UiPath-SAIv1 Questions and Answers

 The ML Extractor is a data extraction tool that uses machine learning models provided by UiPath to identify and extract data from documents. The ML Extractor can work with predefined document types, such as invoices, receipts, purchase orders, and utility bills, or with custom document types that are trained using the Data Manager and the Machine Learning Classifier Trainer12.

According to the best practice, the ML Extractor should be chosen based on the document types, language, and data quality of the documents being processed. It is important to select an ML Extractor that is specifically trained or optimized for the document types that are relevant for the use case, as different document types may have different layouts, fields, and formats. It is also important to take into account the language of the documents, as some ML Extractors may support only certain languages or require specific language settings. Moreover, it is important to consider the quality and diversity of the training data used to train the ML Extractor, as this may affect the accuracy and reliability of the extraction results. The training data should be representative of the real-world data, and should cover various scenarios, variations, and exceptions3.

References: 1: Machine Learning Extractor - UiPath Activities 2: Machine Learning Classifier Trainer - UiPath Document Understanding 3: Data Extraction - UiPath Document Understanding

In the Document Understanding framework, the dispatcher is responsible for ensuring that one job is created for each input file. It works by submitting files to be processed individually, ensuring that each document or group of documents is handled as a separate transaction. This allows for more efficient processing and better tracking of each file, especially in high-volume workflows where managing each file as a separate job is critical for performance and error handling.

(Source: UiPath Documentation on Document Understanding)

In the context of a machine learning pipeline, specifically within the train.py file in UiPath AI models, the function responsible for persisting the trained model is typically named save(self). This function is invoked after the model has been trained, and it ensures that the model's state, weights, and configurations are saved to disk or another persistent storage medium. The saved model can then be reused for inference or further fine-tuning in future executions.

For more details, refer to:

UiPath AI Center Documentation: Training Models

Model Persistence: Saving Machine Learning Models in AI Center

Recall is a metric that measures the proportion of all possible true positives that the model was able to identify for a given concept1. A true positive is a case where the model correctly predicts the presence of a concept in the data. Recall is calculated as the ratio of true positives to the sum of true positives and false negatives, where a false negative is a case where the model fails to predict the presence of a concept in the data. Recall can be interpreted as the sensitivity or completeness of the model for a given concept2. For example, if there are 100 verbatims that should have been labelled as ‘Request for information’, and the model detects 80 of them, then the recall for this concept is 80% (80 / (80 + 20)). A high recall means that the model is good at finding all the relevant cases for a concept, while a low recall means that the model misses many of them.

References: 1: Recall 2: Precision and Recall

When setting up a classification label in UiPath's Out Of the Box (OOB) labeling templates, you need to provide several key details: the name of the label, the classification type (which defines the kind of label), the input to be labeled, the attribute name that describes the label's context, a shortcut for quick access, and a color for visual distinction. These fields ensure the label is fully defined and easy to manage in workflows.

(Source: UiPath Document Understanding documentation)

The Machine Learning Extractor utilizes machine learning models to effectively extract data from documents, especially when dealing with varying structures or formats within the same document type. This capability is crucial in scenarios where documents do not follow a strict template and have variations in their layout or content organization. The extractor can be trained to understand these variations and accurately extract the needed information.

The Machine Learning Extractor is a data extraction tool that uses machine learning models to extract data from various types of documents, such as invoices, receipts, or forms. It is especially useful when the same document type has multiple layouts or formats, as it can learn and infer the values for the targeted fields, even from documents and layouts it has never seen before1.

The Machine Learning Extractor can be used with one of UiPath’s public Document Understanding endpoints, which provide generic models for certain document types, or with custom trained machine learning models hosted in AI Center, which can be tailored to specific use cases. The Machine Learning Extractor can be configured and trained using the Data Extraction Scope activity in UiPath Studio2.

References:

Document Understanding - Machine Learning Extractor

UiPath Activities - Data Extraction Scope

The model rating is a proprietary score that assesses the overall health and performance of a model in UiPath Communications Mining. It considers four main factors: balance, underperforming labels, coverage, and all labels. The model rating is a score from 0 to 100, which equates to a rating of ‘Poor’ (0-49), ‘Average’ (50-69), ‘Good’ (70-89) or ‘Excellent’ (90-100). A model rating of 70-90 or better indicates that the model has sufficient training and performs well in all of the most important areas. A model rating of 70-90 or better also means that the model has a balanced and representative training data, a low number of labels with performance issues or warnings, a high coverage of the dataset by informative labels, and a high average precision of all labels.

