Microsoft Role-based AI-102 Questions & Answers

• Question 221:

  You are building a chatbot by using the Microsoft Bot Framework SDK. The bot will be used to accept food orders from customers and allow the customers to customize each food item.

  You need to configure the bot to ask the user for additional input based on the type of item ordered. The solution must minimize development effort.

  Which two types of dialogs should you use? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. adaptive

  B. action

  C. waterfall

  D. prompt

  E. input

  Correct Answer: CD

• Question 222:

  You are developing the chatbot.

  You create the following components:

  1.

  A QnA Maker resource

  2.

  A chatbot by using the Azure Bot Framework SDK

  You need to integrate the components to meet the chatbot requirements.

  Which property should you use?

  A. QnAMakerOptions.StrictFilters

  B. QnADialogResponseOptions.CardNoMatchText

  C. QnAMakerOptions.RankerType

  D. QnAMakerOptions.ScoreThreshold

  Correct Answer: D

  Technical Requirements says "AI solution responses must have a confidence score that is equal to or greater than 70 percent" and "When the response confidence score is low, ensure that the chatbot can provide other response options to the customers" https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/concepts/confidence-score#set-threshold

• Question 223:

  You are developing the knowledgebase by using Azure Cognitive Search.

  You need to meet the knowledgebase requirements for searching equivalent terms.

  What should you include in the solution?

  A. synonym map

  B. a suggester

  C. a custom analyzer

  D. a built-in key phrase extraction skill

  Correct Answer: A

  Within a search service, synonym maps are a global resource that associate equivalent terms, expanding the scope of a query without the user having to actually provide the term. For example, assuming "dog", "canine", and "puppy" are mapped synonyms, a query on "canine" will match on a document containing "dog".

  Create synonyms: A synonym map is an asset that can be created once and used by many indexes.

  Reference: https://docs.microsoft.com/en-us/azure/search/search-synonyms

• Question 224:

  You are developing the chatbot.

  You create the following components:

  1.

  A QnA Maker resource

  2.

  A chatbot by using the Azure Bot Framework SDK

  You need to add an additional component to meet the technical requirements and the chatbot requirements.

  What should you add?

  A. Microsoft Translator

  B. Language Understanding

  C. Dispatch

  D. chatdown

  Correct Answer: A

  "If you need to support a knowledge base system, which includes several languages, you can:

  1) Use the Translator service to translate a question into a single language before sending the question to your knowledge base. This allows you to focus on the quality of a single language and the quality of the alternate questions and

  answers.

  2) Create a QnA Maker resource, and a knowledge base inside that resource, for every language. This allows you to manage separate alternate questions and answer text that is more nuanced for each language. This gives you much more

  flexibility but requires a much higher maintenance cost when the questions or answers change across all languages."

  https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/overview/language-support#supporting-multiple-languages-in-one-knowledge-base

• Question 225:

  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?

  A. Create a custom language model

  B. Configure audio indexing for videos only

  C. Enable multi-language detection for videos

  D. Build a custom Person model for webinar presenters

  Correct Answer: A

  https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-language-model-overview Azure Video Indexer supports automatic speech recognition through integration with the Microsoft Custom Speech Service. You can customize the Language model by uploading adaptation text, namely text from the domain whose vocabulary you'd like the engine to adapt to. Once you train your model, new words appearing in the adaptation text will be recognized, assuming default pronunciation, and the Language model will learn new probable sequences of words.

• Question 226:

  You need to develop an extract solution for the receipt images. The solution must meet the document processing requirements and the technical requirements. You upload the receipt images to the Form Recognizer API for analysis, and the API returns the following JSON.

  

  Which expression should you use to trigger a manual review of the extracted information by a member of the Consultant-Bookkeeper group?

  A. documentResults.docType == "prebuilt:receipt"

  B. documentResults.fields.*.confidence < 0.7

  C. documentResults.fields.ReceiptType.confidence > 0.7

  D. documentResults.fields.MerchantName.confidence < 0.7

  Correct Answer: B

• Question 227:

  You are developing the knowledgebase by using Azure Cognitive Search. You need to process wiki content to meet the technical requirements. What should you include in the solution?

