(2026新題目)AI900-2026中文-Quiz1

Category: None

AI900-2026c-Q1

At which layer can you apply content filters to suppress prompts and responses for a responsible generative AI solution?
在哪個層級可以應用內容篩選器，以抑制負責任生成式 AI 解決方案中的提示與回應？

metaprompt and grounding (元提示與接地)

model (模型)

safety system (安全系統)

user experience (使用者體驗)

Category: None

AI900-2026c-Q2

[Answer choice] can used to identify constraints and styles for the responses of a generative AI model.
[答案選項] 可用於識別生成式 AI 模型回應的限制與風格。

Data grounding (數據接地)

Embeddings (內嵌)

System messages (系統訊息)

Tokenization (代幣化)

Category: None

AI900-2026c-Q3

The four-step process to apply responsible AI principles to generative AI includes [Answer choice].
將負責任 AI 原則應用於生成式 AI 的四步流程包括 [答案選項]。

identifying potential harms, measuring harms, mitigating risks, and planning for deployments (識別潛在危害、測量危害、減輕風險及規劃部署)

…monitoring system performance…

…securing infrastructure…

…training models…

Category: None

AI900-2026c-Q4

Generative AI is used to generate [Answer choice].
生成式 AI 用於生成 [答案選項]。

classifications… (分類)

new content based on patterns learned from training data (基於學習模式的新內容)

new datasets… (新數據集)

predictions… (預測)

Category: None

AI900-2026c-Q5

A key feature of a generative AI model is that it can [Answer choice].
生成式 AI 模型的一個關鍵特徵是它可以 [答案選項]。

assign labels…

follow predefined rules…

identify anomalies…

produce original outputs based on patterns learned from training data (產生原始輸出)

Category: None

AI900-2026c-Q6

Which statement best describes a capability of a generative AI model?
下列哪項陳述最能描述生成式 AI 模型的功能？

classifies data…

detects patterns…

generates new content based on learned patterns (生成新內容)

uses rule-based logic…

Category: None

AI900-2026c-Q7

Which two scenarios are common use cases for generative AI?
哪兩個場景是生成式 AI 的常見使用案例？

anomaly detection (異常檢測)

image generation (影像生成)

summarization (摘要)

translation (翻譯)

Category: None

AI900-2026c-Q8

Which responsible AI risk should you identify and mitigate?
您應該識別並減輕哪種負責任 AI 風險？

adversarial vulnerability

bias…

lack of accessibility

lack of transparency (缺乏透明度)

Category: None

AI900-2026c-Q9

[Answer choice] can search, classify, and compare sources of text for similarity.
[答案選項] 可以搜尋、分類並比較文字來源的相似性。

Data grounding

Embeddings (內嵌)

Machine learning

System messages

Category: None

AI900-2026c-Q10

Microsoft Foundry can be used to [Answer choice].
Microsoft Foundry 可用於 [答案選項]。

build, customize, and manage AI apps and agents (構建、自定義與管理 AI 應用)

monitor VM metrics

store training data

train LLMs from raw data

Category: None

AI900-2026c-Q11

Azure OpenAI in Foundry Models can be used to [Answer choice].
Azure OpenAI in Foundry Models 可用於 [答案選項]。

access and deploy models, such as GPT (存取並部署 GPT 等模型)

build vision models

manage API keys

orchestrate ML pipelines

Category: None

AI900-2026c-Q12

Which service should you use?
您需要最新的模型、內置安全系統與控制，應使用哪種服務？

Azure Language…

Azure Machine Learning

Azure OpenAI in Foundry Models

Azure Vision…

Category: None

AI900-2026c-Q13

Which AI technique should be used to extract the name of a store from a photograph?
應使用哪種 AI 技術從店面照片中提取店名？

image classification

NLP

optical character recognition (OCR, 光學字元辨識)

semantic segmentation

Category: None

AI900-2026c-Q14

Which two specialized domain models are supported by Azure Vision when categorizing an image?
影像分類時，Azure Vision 支援哪兩個領域模型？

celebrities (名人)

image types

landmarks (地標)

people_

Category: None

AI900-2026c-Q15

Which computer vision service provides bounding coordinates as part of its output?
哪種電腦視覺服務的輸出包含邊界座標？

image analysis

image classification

object detection (物件檢測)

semantic segmentation

Category: None

AI900-2026c-Q16

Which process allows you to use object detection?
哪個流程允許您使用物件檢測？

sentiment analysis

extracting text…

granting access…

tracking livestock in a field (追蹤農田牲畜)

