A.  

Natural Language Processing (NLP)

B.  

Virtual Reality.

C.  

Cloud Computing.

D.  

Robotic Process Automation

A.  

Existence of a non-empty root folder, requirements.txt file, and train.py file in the root folder which implements a class Main. The class is further validated to implement an__init_function.

B.  

Existence of a non-empty root folder, requlrements.txt file, and main.py file in the root folder which implements a class Main. The class is further validated to implement an__init and a predict function.

C.  

Existence of a non-empty root folder, main.py file in the root folder which implements a dass Main. The class is further validated to implement an__init__and a predict function.

D.  

Existence of a requirements.txt file, and main.py file which implements a class Main. The class is further validated lo implement an__init__and a predict function.

A.  

The popularity of the ML Extractor among other UiPath users should be the primary factor when choosing a UiPath ML Extractor.

Opt for the ML Extractor that has the highest number of downloads or positive reviews.

B.  

Consider the document types, language, and data quality when choosing an ML Extractor.

It is important to select one that is specifically trained or optimized for the document types being processed.

It is also important to take into account the quality and diversity of the training data used to train the ML Extractor to ensure accurate and reliable extraction results.

C.  

The cost of the ML Extractor should be the main consideration when choosing an ML Extractor.

Select the ML Extractor that offers the lowest price, regardless of its performance or suitability for the specific document understanding needs.

D.  

The size of the ML Extractor is the most important factor to consider when choosing an ML Extractor.

Bigger models always perform better and provide more accurate extraction results because the development team invested time and effort into creating the algorithm, which in turn will result in better performance for the trained model.

A.  

Error, Critical, Info, Warning, Verbose

B.  

Exception, Info, Warning, Verbose

C.  

Error, Info, Warning, Verbose

D.  

Fatal, Error, Warning, Info, Trace

A.  

RPA Developer.

B.  

Process Controller.

C.  

Administrator.

D.  

Data Scientist.

A.  

For use cases in which non-variable format documents need to be processed.

B.  

For structured or semi-structured documents where the extraction method is based on a set of FlexiCapture definition files.

C.  

For structured or semi-structured documents where for certain fields, data is always found in a strict, predictable format and context.

D.  

For structured or semi-structured documents in which layouts of different document providers vary greatly.

A.  

Using the Al Center IDE (Integrated Development Environment).

B.  

Using the Al Center model builder.

C.  

Using a Python IDE (Integrated Development Environment) or an AutoML platform.

D.  

Using a C/C++ IDE (Integrated Development Environment), then upload the code to Al Center IDE.

A.  

The number of occurrences and the extraction confidence.

B.  

The page number from which the field was extracted and the exact position on the page.

C.  

The extraction confidence and the digitization confidence.

D.  

The position on the page.

A.  

Digitized Object Model is an XML object containing information such as page data, content, and coordinates for every image identified in the file.

B.  

Data Object Model is a YAML object containing information such as name, content type, text length, and the number of pages.

C.  

Document Object Model is a JSON object containing information such as name, content type, text length, and the number of pages.

D.  

Digitize Object Module is an XML object containing information such as mandatory field names, types, and values

A.  

Load Taxonomy, Digitization, Categorization, Data Validation, and Export

B.  

Load Document, Categorization, Data Extraction, and Validation

C.  

Load Taxonomy, Digitization, Classification, Data Extraction, and Data Validation Export

D.  

Import, Classification, Text Extractor, and Data Validation

A.  

To integrate with other connected automations seamlessly.

B.  

To offer a fully functional document processing tool that is easy to use and execute.

C.  

To create custom workflows from scratch.

D.  

To eliminate the need for exception handling in workflows.

A.  

Status not valid.

B.  

Status is Unknown.

C.  

Status is Pending.

D.  

Status is New.

A.  

It requires manual data entry, as structured documents cannot be processed automatically.

B.  

It relies on AI models for natural language processing.

C.  

It uses optical character recognition (OCR) to extract text from the documents.

D.  

It leverages predefined templates for accurate data extraction.

A.  

An ML skill is by default public and can be made private.

B.  

An ML skill is by default private and can be made public.

C.  

An ML skill is by default public and can't be made private.

D.  

An ML skill is by default private and can't be made public.

A.  

Use them as a template to create other tests.

B.  

Simply run the existing tests

C.  

Based on the use case developed, create test data to test existing and new tests.

D.  

Based on the use case developed, create test data to test existing tests.

A.  

When the custom document types are very similar and file splitting is not necessary.

B.  

When the custom document types are not similar and file splitting is not necessary.

C.  

When the custom document types are not similar and file splitting is necessary.

D.  

When the custom document types are very similar and file splitting is necessary.

A.  

Exact match and Auto.

B.  

Exact match and First span.

C.  

Exact match and Native string search.

D.  

Exact match and Levenshtein.

A.  

Identifies and extracts specific information that should be processed.

B.  

Applies rules for validating that the information extracted from a document is correct.

C.  

Digitizes the document that should be processed.

D.  

Identifies words and their coordinates from images and PDFs.

