AI-900-KR 문제 111
이미지 속의 유명인을 식별하는 앱을 만들어야 합니다.
어떤 서비스를 사용해야 하나요?
어떤 서비스를 사용해야 하나요?
정답: D
According to the Microsoft Azure AI Fundamentals (AI-900) official learning path, the appropriate service for recognizing celebrities in images is Azure AI Vision (formerly Computer Vision). This service is part of Azure's Cognitive Services suite and specializes in analyzing visual content using pretrained deep learning models. One of its built-in capabilities, as documented in Microsoft Learn: "Analyze images with Azure AI Vision", includes object detection, face detection, and celebrity recognition.
The Azure AI Vision Analyze API can detect and identify thousands of objects, brands, and celebrities. When an image is submitted to the service, the model compares detected faces to a known database of public figures and returns metadata including celebrity names, confidence scores, and bounding box coordinates. This makes it ideal for applications that need to recognize well-known individuals automatically-such as media cataloging, content tagging, or entertainment apps.
The other options are incorrect:
* A. Azure OpenAI Service provides generative AI and language models (like GPT-4), but it cannot analyze image content directly in the context of AI-900 fundamentals.
* B. Azure Machine Learning is for custom model training and deployment, not a prebuilt vision recognition service.
* C. Conversational Language Understanding (CLU) processes natural language input, not images.
Therefore, the correct service for identifying celebrities in images is D. Azure AI Vision.
The Azure AI Vision Analyze API can detect and identify thousands of objects, brands, and celebrities. When an image is submitted to the service, the model compares detected faces to a known database of public figures and returns metadata including celebrity names, confidence scores, and bounding box coordinates. This makes it ideal for applications that need to recognize well-known individuals automatically-such as media cataloging, content tagging, or entertainment apps.
The other options are incorrect:
* A. Azure OpenAI Service provides generative AI and language models (like GPT-4), but it cannot analyze image content directly in the context of AI-900 fundamentals.
* B. Azure Machine Learning is for custom model training and deployment, not a prebuilt vision recognition service.
* C. Conversational Language Understanding (CLU) processes natural language input, not images.
Therefore, the correct service for identifying celebrities in images is D. Azure AI Vision.
AI-900-KR 문제 112
허가 없이 얻은 데이터를 사용하여 만들어진 자연어 처리(NIP) 모델이 있습니다.
이는 책임 있는 AI에 대한 Microsoft 원칙 중 어떤 것을 위반하는 것입니까?
이는 책임 있는 AI에 대한 Microsoft 원칙 중 어떤 것을 위반하는 것입니까?
정답: A
According to the Microsoft Azure AI Fundamentals (AI-900) official study materials and Microsoft's Responsible AI Principles, one of the core principles is "Privacy and Security." This principle ensures that AI systems protect personal and sensitive information, maintaining compliance with privacy laws, data protection regulations, and ethical data-handling practices.
If a Natural Language Processing (NLP) model is created using data obtained without permission, it directly violates this principle. Data collected without proper consent breaches user privacy and potentially violates regulations such as GDPR (General Data Protection Regulation) or other global privacy frameworks.
The Privacy and Security principle emphasizes the following:
* AI systems must ensure data collection and usage transparency.
* Data must be lawfully acquired and used with consent.
* Systems should protect data against unauthorized access or misuse.
In contrast:
* Inclusiveness promotes accessibility and fairness for all users.
* Transparency focuses on explaining how AI systems make decisions.
* Reliability and safety ensure systems function as intended and minimize harm.
Therefore, using unapproved data clearly breaches Privacy and Security, as it involves unethical data sourcing and endangers user trust.
If a Natural Language Processing (NLP) model is created using data obtained without permission, it directly violates this principle. Data collected without proper consent breaches user privacy and potentially violates regulations such as GDPR (General Data Protection Regulation) or other global privacy frameworks.
The Privacy and Security principle emphasizes the following:
* AI systems must ensure data collection and usage transparency.
* Data must be lawfully acquired and used with consent.
* Systems should protect data against unauthorized access or misuse.
In contrast:
* Inclusiveness promotes accessibility and fairness for all users.
* Transparency focuses on explaining how AI systems make decisions.
* Reliability and safety ensure systems function as intended and minimize harm.
Therefore, using unapproved data clearly breaches Privacy and Security, as it involves unethical data sourcing and endangers user trust.
AI-900-KR 문제 113
귀사에서 병 재활용 기계를 제작하려고 합니다. 재활용 기계는 올바른 모양의 병을 자동으로 식별하고 나머지는 모두 폐기해야 합니다.
회사에서는 어떤 유형의 AI 워크로드를 사용해야 합니까?
회사에서는 어떤 유형의 AI 워크로드를 사용해야 합니까?
정답: C
According to Microsoft's AI-900 study guide and the Microsoft Learn module "Identify common types of AI workloads", computer vision is the branch of AI that enables machines to interpret and act upon visual inputs such as photos, videos, or camera feeds.
In this scenario, the recycling machine must identify bottles based on their shape and reject other objects. This requires the AI system to visually analyze an image or a video stream and make a decision based on shape recognition-a classic computer vision application.
Computer vision models are trained with labeled image data (e.g., images of correct bottle shapes vs. incorrect items). Using techniques such as object detection or image classification, the model learns to detect patterns and identify whether an image matches the desired object.
The other options are not suitable:
* A. Anomaly detection identifies unusual data patterns, not visual features.
* B. Conversational AI handles human-computer interactions via text or voice.
* D. Natural language processing (NLP) deals with understanding and generating human language.
