AI-102 practice questions 181–190

1. Question 181 · 328 in bank

   You have an Azure subscription that contains an Azure App Service app named App1. You provision a multi-service Azure Cognitive Services resource named CSAccount1. You need to configure App1 to access CSAccount1. The solution must minimize administrative effort. What should you use to configure App1?

   • Aa system-assigned managed identity and an X.509 certificate
   • Bthe endpoint URI and an OAuth token
   • Cthe endpoint URI and a shared access signature (SAS) token
   • Dthe endpoint URI and subscription key

   Show answer

   Answer: D

   Explanation

   D is right, but i sure hope that nobody uses keys anymore. its considered bad practice, use managed identities, rbac to do this.

   Source: Adapted from community discussion — JakeCallham

   Next question

2. Question 182 · 328 in bank

   You have an Azure subscription that contains a multi-service Azure Cognitive Services Translator resource named Translator1. You are building an app that will translate text and documents by using Translator1. You need to create the REST API request for the app. Which headers should you include in the request?

   • Athe access control request, the content type, and the content length
   • Bthe subscription key and the client trace ID
   • Cthe resource ID and the content language
   • Dthe subscription key, the subscription region, and the content type

   Show answer

   Answer: D

   Explanation

   Answer is correct https://learn.microsoft.com/en-us/azure/ai-services/translator/reference/v3-0-translate content-type is required header https://learn.microsoft.com/en-us/azure/ai-services/translator/reference/v3-0-reference When you use a multi-service secret key, you must include two authentication headers with your request. There are two headers that you need to call the Translator. Ocp-Apim-Subscription-Key The value is the Azure secret key for your multi-service resource. Ocp-Apim-Subscription-Region The value is the region of the multi-service resource. Region is required for the multi-service Text API subscription. The region you select is the only region that you can use for text translation when using the multi-service key. It must be the same region you selected when you signed up for your multi-service subscription through the Azure portal. D is the only option with both the headers

   Source: Adapted from community discussion — audlindr

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   Next question

3. Question 183 · 328 in bank

   You have a file share that contains 5,000 images of scanned invoices. You need to analyze the images. The solution must extract the following data: • Invoice items • Sales amounts • Customer details What should you use?

   • ACustom Vision
   • BAzure AI Computer Vision
   • CAzure AI Immersive Reader
   • DAzure AI Document Intelligence

   Show answer

   Answer: D

   Explanation

   D. Azure AI Document Intelligence This service is specifically designed for tasks like automated invoice processing and can extract key information from documents.

   Source: Adapted from community discussion — GHill1982

   References

   • Microsoft Learn

   Next question

4. Question 184 · 328 in bank

   HOTSPOT - You are developing a text processing solution. You have the function shown below.

   

   For the second argument, you call the function and specify the following string. Our tour of Paris included a visit to the Eiffel Tower For each of the following statements, select Yes if the statement is true. Otherwise, select No.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   Should by NYN. Key phrases would be (tested with API): Eiffel Tower, tour, Paris, visit Entities are: Eiffen Tower, Paris

   Source: Adapted from community discussion — Harry300

   

   Next question

5. Question 185 · 328 in bank

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

   

   You call the method by using the following code. get_key_phrases(text_analytics_client, "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.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   From top to bottom Yes is CORRECT. The Key Phrase Extraction API evaluates unstructured text, and for each JSON document, returns a list of key phrases. As defined in the section print(‘{keyphrase}’)function it prints the key phrases extracted from the input string to the console. No is CORRECT. The function is designed to extract key phrases only and here in the options we have “the”, “on” which are not the key phrase but the general words. Therefore, it is unlikely it includes "the" and "on". The output might include "cat" and "mat" depending on how exactly the function is implemented. No is CORRECT. In the function defined we are not stating anywhere specifically to print the confidence level. If we want to extract the confidence level we can utilize Named Entity Recognition.

   Source: Adapted from community discussion — syupwsh

   References

   • Microsoft Learn

   

   Next question

6. Question 186 · 328 in bank

   HOTSPOT - You are developing a service that records lectures given in English (United Kingdom). You have a method named append_to_transcript_file that takes translated text and a language identifier. You need to develop code that will provide transcripts of the lectures to attendees in their respective language. The supported languages are English, French, Spanish, and German. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   

   Next question

7. Question 187 · 328 in bank

   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?

   • Athe style attribute of the mstts:express-as element
   • Bthe effect attribute of the voice element
   • Cthe pitch attribute of the prosody element
   • Dthe level attribute of the emphasis element

   Show answer

   Answer: B

   Explanation

   Answer is correct: The audio effect processor that's used to optimize the quality of the synthesized speech output for specific scenarios on devices. For some scenarios in production environments, the auditory experience might be degraded due to the playback distortion on certain devices. For example, the synthesized speech from a car speaker might sound dull and muffled due to environmental factors such as speaker response, room reverberation, and background noise. The passenger might have to turn up the volume to hear more clearly. To avoid manual operations in such a scenario, the audio effect processor can make the sound clearer by compensating the distortion of playback. The following values are supported: eq_car – Optimize the auditory experience when providing high-fidelity speech in cars, buses, and other enclosed automobiles. eq_telecomhp8k – Optimize the auditory experience for narrowband speech in telecom or telephone scenarios. You should use a sampling rate of 8 kHz. If the sample rate isn't 8 kHz, the auditory quality of the output speech isn't optimized.

   Source: Adapted from community discussion — chandiochan

   References

   • Microsoft Learn

   Next question

8. Question 188 · 328 in bank

   You are building a Conversational Language Understanding model for an e-commerce chatbot. Users can speak or type their billing address when prompted by the chatbot. You need to construct an entity to capture billing addresses. Which entity type should you use?

   • Amachine learned
   • BRegex
   • Clist
   • DPattern.any

   Show answer

   Answer: A

   Explanation

   The link provided mentions addresses under 'ML Entities with Structure'. Will be hard to identify all possible international addresses with RegEx.

   Source: Adapted from community discussion — Internal_Koala

   References

   • Microsoft Learn
   • Microsoft Learn

   Next question

9. Question 189 · 328 in bank

   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?

   • AAzure AI Immersive Reader
   • BAzure AI Translator
   • CAzure AI Document Intelligence
   • DAzure AI Language

   Show answer

   Answer: A

   References

   • Microsoft Learn

   Next question

10. Question 190 · 328 in bank

    HOTSPOT - You are building an app that will answer customer calls about the status of an order. The app will query a database for the order details and provide the customers with a spoken response. You need to identify which Azure AI service APIs to use. The solution must minimize development effort. Which object should you use for each requirement? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer: See figure below

    Explanation

    To convert customer calls into text queries, you should use the SpeechRecognizer object. This is part of the Speech service in Azure Cognitive Services and it converts spoken language into written text. To provide customers with the order details in a spoken response, you should use the SpeechSynthesizer object. This service converts text into lifelike speech, which can be used to deliver information to customers in a more interactive way. So, the answer is: Convert customer calls into text queries: SpeechRecognizer Provide customers with the order details: SpeechSynthesizer

    Source: Adapted from community discussion — Murtuza

    References

    • Microsoft Learn
    • Microsoft Learn

    

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AI-102 practice, question 181. 328 questions available.