AI-102 Designing and Implementing a Microsoft Azure AI Solution Questions and Answers

The provided code uses the Azure AI Language – Text Analytics client to call the ExtractKeyPhrases method.

The method ExtractKeyPhrases(text) identifies the most important words and phrases in the input text.

The input string is:

" the quick brown fox jumps over the lazy dog "

The ExtractKeyPhrases API removes stopwords such as " the, " " over, " and " jumps " and extracts only meaningful keywords.

Therefore, the returned list of key phrases will include:

" Quick brown fox "

" Lazy dog "

When printed, the console output after " Key phrases: " will show:

Quick brown fox

Lazy dog

This matches option C (Quick brown fox lazy dog), since the key phrases are concatenated as output lines.

Correct Answer: C. Quick brown fox lazy dog

Microsoft References

Azure AI Language – Key phrase extraction

TextAnalyticsClient.ExtractKeyPhrases method (Azure.AI.TextAnalytics)

To access multiple Azure AI capabilities (e.g., Speech and Language) using a single endpoint and a single set of credentials, you should provision an Azure AI multi-service resource (called Azure AI service in the portal; formerly “Cognitive Services” multi-service account). This resource provides one endpoint and one key (or Microsoft Entra ID) that authorizes calls across supported services, including Speech and Language. Creating separate “Azure AI Speech” or “Azure AI Language” resources would give you distinct endpoints/keys for each, which does not meet the requirement. Azure AI Content Safety is unrelated.

Microsoft References

Azure AI services multi-service resource (single endpoint/credential across services).

https://learn.microsoft.com/azure/ai-services/multi-service-resource

What are Azure AI services (overview of consolidated access model).

https://learn.microsoft.com/azure/ai-services/what-are-ai-services

In the Azure portal, the Keys and Endpoint blade for a Cognitive Service resource provides:

API keys (for authentication)

Endpoint URL (the REST interface base URL)

Identity blade relates to managed identities.

Properties blade shows metadata (resource ID, location, subscription ID).

Networking blade controls network access and firewall rules.

Correct Answer: B. Keys and Endpoint

When using the Speech SDK’s speech translation, a TranslationRecognitionResult includes a Reason property (type ResultReason ) indicating the outcome. For successful translation results, the reason is ResultReason.TranslatedSpeech . In that case, you can read the recognized source text from translationRecognitionResult.Text and iterate the translated outputs from translationRecognitionResult.Translations (a dictionary keyed by target language code).

RecognizingSpeech corresponds to interim hypotheses raised on the Recognizing event and is not the final result reason used here; NoMatch is the branch already handled for unrecognized audio.

Microsoft Azure AI References

Azure AI Speech SDK – Speech translation overview and TranslationRecognizer usage (C#): result handling with ResultReason.TranslatedSpeech , reading Text and Translations .

Speech SDK API reference – TranslationRecognitionResult ( Reason , Text , Translations ) and ResultReason enum (values include TranslatedSpeech , NoMatch , Canceled ).

The Cognitive Services OpenAI User role grants least-privilege read/use permissions: view resource endpoints, list available models, use existing deployments in Azure OpenAI Studio (e.g., generate text and images ). It cannot create or manage deployments (that would require Cognitive Services OpenAI Contributor ), satisfying least-privilege.

References

Azure OpenAI built-in roles: OpenAI User vs OpenAI Contributor .

https://learn.microsoft.com/azure/ai-services/openai/how-to/role-based-access-control

Azure RBAC for Azure AI services.

https://learn.microsoft.com/azure/ai-services/role-based-access-control?tabs=azure-portal

First blank: speech_recognition_language

Second blank: add_target_language

speech_translation_config = speechsdk.translation.SpeechTranslationConfig(

subscription=os.environ.get( ' SPEECH_KEY ' ),

region=os.environ.get( ' SPEECH_REGION ' )

)

# Source (recognition) language: English (US)

speech_translation_config.speech_recognition_language = " en-US "

# Target translation language: Italian

speech_translation_config.add_target_language( " it " )

audio_config = speechsdk.audio.AudioConfig(use_default_microphone= True )

recognizer = speechsdk.translation.TranslationRecognizer(

translation_config=speech_translation_config,

audio_config=audio_config

)

