Subscribe

UiPath Document Understanding

UiPath Document Understanding

Intelligent Form Extractor

What is Intelligent Form Extractor

The Intelligent Form Extractor is a specialized tool for processing fixed-layout documents for data extraction, that is building on top of the Form Extractor and adding extra capabilities, such as

  • handwriting recognition and handwritten data extraction,
  • signature detection.

The additional features of Intelligent Form Extractor, when compared to Form Extractor, make it a very good fit for processing all types of forms that

  • may be printed OR handwritten,
  • may require checking whether the form is signed or not.

These two additional features are configurable from the activity's Template Manager wizard, in addition to the configurations already present in the Form Extractor.

This extractor does not have learning (training) capabilities and requires up-front configuration.

👍

Tips:

More related information about Intelligent Form Extractor:

Special Requirements

You need to use your Automation Cloud Document Understanding API Key, or host your own instance of the Intelligent Form Extractor in AI Center on-prem, to use this extractor.

How to Configure

Activity Configuration

The Intelligent Form Extractor has two major configurations to be considered:

  • the Template Manager wizard - that allows you to define templates to be applied to incoming documents. This wizard enables the Template Editor and the Boolean field interpretation settings.
  • the MinOverlapPercentage setting - that allows you to control how strict the value area matching should be. Accepts a value between 0 and 100, and it controls what words are accepted or rejected from being part of a given value, based on how well their location fits the area defined in the template.

More information about using the Intelligent Form Extractor activity wizard can be found here.

Updated 5 months ago


Intelligent Form Extractor


Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.