AI-900-KR 문제 86
구조화되지 않은 대량의 데이터에서 데이터 간의 관계를 추출하는 것은 어떤 유형의 AI 워크로드의 예입니까?
정답: B
Extracting relationships and insights from large volumes of unstructured data (such as documents, text files, or images) aligns with the Knowledge Mining workload in Microsoft Azure AI. According to the Microsoft AI Fundamentals (AI-900) study guide and Microsoft Learn module "Describe features of common AI workloads," knowledge mining involves using AI to search, extract, and structure information from vast amounts of unstructured or semi-structured content.
In a typical knowledge mining solution, tools like Azure AI Search and Azure AI Document Intelligence work together to index data, apply cognitive skills (such as OCR, key phrase extraction, and entity recognition), and then enable users to discover relationships and patterns through intelligent search. The process transforms raw content into searchable knowledge.
The key characteristics of knowledge mining include:
* Using AI to extract entities and relationships between data points.
* Applying cognitive skills to text, images, and documents.
* Creating searchable knowledge stores from unstructured data.
Hence, B. Knowledge Mining is correct.
The other options-computer vision, NLP, and anomaly detection-deal with image recognition, language understanding, and data irregularities, respectively, not large-scale information extraction.
In a typical knowledge mining solution, tools like Azure AI Search and Azure AI Document Intelligence work together to index data, apply cognitive skills (such as OCR, key phrase extraction, and entity recognition), and then enable users to discover relationships and patterns through intelligent search. The process transforms raw content into searchable knowledge.
The key characteristics of knowledge mining include:
* Using AI to extract entities and relationships between data points.
* Applying cognitive skills to text, images, and documents.
* Creating searchable knowledge stores from unstructured data.
Hence, B. Knowledge Mining is correct.
The other options-computer vision, NLP, and anomaly detection-deal with image recognition, language understanding, and data irregularities, respectively, not large-scale information extraction.
AI-900-KR 문제 87
슈퍼마켓 선반 이미지에서 제품의 브랜드 이름을 식별하는 봇이 있습니다.
봇은 어떤 서비스를 사용하나요?
봇은 어떤 서비스를 사용하나요?
정답: C
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module "Describe features of computer vision workloads on Azure," the Custom Vision service is a specialized part of Azure Cognitive Services that allows developers to train image classification and object detection models tailored to their own data. It is particularly useful when prebuilt models, such as those in the standard Computer Vision service, cannot accurately recognize domain-specific objects - such as specific product brands or packaging.
In this scenario, the bot must identify brand names of products in images of supermarket shelves. Since brand logos and packaging designs are unique to each company, a general-purpose image analysis model would not perform accurately. The Custom Vision Image Classification capability allows you to upload labeled images (e.g., various brands) and train a model to distinguish between them. Once trained, the model can classify new images and recognize which brand appears on the shelf.
Let's analyze the other options:
* A. AI enrichment for Azure Search capabilities: Used in knowledge mining to extract information from documents, not image brand identification.
* B. Computer Vision Image Analysis capabilities: Provides prebuilt functionality such as detecting objects, describing images, and identifying common items (like "bottle" or "box") but cannot differentiate custom brand names.
* D. Language understanding capabilities: Deals with processing and understanding natural language text, not images.
Therefore, identifying specific brand names from images requires a custom-trained image classification model, making Custom Vision Image Classification capabilities the correct answer.
# Final Verified answer:
C). Custom Vision Image Classification capabilities
In this scenario, the bot must identify brand names of products in images of supermarket shelves. Since brand logos and packaging designs are unique to each company, a general-purpose image analysis model would not perform accurately. The Custom Vision Image Classification capability allows you to upload labeled images (e.g., various brands) and train a model to distinguish between them. Once trained, the model can classify new images and recognize which brand appears on the shelf.
Let's analyze the other options:
* A. AI enrichment for Azure Search capabilities: Used in knowledge mining to extract information from documents, not image brand identification.
* B. Computer Vision Image Analysis capabilities: Provides prebuilt functionality such as detecting objects, describing images, and identifying common items (like "bottle" or "box") but cannot differentiate custom brand names.
* D. Language understanding capabilities: Deals with processing and understanding natural language text, not images.
Therefore, identifying specific brand names from images requires a custom-trained image classification model, making Custom Vision Image Classification capabilities the correct answer.
# Final Verified answer:
C). Custom Vision Image Classification capabilities
AI-900-KR 문제 88
다음 각 문장에 대해, 문장이 사실이라면 '예'를 선택하세요. 그렇지 않으면 '아니요'를 선택하세요.
참고: 정답 하나당 1점입니다.
참고: 정답 하나당 1점입니다.
정답:
Explanation:
In Microsoft Azure AI Language Service, both Named Entity Recognition (NER) and Key Phrase Extraction are core features for text analytics. They serve distinct purposes in analyzing and structuring unstructured text data.
* Named Entity Recognition (NER):NER is used to identify and categorize specific entities within text, such as people, organizations, locations, dates, times, and quantities. According to Microsoft Learn's
"Analyze text with Azure AI Language" module, NER scans text to extract these entities along with their types. Therefore, the statement "Named entity recognition can be used to retrieve dates and times in a text string" is True (Yes).