Comprehensive Detailed Explanation along with All References available from Microsoft Azure AI Solution at the end of the explanation

To translate speech, configure a SpeechTranslationConfig with (1) the recognition language of the input audio and (2) one or more target languages for translation. In Python, you set the input language with the speech_recognition_language property (e.g., " en-US " ), and you add a target with add_target_language( " < locale > " ) (e.g., " it " for Italian). This exactly matches the SDK guidance and examples for speech translation. Microsoft Learn

speech_recognition_language specifies the locale used by the recognizer to understand the spoken input.

add_target_language( " it " ) adds Italian as a translation output language.

Microsoft References

How to translate speech with the Speech SDK (Python examples show translation_config.speech_recognition_language = from_language and translation_config.add_target_language(...) ). Microsoft Learn

SpeechTranslationConfig (Python) reference — add_target_language(language: str) . Microsoft Lea rn

Recognize speech (property usage for speech_recognition_language ). Microsoft Learn

Language support for Speech service (locales and codes for recognition/translation)

This question is about selecting valid training files for a custom Form Recognizer model in Azure AI Document Intelligence (formerly Form Recognizer).

Supported File Formats for Training

According to Microsoft documentation, Form Recognizer supports the following for training and analysis:

PDF (≤ 500 pages, ≤ 50 MB for training)

JPEG/JPG (≤ 50 MB)

PNG (≤ 50 MB)

TIFF (≤ 50 MB)

Unsupported:

MP4 → Video not supported.

GIF → Not supported.

Maximum File Size Rules (for training input files):

Images (JPG, PNG, TIFF): ≤ 50 MB

PDFs: ≤ 50 MB

Note: 500 pages limit applies to PDFs.

File-by-File Analysis

File1 – PDF – 20 MB

Type supported.

Size within limit ( < 50 MB).

Valid ✅

File2 – MP4 – 100 MB

MP4 is not supported.

Invalid ❌

File3 – JPG – 20 MB

Type supported.

Size within limit ( < 50 MB).

Valid ✅

File4 – PDF – 100 MB

Type supported.

Size exceeds the 50 MB maximum limit.

Invalid ❌

File5 – GIF – 1 MB

GIF format not supported.

Invalid ❌

File6 – JPG – 40 MB

Type supported.

Size within limit ( < 50 MB).

Valid ✅

Correct Answer:

A. File1, C. File3, F. File6

Microsoft References

Azure AI Document Intelligence (Form Recognizer) – Supported file formats

Train a custom model with Azure Form Recognizer

Comprehensive Detailed Explanation

The scenario:

You are building an Azure WebJob to create knowledge bases from an array of URLs.

You already have a QnAMakerClient object instantiated with the relevant API keys.

You need to know what steps are required to create a knowledge base programmatically.

Step 1 – Create a CreateKbDTO object

CreateKbDTO is the request payload for creating a knowledge base.

It contains the name of the knowledge base and its sources, which may include:

A list of URLs.

A list of QnA pairs ( QnADTO ).

A list of files ( FileDTO ).

In this case, since the WebJob provides URLs, they will be passed inside the CreateKbDTO.Sources property.

Step 2 – Call client.Knowledgebase.CreateAsync

Once the CreateKbDTO object is defined, you use the QnAMakerClient to send the request:

var response = await client.Knowledgebase.CreateAsync(createKbDTO);

This triggers the asynchronous creation of a new knowledge base in the QnA Maker service.

Why not A or C?

A. Create a list of FileDTO objects: Not required here, because the question specifies URLs, not files.

C. Create a list of QnADTO objects: Also not needed, since you’re not directly supplying QnA pairs; the knowledge base will be built from URLs.

Correct Answer

B. Call the client.Knowledgebase.CreateAsync method.

D. Create a CreateKbDTO object.

Microsoft References

QnA Maker – Create Knowledge Base API

QnAMakerClient Class – Azure SDK for .NET

CreateKbDTO Class

To create a resource that can generate fictional stories from prompts, you need an Azure OpenAI account (--kind OpenAI).

