Microsoft Role-based AI-102 Questions & Answers

• Question 11:

  You are examining the Language service output of an application.

  The text analyzed is: Our tour guide took us up the Space Needle during our trip to Seattle last week.

  The response contains the data shown in the following table.

  

  Which Language service API is used 10 analyze the Text?

  A. Entity Linking

  B. Named Entity Recognition

  C. Key Phrase Extraction

  D. Sentiment Analysis

  Correct Answer: B

• Question 12:

  You are building a chatbot.

  You need to configure the chatbot to query a knowledge base.

  Which dialog class should you use?

  A. AdaptiveDialog

  B. QnAMakerDialog

  C. ComponentDialog

  D. SkillDialog

  Correct Answer: B

• Question 13:

  You have a Language service resource that performs the following:

  1.

  Sentiment analysis

  2.

  Named Entity Recognition (NER)

  3.

  Personally Identifiable Information (Pll) identification

  You need to prevent the resource from persisting input data once the data is analyzed.

  Which query parameter in the Language service API should you configure?

  A. loggingOptOut

  B. piiCategories

  C. showStats

  D. Model-version

  Correct Answer: A

• Question 14:

  DRAG DROP

  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 of actions to the answer area and arrange them in the correct order. (Choose four.)

  Select and Place:

  

  Correct Answer:

  

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

  Product descriptions, transcripts, and all text must be available in English, Spanish, and Portuguese.

  Step 1: Upload the video to blob storage

  Given a video or audio file, the file is first dropped into a Blob Storage. T

  Step 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 video insights. 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

• Question 15:

  DRAG DROP

  You are developing the smart e-commerce project.

  You need to design the skillset to include the contents of PDFs in searches.

  How should you complete the skillset design diagram? To answer, drag the appropriate services to the correct stages. Each service may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll

  to view content.

  NOTE: Each correct selection is worth one point.

  Select and Place:

  

  Correct Answer:

  

  Box 1: Azure Blob storage

  At the start of the pipeline, you have unstructured text or non-text content (such as images, scanned documents, or JPEG files). Data must exist in an Azure data storage service that can be accessed by an indexer.

  Box 2: Computer Vision API

  Scenario: Provide users with the ability to search insight gained from the images, manuals, and videos associated with the products.

  The Computer Vision Read API is Azure's latest OCR technology (learn what's new) that extracts printed text (in several languages), handwritten text (English only), digits, and currency symbols from images and multi-page PDF documents.

  Box 3: Translator API

  Scenario: Product descriptions, transcripts, and all text must be available in English, Spanish, and Portuguese.

  Box 4: Azure Files

  Scenario: Store all raw insight data that was generated, so the data can be processed later.

  Incorrect Answers:

  The custom vision API from Microsoft Azure learns to recognize specific content in imagery and becomes smarter with training and time.

  Reference:

  https://docs.microsoft.com/en-us/azure/search/cognitive-search-concept-intro https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-ocr

• Question 16:

  You have a chatbot that was built by using Microsoft Bot Framework and deployed to Azure.

  You need to configure the bot to support voice interactions. The solution must support multiple client apps.

  Which type of channel should you use?

  A. Cortana

  B. Microsoft Teams

  C. Direct Line Speech

  Correct Answer: C

• Question 17:

  You plan to build an app that will generate a list of tags for uploaded images. The app must meet the following requirements:

  1.

  Generate tags in a users preferred language.

  2.

  Support English, French, and Spanish.

  3.

  Minimize development effort

  You need to build a function that will generate the tags for the app. Which Azure service endpoint should you use?

  A. Custom Vision image classification

  B. Content Moderator Image Moderation

  C. Custom Translator

  D. Computer Vision image Analysis

  Correct Answer: D

• Question 18:

  You use the Microsoft Bot Framework Composer to build a chatbot that enables users to purchase items.

  You need to ensure that the users can cancel in-progress transactions. The solution must minimize development effort.

  What should you add to the bot?

  A. a language generator

  B. a custom event

  C. a dialog trigger

  D. a conversation activity

  Correct Answer: C

  https://learn.microsoft.com/en-us/composer/concept-events-and-triggers?tabs=v2x In Bot Framework Composer, each dialog includes one or more event handlers called triggers. Each trigger contains one or more actions. Actions are the instructions that the bot will execute when the dialog receives any event that it has a trigger defined to handle. Once a given event is handled by a trigger, no further action is taken on that event. Some event handlers have a condition specified that must be met before it will handle the event and if that condition isn't met, the event is passed to the next event handler. If an event isn't handled in a child dialog, it gets passed up to its parent dialog to handle and this continues until it's either handled or reaches the bots main dialog. If no event handler is found, it will be ignored and no action will be taken.

• Question 19:

  You are building a chatbot.

  You need to configure the bot to guide users through a product setup process.

  Which type of dialog should you use?

  A. component

  B. waterfall

  C. adaptive

  D. action

  Correct Answer: B

• Question 20:

  You have a factory that produces food products.

  You need to build a monitoring solution for staff compliance with personal protective equipment (PPE) requirements.

  The solution must meet the following requirements:

  1.

  identify staff who have removed masks or safety glasses.

  2.

  Perform a compliance check every 15 minutes.

  3.

  Minimize development effort.

  4.

  Minimize costs. Which service should you use?

  A. Face

  B. Computer Vision

  C. Azure Video Analyzer for Media (formerly Video indexer)

  Correct Answer: A

  Face API is an AI service that analyzes faces in images.

  Embed facial recognition into your apps for a seamless and highly secured user experience. No machine-learning expertise is required. Features include face detection that perceives facial features and attributes " such as a face mask,

  glasses, or face location " in an image, and identification of a person by a match to your private repository or via photo ID.

  Reference:

  https://azure.microsoft.com/en-us/services/cognitive-services/face/