* Key Phrase Extraction:This feature identifies the most important phrases or main topics in a block of text. It is useful for summarization or highlighting central ideas without classifying them into specific categories. Therefore, the statement "Key phrase extraction can be used to retrieve important phrases in a text string" is also True (Yes).
* City Name Retrieval:While key phrase extraction highlights major phrases, it does not extract specific entities like cities or dates. Extracting such details requires Named Entity Recognition, which is designed to find named entities such as city names, people, or organizations. Hence, the statement "Key phrase extraction can be used to retrieve all the city names in a text string" is False (No).
AI-900-KR 문제 89
생성적 AI 솔루션에서 증오적 응답이 반환되는 것을 방지하려면 무엇을 구현해야 합니까?
정답: B
To prevent hateful or harmful responses from being returned by a generative AI solution, the correct approach is to implement content filtering. According to the Microsoft Learn documentation for Azure OpenAI Service and the Responsible AI principles, content filtering is a built-in safety mechanism that automatically screens both user prompts (inputs) and model outputs (responses) for inappropriate, harmful, or policy-violating material.
Content filters are designed to detect and block content such as:
* Hate speech or harassment
* Sexual or explicit material
* Self-harm or violent content
* Personally identifiable information (PII) misuse
In Azure OpenAI, the content filtering system is part of Microsoft's Responsible AI standard and cannot be disabled. It ensures that generative AI models such as GPT-3.5 or GPT-4 operate safely and ethically, reducing the risk of producing offensive or discriminatory text. The filter evaluates model responses in real time and can modify, block, or flag inappropriate outputs before they reach the user.
Let's review the other options:
* A. Abuse monitoring tracks misuse after deployment but does not actively prevent hateful responses.
* C. Fine-tuning customizes a model's style or domain knowledge but does not guarantee filtering of offensive content.
* D. Prompt engineering helps steer model behavior but cannot fully prevent harmful outputs.
Therefore, to proactively prevent hateful, unsafe, or offensive responses in a generative AI system built on Azure OpenAI, the correct and Microsoft-verified approach is B. Content filtering.
Content filters are designed to detect and block content such as:
* Hate speech or harassment
* Sexual or explicit material
* Self-harm or violent content
* Personally identifiable information (PII) misuse
In Azure OpenAI, the content filtering system is part of Microsoft's Responsible AI standard and cannot be disabled. It ensures that generative AI models such as GPT-3.5 or GPT-4 operate safely and ethically, reducing the risk of producing offensive or discriminatory text. The filter evaluates model responses in real time and can modify, block, or flag inappropriate outputs before they reach the user.
Let's review the other options:
* A. Abuse monitoring tracks misuse after deployment but does not actively prevent hateful responses.
* C. Fine-tuning customizes a model's style or domain knowledge but does not guarantee filtering of offensive content.
* D. Prompt engineering helps steer model behavior but cannot fully prevent harmful outputs.
Therefore, to proactively prevent hateful, unsafe, or offensive responses in a generative AI system built on Azure OpenAI, the correct and Microsoft-verified approach is B. Content filtering.
AI-900-KR 문제 90
귀사는 위젯을 제조합니다.
위젯의 디지털 사진이 1,000장 있습니다.
사진 내에서 위젯의 위치를 파악해야 합니다.
무엇을 사용해야 하나요?
위젯의 디지털 사진이 1,000장 있습니다.
사진 내에서 위젯의 위치를 파악해야 합니다.
무엇을 사용해야 하나요?
정답: B
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module "Explore computer vision in Microsoft Azure," object detection is a computer vision technique used to locate and identify objects within an image. It not only determines what objects are present but also where they appear in the image by returning bounding box coordinates around each detected item.
In this scenario, the goal is to identify the location of widgets within digital photos. This requires both recognition (knowing that the object is a widget) and localization (determining its position). The Custom Vision service in Azure allows you to train a model specifically for your own images, making it ideal for recognizing company-specific products such as widgets. By selecting the Object Detection domain in Custom Vision, you can label regions of interest in your training images. The model then learns to detect and locate those objects in new photos.
Let's examine the other options:
* A. Computer Vision Spatial Analysis: Used for people tracking, movement detection, and occupancy analytics in video streams - not for locating products in still images.
* C. Custom Vision classification: This model categorizes an image as a whole (e.g., "contains a widget" or "does not contain a widget") but does not locate objects within the image.
* D. Computer Vision Image Analysis: Provides general image tagging, description, and OCR capabilities but does not pinpoint object locations.
In this scenario, the goal is to identify the location of widgets within digital photos. This requires both recognition (knowing that the object is a widget) and localization (determining its position). The Custom Vision service in Azure allows you to train a model specifically for your own images, making it ideal for recognizing company-specific products such as widgets. By selecting the Object Detection domain in Custom Vision, you can label regions of interest in your training images. The model then learns to detect and locate those objects in new photos.
Let's examine the other options:
* A. Computer Vision Spatial Analysis: Used for people tracking, movement detection, and occupancy analytics in video streams - not for locating products in still images.
* C. Custom Vision classification: This model categorizes an image as a whole (e.g., "contains a widget" or "does not contain a widget") but does not locate objects within the image.
* D. Computer Vision Image Analysis: Provides general image tagging, description, and OCR capabilities but does not pinpoint object locations.
- 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
- 3051Microsoft.MS-102-KR.v2026-09-01.q239
- 1559Microsoft.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.