AI-102 Practice Test 48 — 15 Questions

Question 1

You need to extract entities such as dates, locations, and organization names from unstructured text documents. Which Azure AI service should you use?

Accepted Answer

Azure AI Language Service. Azure AI Language Service provides pre-built capabilities for entity recognition, including extracting dates, locations, and organization names from unstructured text via its Named Entity Recognition (NER) feature. This service is specifically designed for text analytics tasks, making it the correct choice for entity extraction from text documents.

Answer

Computer Vision

Answer

Azure AI Document Intelligence

Answer

Azure AI Speech Service

Question 2

Your knowledge mining solution uses Azure AI Document Intelligence to extract data from purchase orders. The extracted data is then indexed by Azure AI Search. You need to ensure that the search index includes the purchase order number and total amount as searchable fields. What should you do?

Accepted Answer

Create a custom skill that calls Azure AI Document Intelligence and returns extracted fields, then use outputFieldMappings to map to index fields.. Azure AI Document Intelligence extracts structured data (like PO number and total amount) from documents, but this data must be explicitly mapped to Azure AI Search index fields using outputFieldMappings in a custom skill. The custom skill invokes Document Intelligence via the Skillset, and outputFieldMappings bridge the extracted fields to the search index schema, making them searchable. This approach ensures the extracted fields are ingested into the index without manual intervention.

Answer

Use Azure AI Document Intelligence's pre-built model to analyze documents and store results in a database, then use a SQL indexer to index the database.

Answer

Use the OCR skill to extract text and then use regular expressions to find PO number and total.

Answer

Manually enter the extracted data into the search index.

Question 3

Refer to the exhibit. You are creating a Custom Vision project using the Azure AI Custom Vision API. The training data is stored in Azure Blob Storage with a SAS URI. The project creation fails with an authorization error. What is the most likely reason?

Accepted Answer

The SAS token is expired or has insufficient permissions. The Custom Vision project creation fails because the SAS URI used to access training data in Azure Blob Storage has an expired token or lacks sufficient permissions (e.g., read/list). Custom Vision requires a valid SAS token with at least read and list permissions to import images from the container. An expired or under-permissioned SAS token results in an authorization error when the service attempts to access the blob storage.

Answer

The domain 'general' is invalid

Answer

The exportModelContainerUri is missing

Answer

The project type 'Classification' is not supported

Question 4

A company uses Azure AI Document Intelligence to extract data from invoices. Recently, extraction accuracy dropped for new vendor formats. Which strategy should you implement to improve accuracy without retraining the entire model?

Accepted Answer

Train a custom extraction model using labeled examples from the new vendor formats.. Training a custom extraction model using labeled examples from the new vendor formats allows Azure AI Document Intelligence to learn the specific layout and field patterns of those invoices without affecting the prebuilt model's performance on other formats. This approach leverages the custom model training capability, which is designed to adapt to unique document structures while preserving the existing extraction logic for previously supported formats.

Answer

Increase the confidence threshold for extraction results.

Answer

Switch from Document Intelligence to Azure AI Language service.

Answer

Increase the number of transactions per second (TPS) limit.

Question 5

Your organization is using Azure AI Document Intelligence to process expense reports. The reports are submitted as images and need to be classified into categories (e.g., travel, office supplies) before extraction. Which feature of Document Intelligence should you use?

Accepted Answer

Custom classification model. Azure AI Document Intelligence's custom classification model is specifically designed to categorize documents (such as expense report images) into user-defined classes (e.g., travel, office supplies) before any extraction occurs. This model uses a trained classifier to assign a document type based on its visual and textual features, enabling downstream processing with the appropriate extraction model.

Answer

OCR capability

Answer

Layout extraction

Answer

Prebuilt expense report model

Question 6

A company uses the Face API to detect and identify employees for building access. They need to ensure that the system complies with GDPR requirements for biometric data. Which action should they take?

Accepted Answer

Obtain explicit consent from each employee before enrollment.. Under GDPR, biometric data (such as facial recognition templates) is classified as special category data requiring explicit consent for processing. The Face API itself does not manage consent; the responsibility lies with the application layer. Option C is correct because obtaining explicit consent from each employee before enrollment is a fundamental GDPR requirement for lawful processing of biometric data.

Answer

Store faces in a secure database and delete after 30 days.

Answer

Anonymize the face data by blurring key features.

Answer

Use encryption for stored face templates.

Question 7

Your company uses Azure Cognitive Search to index millions of documents. Users report that search results include irrelevant documents. You need to improve search relevance by boosting documents that contain the search term in the title field. Which scoring profile configuration should you use?

Accepted Answer

Create a tagging scoring profile that boosts by the title field with a weight of 10.. A tagging scoring profile boosts documents based on matching tags from a specific field (like title), and the weight parameter controls the boost magnitude. Option B is incorrect because a freshness scoring profile boosts by recency, not by term presence in a field. Option C is incorrect because a distance scoring profile boosts based on geospatial proximity, not text fields. Option D is incorrect because a magnitude scoring profile boosts based on numeric field values, not text fields; a linear boosting function is used for magnitude profiles, but this does not apply to boosting by title.

Answer

Create a freshness scoring profile with a boosting duration of 30 days.

Answer

Create a distance scoring profile with a reference point parameter.

Answer

Create a magnitude scoring profile with a boosting function of 'linear'.

Question 8

A company plans to use Azure Cognitive Search to index a large number of PDF documents stored in Azure Blob Storage. The documents contain sensitive personally identifiable information (PII). The search results should only be accessible to authorized users based on their Azure Active Directory (Azure AD) group membership. Which combination of features should the company implement?

