Microsoft

AI-102
Designing and Implementing a Microsoft Azure AI Solution
QUESTION & ANSWERS

https://www.microsoftdumps.us/AI-102-exam-questions
 Topics Number of Questions Question Sequance
Topic 1 1 1-1
Topic 2 1 2-2
Topic 3 26 3 - 28
Mix Questions 9 29 - 37
Total 37

Topic 1
Case Study: Topic 1

QUESTION: 1

You are planning the product creation project.You need to recommend a process for analyzing videos.Which
four actions should you perform in sequence? To answer, move the appropriate actions from the list
ofactions to the answer area and arrange them in the correct order. (Choose four.)

Answer :

https://www.microsoftdumps.us/AI-102-exam-questions
 Explanation/Reference:

Scenario: All videos must have transcripts that are associated to the video and included in productdescriptions.Product

descriptions, transcripts, and all text must be available in English, Spanish, and Portuguese.Step 1: Upload the video to blob

storageGiven a video or audio file, the file is first dropped into a Blob Storage. TStep 2: Index the video by using the Video

Indexer API.When a video is indexed, Video Indexer produces the JSON content that contains details of the specified

videoinsights. The insights include: transcripts, OCRs, faces, topics, blocks, etc.Step 3: Extract the transcript from the Video

Indexer API.Step 4: Translate the transcript by using the Translator API.Reference:https://azure.microsoft.com/en-us/blog/get-

video-insights-in-even-more-languages/https://docs.microsoft.com/en-us/azure/media-services/video-indexer/video-indexer-

output-json-v2

Topic 2
Case Study: Topic 2

QUESTION: 2

You are developing the knowledgebase.You use Azure Video Analyzer for Media (previously Video indexer) to
obtain transcripts of webinars.You need to ensure that the solution meets the knowledgebase
requirements.What should you do?

https://www.microsoftdumps.us/AI-102-exam-questions
 Option A : Create a custom language model

Option B : Configure audio indexing for videos only

Option C : Enable multi-language detection for videos

Option D : Build a custom Person model for webinar presenters

Correct Answer: B

Explanation/Reference:

Can search content in different formats, including videoAudio and video insights (multi-channels). When indexing by one

channel, partial result for those models willbe available.Keywords extraction: Extracts keywords from speech and visual

text.Named entities extraction: Extracts brands, locations, and people from speech and visual text via naturallanguage

processing (NLP).Topic inference: Makes inference of main topics from transcripts. The 2nd-level IPTC taxonomy is

included.Artifacts: Extracts rich set of "next level of details" artifacts for each of the models.Sentiment analysis: Identifies

positive, negative, and neutral sentiments from speech and visual text.Reference:https://docs.microsoft.com/en-

us/azure/azure-video-analyzer/video-analyzer-for-media-docs/video-indexer-overview

Topic 3
Case Study: Topic 3

QUESTION: 3

You have the following C# method for creating Azure Cognitive Services resources programmatically.

You need to call the method to create a free Azure resource in the West US Azure region. The resource will
beused to generate captions of images automatically.Which code should you use?

Option A : create_resource(client, "res1", "ComputerVision", "F0", "westus")

Option B : create_resource(client, "res1", "CustomVision.Prediction", "F0", "westus")

Option C : create_resource(client, "res1", "ComputerVision", "S0", "westus")

Option D : create_resource(client, "res1", "CustomVision.Prediction", "S0", "westus")

https://www.microsoftdumps.us/AI-102-exam-questions
 Correct Answer: B

Explanation/Reference:

Explanationhttps://azure.microsoft.com/en-us/pricing/details/cognitive-services/computer-vision/

QUESTION: 4

You are training a Language Understanding model for a user support system.You create the first intent
named GetContactDetails and add 200 examples.You need to decrease the likelihood of a false positive.What
should you do?

Option A : Enable active learning.

Option B : Add a machine learned entity.

Option C : Add additional examples to the GetContactDetails intent.

Option D : Add examples to the None intent.