A.  

Each label should be identifiable from the text of the individual verbatim (not thread) to which it will be applied.

B.  

Each label should include customer experience/sentiment analysis in its coverage.

C.  

Each parent label should have at least 3 children labels to ensure specificity.

D.  

Each label should overlap sliqhtlv with a few distinct others so we ensure 100% coveraqe.

A.  

Kick-off phase

B.  

Solution Design phase

C.  

Process Design phase

D.  

User Acceptance Testing phase

A.  

Train models using unsupervised learning.

B.  

View, save, and modify dataset model versions.

C.  

Access detailed, queryable charts, statistics, and customizable dashboards.

D.  

Monitor model performance and receive recommendations.

A.  

Data labeling session name and dataset.

B.  

Data labeling name, dataset. and Al Center project.

C.  

Dataset and Al Center project.

D.  

Data labeling name, language, and number of documents.

A.  

Taxonomy, Document Object Model, Automatic Extraction Results, Document Directory.

B.  

Taxonomy, Document Path, Document Object Model, Document Text, Automatic Classification Results.

C.  

Taxonomy, Document Path, Document Directory, Document Text, Automatic Extraction Results.

D.  

Taxonomy, Document Path, Document Object Model, Document Text.

A.  

evaluate(self, evaluation_directory)

B.  

save(self)

C.  

train(setf. trainmg_directory}

D.  

__init_(self)

A.  

Running reports and sending them via email to stakeholders overnight.

B.  

Generating invoices that require manual approval before issuing.

C.  

Providing on-demand assistance to users for specific activities.

D.  

Resolving customer queries with real-time input from support agents.

A.  

A collection of raw unlabeled communications data of a similar type, that can be associated with up to 10 datasets.

B.  

The model that we create when training the platform to understand the data in those sources.

C.  

A permissioned storage area within the platform which contains communications and labels.

D.  

A user-permissioned project containing a taxonomy with labels and entities.

A.  

The changes made by one user override the changes made by others.

B.  

The changes made by all users are saved successfully.

C.  

Concurrent labeling is not allowed.

D.  

A warning message is displayed to the other user(s) indicating unsuccessful changes.

A.  

Pipeline type: Full

Package Major Version: 23.10.4.0 Package Minor Version: 1 Input Dataset: 800 pages Evaluation Dataset: 100 pages

B.  

Pipeline type: Evaluate

Package Major Version: 23.10.4.0 Package Minor Version: 0 Input Dataset: 1000+800 pages Evaluation Dataset: 100 pages

C.  

Pipeline type: Full Package Major Version: 23.10.4.0 Package Minor Version: 0 Input Dataset: 1000+800 pages Evaluation Dataset: 100 pages

D.  

Pipeline type: Training Package Major Version: 23.10.4.0 Package Minor Version: 1 Input Dataset: 1000+800 Evaluation Dataset: N/A

A.  

Hybrid and manual data extraction.

B.  

Rule-based and model-based data extraction.

C.  

Rule-based and hybrid data extraction.

D.  

Manual and model-based data extraction.

A.  

Document Types. Taxonomy. Languages. Success Criteria. OCR, ML Model.

B.  

Document Types. Taxonomy. Templates. Languages. Scans/Digital docs, Success Criteria. Technical Criteria.

C.  

Document Types. Technical Criteria, Templates. Languages, Scans/Digital docs, OCR quality.

D.  

Document Types. Templates. Technical Criteria. Languages. Scans/Digital docs. Success Criteria. OCR engines.

A.  

The extraction confidence and the digitization confidence.

B.  

The number of occurrences and the extraction confidence.

C.  

The position on the page.

D.  

The page number from which the field was extracted and the exact position on the page.

A.  

Data Scientist.

B.  

Administrator.

C.  

RPA Developer.

D Process Controller

A.  

Label predictions.

B.  

Entity descriptions.

C.  

Entity predictions.

D.  

Label descriptions.

A.  

Pre-trained. fine-tunable, and reviewed.

B.  

Pre-trained. custom training, and fine-tunable.

C.  

Custom training, fine-tunable, and reviewed.

D.  

Pre-trained, custom training, and reviewed.

A.  

To select which extractors are trained for each document type and field.

B.  

To present a document processing specific user interface for validating and correcting automatic classification outputs.

C.  

To create and edit a Taxonomy file specific to the current automation project.

D.  

To select the type of ML that can be used in the project.

A.  

General fields and datasets.

B.  

Labels and sources.

C.  

Messages, labels, and general fields.

D.  

Labels and general fields.

A.  

The model makes correct predictions across the majority of the dataset.

B.  

All of the labels in the dataset have at least 25 training examples.

C.  

Many of the labels in the taxonomy have amber or red performance warnings.

D.  

2% of the dataset has been reviewed by a model trainer.

A.  

Using Read Taxonomy activity.

B.  

Using DeserializeTaxonomy activity.

C.  

Using Load Taxonomy activity.

D.  

Using DocumentTaxonomy.Deserialize method inside an Assign activity.

A.  

