Microsoft AI-900 시험

Question No : 1

You have a webchat bot that provides responses from a QnA Maker knowledge base.
You need to ensure that the bot uses user feedback to improve the relevance of the responses over time.
What should you use?

• A.key phrase extraction
• B.sentiment analysis
• C.business logic
• D.active learning

답을 확인하기

정답:
Explanation:
Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/improve-knowledge-base

Question No : 2

You need to provide content for a business chatbot that will help answer simple user queries.
What are three ways to create question and answer text by using QnA Maker? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

• A.Generate the questions and answers from an existing webpage.
• B.Use automated machine learning to train a model based on a file that contains the questions.
• C.Manually enter the questions and answers.
• D.Connect the bot to the Cortana channel and ask questions by using Cortana.
• E.Import chit-chat content from a predefined data source.

답을 확인하기

정답:
Explanation:
Automatic extraction
Extract question-answer pairs from semi-structured content, including FAQ pages, support websites, excel files, SharePoint documents, product manuals and policies.
Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/concepts/content-types

Question No : 3

DRAG DROP
Match the services to the appropriate descriptions.
To answer, drag the appropriate service from the column on the left to its description on the right. Each service may be used once, more than once, or not at all. NOTE: Each correct match is worth one point

답을 확인하기

정답:


Speech: Enables the real-time transcription of speech-to-text.
Explanation:
Enables the use of natural language to query a knowledge base.
This corresponds to "QnA Maker". QnA Maker is a cloud-based API service that lets you create a conversational question-and-answer layer over your data.
Enables the real-time transcription of speech-to-text.
This corresponds to "Speech". Azure's Speech service provides APIs to convert spoken language into written text.

Question No : 4

HOTSPOT
For each of the following statements, select Yes if the statement is True. Otherwise, select No. NOTE: Each correct selection is worth one point.

답을 확인하기

정답:

Question No : 5

HOTSPOT
Select the answer that correctly completes the sentence

답을 확인하기

정답:

Question No : 6

HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

답을 확인하기

정답:


Explanation:
Text
Description automatically generated

Question No : 7

HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

답을 확인하기

정답:


Explanation:
Box 1: Yes
Azure bot service can be integrated with the powerful AI capabilities with Azure Cognitive Services.
Box 2: Yes
Azure bot service engages with customers in a conversational manner.
Box 3: Yes
Azure Bot Service can import frequently asked questions (FAQ) to question and answer sets.
Yes, this is true. Azure Bot Service can utilize QnA Maker to import FAQs, creating a knowledge base that the bot can use to answer user queries automatically.

Question No : 8

HOTSPOT
Select the answer that correctly completes the sentence.

답을 확인하기

정답:

Question No : 9

HOTSPOT
Select the answer that correctly completes the sentence.

답을 확인하기

정답:

Question No : 10

HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

답을 확인하기

정답:


Explanation:
Chatbots can support voice input.
Yes, this is true. Many chatbots are capable of processing and responding to voice input using natural language processing and speech recognition technologies.
A separate chatbot is required for each communication channel.
No, this is false. A single chatbot
can be integrated into multiple communication channels, such as websites, messaging apps, and social media platforms, enabling it to interact with users across various platforms.
Chatbots manage conversation flows by using a combination of natural language and constrained option responses.
Yes, this is true. Chatbots often guide conversations using natural language for a more human-like interaction and can also provide users with predefined options to choose from for easier and more structured responses.

Question No : 11

HOTSPOT
Select the answer that correctly completes the sentence.

답을 확인하기

정답:


Explanation:
Using Recency, Frequency, and Monetary (RFM) values to identify segments of a customer base is an example of "clustering."
Clustering is used to group data points that are similar to each other. In this case, customers are being grouped based on their RFM values, which is a common technique in customer segmentation.

Question No : 12

You have an Azure Machine Learning pipeline that contains a Split Data module. The Split Data module outputs to a Train Model module and a Score Model module.
What is the function of the Split Data module?

• A.selecting columns that must be included in the model
• B.creating training and validation datasets
• C.diverting records that have missing data
• D.scaling numeric variables so that they are within a consistent numeric range

답을 확인하기

정답:

Question No : 13

HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

답을 확인하기

정답:

Question No : 14

HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

답을 확인하기

정답:


Explanation:
You train a regression model by using unlabeled data.
No, this is false. Regression models are supervised learning models that require labeled data for training. Unlabeled data doesn't have the outcome variable needed for regression training.
The classification technique is used to predict sequential numerical data over time.
No, this is false. Classification is used for categorizing inputs into two or more classes, not for predicting numerical data over time. Time series forecasting or regression techniques are more suitable for predicting numerical data over time.
Grouping items by their common characteristics is an example of clustering.
Yes, this is true. Clustering is an unsupervised learning technique where you group data points that have similar characteristics.

Question No : 15

HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

답을 확인하기

정답:


Explanation:
A restaurant can use a chatbot to empower customers to make reservations by using a website or an app.
Yes, this is true. A chatbot can facilitate the reservation process by interacting with customers, collecting necessary information, and completing the reservation automatically.
A restaurant can use a chatbot to answer inquiries about business hours from a webpage.
Yes, this is true. A chatbot can be programmed to answer common customer queries, such as business hours, directly from the webpage.
A restaurant can use a chatbot to automate responses to customer reviews on an external website.
No, this might not be true. While a chatbot can respond to customer queries and comments on platforms where it’s integrated, automating responses on external websites where the chatbot doesn't have direct integration or access might not be feasible. Plus, automated responses to reviews, especially on external websites, might not always be the best approach due to the need for personalized and thoughtful responses.