Correct Answer: A

Explanation/Reference:

Active learning is a technique of machine learning in which the machine learned model is used to identifyinformative new

examples to label. In LUIS, active learning refers to adding utterances from the endpointtraffic whose current predictions are

unclear to improve your model.Reference:https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-glossary

QUESTION: 5

You have a bot that was built by using the Microsoft Bot Framework composer as shown in the following
exhibit.

https://www.microsoftdumps.us/AI-102-exam-questions
Use the drop-down menus 10 select the answer choice that completes each statement based on the
informationpresented in the graphic.NOTE: Each correct selection is worth one point

Answer :

Explanation/Reference:

QUESTION: 6

You are designing a conversation flow to be used in a chatbot.You need to test the conversation flow by
using the Microsoft Bot Framework Emulator.How should you complete the .chat file? To answer, select the
appropriate options in the answer area.NOTE: Each correct selection is worth one point.

https://www.microsoftdumps.us/AI-102-exam-questions
Answer :

https://www.microsoftdumps.us/AI-102-exam-questions
Explanation/Reference:

Graphical user interface, text, application Description automatically generated

Reference: https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-howto-add-media-attachments?view=azure-bot-

service-

QUESTION: 7

You are building a chatbot by using the Microsoft Bot Framework SDK.You use an object named UserProfile to
store user profile information and an object named ConversationDatato store information related to a
conversation.You create the following state accessors to store both objects in state.var userStateAccessors =
_userState.CreateProperty(nameof(UserProfile));var conversationStateAccessors
=_conversationState.CreateProperty(nameof(ConversationData));The state storage mechanism is set to
Memory Storage.For each of the following statements, select Yes if the statement is true. Otherwise, select
No.NOTE: Each correct selection is worth one point.

https://www.microsoftdumps.us/AI-102-exam-questions
 Answer :

Explanation/Reference:

Box 1: Yes

You create property accessors using the CreateProperty method that provides a handle to the BotState object.Each state

property accessor allows you to get or set the value of the associated state property.Box 2: YesBox 3: NoBefore you exit the

turn handler, you use the state management objects' SaveChangesAsync() method to writeall state changes back to

storage.Reference:https://docs.microsoft.com/en-us/azure/bot-service/bot-builder-howto-v4-state

https://www.microsoftdumps.us/AI-102-exam-questions
QUESTION: 8

Which Azure Storage service implements the key/value model?

Option A : Azure Files

Option B : Azure Blob

Option C : Azure Table

Option D : Azure Queue

Correct Answer: C

QUESTION: 9

You have an Azure subscription that contains an Azure Cognitive Service for Language resource. You need to
identify the URL of the REST interface for the Language service. Which blade should you use in the Azure
portal?

Option A : Identity

Option B : Keys and Endpoint

Option C : Properties

Option D : Networking

Correct Answer: B

QUESTION: 10

You are building a language model by using a Language Understanding service.You create a new Language
Understanding resource.You need to add more contributors.What should you use?

Option A : a conditional access policy in Azure Active Directory (Azure AD)

Option B : the Access control (1AM) page for the authoring resources in the Azure portal

Option C : the Access control (1AM) page for the prediction resources in the Azure portal

https://www.microsoftdumps.us/AI-102-exam-questions
 Correct Answer: B

Explanation/Reference:

Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-collaborate

QUESTION: 11

You train a Custom Vision model to identify a company’s products by using the Retail domain.You plan to
deploy the model as part of an app for Android phones.You need to prepare the model for deployment.Which
three actions should you perform in sequence? To answer, move the appropriate actions from the list
ofactions to the answer area and arrange them in the correct order.

Answer :

https://www.microsoftdumps.us/AI-102-exam-questions
Explanation/Reference:

In user want to change to deploy offline model1. Change model domain to compact model2. Retrain compact model3. Export

modelReference:https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/export-your-model

QUESTION: 12

You are building a natural language model.You need to enable active learning.What should you do?

Option A : Add show-all-intents=true to the prediction endpoint query.

Option B : Enable speech priming.

Option C : Add log=true to the prediction endpoint query.

Option D : Enable sentiment analysis.

