My FeedDiscussionsHeadless CMS
New
Sign in
Log inSign up
Learn more about Hashnode Headless CMSHashnode Headless CMS
Collaborate seamlessly with Hashnode Headless CMS for Enterprise.
Upgrade ✨Learn more

History and future of chatbots

Siraj abbas's photo
Siraj abbas
·Apr 29, 2017

Many of us end up our day by saying “set an alarm for tomorrow morning” to your smartphone’s personal assistant.I have the habit of squeezing my smartphone.Here comes the importance of a chatbot.

Actually what exactly a chatbot or chatterbot is?

It is as simple as saying a piece of software code that communicate with you.The medium of channel depends on each chatbot.In general those bots communicate with us,Talks to you through different channels like Facebook messenger, Skype,Siri,Telegram etc.

The term “ChatterBot” was originally coined by Michael Mauldin (creator of the first Verbot, Julia) in 1994 to describe these conversational programs.But bots was there before that.In 1950 Alan Turing & Joseph Weizenbaum did a Turing test for intelligence in a computer.We can say that modern form of chat bots were originated from their test.

In 1988 British programmer Rollo Carpenter created Jabberwacky, which is a chatterbot. Its stated aim is to “simulate natural human chat in an interesting, entertaining and humorous manner”. It is an early attempt at creating an artificial intelligence through human interaction.

After that the major developement was the introduction of a chatbot called SmarterChild. It was founded in 2000, ActiveBuddy was the brainchild of Robert Hoffer, Timothy Kay and Peter Levitan. The idea for instant messaging bots came from the team’s vision to add natural language comprehension functionality to the increasingly popular instant messaging and SMS platforms. The original implementation took shape as a word-based adventure game but quickly grew to include a wide range of database applications including instant access to news, weather, stock information, movie times, yellow pages listings, and detailed sports data, as well as a variety of tools (personal assistant, calculators, translator, etc.)

Then the big shot Microsoft came into action.They developed Xioice ChatBot after years of researches on NLP(Natural Language Processing).It was capable of recognizing human feelings.It operates on machine learning techniques.

Software Architecture

At present anyone can create a chatbot without having much effort.There are built in libraries available on different platforms.All w e need is the following three components.

Backend technology: NodeJS, PHP, JAVA, Python etc Frontend technology: Any popular messenger apps (FB MEssenger, Slack, Telegram etc) For connecting the above two: Web Server.

There are two types of chatbots dumb bots and smartbots

DUMB BOTS Command based. Follow set of rules. Respond to specific command. Eg: Weather forecast

SMART BOTS Learning based Not rely on pre-planned commands Eg: What’s happening?

Here is some practical applications

Uber to book taxi. CNN for news updates Pizza Hut to order Pizza

Here is an interesting conversation I found on internet, between a human and a chatbot that could be possible in future

You — “Where is a good place to get coffee near me? Search

Chatbot — “There are three coffee shops near you rated five stars on xxx website”.

You — “Add the highest rated coffee shop chatbot to this chat”. Coffee

Chatbot — “Hello, this is xxx bot, what’s up?”

You — “Send directions to your shop and order a flat white” Coffee

Chatbot — “No problem, directions are in your xxx map, do you want to pay using your xxx wallet?

You — “Yes” Coffee

Chatbot — “Ok, 3.99 has been paid, see you in 12 minutes. We have some delicious muffins just out of the oven too…” PA

Chatbot — “Hi, I noticed you are going for coffee, it looks like it is raining outside, want me to order you a taxi rather than walk?”

You — “Yes, leaving in 2 minutes” PA

Chatbot — “Ok, your driver is called Sammy and the car registration is xxx, he will meet you outside.”

follow me on

Facebook,Twitter,LinkedIn