UiPath Document Understanding Activities

The UiPath Document Understanding Activities package enables the usage of a complete document processing framework.

Introduction to the UiPath Document Understanding Activities Package

The UiPath Document Understanding Activities package provides a comprehensive document processing framework that encompasses taxonomy definition, digitization, document classification, data extraction, data validation, and the training of classifiers or extractors.

Activities in the UiPath Document Understanding Activities Package

The following activities are included in this package:

PDF Operations

• Set PDF Password - Changes the password of a specified PDF file.
• Merge PDFs - Joins a collection of file objects.
• Get PDF Page Count - Provides the total number of pages in a PDF file.
• Extract PDF Text - Extracts the text from a PDF document.
• Extract PDF Images - The activity extracts all the images it finds in the PDF file.
• Extract PDF Page Range - Extracts a specified range of pages from a PDF document.

Data Extraction and Management

• Extract Document Data - Extracts data from an input file or Document Data object, and stores the results into a Document Data object (either the one received as input or a newly created one for the input file).

Tasks Validation

• Create Validation Task and Wait - Allows you to visualize and modify, in Action Center, the Extraction Results for the provided documents, by pausing the workflow until the validation action is executed.
• Wait for Validation Task and Resume - Allows you to pause the action until the document is validated, automatically resuming the action, once the validation is complete.
• Create Validation Task - Allows you to create a document validation action.

Document Classification

• Classify Document - Allows you to classify documents using classification models.

Features and Applications of the UiPath Document Understanding Activities Package

The UiPath Document Understanding Activities package can be utilized in various use cases, enhancing document processing and automation capabilities:

• Invoice Processing - Automate the extraction of relevant information from invoices, such as vendor details, invoice amounts, and dates. Use validation tasks to review and verify extracted data for accuracy.
• Document Classification and Sorting - Implement automated document classification to categorize incoming documents based on their content. For example, classify documents into categories like contracts, reports, and correspondence.
• Data Entry Automation - Streamline data entry processes by extracting required information from various documents. This can include forms, applications, or any document containing structured data.