Correct Answer: C

Explanation/Reference:

Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-review-endpoint-utterances#log-user-

queries

QUESTION: 13

You are building a bot by using Microsoft Bot Framework.You need to configure the bot to respond to spoken
requests. The solution must minimize development effort.What should you do?

Option A : Deploy the bot to Azure and register the bot with a Direct Une Speech channel

Option B : Integrate the bot with Cortana by using the Bot Framework SDK.

Option C : Create an Azure function that will call the Speech service and connect the bot to the function.

Option D : Deploy the bot to Azure and register the bot with a Microsoft Teams channel.

Correct Answer: A

https://www.microsoftdumps.us/AI-102-exam-questions
QUESTION: 14

You are developing a text processing solution.You develop the following method.

You call the method by using the following code.GetKeyPhrases(textAnalyticsClient, "the cat sat on the
mat");For each of the following statements, select Yes if the statement is true. Otherwise, select No.NOTE:
Each correct selection is worth one point

Answer :

Explanation/Reference:

https://www.microsoftdumps.us/AI-102-exam-questions
Box 1: YesThe Key Phrase Extraction API evaluates unstructured text, and for each JSON document, returns a list of

keyphrases.Box 2: No'the' is not a key phrase.This capability is useful if you need to quickly identify the main points in a

collection of documents. Forexample, given input text "The food was delicious and there were wonderful staff", the service

returns themain talking points: "food" and "wonderful staff".Box 3: NoKey phrase extraction does not have confidence

levels.Reference:https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-

to-keyword-extrac

QUESTION: 15

Match the types of workloads to the appropriate scenarios.To answer, drag the appropriate workload type
from the column on the left to its scenario on the right. Eachworkload type may he used once, more than
once, or not at all.NOTE: Each correct match is worth one point.

Answer :

Explanation/Reference:

QUESTION: 16

Your company needs to implement a relational database in Azure. The solution must minimize ongoing
maintenance. Which Azure service should you use?

Option A : SQL Server on Azure Virtual Machines

Option B : Azure SOL Database

Option C : Azure HDInsight

https://www.microsoftdumps.us/AI-102-exam-questions
 Option D : Azure Cosmos DB

Correct Answer: B

QUESTION: 17

Select the answer that correctly completes the sentence.

Answer :

Explanation/Reference:

QUESTION: 18

You have a web app that uses Azure Cognitive Search.When reviewing billing for the app, you discover much
higher than expected charges. You suspect that thequery key is compromised.You need to prevent
unauthorized access to the search endpoint and ensure that users only have read onlyaccess to the
documents collection. The solution must minimize app downtime.Which three actions should you perform in
sequence? To answer, move the appropriate actions from the list ofactions to the answer area and arrange
them in the correct order.

https://www.microsoftdumps.us/AI-102-exam-questions
 Answer :

Explanation/Reference:

Graphical user interface, text Description automatically generated

Reference: https://docs.microsoft.com/en-
us/azure/search/search-security-api-keys

QUESTION: 19

You have a chatbot that uses a QnA Maker application.You enable active learning for the knowledge base
used by the QnA Maker application.You need to integrate user input into the model.Which four actions should
you perform in sequence? To answer, move the appropriate actions from the list ofactions to the answer area
and arrange them in the correct order.

https://www.microsoftdumps.us/AI-102-exam-questions
Answer :

https://www.microsoftdumps.us/AI-102-exam-questions
Explanation/Reference:

Graphical user interface, application Description automatically generated

Step 1: For the knowledge base, select Show active learning suggestions.In order to see the suggested questions, on the Edit

knowledge base page, select View Options, then selectShow active learning suggestions.Step 2: Approve and reject

suggestions.Each QnA pair suggests the new question alternatives with a check mark, , to accept the question or an x toreject

the suggestions. Select the check mark to add the question.Step 3: Save and train the knowledge base.Select Save and Train

to save the changes to the knowledge base.Step 4: Publish the knowledge base.Select Publish to allow the changes to be

available from the GenerateAnswer API.When 5 or more similar queries are clustered, every 30 minutes, QnA Maker suggests

the alternate questionsfor you to accept or reject.Reference:https://docs.microsoft.com/en-us/azure/cognitive-

services/qnamaker/how-to/improve-knowledge-base

QUESTION: 20

Select the answer that correctly completes the sentence.

