document-understanding
2022.10
false
UiPath logo, featuring letters U and I in white

Document Understanding User Guide

Automation CloudAutomation Cloud Public SectorAutomation SuiteStandalone
Last updated Nov 11, 2024

Machine Learning Classifier

Machine Learning Classifier uses a machine learning model deployed as an ML Skill in AI Center to perform document classification tasks.

How to Configure at Design-Time

Perform the following steps to use the Machine Learning Classifier:

  1. Create a classifier model on AI Center.
    Note: Use the DocumentClassifier package available under Out-of-Box Document Understanding packages on AI Center. The data required for model training is collected through Machine Learning Classifier Trainer.
  2. Use the Taxonomy Manager Wizard to define your document type, with the fields you are targeting for data extraction. The Machine Learning Classifier activity can work by default with Invoices, Purchase Orders, Receipts, and Utility Bills.
  3. Drag and drop the Machine Learning Classifier activity into the Classify Document Scope activity. Review the message and click OK.
  4. In the Machine Learning Classifier wizard that automatically opens, provide the ML Skill and the ApiKey information.

When To Use

Consider using the Machine Learning Classifier in the following situations:

  • You need to classify single documents into different document types. No splitting is required.
  • Use ML Classifier with documents that have a high variability. For low variability, use the Intelligent Keyword Classifier or the Keyword Classifier. A trained Machine Learning Extractor can differentiate more easily between two similar document types than the Intelligent Keyword Extractor.

Learn More

To learn more about Machine Learning Classifier, please visit this page.

  • How to Configure at Design-Time
  • When To Use
  • Learn More

Was this page helpful?

Get The Help You Need
Learning RPA - Automation Courses
UiPath Community Forum
Uipath Logo White
Trust and Security
© 2005-2024 UiPath. All rights reserved.