To protect data with a customer-managed key (CMK) , you must pass the key information (Key Vault URI, key name, key version) via the --encryption parameter when creating the Cognitive Services account. The JSON shown (with keyName, keyVersion, and keyVaultUri) is exactly the payload expected by --encryption.

A complete example pattern:

az cognitiveservices account create \

-n myresource -g myResourceGroup -l westeurope \

--kind OpenAI --sku S \

--assign-identity \

--encryption ' {

" keyName " : " keyname " ,

" keyVersion " : " secretVersion " ,

" keyVaultUri " : " https:// < your-kv > .vault.azure.net/ "

} '

(Adding --assign-identity allows the service to access the Key Vault key; the hotspot specifically asks for the parameter that takes the JSON block and the resource kind, which are --encryption and OpenAI.)

Microsoft References

Azure CLI: Create Cognitive Services account with customer-managed keys using --encryption.

https://learn.microsoft.com/azure/ai-services/cognitive-services-encryption-keys#configure-customer-managed-keys

Azure Cognitive Services (Azure AI services) CLI parameters including --kind OpenAI .

https://learn.microsoft.com/azure/ai-services/cognitive-services-management-api-cli#create-a-cognitive-services-account

When deploying Cognitive Services containers (such as Anomaly Detector), the container requires a billing parameter in the docker run command.

This parameter points to the Azure resource key and endpoint for billing.

Fluentd is for logging.

Http Proxy is optional for outbound connectivity.

Mounts are used for local storage but are not mandatory for billing.

Correct Answer: B

You are analyzing an image with Azure AI Content Safety using the following request payload:

{

" image " : {

" content " : " < base_64_string > "

},

" categories " : [

" Violence "

],

" outputType " : " EightSeverityLevels "

}

Key Points:

Category specified → " Violence "

The Content Safety API will check for violent content in the image.

Test image description → A simple circle.

This is not violent in any way.

Output type → " EightSeverityLevels "

This setting returns a floating-point severity score from 0.0 (no severity) up to 7.0 (highest severity).

Expected result:

Since the image is only a circle (non-violent), the violence severity level will be at the lowest possible value: 0.0

Correct Answer: B. 0.0

Microsoft References

Azure AI Content Safety – Image moderation

Content Safety severity levels

 SpeechRecognitionLanguage must be set to " fr " (French).

 AddTargetLanguage( " de " ) must be used to specify German as the translation output.

Correct Code Completion

var speechTranslationConfig =

SpeechTranslationConfig.FromSubscription(speechKey, speechRegion);

speechTranslationConfig.SpeechRecognitionLanguage = " fr " ;

speechTranslationConfig.AddTargetLanguage( " de " );

Explanation

SpeechRecognitionLanguage → sets the source spoken language that the Speech service listens to (here, French).

AddTargetLanguage( " de " ) → adds German as the target translation language.

SpeechSynthesisLanguage would be used if you want to speak out the translation, but since the requirement is only about defining input and output languages, we use AddTargetLanguage .

Microsoft Reference

Speech translation with Speech SDK

Final Answer:

First blank → SpeechRecognitionLanguage

Second blank → AddTargetLanguage

Analysis of Options:

A. Lower the confidence score threshold of App1

Would just accept more low-confidence predictions, but won’t add support for a new format. ❌

B. Lower the accuracy threshold of App1

Similar reasoning: affects prediction acceptance, not model capabilities. ❌

C. Add the additional contract format to the existing training set and retrain the model

Correct approach. You extend the training data to include the new format, retrain, and reuse the same model. ✅

D. Create a new training set and add the additional contract format

This means starting from scratch, which requires more effort. Not minimal. ❌

E. Create and train a new custom model

Same as D, higher effort than necessary. ❌

Correct Answer:

C. Add the additional contract format to the existing training set. Retrain the model.

Microsoft Reference:

Azure AI Document Intelligence – Custom models

Comprehensive Detailed Explanation

You are working with a custom question answering project in Azure AI Language (formerly QnA Maker). The requirement is to enable the chatbot to engage in multi-turn conversations.

