AI-102 practice questions 11–20

1. Question 11 · 328 in bank

   HOTSPOT - You are developing an internet-based training solution for remote learners. Your company identifies that during the training, some learners leave their desk for long periods or become distracted. You need to use a video and audio feed from each learner's computer to detect whether the learner is present and paying attention. The solution must minimize development effort and identify each learner. Which Azure Cognitive Services service should you use for each requirement? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Hot Area:

   

   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

   Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/what-are-cognitive-services

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn

   

   Next question

2. Question 12 · 328 in bank

   DRAG DROP - You plan to use a Language Understanding application named app1 that is deployed to a container. App1 was developed by using a Language Understanding authoring resource named lu1. App1 has the versions shown in the following table.

   

   You need to create a container that uses the latest deployable version of app1. 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. Select and Place:

   

   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 solution link: "The Language Understanding (LUIS) container loads your trained or published Language Understanding model." Trained alone is deployable, v1.1

   Source: Adapted from community discussion — sdokmak

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

3. Question 13 · 328 in bank

   Select 2

   You plan to provision a QnA Maker service in a new resource group named RG1. In RG1, you create an App Service plan named AP1. Which two Azure resources are automatically created in RG1 when you provision the QnA Maker service? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

   • ALanguage Understanding
   • BAzure SQL Database
   • CAzure Storage
   • DAzure Cognitive Search
   • EAzure App Service

   Show answer

   Answer: DE

   Explanation

   Right answer : at the creation, we have to precise Azure Search an Azure Web App details. "When you create a QnAMaker resource, you host the data in your own Azure subscription. Azure Search is used to index your data." & "When you create a QnAMaker resource, you host the runtime in your own Azure subscription. App Service is the compute engine that runs the QnA Maker queries for you."

   Source: Adapted from community discussion — methodidacte

   References

   • Microsoft Learn
   • azure.microsoft.com documentation
   • Microsoft Learn
   • Microsoft Learn

   Next question

4. Question 14 · 328 in bank

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

   • Aa conditional access policy in Azure Active Directory (Azure AD)
   • Bthe Access control (IAM) page for the authoring resources in the Azure portal
   • Cthe Access control (IAM) page for the prediction resources in the Azure portal

   Show answer

   Answer: B

   Explanation

   B is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/luis/luis-how-to-collaborate#add-contributor-to-azure-authoring-resource In the Azure portal, find your Language Understanding (LUIS) authoring resource. It has the type LUIS.Authoring. In the resource's Access Control (IAM) page, add the role of contributor for the user that you want to contribute.

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn
   • Microsoft Learn

   Next question

5. Question 15 · 328 in bank

   Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You have an Azure Cognitive Search service. During the past 12 months, query volume steadily increased. You discover that some search query requests to the Cognitive Search service are being throttled. You need to reduce the likelihood that search query requests are throttled. Solution: You migrate to a Cognitive Search service that uses a higher tier. Does this meet the goal?

   • AYes
   • BNo

   Show answer

   Answer: A

   Explanation

   The best answer is: • A. Yes Reason for choosing this option: Azure Cognitive Search service tiers determine the resources available for that service. Higher tiers provide more resources such as increased document counts, indexing speed, and query capacity. If the query volume has increased and requests are being throttled, it indicates that the current tier’s resources are insufficient to handle the load. Migrating to a higher tier will provide more resources, reducing the likelihood of throttling.

   Source: Adapted from community discussion — CDL_Learner

   References

   • Microsoft Learn
   • Microsoft Learn

   Next question

6. Question 16 · 328 in bank

   DRAG DROP - You need to develop an automated call handling system that can respond to callers in their own language. The system will support only French and English. Which Azure Cognitive Services service should you use to meet each requirement? To answer, drag the appropriate services to the correct requirements. Each service may be used once, more than once, or not at all. You may need to drag the split bat between panes or scroll to view content. NOTE: Each correct selection is worth one point. Select and Place:

   

   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

   It should be: - Speech to Text with AutoDetectSourceLanguageConfig. It can't be Text Analytics because the input is callers' voice. - Text to Speech: the output is voice.

   Source: Adapted from community discussion — Khiem

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

7. Question 17 · 328 in bank

   You have receipts that are accessible from a URL. You need to extract data from the receipts by using Form Recognizer and the SDK. The solution must use a prebuilt model. Which client and method should you use?