Therefore, because the task requires visual recognition of bottle shapes, the appropriate AI workload is Computer Vision.
Reference:Microsoft Learn - Identify common types of AI workloads: Computer Vision, NLP, Conversational AI, and Anomaly Detection (AI-900 Learning Path)
In this scenario, the recycling machine must identify bottles based on their shape and reject other objects. This requires the AI system to visually analyze an image or a video stream and make a decision based on shape recognition-a classic computer vision application.
Computer vision models are trained with labeled image data (e.g., images of correct bottle shapes vs. incorrect items). Using techniques such as object detection or image classification, the model learns to detect patterns and identify whether an image matches the desired object.
The other options are not suitable:
* A. Anomaly detection identifies unusual data patterns, not visual features.
* B. Conversational AI handles human-computer interactions via text or voice.
* D. Natural language processing (NLP) deals with understanding and generating human language.
Therefore, because the task requires visual recognition of bottle shapes, the appropriate AI workload is Computer Vision.
Reference:Microsoft Learn - Identify common types of AI workloads: Computer Vision, NLP, Conversational AI, and Anomaly Detection (AI-900 Learning Path)
AI-900-KR 문제 114
다음 각 문장에 대해, 문장이 사실이라면 '예'를 선택하세요. 그렇지 않으면 '아니요'를 선택하세요.
참고: 정답 하나당 1점입니다.
참고: 정답 하나당 1점입니다.
정답:
Explanation:
The Azure AI Language Service includes several natural language processing features, such as question answering, language understanding, entity recognition, sentiment analysis, and more. Each feature serves a distinct purpose, and understanding their differences is key to selecting the correct AI workload.
* "You can use Azure AI Language Service ' s question answering to query an Azure SQL database." - NOThe question answering feature is designed to retrieve answers from text-based knowledge sources (for example, FAQs, documents, or website content). It cannot directly query a database such as Azure SQL. Querying databases requires Azure Cognitive Search, Azure OpenAI, or custom integration using application logic, not the question answering model.
* "You should use Azure AI Language Service ' s question answering when you want a knowledge base to provide the same answer to different users who submit similar questions." - YESThis is the primary use case of question answering. It allows developers to build a knowledge base (KB) of predefined question-answer pairs or extract answers from documents. When users submit semantically similar questions (e.g., "What are your office hours?" or "When are you open?"), the service returns the same consistent answer.
* "Azure AI Language Service ' s question answering can determine the intent of a user utterance." - NODetermining user intent is part of the Language Understanding (LUIS) capability, not question answering. LUIS models map natural language inputs to intents and entities, typically used in bots or applications that execute tasks (like booking a meeting or checking weather).
Hence, correct answers are: No, Yes, No - aligning with the AI-900 official study guide and Microsoft Learn module "Identify Azure AI Language capabilities."
AI-900-KR 문제 115
문서의 텍스트를 요약하려면 어떤 Azure OpenAI 모델을 사용해야 합니까?
정답: D
According to the Microsoft Learn documentation and the Azure AI Fundamentals (AI-900) study guide, the GPT (Generative Pre-trained Transformer) family of models within Azure OpenAI Service is used for text- based natural language tasks, including summarization, content generation, and text completion.
When you need to summarize text from a document, GPT models (such as GPT-3.5 or GPT-4) can process large sections of text, extract the most relevant details, and generate concise summaries that retain the key meaning. The summarization task uses the model's natural language understanding capabilities to identify core concepts and generate human-like, coherent text.
Other options are incorrect:
* A. Whisper # Used for speech-to-text transcription, not text summarization.
* B. DALL-E # Generates images from text prompts, not text summaries.
* C. Codex # Specializes in code generation and completion, not document summarization.
When you need to summarize text from a document, GPT models (such as GPT-3.5 or GPT-4) can process large sections of text, extract the most relevant details, and generate concise summaries that retain the key meaning. The summarization task uses the model's natural language understanding capabilities to identify core concepts and generate human-like, coherent text.
Other options are incorrect:
* A. Whisper # Used for speech-to-text transcription, not text summarization.
* B. DALL-E # Generates images from text prompts, not text summaries.
* C. Codex # Specializes in code generation and completion, not document summarization.
- 다른 버전
- 2020Microsoft.AI-900-KR.v2026-05-11.q134
- 1502Microsoft.AI-900-KR.v2026-03-02.q135
- 1922Microsoft.AI-900-KR.v2026-02-07.q121
- 4334Microsoft.AI-900-KR.v2026-01-05.q136
- 1704Microsoft.AI-900-KR.v2026-01-01.q158
- 최근 업로드
- 1367Salesforce.AP-223.v2026-09-01.q94
- 1001Splunk.SPLK-5001.v2026-09-01.q60
- 1136Cisco.300-540.v2026-09-01.q62
- 3048Microsoft.MS-102-KR.v2026-09-01.q239
- 1555Microsoft.AI-900-KR.v2026-09-01.q162
- 4367Microsoft.AZ-104-KR.v2026-08-31.q361
- 1855Microsoft.PL-400-KR.v2026-08-31.q166
- 2479USGBC.LEED-Green-Associate-KR.v2026-08-31.q214
- 149HP.HPE0-V27-KR.v2026-08-31.q76
- 131Microsoft.DP-700-KR.v2026-08-31.q62
[×]
PDF 파일 다운로드
메일 주소를 입력하시고 다운로드 하세요. Microsoft.AI-900-KR.v2026-09-01.q162 모의시험 시험자료를 다운 받으세요.