Multi-turn conversation: This occurs when a bot needs to ask clarifying questions or present follow-up options to guide the user toward the right answer.

Now let’s evaluate the options:

A. Add alternate questions

Alternate questions help improve query matching by allowing different phrasings of the same question.

This does not enable multi-turn dialogue.

B. Enable chit-chat

Chit-chat adds conversational personality (e.g., greetings, small talk).

Useful for user engagement but not for structured multi-turn dialogues.

C. Add follow-up prompts ✅

Follow-up prompts allow you to define next-step questions after an answer.

They are the key mechanism in custom question answering to enable multi-turn conversation flows.

Example: If the answer is about " subscriptions, " the follow-up prompts might include " How to upgrade? " or " How to cancel? "

D. Enable active learning

Active learning helps improve accuracy by suggesting alternative phrasing for questions based on user feedback.

This is for model refinement, not multi-turn conversation.

Thus, the correct way to configure the project for multi-turn conversations is to add follow-up prompts.

Correct Answer: C. Add follow-up prompts

Microsoft References

Custom question answering in Azure AI Language – Multi-turn conversations

Custom question answering overview

 The subscription will be charged 86 tokens for the execution of the session. No

 The text completion was truncated because the Max response tokens value was exceeded. No

 The prompt_tokens value will be included in the calculation of the Max response tokens value. No

From the response payload:

usage.prompt_tokens = 37

usage.completion_tokens = 86

usage.total_tokens = 123

finish_reason = " stop "

Billing is for total tokens (input + output), not just completion tokens.

Azure OpenAI bills on both prompt (input) and completion (output) tokens. Here, the total is 123 tokens, so it is not just 86. Hence No.

Not truncated by max response tokens.

If a response hits the maximum allowed output tokens, finish_reason would be " length " . Here it is " stop " and the model produced only 86 completion tokens while Max response tokens was set to 100, so the limit was not reached. Hence No.

max response tokens applies only to the generated output, not the prompt.

max_tokens (Max response tokens) limits the number of tokens the model may generate in the completion; it does not include prompt_tokens . Hence No.

Microsoft References

Azure OpenAI Service – Chat Completions API (parameters, max_tokens , response usage , finish_reason ).

https://learn.microsoft.com/azure/ai-services/openai/reference#chat-completions

Azure OpenAI pricing and token usage model (charges for input and output tokens).

https://learn.microsoft.com/azure/ai-services/openai/overview#pricing

Token counting and limits (context vs. max output tokens).

https://learn.microsoft.com/azure/ai-services/openai/concepts/tokenizers#token-limits

The question is about creating an Azure Cognitive Services resource programmatically with C#.

Key requirements from the question:

Free resource → This requires the F0 (Free) pricing tier.

West US region → Location should be " westus " .

Generate captions of images automatically → This requires the Computer Vision service.

Option Analysis

A. create_resource(client, " res1 " , " ComputerVision " , " F0 " , " westus " )

Uses " ComputerVision " kind → Correct, because Computer Vision provides the image captioning feature.

Tier is " F0 " → Correct, free tier.

Location " westus " → Correct.

This is the correct answer.

B. create_resource(client, " res1 " , " CustomVision.Prediction " , " F0 " , " westus " )

Custom Vision is for building and deploying custom image classifiers.

The Prediction resource is specifically for running inference, not general captioning.

Wrong service for the requirement.

C. create_resource(client, " res1 " , " ComputerVision " , " S0 " , " westus " )

" ComputerVision " is correct.

But " S0 " is a paid tier, not the required free tier.

Does not meet the requirement.

D. create_resource(client, " res1 " , " CustomVision.Prediction " , " S0 " , " westus " )

Wrong service (captioning is not handled by Custom Vision).

Wrong tier (paid instead of free).

Incorrect.

Correct Answer: A. create_resource(client, " res1 " , " ComputerVision " , " F0 " , " westus " )

Microsoft References

Azure AI Computer Vision documentation

Create a Cognitive Services resource in Azure

Computer Vision capabilities – Image analysis and captioning

Comprehensive Detailed Explanation

You’re creating a resource that will handle sentiment analysis (Language) and OCR (Vision) with a single key and endpoint. That is a Cognitive Services multi-service (Azure AI services) account.

