Microsoft Azure AI Fundamentals (AI-900 Korean Version) - AI-900 Korean Exam Practice Test
Azure OpenAI 서비스를 배포하여 이미지를 생성합니다.
서비스가 유해한 콘텐츠로부터 최고 수준의 보호를 제공하는지 확인해야 합니다.
어떻게 해야 하나요?
서비스가 유해한 콘텐츠로부터 최고 수준의 보호를 제공하는지 확인해야 합니다.
어떻게 해야 하나요?
Correct Answer: A
Vote an answer
Explanation: Only visible for Fast2test members. You can sign-up / login (it's free).
귀하는 전자상거래 사업을 위한 대화형 언어 이해 모델을 구축하고 있었습니다.
모델의 의도된 범위를 벗어난 발언이 있을 경우 이를 감지할 수 있어야 합니다.
어떻게 해야 하나요?
모델의 의도된 범위를 벗어난 발언이 있을 경우 이를 감지할 수 있어야 합니다.
어떻게 해야 하나요?
Correct Answer: B
Vote an answer
Explanation: Only visible for Fast2test members. You can sign-up / login (it's free).
개인 디지털 사진 컬렉션에 레이블을 지정하는 모델을 만들어야 합니다.
어떤 Azure AI 서비스를 사용해야 하나요?
어떤 Azure AI 서비스를 사용해야 하나요?
Correct Answer: D
Vote an answer
Explanation: Only visible for Fast2test members. You can sign-up / login (it's free).
디지털 사진에 대한 자동 캡션을 생성하는 데 사용할 수 있는 컴퓨터 비전 기능은 무엇입니까?
Correct Answer: C
Vote an answer
Explanation: Only visible for Fast2test members. You can sign-up / login (it's free).
Azure Al 언어 기능 중 어떤 기능을 사용하면 소셜 미디어 게시물에서 날짜, 사람 이름 등의 데이터를 검색할 수 있나요?
Correct Answer: D
Vote an answer
Explanation: Only visible for Fast2test members. You can sign-up / login (it's free).
다음 각 문장에 대해, 문장이 사실이라면 '예'를 선택하세요. 그렇지 않으면 '아니요'를 선택하세요.
참고: 정답 하나당 1점입니다.
참고: 정답 하나당 1점입니다.
Correct Answer:
Explanation:
Location of a damaged product # Yes
Multiple instances of the same product # Yes
Multiple types of damaged products # Yes
All three statements are Yes, because they correctly describe the capabilities of object detection, one of the major workloads in computer vision, as defined in the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn module: "Describe features of computer vision workloads on Azure." Object detection is an advanced computer vision technique that allows AI systems not only to classify objects within an image but also to locate them by drawing bounding boxes around each detected object. This differentiates it from simple image classification, which only identifies what objects exist in an image without specifying their locations.
* Identifying the location of a damaged product - YesAccording to Microsoft Learn, object detection can return the coordinates or bounding boxes for recognized objects. Therefore, if the model is trained to detect damaged products, it can pinpoint exactly where those defects appear within an image.
* Identifying multiple instances of a damaged product - YesObject detection models can detect multiple objects of the same class in one image. For instance, if an image contains several damaged products, each will be identified and marked individually. This feature supports tasks such as automated quality inspection in manufacturing, where several defective units may appear simultaneously.
* Identifying multiple types of damaged products - YesObject detection can also distinguish different classes of objects. When trained on multiple labels (e.g., cracked, scratched, or broken items), the model can detect and classify each type of damage in one image.
In Microsoft's AI-900 framework, object detection is presented as a critical part of computer vision workloads capable of locating and classifying multiple objects and categories within visual content.
Azure OpenAI 서비스를 사용하는 생성 AI 솔루션에서 유해한 콘텐츠를 식별해야 합니다.
무엇을 사용해야 하나요?
무엇을 사용해야 하나요?
Correct Answer: D
Vote an answer
Explanation: Only visible for Fast2test members. You can sign-up / login (it's free).
문장을 완성하려면 답변란에서 적절한 옵션을 선택하세요.
Correct Answer:
Explanation:
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and the Microsoft Learn module "Identify features and uses of speech capabilities", speech recognition refers to the process of converting spoken words into written text. When a speaker's voice is transcribed into subtitles during a presentation, the system listens to the audio input, identifies the spoken words, and generates corresponding text in real time. This is precisely what speech recognition technology accomplishes.
Azure provides this functionality through the Azure Speech Service, which supports multiple speech-related features:
* Speech-to-Text (Speech Recognition) - Converts spoken audio into text.
* Text-to-Speech (Speech Synthesis) - Converts written text into spoken audio.
* Speech Translation - Translates spoken words into another language.
In this case, the session is transcribed into subtitles in the same language, not translated or spoken aloud, so the correct feature is Speech Recognition.
Let's review the other options:
* Sentiment Analysis: This belongs to the Text Analytics service under natural language processing (NLP) and is used to determine the emotional tone of text, not to convert speech to text.
* Speech Synthesis: Converts text into audible speech (Text-to-Speech), the reverse of what is happening in this scenario.
* Translation: Converts spoken or written words from one language to another. Here, no translation is mentioned-only transcription.
Therefore, the described process-turning live spoken language into readable subtitles-is an example of Speech Recognition, a speech-to-text AI capability provided by Azure Cognitive Services.
Final answer: Speech recognition
Reference:Microsoft Learn - Identify speech capabilities of Azure AI services (AI-900 Learning Path)