Category: None

AI900-2026c-Q17

What allows you to identify different types of bone fractures in X-ray images?
什麼技術能在 X 光影像中識別骨折類型？

conversational AI

facial detection

image classification (影像分類)

object detection

Category: None

AI900-2026c-Q19

Which feature of computer vision involves associating an image with metadata that summarizes its attributes?
將影像與總結其屬性的元數據關聯起來的功能是？

categorizing

content organization

detecting image types

tagging (標籤)

Category: None

AI900-2026c-Q20

What should you use to perform one-to-many or one-to-one face matching?
執行「一對多」或「一對一」臉部比對時應使用？

Custom Vision

face attributes

face identification (臉部識別)

face verification (臉部驗證)

Category: None

AI900-2026c-Q21

Which service can you use to train an image classification model?
您可以使用哪種服務來訓練影像分類模型？

Azure Vision…

Azure AI Custom Vision

Azure Face…

Azure Language…

Category: None

AI900-2026c-Q22

Which service should you use? (Analyzing vehicles, buildings in images)
分析影像以識別物體與場景應使用哪種服務？

Azure AI Video Indexer

Azure Document Intelligence…

Azure Face service

Azure Vision in Foundry Tools

Category: None

AI900-2026c-Q23

What should the model include? (Predicting diabetes likelihood)
（根據年齡和體脂預測患病率）模型應包含？

three features

three labels

two features and one label (兩個特徵一個標籤)

two labels and one feature

Category: None

AI900-2026c-Q24

Which assumption of the multiple linear regression model should be satisfied to avoid misleading predictions?
多元線性回歸應滿足哪項假設？

Features depend…

Features are independent of each other (特徵相互獨立)

Labels depend…

Labels are independent…

Category: None

AI900-2026c-Q25

In a regression machine learning algorithm, what are the characteristics of features and labels in a training dataset?
訓練數據集中特徵與標籤的特徵是？

known feature and label values (已知特徵與標籤值)

known feature… unknown label…

unknown…

unknown feature… known label…

Category: None

AI900-2026c-Q26

Which two attributes are the features? (E-scooter hires predictions)
哪兩個屬性是特徵？

distance traveled

battery levels

e-scooter hires

weather temperature (溫度)

weekday or weekend (工作日/週末)

Category: None

AI900-2026c-Q27

Which resource should you create first in Azure Machine Learning studio?
應首先在 studio 中創建哪種資源？

a dataset (數據集)

a workspace

a container instance

an AKS cluster

Category: None

AI900-2026c-Q28

What should you do first in the Machine Learning designer?
在 Designer 中首先應做什麼？

Add a dataset

Add modules

Create a pipeline (創建管道)

Deploy a service

Category: None

AI900-2026c-Q29

What should you do first in the Machine Learning designer? (Deploy predictive service)
部署預測服務時，首先應做什麼？

Add a dataset

Add modules

Create an inference pipeline (創建推理管道)

Create cluster

Category: None

AI900-2026c-Q30

Which three data transformation modules are in the Azure Machine Learning designer?
哪些是 Designer 中的數據轉換模塊？

Clean Missing Data (清理缺失數據)

Model Evaluate Model

Normalize Data (標準化數據)

Select Columns in Dataset (選擇數據列)

Train Clustering

Category: None

AI900-2026c-Q31

What is an unsupervised machine learning algorithm module?
什麼是非監督式學習算法模塊？

Classification

K-Means Clustering (K-Means 聚類)

Linear Regression

Normalize Data

Category: None

AI900-2026c-Q32

What is the first step in the statistical analysis of terms in a text in the context of NLP?
文字統計分析的第一步是？

vectorized model

counting word occurrences

encoding words…

removing stop words (去除停用詞)

Category: None

AI900-2026c-Q33

Which two types of files can be imported to generate a knowledge base?
哪兩種文件類型可導入以生成知識庫？

CSV

DOC

MP4

PDF

ZIP

Category: None

AI900-2026c-Q34

Which two features allow you to identify issues as well as people and products?
哪兩項功能可識別概念與特定實體？

Bot Service

CLU

key phrase extraction (關鍵短語提取)

named entity recognition (命名實體識別)