Answer :

https://www.microsoftdumps.us/AI-102-exam-questions
Explanation/Reference:

QUESTION: 21

You need to create a visualization of running sales totals per quarter as shown in the following exhibit.

What should you create in Cower Bl Desktop;1

Option A : a waterfall chart

Option B : a ribbon chart

Option C : a bar chart

Option D : a decomposition tree

Correct Answer: C

QUESTION: 22

You plan to build an app that will generate a list of tags for uploaded images. The app must meet the
followingrequirements:• Generate tags in a user’s preferred language.• Support English, French, and
Spanish.• Minimize development effortYou need to build a function that will generate the tags for the app.
Which Azure service endpoint should youuse?

https://www.microsoftdumps.us/AI-102-exam-questions
 Option A : Custom Vision image classification

Option B : Content Moderator Image Moderation

Option C : Custom Translator

Option D : Computer Vision Image Analysis

Correct Answer: A

QUESTION: 23

You are building a Language Understanding solution.You discover that many intents have similar utterances
containing airport names or airport codes.You need to minimize the number of utterances used to fram the
model.Which type of custom entity should you use?

Option A : Pattera.any

Option B : machine-learning

Option C : list

Option D : regular expression

Correct Answer: C

QUESTION: 24

You are building a model to detect objects in images.The performance of the model based on training data is
shown in the following exhibit

https://www.microsoftdumps.us/AI-102-exam-questions
 Answer :

Explanation/Reference:

QUESTION: 25

You are building a chatbot for a travel agent. The chatbot will use the Azure OpenAI GPT 3.5 model and will
be used to make travel reservations. You need to maximize the accuracy of the responses from the chatbot.
What should you do?

Option A :

Configure the model to include data from the travel agent's database.

Option B :

Set the Top P parameter for the model to 0.

https://www.microsoftdumps.us/AI-102-exam-questions
 Option C :

Set the Temperature parameter for the model to 0.

Option D :

Modify the system message used by the model to specify that the answers must be accurate.

Correct Answer: A

QUESTION: 26

You are building an Azure web app named App1 that will translate text from English to Spanish. You need to
use the Text Translation REST API to perform the translation. The solution must ensure that you have data
sovereignty in the United States. How should you complete the URI? To answer, select the appropriate
options in the answer area. NOTE: Each correct selection is worth one point.

Answer :

https://www.microsoftdumps.us/AI-102-exam-questions
Explanation/Reference:

1. api-nam.cognitive.microsofttranslator.com 2. translate https://learn.microsoft.com/en-us/azure/cognitive-

services/Translator/reference/v3-0-reference#base-urls Requests to Translator are, in most cases, handled by the datacenter

that is closest to where the request originated. If there's a datacenter failure when using the global endpoint, the request may

be routed outside of the geography. To force the request to be handled within a specific geography, use the desired

geographical endpoint. All requests are processed among the datacenters within the geography. - United States api-

nam.cognitive.microsofttranslator.com https://learn.microsoft.com/en-us/azure/cognitive-services/translator/reference/rest-api-

guide - translate Translate specified source language text into the target language text.

QUESTION: 27

You are building an app that will use the Azure Video Indexer service.

You plan to train a language model to recognize industry-specific terms.

You need to upload a file that contains the industry-specific terms.

Which file format should you use?

Option A :

PDF

Option B :

XML

Option C :

TXT

Option D :

XLS

https://www.microsoftdumps.us/AI-102-exam-questions
 Correct Answer: C

QUESTION: 28

You have an Azure subscription that contains an Azure OpenA1 resource named AH.

You plan to build an app named App1 that will write press releases by using AM.

You need to deploy an Azure OpenA1 model for Appl. The solution must minimize development effort.

