentIndex: Document number (category wise)
    • pageIndex: Page number (document wise)
    • category: The category to which the file belongs to after classification. For example, all HR related documents will be placed in one category.
    • classConfidence: Based on training data, system classifies the documents and identifies threshold percentage value that shows classification such as, which file belongs to which category.
    • splitConfidence: Based on training data, system splits the documents into various categories and identifies split percentage value that shows split confidence for classification.
  7. Click Save and Run.