Explore how to implement chatbot solutions using Azure AI Language, including tips on intent creation and utterance optimization for real-world applications.
Table of Contents
Question
Your organization, Xerigon Corporation, is developing an AI-based application with chatbot functionality for a pizza restaurant. Customers will use the chatbot to place orders, inquire about the menu, and track deliveries. You are currently working on the order placement functionality.
You want to enable the chatbot to understand when a customer wants to order a pizza with specific toppings.
What should you do in the given scenario?
A. Create an intent and add utterances with specific pizza toppings such as “I want a pepperoni and mushroom pizza” or “Can I get a pizza with extra cheese and olives?”
B. Create an intent and add utterances such as “I want a pizza” and “I’d like to order a pizza”.
C. Use pre-built language understanding models to automatically identify pizza orders without any manual configuration.
D. Create one entity representing pizza toppings and a separate entity for pizza sizes.
Answer
A. Create an intent and add utterances with specific pizza toppings such as “I want a pepperoni and mushroom pizza” or “Can I get a pizza with extra cheese and olives?”
Explanation
In the given scenario, you would create an intent and add utterances with specific pizza toppings such as “I want a pepperoni and mushroom pizza” or “Can I get a pizza with extra cheese and olives?”. This option focuses on creating an intent specifically designed to capture pizza orders with specific toppings. By including utterances such as these, the chatbot can be trained to recognize the intent and extract the topping information using entities.
An intent represents the purpose or goal behind a user’s input. It is the action the user wants to take. For example, in the scenario above, the intent is to “order a pizza with specific toppings.” When you specify intents, you are allowing the model to understand and categorize different user requests.
Utterances are the actual phrases or sentences that users type or say to express their intent. They are real-world examples of how users might phrase their requests. In this scenario, “I want a pepperoni and mushroom pizza” and “Can I get a pizza with extra cheese and olives?” are utterances.
In the given scenario, you would not create one entity representing pizza toppings and a separate entity for pizza sizes. Entities are created once you have created the intent and utterances. Entities are like variables that hold specific pieces of information. They help extract information within an intent, but they do not define the intent itself.
You would not create an intent and add utterances such as “I want a pizza” and “I’d like to order a pizza” in the given scenario. This option creates a generic intent. Intents represent the user’s goal or action they want to perform. However, the provided utterances (“I want a pizza”, “I’d like to order a pizza”) are too broad. They only capture the general desire to order a pizza, not the specific need to order a pizza with particular toppings.
You would not use pre-built language understanding models to automatically identify pizza orders without any manual configuration in the given scenario. Pre-built language understanding models are trained on massive datasets of general conversational text.
Microsoft Azure AI Engineer Associate AI-102 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Engineer Associate AI-102 exam and earn Microsoft Azure AI Engineer Associate AI-102 certification.