References: Communications Mining - Model Rating, Communications Mining - Understanding and improving model performance

The typical machine learning model deployment process in UiPath AI Center usually takes between 10-15 minutes1. This process involves wrapping the model in UiPath’s serving framework and deploying it within a namespace on AI Fabric’s Kubernetes cluster that is only accessible by your tenant1. Please note that the actual time may vary depending on the complexity of the model and other factors.

AI Center - Managing ML Skills (uipath.com)

The Label Trends table in UiPath Communications Mining shows the trend of the top 10 highest volume labels over the selected time period, as well as their percentage change and rank change compared to the previous period1. The table allows users to quickly identify which labels are increasing or decreasing in volume, and by how much, over time. The table also shows the net sentiment score for each label, which is calculated as the difference between the positive and negative sentiment probabilities for each verbatim2. The table can be filtered by data type, source, date range, and label category. Users can also sort the table by label name, volume, percentage change, rank change, or net sentiment1.

References: 1: Trends 2: Sentiment Analysis

Unattended automation is ideal for tasks that can run independently without human intervention, such as scheduled activities during off-hours. Running reports and emailing stakeholders overnight is a perfect use case for unattended bots, which can execute the process autonomously.

 Entity predictions refer to the process of identifying and highlighting a specific span of text within a communication that represents a value for a predefined entity type. For example, an entity type could be “Organization” and an entity value could be “UiPath”. Entity predictions are made by the platform based on the training data and the rules defined for each entity type. Users can review, accept, reject, or modify the entity predictions using the Classification Station interface12.

References: Communications Mining - Reviewing and applying entities, Communications Mining - Predictions - UiPath Documentation Portal.

 According to the UiPath documentation, the Classify stage of the Document Understanding Framework is used to automatically determine what document types are found within a digitized file. The document types are defined in the project taxonomy, which is a collection of all the labels and fields applied to the documents in a dataset. The Classify stage uses one or more classifiers, which are algorithms that assign document types to files based on their content and structure. The classifiers can be configured and executed using the Classify Document Scope activity, which also allows for document type filtering, taxonomy mapping, and minimum confidence threshold settings. The Classify stage outputs the classification information in a unified manner, irrespective of the source of classification. The documents that are classified are then sent to the next stage of the framework, which is Data Extraction. The documents that are not classified or skipped are either excluded from further processing or sent to Action Center for human validation and correction.

References:

Document Understanding - Document Classification Overview

Document Understanding - Introduction

Generative Extraction & Classification using Document Understanding in Cross-Platform Projects (Public Preview)

In UiPath AI Center, the platform supports several types of machine learning (ML) models, including:

Out-of-the-box models from UiPath: Pre-built models designed for common automation tasks.

Models from UiPath technology partners: External models developed by UiPath’s partners.

Open-source models: Community-contributed models that can be used and adapted for various use cases.

Custom models: Models that users build and train specifically for their projects using their datasets.

This flexibility in model support ensures that organizations can leverage a wide range of machine learning capabilities to suit different automation needs.

For more details, refer to:

UiPath AI Center Documentation: AI Center Models

Machine Learning Model Types: Types of Models in UiPath AI Center

In UiPath Communications Mining, Dashboards are fully customizable pages that allow users to display relevant charts, visualizations, and insights for a specific dataset. These dashboards provide critical insights into the performance of models, labels, and other metrics relevant to the communication mining process. Users can create and adjust these dashboards to reflect specific data points, making them a powerful tool for tracking and improving model performance over time.

For more details, refer to:

UiPath Communications Mining Dashboards: Customizing Dashboards

UiPath AI Center Documentation: Dashboards and Visualization

UiPath provides out-of-the-box pre-trained models that are ready for use and cover a wide variety of document types. These models can be used as-is for common use cases or fine-tuned based on specific requirements, making them versatile for different projects

The Custom Named Entity Recognition out-of-the-box model is a machine learning package that allows you to bring your own dataset tagged with entities you want to extract from unstructured text. The model can be trained and deployed using the UiPath AI Center, and can be integrated with the UiPath Document Understanding framework. The model can be used to extract and classify text in various domains and formats, such as emails, letters, web pages, research papers, and call transcripts. For example, you can use the model to extract information such as names, dates, addresses, amounts, products, or any other custom entity from your documents. The model supports multiple languages and can be customized according to your needs.

