How To Develop A Chat Bot Using Amazon Lex?

From time to time, humans have been trying to find more and more ways to make lives easier using technology. With all sorts of applications & software taking care of day to day life, chatbots are soon becoming an integral part of daily life.  It’s the latest buzzword. Amazon Lex is one of the most popular platforms for building chatbots. This tutorial will guide you through the whole process of making a chatbot using Amazon Lex. 

Let’s take a look at the topics covered in this Amazon Lex tutorial:

• What is chatbot technology?
• What do bots do?
• What is Amazon Lex Bot?
• Demo: How to build a chatbot using Amazon Lex?

What is chatbot technology?

“A chatbot is a computer program which conducts a conversation in natural language via auditory or textual methods, understands the intent of the user, and sends a response based on business rules and data of the organization.”

In simple terms, chatbot is a service or tool that you can communicate with via chat interface. Chatbot understands what you are trying to imply and replies with a relevant message or directly completes the desired task for you.

How And When Did Chatbot Evolution Start?

If you have thought chatbots are new technology, then you are wrong. In fact, the first chatbot, Eliza, was built in 1966 at the MIT Artificial Intelligence Laboratory by Joseph Weizenbaum to mimic psychotherapist from only 200 lines of code. Then in 1988, when Rollo Carpenter started the Jabberwacky project a voice-operated entertainment AI chatbot. Here’s how chatbots evolved since then:

What do bots do?

Chatbots are relevant because of the following reasons:

• They make available to people, the right information at the right time, right place and most importantly only when they want.
• About 90% of our time on mobile is spent on email and messaging platforms.  So it makes sense to engage customers using chatbots instead of diverting them to a website or a mobile app.
• The advancements in artificial intelligence, machine learning, and natural language processing, allowing bots to converse more and more, like real people.

Modern chatbots do not rely solely on text, and will often show useful cards, images, links, and forms, providing an app-like experience. Depending on way bots are programmed, we can categorize them into two variants of chatbots: Rule-Based (dumb bots) & Self Learning (smart bots).

1. Rule-Based Chatbots: This variety of bots answer questions based on some simple rules that they are trained on. 
2. Self Learning Chatbots: This variety of bots rely on Artificial Intelligence(AI) & Machine Learning(MI) technologies to converse with users.

There are platforms that employ all the complex technologies and allow you to create chatbots in few simple steps & customize them according to your likes. Amazon lex is one such platform.

What Is Amazon Lex Bot?

Amazon Lex is a fully managed service for building conversational interfaces into any application using voice and text. It provides deep learning functionalities like:

• Automatic Speech Recognition (ASR) for converting speech to text
• Natural Language Understanding (NLU) to recognize the intent of the text

Amazon Lex enables you to quickly & easily build chatbots with highly engaging user experiences and lifelike conversational interactions. Now you might be wondering,

Is Amazon Lex free? 

Yes, it definitely is and you can use most of its features under AWS Free Tier.

Benefits of using Amazon Lex:

• Simplicity: It offers an easy-to-use console to create your own chatbot in minutes & predefined bots to help you get started.
• Inbuilt Technologies: You supply just a few example phrases, and Amazon Lex builds a complete natural language model through which the bot can interact using voice and text.
• Seamless deployment and scaling: As the user engagement increases, you don’t need to worry about provisioning hardware and managing infrastructure to power your bot experience.
• Built-in integration with AWS: Amazon Lex allows integrating with many other services on the AWS platform including AWS Lambda, Amazon CloudWatch, Amazon Cognito, and Amazon DynamoDB & many others.
• Cost-Effective: With Amazon Lex, there are no upfront costs or minimum fees. You will have to pay only for the text or speech requests that you make

Let’s consider a use-case to understand the capabilities of Amazon Lex.

Use-Case: To get banking information through an Amazon Lex chatbot.

Using Amazon Chatbot, you can build powerful interfaces to use with mobile applications. You can add a voice or text chat interface to create bots on mobile devices that can help customers with basic tasks. 

Let’s say you want to get your bank account balance & you are using Amazon Lex Chatbot. Amazon Lex understands your request and performs necessary background tasks. It coordinates with Amazon Polly and asks you for further inputs in form of speech. Once it receives the information, it invokes AWS Lambda. Lambda retrieves the requested information or performs other types of actions. Like it might trigger Amazon SNS service to send you a notification or integrate with AWS CloudWatch to store logs & events.

So, now you know how Amazon Lex works to fulfill your requests. Let’s take a look at a few other interesting use-cases:

• NASA’ star robotic ambassador “Rov-E,” is a close replica of real NASA Mars rovers. Through Amazon Lex, NASA staff can easily navigate Rov-E via voice commands. 
• OhioHealth uses Amazon Lex to provide the right care to our patients at the right time and in the right place. 
• HubSpot’ GrowthBot is an all-in-one chatbot which helps marketers and salespeople be more productive by providing access to relevant data and services using a conversational interface. 

These use-cases definitely seem interesting. 

So, if this has spiked your interest & if you are eager to create a chatbot of your own on Amazon Lex, go ahead and watch the video provided below. This video takes you through a step by step procedure on how to create a chatbot on Amazon Lex.

Demo: How to create a chatbot using Amazon Lex

As the chatbot is built on Amazon Web Services, you need to create an account. Once you have your account set up, we can start building the chatbot. This video demonstrates how to build a chatbot using some simple response.

I hope you have watched the video & successfully created a chatbot of your own. Finally, if you are wondering if bots will overrun humans. No, I don’t think so. Bots are and will always remain bots, essentially robotic in their nature and interactions. Bottom line, they are developed to listen and obey, to perform tasks for humans and make our lives easier.

So this is it! I hope this article was informative and added value to your knowledge. If you are interested to take your knowledge on Amazon Web Services to the next level, then enroll for the AWS Architect Certification Training course by Edureka.

Got a question for us? Please mention it in the comments section of “Amazon Lex” and we will get back to you.