Train Classifiers Scope

UiPath.IntelligentOCR.Activities.Training.TrainClassifiers

Description

Provides a scope for any classifier activities you want to train. The activities must be manually dragged and dropped into the body of the activity.

Project compatibility

Windows-Legacy | Windows

Configuration

Designer panel

• 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 Document activity. Visit Digitize Document for more information on how to achieve this. This field supports only strings and String variables.
• DocumentObjectModel - The Document Object Model (DOM) 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. Visit Digitize Document for more information on how to achieve this. This field supports only Document variables.
• HumanValidatedData - The output from the validation station, stored in an ExtractionResult proprietary variable. Incompatible with HumanValidatedClassificationData.
  Note:

  • If the DocumentObjectModel and HumanValidatedData files are from different sources, an error is thrown at runtime.
  • The validation station can act as both classification and validation station.
• HumanValidatedClassificationData - The output from the classification station, stored in an ClassificationResult[] proprietary variable. Incompatible with HumanValidatedData.
• Taxonomy - The Taxonomy against which the document is to be processed, stored in a DocumentTaxonomy variable. This field supports only DocumentTaxonomy variables.

Properties panel

Common

• DisplayName - The display name of the activity.

Input

• DocumentObjectModel - The Document Object Model (DOM) 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. Visit Digitize Document for more information on how to achieve 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 Document activity. Visit Digitize Document for more information on how to achieve this. This field supports only strings and String variables.
• HumanValidatedClassificationData - The output from the classification station, stored in an ClassificationResult[] proprietary variable. Incompatible with HumanValidatedData.
• HumanValidatedData - The output from the validation station, stored in an ExtractionResult proprietary variable. Incompatible with HumanValidatedClassificationData.
  Note:

  • If the DocumentObjectModel and HumanValidatedData files are from different sources, an error is thrown at runtime.
  • The validation station can act as both classification and validation station.
• 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.

The Configure Classifiers Wizard accessed via the Train Classifiers Scope allows you to choose which classifiers are trained for each document type.

Using the Configure Classifiers Wizard

Follow the steps below to configure the wizard:

1. Add a Train Classifiers Scope activity to your workflow.
2. Place a classifier trainer activity inside the Train Classifiers Scope activity.
   1. Configure your classifiers by selecting Configure Classifiers.
      You can now see the Wizard.

      Figure 1. Overview of the Configure Classifiers wizard
      

      

      
      
3. Select the check boxes for the classifiers you want to activate for each document type. According to these check boxes, classifiers execute only for the document types activated for each of them.
   Figure 2. The selected classifiers for two document types
   

   

   
   
4. Add any taxonomy mapping information into the text fields next to each check box (in case the classifier trainers use internal taxonomies that need to be mapped to the project taxonomy).
5. Select Get of refresh extractor capabilities for the classifiers that support this functionality, to easily map your taxonomy fields with the available document types, or refresh them in case the document types have changed.
6. Select Save once all the classifiers are selected.

Document Understanding Integration

The Train Classifiers Scope activity is part of the Document Understanding solutions. Visit the Document Understanding Guide for more information.