References: AI Center - Custom Named Entity Recognition, Custom Named Entity Recognition Documentation, UiPath AI Center - Document Understanding & Use of UiPath Custom Named Entity Recognition Model

The correct execution order of the Document Understanding template stages is:

Taxonomy

Digitize

Classify

Extract

Extraction Validation

Export

Comprehensive and Detailed Explanation: The Document Understanding template stages are based on a document processing flowchart that follows these steps:

First, you need to define the Taxonomy of the document types and fields that you want to process and extract information from. This is done using the Taxonomy Manager in UiPath Studio1.

Next, you need to Digitize the input documents, which can be in various formats such as PDF, image, or text. This is done using the Digitize Document activity, which converts the documents into a machine-readable format and performs OCR if needed2.

Then, you need to Classify the digitized documents into the predefined document types in your taxonomy. This is done using the Classify Document Scope activity, which can use various classifiers such as Keyword Based Classifier, Machine Learning Classifier, or Intelligent Form Extractor3.

After that, you need to Extract the relevant information from the classified documents based on the fields in your taxonomy. This is done using the Data Extraction Scope activity, which can use various extractors such as Regex Based Extractor, Machine Learning Extractor, or Form Extractor.

Next, you need to perform Extraction Validation to review and correct the extracted information, either manually or automatically. This is done using the Present Validation Station activity, which can use either the Validation Station or the Action Center for human-in-the-loop validation.

Finally, you need to Export the validated information to the desired output location, such as a file, a database, or a queue. This is done using the Export Extraction Results activity, which can use various exporters such as Excel Exporter, CSV Exporter, or Queue Item Exporter.

References:

UiPath Studio - Taxonomy Manager

UiPath Activities - Digitize Document

UiPath Activities - Classify Document Scope

his is confirmed in the UiPath documentation, where the "Train" feature guides users from the dataset creation stage through the necessary steps to optimize the training process. The system recommends next best actions based on progress to ensure efficient and focused training​

In UiPath's Taxonomy Manager, field rules are used to optimize extraction results and perform automatic validation of extracted data. These rules can be applied to specific fields within the document understanding process to ensure that extracted data meets certain predefined conditions or constraints, such as formats, patterns, or value ranges. This allows for higher accuracy in the extraction process and reduces errors, as invalid data can be flagged or corrected based on these rules.

Field rules help automate the validation of data by setting criteria that extracted data must meet, thus enhancing the extraction quality and ensuring that only valid and structured data is processed further in the automation workflow.

For more details, refer to:

UiPath Taxonomy Manager Documentation: Field Rules in UiPath

UiPath Document Understanding Framework: Taxonomy Manager Overview

In UiPath Communications Mining, pinning a model ensures that the predictions shown in the Explore tab are generated from that specific model version. This feature allows users to control which version of the model is actively making predictions, particularly during evaluation or comparison stages. By pinning a model, the user ensures that the UI reflects the predictions from the selected version, helping maintain consistency when analyzing results or making changes.

For more details, refer to:

UiPath Communications Mining: Model Management and Pinning

UiPath AI Center Documentation: Managing Model Versions

UiPath Studio does not allow connecting to multiple source control plugins at the same time. A single version control system (e.g., GIT, TFS, SVN) can be used per project to manage code versions.

UiPath AI Center can be deployed in multiple ways to meet different organizational needs and infrastructures. The available deployment options include:

Cloud availability: Using UiPath's cloud services.

On-premises air-gapped: A fully isolated, offline environment for organizations with strict security requirements.

On-premises online: Deployed on-premise but with internet connectivity.

Hybrid mode: Combining on-premises AI Center with on-premises Orchestrator for flexibility.

Automation Suite: A comprehensive deployment of UiPath tools, including AI Center.

For more details, refer to:

UiPath AI Center Deployment Models: Deployment Options

In UiPath Communications Mining, when a parent label is deleted, both the parent and its child labels are removed from the reviewed messages. Additionally, any messages with updated annotations that were associated with those labels are flagged for review to ensure consistency in the training data​

In UiPath:

Variables are scoped to a specific workflow or sequence and are used to store data for operations within that scope.

Arguments, on the other hand, are used to pass data between workflows, allowing information to flow in or out of invoked workflows.