When creating any Azure resource via ARM (HTTP/REST), the URL must be scoped to a subscription, not a tenant, and use the correct resource provider.

Scope segment: Use

https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{rg}/providers/...

Therefore, choose subscriptions/8d3591aa-96b8-4737-ad09-00f9b1ed35ad (not the tenant scope).

Resource provider: Multi-service cognitive account is under Microsoft.CognitiveServices.

The full path to create would be like:

/providers/Microsoft.CognitiveServices/accounts/{accountName}?api-version=2021-10-01

This creates a single Cognitive Services (Azure AI services) resource that provides one endpoint and one key across multiple services (e.g., Language for sentiment analysis and Vision for OCR).

Microsoft Azure AI Solution References

Azure Resource Manager: Create Cognitive Services account (Microsoft.CognitiveServices/accounts) using REST and API version 2021-10-01.

Azure AI services (Cognitive Services) multi-service resource overview—single key/endpoint across services.

You can use the Speech service to voice-enable a chat bot.

The Direct Line Speech channel uses the text-to-speech service, which has neural and standard voices.

You ' ll need to make a small configuration change so that your bot can communicate with the Direct Line Speech channel using web sockets.

The requirement is:

" Measure the public perception of your brand on social media using natural language processing (NLP). "

A. Content Moderator

Designed to filter offensive or inappropriate content in text, images, and videos.

Not suitable for sentiment analysis or measuring perception.

B. Form Recognizer

Extracts structured data from documents (invoices, receipts, forms).

Not used for analyzing social media posts.

C. Computer Vision

Analyzes images and videos for object detection, image classification, OCR, etc.

Not used for text-based sentiment analysis.

D. Language service ✅

Provides natural language processing (NLP) capabilities such as sentiment analysis, opinion mining, key phrase extraction, entity recognition , and language detection .

Perfect fit for analyzing public perception from social media posts .

The question is about evaluating a Custom Vision classifier after training.

When you train an image classifier in Azure Custom Vision, the service automatically calculates performance metrics to help you evaluate the quality of the model.

Metrics Provided by Custom Vision:

Precision:

The percentage of correct positive predictions out of all positive predictions made.

Formula: Precision = TP / (TP + FP)

Helps determine how reliable positive predictions are.

Recall:

The percentage of actual positives that were correctly predicted.

Formula: Recall = TP / (TP + FN)

Helps determine how many of the true positives were captured.

These two metrics are explicitly shown in the Custom Vision portal and via API.

Option Analysis

A. Recall

Yes, Custom Vision reports recall.

Correct

B. F-score

Not directly reported in the Custom Vision portal.

Although it can be derived from precision and recall, it is not provided as a direct metric.

Incorrect

C. Weighted accuracy

Not reported by Custom Vision.

Incorrect

D. Precision

Yes, Custom Vision reports precision.

Correct

E. Area under the curve (AUC)

Not reported by Custom Vision.

More common in ROC curve analysis, not part of Custom Vision output.

Incorrect

Correct Answer: A. recall, D. precision

Microsoft References

Evaluate the prediction performance of your classifier in Custom Vision

Custom Vision training and evaluation

A view is a virtual table based on the result set of a query.

Views allow you to encapsulate complex queries (including joins and calculated columns) and make them reusable by other users.

Index improves performance but does not store or rerun queries.

Scalar function returns a single value, not a tabular result.

Table stores raw data, not queries.

For a table projection in a knowledge store (skillset definition), the table node must define:

tableName : the table to project into (physical expression).

generatedKeyName : the name of the system-generated key column.

source : an object-shaping expression (projection path) describing what document content flows into the table.

dataSource/dataSourceConnection are service-level objects used by the indexer, not properties of a table projection node.

References

Knowledge store and projections schema: table projections require tableName, generatedKeyName, and source in the skillset JSON.

The question describes:

An Azure subscription with an Azure AI Content Safety resource.

A social media application where users can upload images.

