Using the Classify document action

The IQ Bot Classify document action groups the input documents based on the first page of each document, using the selected model file that is created with the IQ Bot Train Classifier action. Use this action if you are manually creating document groups.

Prerequisites

Note: You will see an error when you create a bot with the following actions and execute the bot:
  1. Use the Classify Document action in the Advanced Classifier package to classify a document.
  2. Use the Extract Data action that is using the learning instance of Unstructured document type in the Document Extraction package to extract data from a document.

Therefore, we recommend not using the Classify Document action and Extract Data action that is using the learning instance of Unstructured document type in the same bot.

Procedure

  1. In the Actions palette, double-click or drag the Classify document action from the Document Classifier package.
  2. In the Input file field, provide the default filepath for incoming files for classification.
  3. In the Classifier field, provide the filepath of the model file.
    You can either select the .zip folder or extract the .icmf file from this folder and select it.
    Note: For better classification results and performance, we recommend that you use the .icmf file available in the .zip folder obtained from the Train Classifier action.
  4. Use the Output folder path option to save the classification output documents.
    The pages from the output document are saved in the respective subfolders based on the categories created in the model file.
  5. Optional: Configure the Confidence threshold (%).
    If the confidence value of the category prediction of a document is less than the confidence threshold, the document is moved to the Unclassified folder.
  6. Select from Normal mode or Express mode.
    • Normal mode: The Classifier parses the entire document and groups it based on the fields in all the pages.
    • Express mode: The Classifier groups the document based on the fields in the first page.
  7. Select or create a list variable to hold the output.
    The classification results as a list with the following keys:
    • fileName
    • pageIndex
    • category
    • confidence