Speech service

Category: None

AI900-2026c-Q35

Which feature returns links to external websites to disambiguate terms?
哪項功能可返回鏈接以消除歧義？

entity recognition (實體識別/鏈接)

key phrase extraction

language detection

sentiment analysis

Category: None

AI900-2026c-Q36

For which two scenarios is the Universal Language Model optimized?
通用語言模型針對哪兩個場景進行了優化？

acoustic

conversational (對話)

dictation (聽寫)

language

pronunciation

Category: None

AI900-2026c-Q37

Which type of translation does the Azure Translator support?
Azure Translator 支援哪種翻譯？

speech-to-speech

speech-to-text

text-to-speech

text-to-text (文字轉文字)

Category: None

AI900-2026c-Q38

Which Azure resource provides direct access to both Translator and Speech services through a single endpoint?
單一端點可存取多個 AI 服務的資源是？

Bot Service

Microsoft Foundry (Azure AI 服務總稱)

Machine Learning

Language Service

Category: None

AI900-2026c-Q39

Which three features are elements of the Azure Language Service?
哪三項是 Language 服務的功能？

Azure Vision…

Content Moderator

Entity Linking (實體鏈接)

PII detection (個資檢測)

Sentiment analysis (情感分析)

Category: None

AI900-2026c-Q40

Which feature can identify distinct user voices?
哪項功能可識別不同的聲音？

language identification

speech recognition (說話者識別)

speech synthesis

speech translation

Category: None

AI900-2026c-Q41

Which NLP workload is used to generate closed caption text for live presentations?
生成現場隱藏式字幕應使用？

Azure Speech in Foundry Tools (語音服務)

Azure Language…

Azure Translator…

Text Analytics

Category: None

AI900-2026c-Q42

Which AI workload provides the ability to generate bounding boxes for vehicles?
產生車輛邊界框的工作負載是？

image analysis

image classification

OCR

object detection (物件檢測)

Category: None

AI900-2026c-Q43

Which AI workload provides the ability to classify individual pixels?
分類個別像素的工作負載是？

image analysis

image classification

object detection

semantic segmentation (語義分割)

Category: None

AI900-2026c-Q44

Which AI workload has the primary purpose of making large amounts of data searchable?
使數據可搜尋的主要技術是？

image analysis

knowledge mining (知識挖掘)

object detection

semantic segmentation

Category: None

AI900-2026c-Q45

Which two scenarios are examples of NLP?
哪兩個是 NLP 的例子？

extracting handwritten…

generating tags…

monitoring network…

performing sentiment analysis (情感分析)

translating text (文字翻譯)

Category: None

AI900-2026c-Q46

Which type of AI workload is this? (Searching text in various docs)
搜尋各種文檔中的文字屬於？

anomaly detection

computer vision

conversational AI

data mining (數據/知識挖掘)

Category: None

AI900-2026c-Q47

Which two AI features are part of Azure Vision?
哪兩個功能屬於視覺服務？

entity recognition

key phrase…

optical character recognition (OCR)

sentiment analysis

spatial analysis (空間分析)

Category: None

AI900-2026c-Q48

Which principle of responsible AI raises awareness about limitations?
提高對局限性認識的原則是？

accountability

privacy…

reliability…

transparency (透明度)

Category: None

AI900-2026c-Q49

Which principle of responsible AI ensures that AI benefits all society?
確保 AI 利益均霑的原則是？

accountability

inclusiveness (包容性)

privacy…

reliability…

Category: None

AI900-2026c-Q50

Which principle ensures that a system meets legal and ethical standards?
確保系統符合法規與道德的原則是？

accountability (問責制)

fairness

inclusiveness

privacy…

(2026新題目)AI900-2026中文-Quiz1

Quiz Summary

Information

Results

Results

Categories

1. Question

2. Question

3. Question

4. Question

5. Question

6. Question

7. Question

8. Question

9. Question

10. Question

11. Question

12. Question

13. Question

14. Question

15. Question

16. Question

17. Question

18. Question

19. Question

20. Question

21. Question

22. Question

23. Question

24. Question

25. Question

26. Question

27. Question

28. Question

29. Question

30. Question

31. Question

32. Question

33. Question

34. Question

35. Question

36. Question

37. Question

38. Question

39. Question

40. Question

41. Question

42. Question

43. Question

44. Question

45. Question

46. Question

47. Question

48. Question

49. Question