Accepted Answer

Index the documents and use security filters with Azure AD group-based access control.. Azure Cognitive Search supports security trimming via OAuth 2.0 and Azure AD group-based access control. By storing group identifiers in a search index field and using a security filter, only users whose Azure AD group membership matches the stored group IDs can see the corresponding search results. This ensures that sensitive PII in PDF documents is only returned to authorized users without exposing the documents themselves.

Answer

Generate shared access signatures (SAS) for each document and include them in the search index.

Answer

Use Azure RBAC to assign permissions to users for the search service and configure field-level security.

Answer

Store Azure AD group membership in a field in the search index and configure an indexer to map the field.

Question 9

You are building a knowledge mining solution using Azure AI Search. You need to ensure that sensitive information such as credit card numbers is automatically removed from the indexed content. Which built-in skill should you add to your skillset?

Accepted Answer

PII Detection skill. The PII Detection skill is the correct built-in skill for automatically identifying and redacting sensitive information like credit card numbers from indexed content in Azure AI Search. It uses pre-trained models to detect patterns such as credit card numbers, social security numbers, and other personally identifiable information, and can either mask or remove them from the text before it is stored in the search index.

Answer

Entity Recognition skill

Answer

Conditional skill

Answer

Text Translation skill

Question 10

You are building a custom copilot using Microsoft Foundry. The copilot must answer questions based on internal documents stored in SharePoint. Which two components are essential for this solution?

Accepted Answer

Azure AI Search with a SharePoint indexer. Azure AI Search with a SharePoint indexer is essential because it ingests and indexes the internal documents from SharePoint, enabling full-text and vector search capabilities that the copilot uses to retrieve relevant content. This indexer automates the crawling of SharePoint sites and keeps the search index synchronized with document changes, which is critical for answering questions based on up-to-date internal data. Additionally, Azure OpenAI Service with a GPT model is necessary to generate natural language answers from the retrieved content, providing the conversational capability of the copilot. Together, they enable the 'retrieve-and-generate' pattern.

Answer

Azure AI Language conversational language understanding (CLU)

Answer

Azure AI Document Intelligence (Form Recognizer)

Question 11

Which THREE factors should be considered when choosing between Azure AI Language's pre-built sentiment analysis and custom sentiment analysis for a specialized domain?

Accepted Answer

Custom models require a large set of labeled training data.. Custom sentiment analysis in Azure AI Language requires a sufficiently large set of labeled training data to fine-tune a model for a specialized domain. Without this data, the custom model cannot learn domain-specific sentiment patterns, making it impractical for scenarios where labeled data is scarce.

Answer

Custom models always have faster response times.

Answer

Pre-built models cannot be used in containers.

Question 12

Your organization is deploying an Azure AI service for document translation. The solution must support custom glossaries and real-time translation. Cost optimization is a key requirement. Which pricing tier should you choose?

Accepted Answer

Standard S1. The Standard S1 tier is the correct choice because it supports custom glossaries and real-time translation, which are required for the document translation solution. Additionally, S1 offers a balance of features and cost, making it optimal for production workloads where cost optimization is a key requirement, unlike the Free F0 tier which has limited throughput and no SLA, or the Premium S2 tier which is designed for high-volume scenarios at a higher cost.

Answer

Free F0

Answer

Basic S0

Answer

Premium S2

Question 13

A hospital uses Azure Custom Vision to classify X-ray images as normal or abnormal. The model achieves 98% accuracy on the test set. However, during deployment, the model misclassifies many abnormal cases as normal, causing missed diagnoses. The hospital has a class imbalance where abnormal cases are only 5% of the data. What should the data scientist do first to address this?

Accepted Answer

Use oversampling or class-weight techniques to balance the training.. The primary issue is class imbalance, where abnormal cases constitute only 5% of the data. Oversampling (e.g., SMOTE) or class-weight techniques adjust the training process to give more importance to the minority class, directly addressing the model's bias toward the majority class and reducing false negatives. This is a standard preprocessing step in Custom Vision and other ML frameworks before tuning hyperparameters or changing algorithms.

Answer

Increase the number of training epochs.

Answer

Add more normal X-ray images to the dataset.

Answer

Switch to a different object detection algorithm.

Question 14

Refer to the exhibit. A developer is training a Language Understanding (LUIS) model. When testing the phrase 'Show me the status of order 98765', the model returns the intent 'OrderStatus' with a low confidence score. What is the most likely reason?

Accepted Answer

The phrase 'Show me the status' was not seen during training.. The phrase is similar to the training utterance but includes extra words ('Show me the') and a different order number. The model may not generalize well without more varied examples. Also, entities are not labeled in the test phrase.

Answer

The entity 'OrderNumber' should be a list entity.

Answer

The phrase contains an entity that was not labeled in training.

Answer

The model is overfitted to the training data.

Question 15

A retail company uses Azure Computer Vision to analyze in-store camera feeds. They recently added a new product line and updated the object detection model. However, the model fails to detect the new products. What should the company do first?

Accepted Answer

Retrain the custom object detection model with images of the new products.. The model fails to detect new products because it was never trained on them. Retraining the custom object detection model with labeled images of the new products is the correct first step, as it updates the model's knowledge to recognize the new product line. Pre-built models or threshold adjustments cannot add new object classes.

Answer

Use the pre-built 'products' model from Computer Vision.

Answer

Increase the confidence threshold in the API call.

Answer

Recreate the Computer Vision resource in a different region.