Activities

The following table shows the available activities in the UiPath.IntelligentOCR.Activities package.

Table 1. The available activities in the IntelligentOCR package

	Description
Load Taxonomy	Turns the `taxonomy.json` file created with the help of the Taxonomy Manager into a variable that can be further used with other activities.
Digitize Document	Digitizes a document, extracting its Document Object Model (DOM) and text and storing them in their corresponding variable types.
Classify Document Scope	Provides a scope for classifier activities, providing all of the necessary files needed to perform document classification.
Keyword Based Classifier	Uses a keyword-based document classification algorithm designed for files with repeatable titles, and classifies a document based on a given training set from a specified file when used within the Classify Document Scope activity.
Document Understanding Project Classifier¹	Classifies documents from a specific Document Understanding modern project, and version, through the classifier trained within that version.
Intelligent Keyword Classifier	Enables you to classify and split document packages into individual document types.
Present Classification Station	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.
Create Document Classification Action	Creates an action of type Document Classification in Action Center.
Wait For Document Classification Action And Resume	The activity can be used to suspend the execution of the current workflow until a specified document classification action is completed.
Train Classifiers Scope	Provides a scope for any classifier activities you want to train.
Keyword Based Classifier Trainer	Incorporates a keyword-based document classification algorithm, targeting classification for files that have repeatable titles.
Intelligent Keyword Classifier Trainer	Trains the Learning Data added as variables. The used keywords can be defined by the user or vector learned.
Data Extraction Scope	Provides a scope for extractor activities, enabling you to configure them according to the document types defined in your taxonomy.
Document Understanding Project Extractor¹	Extracts data from documents using a certain modern project and version.
RegEx Based Extractor	Enables you to create and use a custom Regular Based Expression to extract information from a document.
Form Extractor	The Form Extractor is best suited for extracting, matching, and reporting specific information by analyzing the word's position inside the document, or detecting a signature.
Intelligent Form Extractor	Analyses, extracts, matches, and reports the required information from a document by taking into consideration the words' position, including handwritten and signed fields.
Present Validation Station	Opens the Validation Station, which enables users to review and correct document classification and automatic data extraction results.
Create Document Validation Action	Creates an action of type `Document Validation` in Action Center.
Wait For Document Validation Action And Resume	The activity can be used to suspend the execution of the current workflow until a specified document validation action is completed.
Train Extractors Scope	Provides a scope for any extractor activities you want to train.
Export Extraction Results	Gives you easy access to extraction results by exporting results from an `ExtractionResult` variable to a `DataSet` variable which can be further processed.
Machine Learning Extractor	Enables data extraction from documents using machine learning models provided by UiPath®.
Machine Learning Extractor Trainer	Enables the collection of data that has been processed through Validation Station so that it can be imported into Document Manager.
Machine Learning Classifier	Enables data classification from documents using document classification ML models provided by UiPath®.
Machine Learning Classifier Trainer	Enables the collection of data that has been processed through Classification Station so that it can be imported into a user-specified AI Center dataset.
Generative Classifier²	Allows you to classify documents using generative models.
Generative Extractor²	Allows you to extract documents using generative models.

¹ - Projects using IntelligentOCR versions 6.22.1 and higher may encounter an error at the Classify Document Scope or Data Extraction Scope activities when consuming modern projects from Document Understanding in Automation Suite. The error message is: "The HTTP resource that matches the request URI ' ' does not support the API version '1.1'". The error occurs due to the incompatibility between Intelligent OCR package versions 6.22.1 and higher, and Document Understanding in Automation Suite versions 2024.10 and lower. To avoid this error when working with Automation Suite versions 2024.10 and lower, use IntelligentOCR version 6.22.0.

² - Projects using ML.Activities versions 1.31.2 and higher throw an error when consuming modern projects from Document Understanding in Automation Suite. The error message is: "The HTTP resource that matches the request URI ' ' does not support the API version '1.1'". This occurs due to the incompatibility between ML.Activities package versions 6.22.1 and higher, and Document Understanding in Automation Suite versions 2024.10 and lower. To avoid this error when working with Automation Suite versions 2024.10 and lower, use an ML.Activities version lower than 1.31.2.