Microsoft Microsoft Certifications AI-100 Questions & Answers

• Question 151:

  You are developing a mobile app for a conference provider. The mobile app will use speech-to-text to provide real-time transcription at a conference.

  You need to ensure that the app can identify participants at the conference when they make contributions.

  What actions should you take?

  A. Instruct each participant to record the conference in the .wav format.

  B. Instruct each participant to create a voice signature.

  C. Instruct each participant to sign up for Azure Speech Services.

  D. Instruct each participant to install the Speech SDK on their mobile device.

  Correct Answer: B

  The first step is to create voice signatures for the conversation participants. Creating voice signatures is required for efficient speaker identification.

  Note: In addition to the standard baseline model used by the Speech Services, you can customize models to your needs with available data, to overcome speech recognition barriers such as speaking style, vocabulary and background noise.

  Reference:

  https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-use-conversation-transcription

• Question 152:

  You are designing an AI workflow that performs data analysis from multiple data sources. The data sources consist of JSON files that have been uploaded to an

  Azure Storage account, on-premises Oracle databases, and Azure SQL databases.

  Which service should you recommend to ingest the data?

  A. Azure Data Factory

  B. Azure Kubernetes Service (AKS)

  C. Azure Bot Service

  D. Azure Databricks

  Correct Answer: A

  Azure Data Factory is a fully managed data integration service that allows you to create workflows and pipelines to orchestrate and automate data movement and transformation. It supports a wide range of data sources and provides built-in connectors for Azure Storage, Oracle databases, and Azure SQL databases.

• Question 153:

  You are developing an app that will perform the following tasks:

  Evaluate trends in blue chip stock prices over the past decade.

  Identify unusual fluctuations in stock prices.

  Produce visual representations of the data.

  You need to determine which Azure Cognitive Services APIs would be suitable for the app.

  Which of the following actions should you take?

  A. Make use of the Anomaly Detector API

  B. Make use of the Computer Vision API

  C. Make use of the QnA Maker API

  D. Make use of the Custom Vision API

  Correct Answer: A

  The Anomaly Detector API is designed to detect anomalies and unusual patterns in time-series data. It can analyze the historical stock price data over the past decade to identify any abnormal fluctuations or patterns. By leveraging this API, you can automatically detect unusual behavior in the stock prices and take appropriate actions.

• Question 154:

  You are using the Text Analytics service to create an AI system that analyses documents.

  You want to implement a natural language processing workload that will be able to recognize the important points used in the documents.

  Which of the following actions should you take?

  A. Make use of Language Understanding (LUIS)

  B. Make use of Key phrase extraction

  C. Make use of Document categorization

  D. Make use of Anomaly detection

  Correct Answer: B

  Broad entity extraction: Identify important concepts in text, including key

  Key phrase extraction/ Broad entity extraction: Identify important concepts in text, including key phrases and named entities such as people, places, and organizations.

  Reference:

  https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/natural-language-processing

• Question 155:

  You have a developed an AI app that uses a Cognitive Services API to identify images.

  You want all the processed images to be stored an on-premises datacenter.

  What should you do?

  A. Use a Docker container to host the Cognitive Services API.

  B. Use an Azure Stack Edge Pro to host the Cognitive Services API.

  C. Use an Azure Private Endpoint to host the Cognitive Services API.

  D. Use an Azure Data Box to host the Cognitive Services API.

  Correct Answer: B

  A container is a standard unit of software that packages up code and all its dependencies so the application runs quickly and reliably from one computing environment to another. A Docker container image is a lightweight, standalone,

  executable package of software that includes everything needed to run an application: code, runtime, system tools, system libraries and settings.

  Reference:

  https://www.docker.com/resources/what-container

• Question 156:

  Your company's marketing department is creating a social media campaign that will allow users to submit video messages for the company's social media sites.

  You are developing an AI app for the campaign. Your app must meet the following requirements:

  Add captions to the video messages before they are posted to the social media sites.

  Ensure that no negative video messages are posted to the social media sites. Which of the following actions should you take?