The Document Object Model (DOM) is a data representation of the objects that comprise the structure and content of a document on the web1. In the context of Document Understanding, the DOM is a JSON object that is generated by the Digitize Document activity, which uses the UiPath Document OCR engine to extract the text and layout information from the input document2. The DOM contains the following properties for each document3:

name: The name of the document file.

contentType: The MIME type of the document file, such as application/pdf or image/jpeg.

textLength: The number of characters in the document text.

pages: An array of objects, each representing a page in the document. Each page object has the following properties:

pageNumber: The number of the page, starting from 1.

rotation: The angle of rotation of the page, in degrees. A positive value indicates clockwise rotation, and a negative value indicates counterclockwise rotation.

language: The language code of the page, such as en or fr.

content: An array of objects, each representing a word or a line in the page. Each content object has the following properties:

type: The type of the content, either word or line.

text: The text of the content.

boundingBox: An array of four numbers, representing the coordinates of the top-left and bottom-right corners of the content, in the format [x1, y1, x2, y2]. The coordinates are relative to the page, with the origin at the top-left corner, and the unit is pixel.

confidence: A number between 0 and 1, indicating the confidence level of the OCR engine in recognizing the content.

The DOM can be used as an input for other activities in the Document Understanding framework, such as Classify Document Scope, Data Extraction Scope, or Export Extraction Results. The DOM can also be manipulated using programming code, such as JavaScript or Python, to perform custom operations on the document data.

References:

1: Introduction to the DOM - Web APIs | MDN 2: Digitize Document 3: Document Object Model

In the UiPath Document Understanding Framework, the Train stage enables models to learn from human-validated data. This process involves feeding the corrections made by humans during the validation phase back into the model, allowing it to refine its predictions and improve accuracy over time.

UiPath Documentation

The training component is crucial for classifiers and extractors capable of learning from human feedback. By incorporating validated data, these components can adjust their algorithms to better handle similar documents in the future, enhancing the overall efficiency and effectiveness of the automation process.

Other options are incorrect because:

B. Allows the extractor to improve its prediction over time by using better OCR engines: While better OCR engines can enhance data extraction, this is not the function of the Train stage.

C. Allows a human to validate and correct the extracted data: This describes the Validation stage, not the Train stage.

D. Improves the extractor accuracy by learning from the classification result: Training focuses on learning from human-validated extraction results, not just classification outcomes.

Therefore, the primary purpose of the Train stage is to allow the model to learn from human-validated data, thereby improving its future performance.

According to the UiPath Communications Mining documentation, reviewing and applying entities is a crucial step for improving the accuracy and performance of the entity extraction models. When reviewing entities, users should check all of the predicted entities within a paragraph, as well as any missing or incorrect ones. Users can accept, reject, edit, or create entities using the platform’s interface or keyboard shortcuts. Users can also change the entity type if the value is correct but the type is wrong. Reviewing and applying entities helps the platform learn from the user feedback and refine its predictions over time. It also helps users assess the automation potential and benefit of the communications data.

References:

Communications Mining - Reviewing and applying entities

Communications Mining - Improving entity performance

Export the package from AI Center. This is the first step where you prepare the package to be moved.

On the ML Packages page, click the Import ML Package button. This step is where you start the process of importing the package you've exported.

On the Upload package field, add the zip file downloaded using the Downloading ML Packages procedure. After starting the import process, you will upload the actual package.

Click Create. This is the final step where you finalize the uploading process of your ML package.

Please proceed with these steps in the UiPath AI Center to upload your exported package correctly.

In UiPath Communications Mining, high coverage ensures that a larger proportion of communications is classified with meaningful labels, meaning fewer communications are sent for manual review and more processes are captured for automation. This leads to more effective automation, reducing the need for human intervention and ensuring that the automation use case is fully realized.

For more details, refer to:

UiPath Communications Mining Performance Metrics: Coverage and Automation

 According to the UiPath documentation, UiPath Communications Mining is a tool that enables you to analyze text-based communications data, such as customer feedback, support tickets, or chat transcripts, using natural language processing (NLP) and machine learning (ML) techniques1. One of the features of UiPath Communications Mining is the Comparison page, which allows you to compare two cohorts of verbatims based on different criteria, such as date range, source, metadata, or label2. The Comparison page displays the following information for each cohort3:

Total verbatim count: The number of verbatims in the cohort.

Proportion for each label: The percentage of verbatims in the cohort that are assigned to each label. A label is a category or a topic that is relevant for the analysis, such as sentiment, intent, or issue type. Labels can be predefined or custom-defined by the user.

Statistical significance: The p-value that indicates whether the difference in proportions between the two cohorts is statistically significant or not. A p-value less than 0.05 means that the difference is unlikely to be due to chance.

