Present Classification Station

UiPath.IntelligentOCR.Activities.DocumentClassification.PresentClassificationStation

Opens the Classification Station, which enables users to manually separate the files into document types and also to verify and correct, if needed, the automatic classification and separation of files based on the document type.

Properties

Common

• DisplayName - The display name of the activity.

Input

• AutomaticClassificationResults - Provides the automatic classification results for human review. If not provided, the Classification Station opens for full manual processing.
• DocumentObjectModel - The Document Object Model you want to use to validate the document against. This model is stored in a Document variable and can be retrieved from the Digitize Document activity. Please see the documentation of the activity for more information on how to do this. This field supports only Document variables.
• DocumentPath - The path to the document you want to validate. This field supports only strings and String variables.
  Note: The supported file types for this property field are .png, .gif, .jpe, .jpg, .jpeg, .tiff, .tif, .bmp, and .pdf.
• DocumentText - The text of the document itself, stored in a String variable. This value can be retrieved from the Digitize Documentactivity. Please see the documentation of the activity for more information on how to do this. This field supports only strings and String variables.
• Taxonomy - The Taxonomy against which the document is to be processed, stored in a DocumentTaxonomy variable. This field supports only DocumentTaxonomy variables.

Misc

• Private - If selected, the values of variables and arguments are no longer logged at Verbose level.

Output

• ValidatedClassificationResults - Provides the human validated classification results. This field supports only an array and requires the same for the AutomaticClassificationResults option.

  Important: In case you use an Intel Xe GPU and Classification Station is not displayed properly, we recommend updating the graphics driver to the latest version. For more information, please visit this page.

Using Classification Station

The Classification Station is a powerful tool that enables users to perform, review, and correct, document classification information.

The Classification Station, once opened, presents any classification information along with the file being processed:

Note: Organize your documents by using the Split document option. More information about this feature can be found in the Other options section.

Document View Section

The right area of the Classification Station contains an interactive version of the original document, in which text or document sections can be selected, and words can be clicked based on the output of the digitization process.

This area also contains options for zooming in and out, selecting and rotating pages, searching through the document, or switching to text view.

Here are the options available in the right part of the Validation Station screen:

Option	Description
	Displays all the available keyboard shortcuts supported by the Classification Station. - Keyboard shortcuts - Switches the panel side from left to right
	Toggles between the text view and image view of the document. - Image view - Text only view
- Text* \)\)* Active only when the Text only view option is active	Sets the selection mode while in text view - Text - Tokens
	Sets the selection mode while in image view - Tokens - Custom area - Choose after selection
	Rotates the current page clockwise.
	Initiates a search between results in the document used by the Classification Station.
	Resets the zoom level on the document. This option is enabled only if the document was previously zoomed in or out.
	Zooms in on the document.
	Zooms out on the document.

Here is an example of how to use the View mode, Zoom In, Zoom Out, and Reset Zoom options:

To zoom in or out, you can also use the CTRL+scroll mouse wheel combination: CTRL+scroll up to view a specific section of the document; CTRL+scroll down to view a larger section of the document.

The below example illustrates the Rotate option:

Area selection in image view can be observed below:

Correspondingly, please look at area selection in text view:

The next example explains how to use the Search option:

There are many keyboard shortcuts that can be used to optimize the human interaction with the Classification Station. We encourage you to use them as much as possible. These can be reviewed in the Keyboard Shortcuts popup.

Shortcut	Description
Classification
n	Moves to the next field
p	Moves to the previous field
s	Splits after the selected page
h	Highlights the group reference
a	Adds/changes a reference
DEL	Removes a reference
m ↑	Moves all pages above
m ↓	Moves all pages below
←→↑↓	Navigate through pages
Document
d +	Zooms in
d -	Zooms out
d 0	Resets zoom
d r	Rotates the page clockwise
d t	Toggles the text mode
d s	Changes selection mode
d a	Clears the drawn anchor selection
/	Initiates a search
Accessibility
←→↑↓	Navigate through words Create or move area selection
Shift ←→↑↓	Resize area selection
Enter	Confirm area selection
PageDown PageUp	Next/Previous page
ESC	Deselect all
Alt p	Toggle PDF Viewer focus
General
?	This screen
!	Report document as exception
CTRL ENTER	Save classification
CTRL DEL	Discard all current changes

Navigate through the Classification Station by using the keyboard shortcuts. Activate the Toggle keyboard shortcuts option to avoid accidental triggering the keyboard shortcuts.

Decide whether the validation panel should be on the left or the right side of the screen.

Document Classification Section

The classification fields are influenced by the Taxonomy and they provide you with three possible situations:

• If the classification information for a given part of the document is provided and is correct, then no action is required for this field.
• If there is no classification information provided for a given part of the document, you can either leave it as Not Classified or select the right document type for it.
• If the page range provided for a given part of the document (classified or not, correctly or not) is not accurate as far as pages go (there are missing pages or extra pages), you can correct these by moving pages to the above or below parts.

On the left side of the screen the user is presented with all classifications.

The user can select the desired document type (that has been previously defined in Taxonomy) for any given page range of the document, from the document type dropdown:

The Document Type field has an Options drop-down menu that can be accessed by clicking on the button. A drop-down list becomes visible, displaying multiple editing options.

Below you can find all the options available from the drop-down menu:

Note: A reference is a token or collection of tokens in a document that can be used as keywords to identify the class of the document. References selected by the user are added to the Keyword Learning file through the Train Classifier Scope.

• Add reference - A reference can be added as support to the document type selection performed by the user.

  
  

  

  
  

• Remove reference - Removes a reference that was previously added for the given document type section.

  
  

  

  
  

• Change reference - Changes the reference to a new one, in case a reference already existed.

  
  

  

  
  

• Move all pages up - Moves the entire section of pages up, to the previously defined document type, Option is active on all sections except for the first one. Using this option will delete the section you are acting upon, unifying the page range with the previous one.

  
  

  

  
  

• Move all pages down - Moves the entire section of pages down, to the next document type defined. Option is active on all sections except for the last one. Using this option will delete the section you are acting upon, unifying the page range with the next one.

  
  

  

  
  

Other options

• Split document - Marks the beginning of a new document type, from where the selection is done, and moves it under a new document type section.

  
  

  

  
  

• Drag and Drop - Allows the rearrangement of pages between sections. Pages can be rearranged with the Drag and Drop option only if the order within a document is kept (page numbers should be consecutive).

  
  

  

  
  

• Remove reference - Removes a reference from a specific page.

  
  

  

  
  

• Highlight reference - Highlights the reference from a specific page.

  
  

  

  
  

Data Confirmation & Validation

Three options are available at the bottom of the Classification Station for the user to confirm or discard the changes.

Button	Function
	Discards all changes done by the user and reverts to the initial state of the validation task.
	Saves the confirmed, corrected data.
	Reports the document as being an exception.

Document Understanding Integration

The Present Classification Station activity is part of the Document Understanding Solutions. Visit the Document Understanding Guide for more information.