Microsoft

AI-102 Free Practice Questions — Page 8

Question 74

DRAG DROP - You have an app that manages feedback. You need to ensure that the app can detect negative comments by using the Sentiment Analysis API in Azure AI Language. The solution must ensure that the managed feedback remains on your company’s internal network. Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. NOTE: More than one order of answer choices is correct. You will receive credit for any of the correct orders you select.

Illustration for AI-102 question 74
Show Answer
Correct Answer: Provision the Language service resource in Azure. Deploy a Docker container to an on-premises server. Run the container and query the prediction endpoint.
Explanation:
To keep data on the internal network, Azure AI Language must be used via containers. You first provision the Language resource to obtain keys and billing, then deploy the Language service container on an on-premises server, and finally run the container and send sentiment analysis requests to the local prediction endpoint.

Question 75

You are designing a content management system. You need to ensure that the reading experience is optimized for users who have reduced comprehension and learning differences, such as dyslexia. The solution must minimize development effort. Which Azure service should you include in the solution?

A. Azure AI Immersive Reader
B. Azure AI Translator
C. Azure AI Document Intelligence
D. Azure AI Language
Show Answer
Correct Answer: A
Explanation:
Azure AI Immersive Reader is specifically designed to improve reading comprehension and accessibility for users with learning differences such as dyslexia. It provides features like text-to-speech, adjustable fonts and spacing, syllable breakdown, and reading aids, and can be integrated with minimal development effort. The other options focus on translation, document extraction, or language analysis rather than optimizing the reading experience.

Question 76

You plan to perform predictive maintenance. You collect IoT sensor data from 100 industrial machines for a year. Each machine has 50 different sensors that generate data at one-minute intervals. In total, you have 5,000 time series datasets. You need to identify unusual values in each time series to help predict machinery failures. Which Azure service should you use?

A. Azure AI Computer Vision
B. Cognitive Search
C. Azure AI Document Intelligence
D. Azure AI Anomaly Detector
Show Answer
Correct Answer: D
Explanation:
The requirement is to detect unusual values (anomalies) in large volumes of time series IoT sensor data to support predictive maintenance. Azure AI Anomaly Detector is specifically designed for univariate and multivariate time series anomaly detection, supports batch and real-time analysis, and fits IoT predictive maintenance scenarios. The other options focus on vision, document processing, or search, not time series anomaly detection.

Question 78

You are developing an app that will use the text-to-speech capability of the Azure AI Speech service. The app will be used in motor vehicles. You need to optimize the quality of the synthesized voice output. Which Speech Synthesis Markup Language (SSML) attribute should you configure?

A. the style attribute of the mstts:express-as element
B. the effect attribute of the voice element
C. the pitch attribute of the prosody element
D. the level attribute of the emphasis element
Show Answer
Correct Answer: B
Explanation:
For motor vehicle scenarios, Azure Speech provides an audio effect processor to compensate for playback distortion and noise (for example, car speakers). This is configured using the effect attribute on the voice element (such as eq_car), which specifically optimizes synthesized speech quality for in-car environments.

Question 79

HOTSPOT - You have an Azure subscription that contains an Azure OpenAI resource. You configure a model that has the following settings: • Temperature: 1 • Top probabilities: 0.5 • Max response tokens: 100 You ask the model a question and receive the following response. For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 79 Illustration for AI-102 question 79
Show Answer
Correct Answer: No No No
Explanation:
Billing is based on total tokens (prompt + completion = 123), not just the 86 completion tokens. The finish_reason is "stop" and completion tokens (86) are below the max response tokens (100), so it was not truncated. Max response tokens applies only to generated output tokens; prompt_tokens are not included in that limit.

Question 80

HOTSPOT - You have an Azure subscription. You need to deploy an Azure AI Document Intelligence resource. How should you complete the Azure Resource Manager (ARM) template? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 80
Show Answer
Correct Answer: type: Microsoft.CognitiveServices/accounts kind: FormRecognizer
Explanation:
Azure AI Document Intelligence (formerly Form Recognizer) is deployed as a Cognitive Services account. In ARM templates this requires the resource type Microsoft.CognitiveServices/accounts with the kind set to FormRecognizer.

Question 81

HOTSPOT - You have a collection of press releases stored as PDF files. You need to extract text from the files and perform sentiment analysis. Which service should you use for each task? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 81
Show Answer
Correct Answer: Extract text: Azure AI Document Intelligence Perform sentiment analysis: Azure AI Language
Explanation:
Azure AI Document Intelligence provides OCR optimized for PDF and document text extraction. Azure AI Language includes built-in sentiment analysis for extracted text.

Question 82

You are building an internet-based training solution. The solution requires that a user's camera and microphone remain enabled. You need to monitor a video stream of the user and detect when the user asks an instructor a question. The solution must minimize development effort. What should you include in the solution?

A. speech-to-text in the Azure AI Speech service
B. language detection in Azure AI Language Service
C. the Face service in Azure AI Vision
D. object detection in Azure AI Custom Vision
Show Answer
Correct Answer: A
Explanation:
Detecting when a user asks a question requires understanding spoken input. Speech-to-text in the Azure AI Speech service can transcribe the microphone audio in real time, after which questions can be identified from the text with minimal additional logic. The other options focus on visual analysis or language identification and do not directly detect spoken questions.

Question 83

You have an Azure OpenAI model named AI1. You are building a web app named App1 by using the Azure OpenAI SDK. You need to configure App1 to connect to AI1. What information must you provide?

A. the endpoint, key, and model name
B. the deployment name, key, and model name
C. the deployment name, endpoint, and key
D. the endpoint, key, and model type
Show Answer
Correct Answer: C
Explanation:
When using the Azure OpenAI SDK, you authenticate against an Azure OpenAI resource, not a raw model name. You must provide the resource endpoint and API key, and specify the deployment name you created for the model. API calls reference the deployment name rather than the underlying model name or type.

Question 84

HOTSPOT - You plan to deploy a containerized version of an Azure Cognitive Services service that will be used for sentiment analysis. You configure https://contoso.cognitiveservices.azure.com as the endpoint URI for the service. You need to run the container on an Azure virtual machine by using Docker. How should you complete the command? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

Illustration for AI-102 question 84
Show Answer
Correct Answer: Container image: mcr.microsoft.com/azure-cognitive-services/textanalytics/sentiment Billing: https://contoso.cognitiveservices.azure.com
Explanation:
Sentiment analysis uses the Text Analytics Sentiment container image. The Billing parameter must point to the Azure Cognitive Services resource endpoint used for metering and authentication.

$19

Get all 278 questions with detailed answers and explanations

  • Instant download HTML + PDF delivered the moment payment clears.
  • Secure Stripe checkout we never see or store your card details.
  • 7-day refund if files are defective see our refund policy.