Apply your foundational concepts of AI and machine learning into building and programming chatbots
Create a chatbot application that interacts in natural language in IBM Cloud
Synthesize data that can be queried to extract sentiment, concepts, entities, and taxonomy by using Watson Discovery
Reveal the emotions, sentiment, and customer preferences found in hotel reviews by using Tone Analyzer and Personality Insights and feed that data to the chatbot
By enrolling in this course, chances are you’ve studied artifical intelligence, built chatbots and have perhaps even used Watson Assistant along the way. But did you know that you can turbocharge your chatbot’s IQ with IBM Watson Discovery, a service designed to reveal the hidden value in your data? Discovery specializes in taking your data–structured or unstructured–and extracting from it answers and patterns.
For example, if you have a large repository, the contents of which could answer customer questions, you’ve got the makings of a great FAQ chatbot.
In this course, you’ll learn how to build queries in Discovery, which allows you to surface answers and patterns from large repositories of data. You’ll next learn to use Discovery to extract insights from a set of hotel reviews. Then, to make that data come to life, you’ll integrate Discovery with other Watson services to create a chatbot that can tell you about the best hotels in a certain US city. By using these Watson services, you’ll add more layers of analysis to help you find the best hotel.
You’ll build your chatbot application with the following Watson services:
By the end of this course, you will have built a fully functioning AI-powered chatbot. Moreover, you should be able to apply the services taught here to your own data sets, enabling you to create sophisticated chatbots of your own.
Lab 1: Build a Watson chatbot
Watson Assistant overview
Deploy Watson Assistant
Import the workspace
Create intents, entities, and dialog
Apply the Jump to action
Add multiple response conditions for a specific intent
Add responses for other intents
Test the chatbot
Lab 2: Build queries by using Watson Discovery
Watson Discovery overview
Access the news collection in the Discovery tool
Understand the data structure
Query the data by using filters
Query the data by using the query parameter
Query the data by using aggregation
Retrieve longer passages from the data
Train Discovery to improve relevancy
Lab 3: Enhance a chatbot with Discovery
Get the starter code and credentials
Integrate Discovery with the chatbot
Test the application
Lab 4: Gain insights by using Discovery
Get the data into Discovery
Find basic insights in the data
Lab 5: Analyze the tone from hotel reviews
Watson Tone Analyzer overview
Deploy the Tone Analyzer service
Analyze the tone in hotel review
Test the tone analysis
Lab 6: Analyze customer preferences
Watson Personality Insights overview
Deploy the Personality Insights service
Get the personality profile
Test the application
This course provides an introduction to developing and deploying cognitive applications. You should have basic knowledge of object-oriented programming, how to use the command line, Node.js, and IBM Watson Assistant (formerly known as Watson Conversation).
You also need:
IBM Cloud account
IBM Cloud command line tool
A text or code editor
If you want to build the chatbot application locally, install Node.js and npm.
If not familiar with IBM Watson Assistant, take the How to Build Chatbots and Make Money course first.