The Comparison page also provides a visual representation of the proportions for each label using a bar chart, and allows the user to drill down into the verbatim content for each label by clicking on the bars3. Therefore, the correct answer is A.

References:

1: About Communications Mining 2: Communications Mining - Comparing Cohorts 3: Communications Mining - Comparison Page

According to the UiPath Communications Mining documentation, the Trends tab in the Reports page displays charts for verbatim volume, label volume, and sentiment over a selected time period. Users can choose the time period for the data in the filter bar, and the time sequencing of the chart (i.e. daily, weekly, etc.) in the top right dropdown menu. The available options for the time sequencing are Daily, Weekly, Monthly, and Yearly. These options allow users to see how the trends change over different time intervals and identify patterns or anomalies.

References:

Communications Mining - Using Reports

Communications Mining - Trends

According to the UiPath documentation, a dataset is a folder of storage containing arbitrary sub-folders and files that allows machine learning models in your project to access new data points. You can edit a dataset’s name, description, or content from the Datasets > [Dataset Name] page, by clicking Edit dataset. However, you can only edit a dataset if it is not currently being used in an active pipeline. A pipeline is a sequence of steps that defines how to train, test, and deploy a machine learning model. If a dataset is being used in an active pipeline, you will see a lock icon next to it, indicating that it cannot be edited. You can either wait for the pipeline to finish or stop it before editing the dataset.

References:

AI Center - Managing Datasets

AI Center - About Datasets

AI Center - About Pipelines

For the described requirements:

ApplyOcrOnPdf set to Auto ensures OCR is applied only when needed.

DegreeOfParallelism set to -1 uses all available logical processors for maximum parallelism.

The environment variable eval.redo_ocr is relevant for Evaluation pipelines because it allows you to rerun OCR when running the pipeline to assess the impact of OCR on extraction accuracy. This assumes an OCR engine was configured when the ML Package was created. The other options are not valid environment variables for Evaluation pipelines.

References: Document Understanding - Evaluation Pipelines

According to the UiPath documentation, a data source is a raw collection of verbatims, which are text-based communications such as survey responses, emails, transcripts, or calls1. A data source can be of a similar type and share a similar intended purpose, such as capturing customer feedback or servicing requests2. A data source can be added to up to 10 different datasets, which are collections of sources and labels that are used to train and evaluate ML models3. Therefore, the correct definition of a UiPath Communications Mining data source is A.

References:

1: Communications Mining - Sources 2: Communications Mining - Managing Sources and Datasets 3: Communications Mining - Understanding the data structure and permissions

To ensure the model is trained effectively, UiPath recommends that regular fields be labeled on at least 10 different pages in Data Manager before exporting the labeled documents to AI Center. This helps in providing enough variation and examples for the model to learn from and generalize effectively.

Mining, it is recommended that users provide a minimum of 25 pinned examples per label to ensure proper training and accurate predictions by the machine learning models. This number allows the platform to have a sufficient variety of examples to generalize and make reliable predictions for each label in real-world scenarios.

The minimum number of pinned examples per label is crucial because it enhances both precision and recall, helping the model effectively differentiate between labels and improving overall model performance. If fewer examples are provided, the model may struggle with generalization and might not perform well in distinguishing between similar or overlapping categories.

This standard of 25 pinned examples is outlined in several UiPath documentation sections and best practices for training models in Communications Mining​

UiPath Documentation

​

UiPath Documentation

​

UiPath Community Forum

For further details, refer to UiPath’s official Communications Mining User Guide on their documentation portal.

In UiPath Communications Mining, the shading of label predictions in the Explore section indicates confidence levels. Darker shading represents a higher confidence score, meaning the model is more certain of the prediction made for that particular label​

 The exported data from the UiPath Document Understanding Template contains the extraction results in a JSON format, along with some additional information that can be useful for debugging or analysis purposes. One of the additional information that can be included is the page number from which the field was extracted and the exact position on the page, represented by the coordinates of the bounding box. This information can help to locate the field on the original document image and to verify the accuracy of the extraction. The additional information can be enabled or disabled by setting the IncludeMetadata parameter to true or false in the Config file of the template.

