When is it recommended to use Main-ActionCenter in the context of the Document Understanding Process?
- A . When implementing an attended process.
- B . When testing locally or implementing an attended process.
- C . When testing locally.
- D . When testing locally or implementing an unattended process.
What components are part of the Document Understanding Process template?
- A . Import. Classification. Text Extractor, and Data Validation.
- B . Load Document. Categorization. Data Extraction, and Validation.
- C . Load Taxonomy, Digitization. Classification, Data Extraction, and Data Validation Export.
- D . Load Taxonomy, Digitization. Categorization. Data Validation, and Export.
What is the Document Object Model (DOM) in the context of Document Understanding?
- A . The DOM is a JSON object containing information such as name, content type, text length, number of pages, page rotation, detected language, content, and coordinates for the words identified in the file.
- B . The DOM is a built-in artificial intelligence system that automatically understands and interprets the content and the type of documents, eliminating the need for manual data extraction.
- C . The DOM is a feature that allows you to convert physical documents into virtual objects that can be manipulated using programming code.
- D . The DOM is a graphical user interface (GUI) tool in UiPath Document Understanding that provides visual representations of documents, making it easier for users to navigate and interact with the content.
DRAG DROP
What is the correct order of uploading a package exported from UiPath AI Center?
Instructions: Drag the steps found on the "Left" and drop them on the "Right" in the correct order.
For an analytics use case, what are the recommended minimum model performance requirements in UiPath Communications Mining?
- 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".
DRAG DROP
What is the correct order of recommended steps when introducing new labels into a mature taxonomy?
Instructions: Drag the steps found on the "Left" and drop them on the "Right" in the correct order.
What do entities represent in UiPath Communications Mining?
- A . Structured data points.
- B . Concepts, themes, and intents.
- C . Thread properties.
- D . Metadata properties.
A
Explanation:
A Document Understanding Process is in production.
According to best practices, what are the locations recommended for exporting the result files?
- 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.
While training a UiPath Communications Mining model, the Search feature was used to pin a certain label on a few communications. After retraining, the new model version starts to predict the tagged label but infrequently and with low confidence.
According to best practices, what would be the correct next step to improve the model’s predictions for the label, in the "Explore" phase of training?
- A . Use the "Rebalance" training mode to pin the label to more communications.
- B . Use the ‘Teach" training mode to pin the label to more communications.
- C . Use the "Low confidence" training mode to pin the label to more communications.
- D . Use the "Search" feature to pin the label to more communications.
DRAG DROP
What is the correct execution order of the Document Understanding template stages?
Instructions: Drag the stages found on the "Left" and drop them on the "Right” in the correct order.
Which of the following are unstructured documents?
- A . Invoices, receipts, purchase orders, and medical bills.
- B . Banking forms, tax forms, surveys, and identity cards.
- C . Contracts, emails, banking forms, and tax forms.
- D . Contracts, agreements, and emails.
When creating a training dataset, what is the recommended number of samples for the Classification fields?
- A . 5-10 document samples from each class.
- B . 10-20 document samples from each class.
- C . 20-50 document samples from each class.
- D . 50-200 document samples from each class.
What is one of the purposes of the Config file in the UiPath Document Understanding Template?
- A . It contains the configuration settings for the UiPath Robot and Orchestrator integration.
- B . It stores the API keys and authentication credentials for accessing external services.
- C . It specifies the output file path and format for the processed documents.
- D . It defines the input document types and formats supported by the template.
Which of the following file types are supported for the DocumentPath property in the Classify Document Scope activity?
- A . .bmp, .pdf, .jpe, .psd
- B . .png, .gif, .jpe, .tiff
- C . .pdf, .jpeg, .raw, tif
- D . .jpe, .eps, .jpg, .tiff
When processing a document type that comes in a high variety of layouts, what is the recommended data extraction methodology?
- A . Model-based data extraction.
- B . Hybrid data extraction.
- C . Manual data extraction.
- D . Rule-based data extraction.
Which is a high-level view of the tabs within an AI Center project?
- A . Dashboard. Datasets. ML Packages. ML Training. ML Evaluation, and ML Logs.
- B . Datasets, Data Labeling. ML Packages, ML Training, ML Evaluation, ML Skills, and ML Logs.
- C . Datasets. Data Labeling. ML Packages. Pipelines, and ML Skills.
- D . Dashboard. Datasets, Data Labeling. ML Packages. Pipelines, ML Skills, and ML Logs.
Can you use Queues in the Document Understanding Process?
- A . The Document Understanding Process can’t use Queues because items waiting for Human Validation for more than 10 days will be marked as Abandoned.