  A. an indexer for Azure Blob storage attached to a skillset that contains the language detection skill and the text translation skill

  B. an indexer for Azure Blob storage attached to a skillset that contains the language detection skill

  C. an indexer for Azure Cosmos DB attached to a skillset that contains the document extraction skill and the text translation skill

  D. an indexer for Azure Cosmos DB attached to a skillset that contains the language detection skill and the text translation skill

  Correct Answer: C

  The wiki contains text in English, French and Portuguese.

  Scenario: All planned projects must support English, French, and Portuguese.

  The Document Extraction skill extracts content from a file within the enrichment pipeline. This allows you to take advantage of the document extraction step that normally happens before the skillset execution with files that may be generated

  by other skills.

  Note: The Translator Text API will be used to determine the from language. The Language detection skill is not required.

  Incorrect Answers:

  Not A, not B: The wiki is stored in Azure Cosmos DB.

  Reference:

  https://docs.microsoft.com/en-us/azure/search/cognitive-search-skill-document-extraction

  https://docs.microsoft.com/en-us/azure/search/cognitive-search-skill-text-translation

• Question 228:

  You are developing the document processing workflow.

  You need to identify which API endpoints to use to extract text from the financial documents. The solution must meet the document processing requirements.

  Which two API endpoints should you identify? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. /vision/v3.2/read/analyzeResults

  B. /formrecognizer/v2.0/custom/models/{modelId}/analyze

  C. /formrecognizer/v2.0/prebuilt/receipt/analyze

  D. /vision/v3.2/describe

  E. /vision/v3.2/read/analyze

  Correct Answer: CE

  C: Analyze Receipt - Get Analyze Receipt Result.

  Query the status and retrieve the result of an Analyze Receipt operation.

  Request URL: https://{endpoint}/formrecognizer/v2.0-preview/prebuilt/receipt/analyzeResults/{resultId}

  E: POST {Endpoint}/vision/v3.1/read/analyze

  Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents.

  Scenario: Contoso plans to develop a document processing workflow to extract information automatically from PDFs and images of financial documents

  The document processing solution must be able to process standardized financial documents that have the following characteristics:

  -Contain fewer than 20 pages.

  -Be formatted as PDF or JPEG files.

  -Have a distinct standard for each office. The document processing solution must be able to extract tables and text from the financial documents. The document processing solution must be able to extract information from receipt images.

  Reference: https://westus2.dev.cognitive.microsoft.com/docs/services/form-recognizer-api-v2-preview/operations/GetAnalyzeReceiptResult https://docs.microsoft.com/en-us/rest/api/computervision/3.1/read/read

• Question 229:

  You are developing the smart e-commerce project.

  You need to implement autocompletion as part of the Cognitive Search solution.

  Which three actions should you perform? Each correct answer presents part of the solution. (Choose three.)

  NOTE: Each correct selection is worth one point.

  A. Make API queries to the autocomplete endpoint and include suggesterName in the body.

  B. Add a suggester that has the three product name fields as source fields.

  C. Make API queries to the search endpoint and include the product name fields in the searchFields query parameter.

  D. Add a suggester for each of the three product name fields.

  E. Set the searchAnalyzer property for the three product name variants.

  F. Set the analyzer property for the three product name variants.

  Correct Answer: ABF

  Scenario: Support autocompletion and autosuggestion based on all product name variants.

  A: Call a suggester-enabled query, in the form of a Suggestion request or Autocomplete request, using an API. API usage is illustrated in the following call to the Autocomplete REST API.

  POST /indexes/myxboxgames/docs/autocomplete?searchandapi-version=2020-06-30

  { "search": "minecraf", "suggesterName": "sg"

  }

  B:

  In Azure Cognitive Search, typeahead or "search-as-you-type" is enabled through a suggester. A suggester provides a list of fields that undergo additional tokenization, generating prefix sequences to support matches on partial terms. For example, a suggester that includes a City field with a value for "Seattle" will have prefix combinations of "sea", "seat", "seatt", and "seattl" to support typeahead.

  F.

  Use the default standard Lucene analyzer ("analyzer": null) or a language analyzer (for example, "analyzer": "en.Microsoft") on the field.

  Reference: https://docs.microsoft.com/en-us/azure/search/index-add-suggesters