Build A Bot With The Language Service And Azure Bot Service Flashcards
What are a popular way to provide support through multiple communication channels. This module describes how to use a knowledge base and azure bot service to create a bot that answers user questions.
Introduction girl on new line in today’s connected world people use a variety of technologies to communicate:
Voice calls. Messaging services. Online chat applications for staff email. Social media platforms. Collaborative workplace tools.
Conversational ai:
While many organisations published support information and answers to frequently ask questions or faq that can be accessed through a web browser or a dedicated up the complexity of the system and services they offer means that answers to specific questions are hard to find.
After these organisations find their support personal personal being overloaded with requests for help through phone calls email text messages social media and other channels
Increasingly organisations are turning to artificial intelligence Solutions that make use of AI agents formerly known as bots to provide a first line of automated support through the full range of channels that we use to communicate. Bots are designed to interact with the users in a conversational manner.
Conversations typically take the form of messages exchanged interns; and one of the most common kinds of conversational exchange is a question followed by an answer. This pattern is the basis for many user support bots and can often be based on existing faq documentation. To implement this kind of solution do you need:
A knowledgeable base of question-and-answer pairs-with some built-in natural language processing model to enable questions that can be raised in multiple ways to be understood with the same semantic meaning.
A bot service that provides an interface to the knowledge base through one or more channels
Language service and azure bot:
You can easily create a user support bath solution on Microsoft azure using a combination of two core services solon
Language service. The language service includes a custom question-answering feature that enables you to create a knowledge base of questions and answer pairs that can be queried using natural language input. Nuts
The question answering capability of in the language service is a newer version of the Q&A maker service-which is still available as a separate service
Azure bot service-the service provides a framework for developing Publishing and managing bots on azure.
Creating a custom question-answering knowledge base:
The first challenge in creating a user support what is to use the language service to create a knowledge base. You can use the language to the US custom question-answering feature to create and publish and and manage knowledge bases
Note
You can write code to create and manage knowledge bases using the language service rest API or SDK. However in most scenarios it is easier to use the language studio
Provision a language service as a resource: To create a knowledge base you must first provision a language service resource in your azure subscription.
Define questions and answers:
After provisioning a language service resource you can use the language serious custom question-answering feature to create a knowledge base that contact consists of question-and-answer pears question-and-answer pairs can be:
Generated from an existing faq document or webpage.
Entered and edited manually
In many cases and knowledge base is created using a combination of all of these techniques semicolons starting with a base start a set of questions and answers from an existing faq document and extending the knowledge base with additional manual entries.
Questions in the knowledge base can be assigned alternative phrasing to help consolidate questions with the same meaning. For example you might include a question like: what is your head office location
You can anticipate different ways this question could be asked by adding an alternative phrasing such as where is your head office located
Test the knowledge base:
After creating a set of question-and-answer pairs you must save it. This process analyses your little questions and answers and applies a built and natural language processing model too match appropriate answers to questions.
Even if they are not phrased exactly as specified in your question definitions they should still be much to do an answer.
Then you can use the built-in test interface in the language studio to test your knowledge base by submitting questions and reviewing the answers that are Returned.
Use the knowledge base:
When you are satisfied with your knowledge base deploy it. Then you can use it over its rest interface. To access the knowledge-based client applications require:
The knowledge base id
The knowledge base in point
That knowledge base authorisation key.
Build a bot with the Azure bot service:
After you’ve created and deployed and knowledge base you can deliver it to users through a bot
Create a bot for your knowledge base:
You can create a custom built by using the Microsoft bot framework SDK to create code for right eye that controls conversation flow and integrates with your knowledge base.
However an easy approach is to use the automatic bath creation functionality which enables you to create a bot for your deployed knowledge base and publish it as an azure bot service application it was just a few clicks
Extend and configure the part colon after creating your bot you can manage it in the Azure portal where you can curl or
Extend the bot functionality by adding custom code.
Test the bot in an interactive test interface.
Configurelogging Analytics and integration with other services.
For simple updates you can edit batco directly in the Azure portal.
However for more comprehensive customisation you can download the Source Code and edit it locally; republishing the bot directly to azure when you’re ready.
Connect channels carolina
When your bot is ready to be delivered to users you can connected to multiple channels and Nicole on making it possible for users to interact with it through web chat email Microsoft teams and other common communication Media.
