AI-102

Front

Build a chatbot with: chit-chat, knowledge base, multilingual support, sentiment analysis, and automatic language model selection.

Back

Language Understanding, Text Analytics, and QnA Maker

Answer explanation

Language Understanding: An AI service that allows users to interact with your applications, bots, and IoT devices by using natural language.

QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data.

Front

Reduce time for employees to log receipts in expense reports. Extract vendor and transaction total from English receipts with minimal development effort.

Back

Form Recognizer

Answer explanation

Correct Answer: C

Azure Form Recognizer is a cognitive service that lets you build automated data processing software using machine learning technology.

Identify and extract text, key/value pairs, selection marks, tables, and structure from your documents ג€"the service outputs structured data that

includes the relationships in the original file, bounding boxes, confidence and more.

Front

POST https://management.azure.com/subscriptions/18c51a87-3a69-47a8-aedc-a54745f708a1/resourceGroups/RG1/providers/Microsoft.CognitiveServices/accounts/contoso1/regenerateKey?api-version=2017-04-18 Body: {"keyName": "Key2"}

Back

A new query key was generated.

Front

Developing a sales system that processes video and text from a public website and notifying users about data processing helps meet which responsible AI principle?

Back

reliability and safety

Front

App1 runs on Azure VM vm1 in vnet1. You want app1 to connect to Azure Cognitive Search service1 without public internet. Solution: Deploy service1 with a public endpoint in a new virtual network and configure Azure Private Link. Does this meet the goal?

Back

No

Front

App1 runs on Azure VM vm1 in vnet1. To connect app1 to Azure Cognitive Search service1 without public internet, you deploy service1 with a public endpoint and configure an IP firewall rule. Does this meet the goal?

Back

No

Front

Predictive maintenance with IoT data from 100 machines (50 sensors each, 1-min intervals) requires identifying unusual values in 5,000 time series datasets.

Back

Anomaly Detector

Front

Adding contributors to a Language Understanding (classic) resource requires:

Back

Access control (IAM) page for authoring resources in Azure portal.

Front

Azure Cognitive Search service is throttling due to increased query volume. Migrating to a higher tier reduces throttling risk.

Back

Yes

Front

Receipts accessible via URL need data extraction using Form Recognizer with a prebuilt model. Which client and method?

Back

FormTrainingClient & StartRecognizeReceiptsFromUri

Answer explanation

Correct Answer: D

To analyze receipts from a URL, use the StartRecognizeReceiptsFromUri method

Example code:

private static async Task AnalyzeReceipt(

FormRecognizerClient recognizerClient, string receiptUri)

{

RecognizedFormCollection receipts = await recognizerClient.StartRecognizeReceiptsFromUri(new Uri(receiptUrl)).WaitForCompletionAsync();

Reference:

https://docs.microsoft.com/en-us/azure/applied-ai-services/form-recognizer/quickstarts/client-library