  A. Implement Form Recognizer in your app.

  B. Implement the Face API in your app.

  C. Implement Custom Vision in your app.

  D. Implement Video Indexer in your app.

  Correct Answer: D

  Video Indexer includes Audio transcription: Converts speech to text in 12 languages and allows extensions. Supported languages include English, Spanish,

  French, German, Italian, Mandarin Chinese, Japanese, Arabic, Russian, Portuguese, Hindi, and Korean.

  When indexing by one channel, partial result for those models will be available, such as sentiment analysis: Identifies positive, negative, and neutral sentiments from speech and visual text.

  Reference:

  https://docs.microsoft.com/en-us/azure/media-services/video-indexer/video-indexer-overview

• Question 157:

  You are developing a bot for an ecommerce application. The bot will support five languages.

  The bot will use Language Understanding (LUIS) to detect the language of the customer, and QnA Maker to answer common customer questions. LUIS supports all the languages.

  You need to determine the minimum number of Azure resources that you must create for the bot.

  You create five instances of QnA Maker and one instance Language Understanding (LUIS).

  Does this action accomplish your objective?

  A. Yes, it does

  B. No, it does not

  Correct Answer: A

  By creating one instance of Language Understanding (LUIS) that supports all five languages, and five instances of QnA Maker to handle the common customer questions in each language, you have fulfilled the requirement of supporting five

  languages in the bot. This approach ensures that you have the necessary Azure resources in place to handle the language detection and question answering functionalities for each language.

  Reference:

  https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/overview/language-support https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-language-support

• Question 158:

  You are developing a bot for an ecommerce application. The bot will support five languages.

  The bot will use Language Understanding (LUIS) to detect the language of the customer, and QnA Maker to answer common customer questions. LUIS supports all the languages.

  You need to determine the minimum number of Azure resources that you must create for the bot.

  You create one instance of QnA Maker and five instances Language Understanding (LUIS).

  Does this action accomplish your objective?

  A. Yes, it does

  B. No, it does not

  Correct Answer: B

  You need to have a new QnA Maker resource for each language.

  If LUIS supports all the languages, you develop a LUIS app for each language. Each LUIS app has a unique app ID, and endpoint log. If you need to provide language understanding for a language LUIS does not support, you can use

  Microsoft Translator API to translate the utterance into a supported language, submit the utterance to the LUIS endpoint, and receive the resulting scores.

  Reference:

  https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/overview/language-support https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-language-support

• Question 159:

  You are developing a mobile application. You want to implement search functionality in the application.

  Your solution must meet the following requirements:

  Users must be able to run searches by typing in their search query.

  Users must be able to run searches by voice commands.

  Which of the following actions should you take?

  A. Make use of Language Understanding (LUIS)

  B. Make use of QnA Maker

  C. Make use of Bing Entity Search

  D. Make use of Azure Cognitive Search

  Correct Answer: A

  Language Understanding (LUIS) is a natural language processing service provided by Microsoft Azure. It allows you to build applications that can understand and interpret user's intents from their spoken or typed input. By using LUIS, you can train a language model to recognize specific search intents and extract relevant entities from user queries. LUIS supports both text and speech input, making it suitable for implementing search functionality that can be accessed via typing or voice commands.

• Question 160:

  You are developing a bot for an ecommerce application. The bot will support five languages.

  The bot will use Language Understanding (LUIS) to detect the language of the customer, and QnA Maker to answer common customer questions. LUIS supports all the languages.

  You need to determine the minimum number of Azure resources that you must create for the bot.

  You create five instances of QnA Maker and one instance Language Understanding (LUIS).

  Does this action accomplish your objective?

  A. Yes, it does

  B. No, it does not

  Correct Answer: A

  By creating one instance of Language Understanding (LUIS) that supports all five languages, and five instances of QnA Maker to handle the common customer questions in each language, you have fulfilled the requirement of supporting five languages in the bot. This approach ensures that you have the necessary Azure resources in place to handle the language detection and question answering functionalities for each language.