IBM Watson assistant

IBM Watson Assistant
Introduction
Setting Up working example Using Nodejs

What is Watson Assistant ?
• Watson Assistant is an AI assistant for business.
• Watson Assistant is an offering for building conversational
interfaces into any application, device, or channel.

Why Watson Assistant ?
• Most chatbots try to mimic human interactions, which can
frustrate users when a misunderstanding arises.
• Watson Assistant is more. It knows when to search for an
answer from a knowledge base, when to ask for clarity,
and when to direct you to a human.
• Watson Assistant can run on any cloud – allowing
businesses to bring AI to their data and apps wherever
they are.

Architecture: Nodejs
Nodejs Server
IBM Watson Assistant Service
Web
Client
Intent, Enteties, DialoguesSkills
Input Information
Assistant

IBM Watson Assistant Service
Skills: Customer Care
Assistant
Skills:Banking
#Intent:Appointment #Intent:Store Location #Intent
@Entities:Holiday @Entities:Phone @Entities:Specialist
Dialog
Oppening
Hours of Operation
Make an Appointment

Service
Input Information
Assistant
Skill
• A skill is an atomic, reusable program that represents a capability in a
specific domain.
• for example, providing weather forecasts or controlling your IOT
devices in your home, such as your thermostat and lighting.
• Users converse with skills to automate tasks or to make decisions.

Key artifacts of a skill
• Intents
• Entities
• Dialog
Service
Input Information
Assistant

• Intents
Goals that you anticipate your users will have when they
converse with the skill.
A user goal when conversing with a weather skill is to get the
forecast
Service
Input Information
Assistant

• Intents
The following are examples of intent names:
#weather_conditions
#pay_bill
#escalate_to_agent
The following might be examples for the
#pay_bill intent:
I need to pay my bill.
Pay my account balance make a payment

• Entities
Objects or terms that your users might use in their utterance,
which provide context for an intent.
For example, an entity might be a city name, which helps the
routing core determine which city to provide a forecast for.
Service
Input Information
Assistant

• Entities
For example, you might have a #buy_something intent.
When a user makes a request that triggers the #buy_something intent,
the assistant's response should reflect an understanding of what the
something is that the customer wants to buy.
You can add a @product entity, and then use it to extract information
from the user input about the product that the customer is interested in
you can add multiple responses to your dialog tree with wording that
differs based on the @product value that is detected in the user's request

• Dialog
The flow of conversation between the user and the skill or skills.
When a skill receives a converse request, a condition is
evaluated and an action is triggered.
A condition might include a specific intent, such as
#get_weather. A response might be "today will be sunny with
clear skies"
Service
Input Information
Assistant

Information available to your skills
• With Watson Assistant Solutions, you can create AI assistants that converse
with multiple skills.
• As a skill developer, you can use several features that enhance the conversation
flow with a single skill and the conversation flow between multiple skills.
• You can add intelligence to your skills to respond in a personalized way and to
enhance routing

The following types of information to add intelligence to your skills
• Profile information
Information about the user that remains relatively unchanged, for
example, their email address.
Instead of each skill managing profile data separately, using the
Profile REST API, you can store this information in a central
location for all skills to use.

The following types of information to add intelligence to your skills
• Information that changes frequently, such as current location or the time of day. You can configure
context variables to include:
Session context
Context information that is available to all skills. For example, when a user asks "What's on in
the cinema tonight", an entertainment skill captures the time of day in the session context.
Built-in shared context
Context information that is available to all skills. Unlike session context information, information
in the built-in shared context must be in a prescribed format and is restricted to a specific set of
fields.
For example, when a user asks "What's the weather like in Manhattan", the weather skill stores
Manhattan in the last referenced location variable. Later when a user asks "Any concerts on
there", the events skill accesses the variable and provides an event listing for Manhattan.
Contextual information

Skill context
Context information that enhances the flow of conversation within a skill. For example, when a user
says "I'm looking for an open-air concert", the entertainment skill captures the event type in the skill
context.
Later in the conversation, when the user asks the assistant "Are there any free ones on today", the
entertainment skill knows from the skill context that the user is asking for a free open-air concert. "
Utterance context
Context information, such as your current location, that is sent by your edge device in the utterance.
The utterance context might capture whether the user is at home or in her car. A skill might use a
different response depending on the utterance context.
For example, when a user is at home and asks for a cinema listing, the film poster is sent with the
response.

In this sample application, you're engaging with a banking virtual assistant/Customer
The assistant simulates a few scenarios, such as making a credit card payment, boo
Watson can understand your entries and respond accordingly
Application Example ?

Prerequisites - Setting up : IBM Watson Assistant Service
• Sign up for an IBM Cloud account.
• Create an instance of the Watson Assistant service and get your credentials:
• Go to the Watson Assistant page in the IBM Cloud Catalog.
• Log in to your IBM Cloud account.
• Click Create.
• Click Show to view the service credentials.
• Copy the apikey value.
• Copy the url value.

https://github.com/watson-developer-cloud/assistant-demo.git
Running Client Locally: Nodejs
In the application folder, copy the .env.example file and create a file called .env
Open the .env file and add the service credentials that you obtained in the previous step.
Download the example Nodejs source code :Client

IBM Watson assistant

Recommended

More Related Content

What's hot (20)

Similar to IBM Watson assistant (20)

More from Prem Sanil (14)

Recently uploaded (20)

IBM Watson assistant