The requirement is to moderate inappropriate content in those uploaded images.

In Azure AI Content Safety SDKs:

You create a ContentSafetyClient by providing the endpoint and key.

The ContentSafetyClient exposes methods such as:

AnalyzeText() → For text moderation

AnalyzeImage() → For image moderation

Let’s review the code structure:

public static void Analyze ( AnalyzeImageOptions request )

{

var endpoint = Environment.GetEnvironmentVariable( " ENDPOINT " );

var key = Environment.GetEnvironmentVariable( " KEY " );

var client = new ContentSafetyClient( new Uri(endpoint), new AzureKeyCredential(key));

return client.AnalyzeImage(request);

}

First dropdown: must be ContentSafetyClient to instantiate the correct client for Azure AI Content Safety.

Second dropdown: since the requirement is image moderation, we must call client.AnalyzeImage(request) .

Other options:

BlocklistClient → used for custom blocklists, not full moderation.

TextCategoriesAnalysis → refers to text analysis categories, not suitable here.

AnalyzeText → would be used only for text moderation.

Therefore, the correct completion is:

ContentSafetyClient

client.AnalyzeImage(request)

Correct Answer:

First dropdown: ContentSafetyClient

Second dropdown: client.AnalyzeImage(request)

Microsoft References

Azure AI Content Safety – Analyze images

Azure AI Content Safety SDK documentation

ContentSafetyClient class

Box 1: " categories " : [ " Locations " , " Persons " , " Organizations " ],

Locations, Persons, Organizations are in the outputs.

Scenario: Contoso plans to develop a searchable knowledgebase of all the intellectual property

Note: The categories parameter is an array of categories that should be extracted. Possible category types: " Person " , " Location " , " Organization " , " Quantity " , " Datetime " , " URL " , " Email " . If no category is provided, all types are returned.

Box 2: { " name " : " entities " }

The include wikis, so should include entities in the outputs.

Note: entities is an array of complex types that contains rich information about the entities extracted from text, with the following fields

name (the actual entity name. This represents a " normalized " form)

wikipediaId

wikipediaLanguage

wikipediaUrl (a link to Wikipedia page for the entity)

etc.

Box 1: Cognitive Service User

Ensure that the members of a group named Management-Accountants can approve the FAQs.

Approve=publish.

Cognitive Service User (read/write/publish): API permissions: All access to Cognitive Services resource except for ability to:

1. Add new members to roles.

2. Create new resources.

Box 2: Cognitive Services QnA Maker Editor

Ensure that the members of a group named Consultant-Accountants can create and amend the FAQs.

QnA Maker Editor: API permissions:

1. Create KB API

2. Update KB API

3. Replace KB API

4. Replace Alterations

5. " Train API " [in new service model v5]

Box 3: Cognitive Services QnA Maker Read

Ensure that the members of a group named the Agent-CustomerServices can browse the FAQs.

QnA Maker Read: API Permissions:

1. Download KB API

2. List KBs for user API

3. Get Knowledge base details

4. Download Alterations

Generate Answer

Step 1: Create a new project and load sample documents

Create a new project. Projects store your configurations and settings.

Step 2: Label the sample documents

When you create or open a project, the main tag editor window opens.

Step 3: Train a custom model.

Finally, train a custom model.

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.

Scenario: When the response confidence score is low, ensure that the chatbot can provide other response options to the customers.

When no good match is found by the ranker, the confidence score of 0.0 or " None " is returned and the default response is " No good match found in the KB " . You can override this default response in the bot or application code calling the endpoint. Alternately, you can also set the override response in Azure and this changes the default for all knowledge bases deployed in a particular QnA Maker service.

Choosing Ranker type: By default, QnA Maker searches through questions and answers. If you want to search through questions only, to generate an answer, use the RankerType=QuestionOnly in the POST body of the GenerateAnswer request.

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

If a bot uses multiple LUIS models and QnA Maker knowledge bases (knowledge bases), you can use the Dispatch tool to determine which LUIS model or QnA Maker knowledge base best matches the user input. The dispatch tool does this by creating a single LUIS app to route user input to the correct model.