References: Document Understanding Process: Studio Template, Export Results

In a Document Understanding Process, particularly when it is in production, it is crucial to manage output data securely and efficiently. Utilizing Network Attached Storage (NAS) and Orchestrator Buckets are recommended practices for exporting result files for several reasons:

Network Attached Storage (NAS): NAS is a dedicated file storage that allows multiple users and client devices to retrieve data from centralized disk capacity. Using NAS in a production environment for storing result files is beneficial due to its accessibility, capacity, and security features. It facilitates easy access and sharing of files within a network while maintaining data security.

Orchestrator Bucket: Orchestrator Buckets in UiPath are used for storing files that can be easily accessed by the robots. This is particularly useful in a production environment because it provides a centralized, cloud-based storage solution that is scalable, secure, and accessible from anywhere. This aligns with the best practices of maintaining high availability and security for business-critical data.

The other options (B, C, and D) include locations that might not be as secure or efficient for a production environment. For example, storing files locally or in a temp folder can pose security risks and is not scalable for large or distributed systems. Similarly, storing directly on a VM might not be the most efficient or secure method, especially when dealing with sensitive data.

In UiPath, the Verbose log level offers the most detailed information about the execution of activities. It logs every possible detail about the automation operations, including variable changes, function calls, and external responses. This level is particularly useful for in-depth debugging and analysis.

UiPath Documentation

The hierarchy of log levels in ascending order of priority is as follows:

Off: No logs are stored.

Verbose: Logs all details about automation operations.

Trace: Logs finer-grained informational events than the Debug level.

Information: Logs informational messages that highlight the progress of the application.

Warning: Logs potentially harmful situations.

Error: Logs error events that might still allow the application to continue running.

Fatal: Logs very severe error events that will presumably lead the application to abort.

Therefore, setting the log level to Verbose ensures that all possible details about the execution are captured, aiding in thorough diagnostics.

Create the new label by assigning it at least once. This is the initial step to introduce a new category or classification within your data taxonomy.

Search for instances in the reviewed data where the new label should have been assigned, and apply the label accordingly. This step is crucial for maintaining consistency across your data set.

Use 'Missed Label' to find all additional missing examples in the reviewed data. This action helps in identifying and rectifying any instances that may have been overlooked during the initial review.

Check validation to ensure the label is performing as expected, and follow recommended actions if further training is required. Validation is key to assess the accuracy and performance of the new label within the system.

In UiPath AI Center, versioning of ML packages is an integral part of managing the lifecycle of machine learning models. Each ML package has a major and minor version to track changes. When an ML package is initially uploaded, it is assigned a major version (e.g., 1.0). If a package is retrained via pipelines, it increments the minor version (e.g., from 1.0 to 1.1). This mechanism helps differentiate between user-uploaded packages and those that have been retrained. Only packages that undergo retraining through pipelines modify their minor version, not the major version. Thus, answer D is correct.

(Source: docs.uipath.com on ML Package Management).

In UiPath Communications Mining, the Reports section provides a variety of tools for analyzing and monitoring messages within a dataset. This includes functionalities like label summaries, trends, and message segmentation, which allow users to gain insights into message volumes, sentiment trends, and other analytical metrics. The Reports section is integral for tracking the performance of messages and the overall dataset, making it useful for monitoring communication channels​

In UiPath Communications Mining, the Label Summary report tab provides a high-level overview and statistics on all labels. This summary gives insights into the performance and distribution of labels across the dataset, helping users understand how well the model is classifying different types of communications.

For more details, refer to:

UiPath Communications Mining Documentation: Label Summary Reports

In UiPath AI Center, datasets can only be deleted if they are not being utilized in any active pipelines. This ensures that datasets tied to running or scheduled operations are not inadvertently deleted, which could disrupt ongoing processes. Once the dataset is confirmed to be unused in any active pipeline, it can safely be removed​

To enable a remote knowledge worker to validate the extracted data from documents in Action Center, the automation workflow needs to include the following activities12:

Create Document Validation Action: This activity creates an action of type Document Validation in Orchestrator Action Center, and returns an action object as output. The action object contains the information needed to resume the workflow after the human validation is completed. The input properties of this activity include the action details, such as title, priority, catalog, and folder, and the document validation data, such as the document object model, the document text, the taxonomy, and the automatic extraction results.

Wait for Document Validation Action and Resume: This activity suspends the execution of the workflow until the human validation is done in Action Center, and then resumes it with the updated extraction results. The input property of this activity is the action object obtained from the Create Document Validation Action activity. The output property is the validated extraction results, which can be used for further processing or exporting.

References: 1: Create Document Validation Action 2: Wait for Document Validation Action and Resume