   • Athe FormRecognizerClient client and the StartRecognizeContentFromUri method
   • Bthe FormTrainingClient client and the StartRecognizeContentFromUri method
   • Cthe FormRecognizerClient client and the StartRecognizeReceiptsFromUri method
   • Dthe FormTrainingClient client and the StartRecognizeReceiptsFromUri method

   Show answer

   Answer: C

   Explanation

   To extract data from receipts using Form Recognizer and the SDK, while using a prebuilt model, you should use option C: the FormRecognizerClient client and the StartRecognizeReceiptsFromUri method. Explanation: Option A (the FormRecognizerClient client and the StartRecognizeContentFromUri method) is incorrect because the StartRecognizeContentFromUri method is used for general content recognition, not specifically for receipts. Option B (the FormTrainingClient client and the StartRecognizeContentFromUri method) is incorrect because the FormTrainingClient client is used for training custom models, not for extracting data from prebuilt models. Option D (the FormTrainingClient client and the StartRecognizeReceiptsFromUri method) is incorrect because the FormTrainingClient client is not used for extracting data; it is used for training custom models. Therefore, the correct choice is option C: the FormRecognizerClient client and the StartRecognizeReceiptsFromUri method.

   Source: Adapted from community discussion — nitz14

   References

   • Microsoft Learn
   • Microsoft Learn

   Next question

8. Question 18 · 328 in bank

   You have a collection of 50,000 scanned documents that contain text. You plan to make the text available through Azure Cognitive Search. You need to configure an enrichment pipeline to perform optical character recognition (OCR) and text analytics. The solution must minimize costs. What should you attach to the skillset?

   • Aa new Computer Vision resource
   • Ba free (Limited enrichments) Cognitive Services resource
   • Can Azure Machine Learning Designer pipeline
   • Da new Cognitive Services resource that uses the S0 pricing tier

   Show answer

   Answer: D

   Explanation

   Question says : ..."You need to configure an enrichment pipeline to perform optical character recognition (OCR) and "text analytics"... Just because of this second requirement Answer is a Multi Cognitive Service (D), alone vision service (=OCR wont make any text analytics, text extraction is not a text analytics !).. Read here : https://learn.microsoft.com/en-us/azure/search/cognitive-search-attach-cognitive-services?tabs=portal

   Source: Adapted from community discussion — Pyguy

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   Next question

9. Question 19 · 328 in bank

   Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You have an Azure Cognitive Search service. During the past 12 months, query volume steadily increased. You discover that some search query requests to the Cognitive Search service are being throttled. You need to reduce the likelihood that search query requests are throttled. Solution: You add indexes. Does this meet the goal?

   • AYes
   • BNo

   Show answer

   Answer: B

   Explanation

   B is correct answer. "How your search queries perform is directly connected to the size and complexity of your indexes. The smaller and more optimized your indexes, the fast Azure Cognitive Search can respond to queries. If your index has been optimized but the performance still isn't where it needs to be, you can choose to scale up or scale out your search service. If you've applied all of the above and still have individual queries that don't perform, you can scale out your index. Depending on the service tier you used to create your search solution, you can add up to 12 partitions. Partitions are the physical storage where your index resides. By default, all new search indexes are created with a single partition. If you add more partitions, the index is stored across them. For example, if your index is 200 GB and you've four partitions, each partition contains 50 GB of your index. Adding extra partitions can help with performance as the search engine can run in parallel in each partition.

   Source: Adapted from community discussion — Eltooth

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   Next question

10. Question 20 · 328 in bank

    Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You have an Azure Cognitive Search service. During the past 12 months, query volume steadily increased. You discover that some search query requests to the Cognitive Search service are being throttled. You need to reduce the likelihood that search query requests are throttled. Solution: You enable customer-managed key (CMK) encryption. Does this meet the goal?

    • AYes
    • BNo

    Show answer

    Answer: B

    Explanation

    B is the answer. https://learn.microsoft.com/en-us/azure/search/search-performance-analysis#throttling-behaviors Throttling occurs when the search service is at capacity. Throttling can occur during queries or indexing. From the client side, an API call results in a 503 HTTP response when it has been throttled. During indexing, there's also the possibility of receiving a 207 HTTP response, which indicates that one or more items failed to index. This error is an indicator that the search service is getting close to capacity. A simple fix to most throttling issues is to throw more resources at the search service (typically replicas for query-based throttling, or partitions for indexing-based throttling). However, increasing replicas or partitions adds cost, which is why it's important to know the reason why throttling is occurring at all. Investigating the conditions that cause throttling will be explained in the next several sections.

    Source: Adapted from community discussion — zellck

    References

    • Microsoft Learn

    Next question

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

AI-102 practice, question 11. 328 questions available.