Which three actions should you perform in sequence in Azure OpenAI Studio? To answer, move the

appropriate actions from the list of actions to the answer area and arrange them in the correct order.

Answer :

Explanation/Reference:

https://www.microsoftdumps.us/AI-102-exam-questions
MIXED Questions

QUESTION: 29

You chose Azure Immersive Reader to improve reading comprehension for new learners while modernizing
your business processes. What are the three Azure Al services utilized by Azure Immersive Reader to
enhance reading accessibility?

Option A :

Speech to Text, Custom Text

Option B :

Translation, Text-to-speech

Option C :

Text to Speech, Custom Text

Option D :

Speech to Text, Translation

Correct Answer: B

Explanation/Reference:

Option A is not correct because Speech to Text is used to transcribe audio streams into text, whereas the Custom Text Azure AI

service is used to categorize text into custom classes. This categorization can then be used by developers to label data.

https://www.microsoftdumps.us/AI-102-exam-questions
Option B is the correct answer because the Azure Immersive Reader uses both Translation and Text to Speech services to

enhance reading accessibility and display images for common words.

Option C is not correct because the Azure Immersive Reader uses both Translation and Text to Speech services. The Custom

Text Azure AI service is used to categorize text into custom classes.

Option D is not correct because the Azure Immersive Reader uses Text to Speech service in addition to the Translation service.

Speech to Text is used to submit audio data and retrieve the transcription results.

If you want to learn more, go to: What are Azure AI services? - Azure AI services | Microsoft Learn and Azure AI Immersive

Reader | Microsoft Azure

QUESTION: 30

You have been assigned the task of utilizing Azure Cognitive Language Service's Language Detection
feature. You will need to provide the JSON inputs and receive two outputs, as shown in the code snippets
below. The first output (Output 1) will provide a confidence score of 1, while the second output (Output 2)
will return a confidence score of 0. Please review the given scenario and complete the provided code
snippets by selecting two appropriate options.

https://www.microsoftdumps.us/AI-102-exam-questions
Option A :

fr

Option B :

French

Option C :

countryHint

https://www.microsoftdumps.us/AI-102-exam-questions
 Option D :

(Unknown)

Correct Answer: B,D

Explanation/Reference:

Option A is incorrect because "fr" is the ISO code for the French language. The correct name of the language is "French".

Option B is the correct option. As the confidence score for ISO code "fr" is 1, the name of the language returned is "French".

Here is the completed code for Output 1:

Option C is incorrect because the "countryHint" parameter provides a hint for a region or country in case a sentence has mixed

languages or if there is any ambiguity with the language.

Option D is the correct option. As the confidence score is 0, the language is unknown. Here is the completed code for Output 2:

https://www.microsoftdumps.us/AI-102-exam-questions
If you want to learn more, go to:

What is language detection in Azure AI Language? - Azure AI services | Microsoft Learn

QUESTION: 31

A start-up developing an app for meme creation aims to:

Text content scanning from images.

Extract text from images.

What API should be used?

Option A :

Text Moderation API

Option B :

Content Moderator Review tool

Option C :

Custom term API

Option D :

Image Moderation API

Correct Answer: D

Explanation/Reference:

Option A is incorrect because the Text Moderation API cannot scan images for text.

Option B is also incorrect. The Content Moderator Review tool provides a service that combines human review with machine-

learning content moderation. However, it is not an API.

https://www.microsoftdumps.us/AI-102-exam-questions
Option C is incorrect as well. The Custom Term API helps create custom term lists for the Text Moderation API.

Option D is the correct option. The Image Moderation API can perform both of the functions listed.

If you want to learn more, go to:

Text Moderation - Content Moderator - Azure AI services | Microsoft Learn

What is Azure Content Moderator? - Azure AI services | Microsoft Learn

Moderate text with custom term lists - Content Moderator - Azure AI services | Microsoft Learn

Image Moderation - Content Moderator - Azure AI services | Microsoft Learn

QUESTION: 32

Which Azure service is designed to extract insights such as spoken words, written text, and faces from video
content?