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/v3.2/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.

Box 1: api-nam.cognitive.microsofttranslator.com

https://docs.microsoft.com/en-us/azure/cognitive-services/translator/reference/v3-0-reference

Box 2: /translate

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.

The requirements state:

All AI solution responses must have a confidence score ≥ 70%.

If the response confidence score is < 70%, the response must be improved by human input.

Members of the Consultant-Bookkeeper group must be able to process financial documents, which includes performing manual review when the AI confidence is below threshold.

Looking at the provided JSON:

" fields " : {

" ReceiptType " : {

" type " : " string " ,

" valueString " : " Itemized " ,

" confidence " : 0.672

},

" MerchantName " : {

" type " : " string " ,

" valueString " : " Tailwind " ,

" confidence " : 0.913

}

}

ReceiptType.confidence = 0.672 → this is below 0.7.

MerchantName.confidence = 0.913 → this is above 0.7.

Therefore, the correct condition for triggering manual review is:

documentResults.fields. < field > .confidence < 0.7

Now, evaluating the options:

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

Always true for receipts, does not check confidence. Not correct.

B. documentResults.fields.*.confidence < 0.7

This is the correct general expression: trigger manual review whenever any field confidence is below 0.7.

C. documentResults.fields.ReceiptType.confidence > 0.7

This would bypass manual review when ReceiptType has high confidence. The requirement is to trigger review when confidence < 0.7, so this is the opposite.

D. documentResults.fields.MerchantName.confidence < 0.7

This only checks one field (MerchantName). In the JSON, MerchantName has confidence 0.913 ( > 0.7), so this condition would not trigger, but ReceiptType clearly needs review. Too narrow.

Correct Answer: B. documentResults.fields.*.confidence < 0.7

Microsoft References

Azure AI Document Intelligence – Confidence scores

Human-in-the-loop for Document Intelligence

Can search content in different formats, including video

Audio and video insights (multi-channels). When indexing by one channel, partial result for those models will be available.

Keywords extraction: Extracts keywords from speech and visual text.

Named entities extraction: Extracts brands, locations, and people from speech and visual text via natural language processing (NLP).

Topic inference: Makes inference of main topics from transcripts. The 2nd-level IPTC taxonomy is included.

Artifacts: Extracts rich set of " next level of details " artifacts for each of the models.

Sentiment analysis: Identifies positive, negative, and neutral sentiments from speech and visual text.

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.

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?search & api-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.

Box 1: QnA Maker Editor

Scenario: Provide all employees with the ability to edit Q & As.

The QnA Maker Editor (read/write) has the following permissions:

Create KB API

Update KB API

Replace KB API

Replace Alterations

" Train API " [in

new service model v5]

Box 2: Contributor

Scenario: Only senior managers must be able to publish updates.

Contributor permission: All except ability to add new members to roles

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.

Comprehensive Detailed Explanation

The requirement is to build an Adaptive Card for the chatbot that supports multilingual product display and meets accessibility requirements.

Product Name Display

The product JSON stores localized names like " name " : { " en " : " ... " , " es " : " ... " , " pt " : " ... " } .

To dynamically render based on the current language, you must use name[language].

This ensures the product name shown in the card adapts automatically to the user’s preferred language.

Stock Level Warning

Business rules require warnings when stock is low or out of stock.

This means you display the stock warning only when stockLevel is not ' OK ' .

Therefore, the correct condition is:

" $when " : " ${stockLevel != ' OK ' } "

Image Alt Text for Accessibility

Accessibility requirements specify that all images must have alt text in English, Spanish, and Portuguese.

In the product JSON, " alttext " is also localized:

" altText " : { " en " : " Bicycle " , " es " : " Bicicleta " , " pt " : " Bicicleta " }

To render the correct localized alt text dynamically, use image.altText[language].

Correct Selections:

First blank: name[language]

Second blank: " $when " : " ${stockLevel != ' OK ' } "

Third blank: image.altText[language]

Microsoft References

Adaptive Cards Templating

Adaptive Card $when property

Multilingual data in Azure Cognitive Search and Adaptive Cards