- B . The Document Understanding Process can use Queues but the Auto Retry Functionality should be disabled.
- C . The Document Understanding Process can use Queues but the Auto Retry Functionality should be enabled.
- D . The Document Understanding Process can’t use Queues because items waiting for Human Validation for more than 24h will be marked as Abandoned.
How long does the typical Machine Learning model deployment process take in UiPath AI Center?
- A . Less than 5 minutes.
- B . Between 5 and 10 minutes.
- C . Between 10 and 15 minutes.
- D . More than 15 minutes.
What are the available options for Scoring in Document Manager, that apply only to string content
type?
- A . Exact match and Naive string search.
- B . Exact match and Phonetic matching.
- C . Exact match and Levenshtein.
- D . Exact match and Finite state automation-based search.
What is the name of the web application that allows users to prepare, review, and make corrections to datasets required for Machine Learning models?
- A . Document Manager.
- B . Digitization.
- C . Data Manager.
- D . ML Extractor.
What does the following expression do?
subTotalAdditions.Select(Function(field) CDec(documentFields(field))).ToList.Sum() + subtotal
- A . Sums up subtotal fields from the config file converted to CDec with the subtotal.
- B . Sums up all the line amounts and converts the fields to CDec.
- C . Sums up all the line amounts converted to CDec and the subtotal
- D . Sums up the subtotal to the total variable by converting it to CDec
What additional information can be included in the exported data, apart from the extraction results?
- 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.
Which technology enables UiPath Communications Mining to analyze and enable action on messages?
- A . Natural Language Processing (NLP)
- B . Virtual Reality.
- C . Cloud Computing.
- D . Robotic Process Automation
Why might labels have bias warnings in UiPath Communications Mining, even with 100% precision?
- A . They were trained using the "Search" option extensively.
- B . They were trained using the "Shuffle" option extensively.
- C . They have low recall.
- D . They lack training examples.
What happens when multiple users try to label the same document concurrently?
- 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.
Which environment variable is relevant for Evaluation pipelines?
- A . eval.enable_ocr
- B . eval.redo_ocr
- C . eval.enable_qpu
- D . eval.use_cuda
What is supervised learning?
- A . Supervised learning is a machine learning paradigm in which algorithms try to solve a problem only by trial and error and using a system of rewards and punishments.
There is no need for labeled input/output pairs to be presented. Instead, the focus is on finding a balance between exploration (of uncharted territory) and exploitation (of current knowledge). - B . Supervised learning is a machine learning paradigm in which algorithms try to solve a problem in an uncertain, potentially complex environment only by trial and error and using a system of rewards and punishments.
There are no correct answers, but feedback is given in the form of rewards and penalties. - C . Supervised learning is a machine learning paradigm with the goal of learning a function that maps input variables with output variables.
In every case there is a correct answer, so the aim is to train the model until it reaches an acceptable level of performance in predicting the outcome, at which point the learning stops. - D . Supervised learning is a machine learning paradigm that refers to algorithms that learn patterns from unlabeled data.
There are only input variables, but no corresponding output variables. The goal of the algorithm is to model the underlying structure of the data, but there are no correct answers and no teachers.
Which of the following OCR (Optical Character Recognition) engines is not free of charge?
- A . Tesseract.
- B . Microsoft Azure OCR.
- C . OmniPaqe.
- D . Microsoft OCR.
What is the purpose of the End Process in the Document Understanding Process?
- A . The purpose of the End Process in the Document Understanding Process is to generate a summary report of the processing statistics and performance metrics.
- B . End Process sets the queue transaction status as Successful in case of no exception, and as Failed in case of an exception with their corresponding Business or System Exception, and the post processing/cleaning if required.
- C . End Process in the Document Understanding Process silently shuts down the Virtual Machine so that another robot can use it.
- D . End Process is a feature in the Document Understanding Process that exports the extracted data into a readable document format.
What is the definition of Deep Learning?
- A . A sub-field of artificial intelligence that enables systems to learn from data.
Systems learn from previous experience and information to deduce and predict future information. To do this they use algorithms that learn to perform a specific task without being explicitly programmed. - B . The theory and development of computer systems that are able to perform tasks that normally require human intelligence and decision making.
- C . A field of artificial intelligence that enables computers to gain high-level understanding from digital images or videos. If AI is the brain, then this is the eye that enables the computer to observe and understand. It works the same as the human eye.
- D . An area of machine learning concerned with artificial neural networks.
These are a series of algorithms that aim to recognize relationships in a set of data through a process that mimics biological neural networks.