Option A :

Azure AI Speech

Option B :

Azure AI Video Indexer

Option C :

Azure Machine Learning

Option D :

Azure AI Bot Service

Correct Answer: B

https://www.microsoftdumps.us/AI-102-exam-questions
Explanation/Reference:

The Azure AI Video Indexer service is designed to extract insights such as spoken words, written text, and faces from video

content. This service builds upon media AI technologies to make it easier to extract insights from videos.

More info: Azure AI Video Indexer – Video Analyzer for Media | Microsoft Azure

QUESTION: 33

In Question answering, how can you make a bot more engaging in casual conversation?

Option A :

By adding chit-chat

Option B :

By implementing SSML

Option C :

By translating text

Option D :

By adding more entities

Correct Answer: A

Explanation/Reference:

Adding chit-chat to a knowledge base in Question answering makes a bot more engaging and natural in casual conversations.

More info: Adding chitchat to a custom question answering project - Azure AI services | Microsoft Learn

https://www.microsoftdumps.us/AI-102-exam-questions
QUESTION: 34

In which scenario is object detection preferable over image classification?

Option A :

Identifying the presence of a particular object in an image.

Option B :

Categorizing images into predefined classes.

Option C :

Detecting multiple objects and their locations in an image.

Option D :

Sorting images based on color patterns.

Correct Answer: C

Explanation/Reference:

Object detection is preferable when you need to identify multiple objects and their locations within images, whereas image

classification is more about categorizing images into predefined classes.

More info: Object detection - Azure AI Vision - Azure AI services | Microsoft Learn

QUESTION: 35

Which underlying model from Azure OpenAI can be used to utilize the functionalities similar to ChatGPT?

Option A :

text-davinci-003

https://www.microsoftdumps.us/AI-102-exam-questions
 Option B :

gpt-3.5-turbo

Option C :

text-embedding-ada-002 (Version 2)

Correct Answer: B

Explanation/Reference:

The functionalities similar to ChatGPT can be utilized using the GPT-3.5 Turbo model from Azure OpenAI. This model is

optimized for chat and works well for traditional completion tasks. It can understand and generate natural language or code.

The GPT-3.5 Turbo model is available for use with the Chat Completions API. It has similar capabilities to text-davinci-003 using

the Completions API instead of the Chat Completions API. It is recommended to use GPT-3.5 Turbo and GPT-3.5 Turbo Instruct

over legacy GPT-3.5 and GPT-3 models.

More info: Azure OpenAI Service models - Azure OpenAI | Microsoft Learn

QUESTION: 36

Which of the following parameters influence the generative behavior of Azure OpenAI models? (Select three)

Option A :

temperature

Option B :

frequency

Option C :

top_p

https://www.microsoftdumps.us/AI-102-exam-questions
 Option D :

max_tokens

Correct Answer: A,C,D

Explanation/Reference:

Temperature: This parameter controls the randomness of the model’s output. At higher temperatures, the model’s responses

can be more creative and unexpected.

Max length (max_tokens): This parameter sets a limit on the number of tokens in the model’s response. One token is roughly

equivalent to four characters in typical English text.

Top probabilities (top_p): This parameter, similar to temperature, controls the randomness of the model’s output but uses a

different method.

More info: Generative AI with Azure OpenAI (GPT-4 Overview) (c-sharpcorner.com)

QUESTION: 37

Sentiment Analysis in Azure Text Analytics is used to determine what?

Option A :

The topic of the text

Option B :

The positive, negative, or neutral tone of the text

Option C :

The language of the text

https://www.microsoftdumps.us/AI-102-exam-questions
 Option D :

The length of the text

Correct Answer: B

Explanation/Reference:

Sentiment Analysis in Azure Text Analytics is used to identify the sentiment expressed in a text sample. It provides sentiment

labels such as “positive”, “negative”, “neutral”, or “mixed” based on the highest confidence score found by the service at a

sentence and document level.

More info: What is sentiment analysis and opinion mining in the Language service? - Azure AI services | Microsoft Learn

https://www.microsoftdumps.us/AI-102-exam-questions