The parent label and any child labels to that parent label are removed from any reviewed messages, any messages with updated annotations are flagged for review.

B.  

The parent label and any child labels to that parent label are removed from any reviewed messages.

C.  

The parent label is removed from any reviewed messages but the child labels to that parent label remain.

D.  

The parent label is removed from any reviewed messages, messages with any child labels to that parent label are flagged for review.

A.  

Network Attached Storage and Orchestrator Bucket.

B.  

Locally, Temp Folder, Network Attached Storage, and Orchestrator Bucket.

C.  

Orchestrator Bucket and Queue Item.

D.  

On a VM, Orchestrator Bucket, and Network Attached Storage.

A.  

Create Document Labeling Action activity

B.  

Create Labeling Task activity

C.  

Create Labeling Action activity

D.  

Create External Task activity

A.  

15

B.  

20

C.  

25

D.  

30

A.  

The higher the coverage, the lower the model's recall, resulting in greater throughput of automatable processes.

B.  

High coverage ensures that the software consumes less computational resources, resulting in cost savings for the organization implementing the automation.

C.  

High coverage on the model means that fewer communications will be sent for manual review and that fewer automatable processes are missed.

D.  

With high coverage, you can increase the amount of data provided downstream via Streams.

A.  

Label bias warnings.

B.  

Increases data security.

C.  

Increases the taxonomy coverage.

D.  

Label precision and recall.

A.  

Out-of-the-box models from UiPath and UiPath technology partners.

B.  

Out-of-the-box models from UiPath technology partners and custom models.

C.  

Out-of-the-box models from UiPath, UiPath technology partners, open-source models from the community, and custom models.

D.  

Out-of-the-box models from UiPath technology partners, and open-source models from the community.

A.  

Download to Excel. Download, and Export to Al Center.

B.  

Download to Excel. Export to Al Center, and Export All.

C.  

Download to Excel and Export All.

D.  

Export to Al Center, Export All. and Download.

A.  

Name, description, and labels.

B.  

Name, description, and permissions.

C.  

Name and description.

D.  

Name and labels.

A.  

An incorrect prediction.

B.  

A lower confidence score.

C.  

Multiple label predictions.

D.  

A higher confidence score.

A.  

Taxonomy Uploading

B.  

Assisted Labelling

C.  

Preview Mode

D.  

Sentiment Analysis

A.  

It guides you through the completion of model training before starling entity training.

B.  

It guides you to focus solely on model refinement.

C.  

It guides you right from the moment you create a dataset with the next best action to take to advance your general fields training.

D.  

It guides you to start entity training without a dataset.

A.  

To classify documents using AI Center out-of-the-box generative models.

B.  

To classify documents using generative OCR.

C.  

To classify documents using generative models.

D.  

To classify documents using a combination of generative and specialized models.

A.  

By sending a GET request to /api/framework/projects/{projectld}/classifiers/generative_classifier/classification with a body containing prompts that specify the 'Invoice' and 'Receipt' names and descriptions.

B.  

By sending a POST request to yapi/framework/projectsy{projectld}/ctassifiers/generative_classifier/classification with a body containing prompts that specify the 'Invoice' and 'Receipt' names and descriptions.

C.  

By sending a PUT request to /api/framework/proiects/{projectld}/classifiers/generative_classifier/classification without any specific classification details in the body of the request.

D.  

By sending a POST request to /api/framework/projects/{projectld}/classifiers/generative_classifier/dassification with a body containing prompts that specify the 'Invoice' and 'Receipt' names and a description for their fields.

A.  

UiPath Communications Mining.

B.  

UiPath Task Mining.

C.  

UiPath Process Mining.

D.  

UiPath Document Understanding.

A.  

Create Document Classification Action.

B.  

Train Classifiers Scope.

C.  

Wait for Document Classification and Resume.

D.  

Present Classification Station.

A.  

The understanding of the parent-label relationship when assigning label predictions.

B.  

The difference between label suggestions and label predictions in a training process.

C.  

The identification of a specific span of text as a value for a particular entity type.

D.  

The model's confidence that a specific concept exists within a communication.

A.  

S2

B.  

S3

C.  

A1

D.  

S4

A.  

Name, Classification type. Input to be labeled. Attribute name. Shortcut, and Color.

B.  

Name, Input to be labeled. Attribute name, and Shortcut.

C.  

Name, Classification type, Attribute name, and Shortcut.

D.  

Name, Classification Type. Attribute name. Color, and Shortcut.

A.  

5

B.  

10

C.  

15

D.  

20

A.  

Verbose

B.  

Warning

C.  

Information

D.  

Error

A.  

Model Ratings of "Good" or better and individual performance factors rated as "Good" or better.

B.  

Model Ratings of "Good" and individual performance factors rated as "Excellent".

C.  

Model Ratings of "Excellent" and individual performance factors rated as "Good" or better.

D.  

Model Ratings of "Excellent" and individual performance factors rated as "Excellent".

A.  

Process unstructured communication data using NLP.

B.  

Analyze financial data.

C.  

Design user interfaces.

D.  

Generate code for automation processes.