I.

INTRODUCTION

A chatbot is a piece of software that conducts a conversation via auditory or textual

methods. Such programs are often designed to convincingly simulate how a human would
behave as a conversational partner, although as of 2019, they are far short of being able to
pass the Turing test. Chatbots are typically used in dialog systems for various practical
purposes including customer service or information acquisition. Some chatbots use
sophisticated natural language processing systems, but many simpler ones scan for
keywords within the input, then pull a reply with the most matching keywords, or the most
similar wording pattern, from a database.

The ChatterBot was originally coined by Michael Mauldin creator of the first Verbot, Julia
in 1994 to describe these conversational programs. Today, most chatbots are accessed
via virtual assistants such as Google Assistant and Amazon Alexa, via messaging
apps such as Facebook Messenger or WeChat, or via individual organizations' apps and
websites. Chatbots can be classified into usage categories that include conversational
commerce (e-commerce via chat), education,healthcare,news.

This criterion depends on the ability of a computer program to impersonate a human in a

real-time written conversation with a human judge to the extent that the judge is unable
to distinguish reliablyon the basis of the conversational content alonebetween the program
and a real human.

A.E.C, C.S.E. 1 chatbots

 II. HISTORY

The first chatbot ever was developed by MIT professor Joseph Weizenbaum in the 1960s.
It was called ELIZA. You’ll read more about ELIZA and other popular chatbots that were
developed in the second half of the 20th century later on. In the year 2009, a company
called WeChat in China created a more advanced Chatbot. Since its launch, WeChat has
conquered the hearts of many users who demonstrate an unwavering loyalty to it. It is a
highly thriving social media platform. Though it has implications and is less performant
than today’s messaging apps such as Facebook Messenger, Slack, and Telegram, it doesn’t
mean that you cannot construct a very smart bot on WeChat.

we saw the intro of the first wave of artificial data technology in the design of chatbots.
Social media platforms like Facebook enabled developers to build a chatbot for their
trademark or service so that customers could carry out some of their daily actions from
inside their messaging platform.

A.E.C, C.S.E. 2 chatbots

 III.OVERVIEW

Chatbots is a computer program that simulates a natural human conversation.user

communicate with a chatbot via the chat interface or by,like how they would talk to a
real person.

Chatbots are typically used in dialog systems for various practical purposes including
customer service or information acquisition. Some chatbots use sophisticated natural
language processing systems, but many simpler ones scan for keywords within the input,
then pull a reply with the most matching keywords, or the most similar wording pattern,
from a database.

A.E.C, C.S.E. 3 chatbots

 IV.TYPES OF CHATBOTS

4.1 SIMPLE CHATBOTS:

Simple chatbots have limited capabilities, and are usually called rule-based bots. They are
task-specific. This means the bot poses questions based on predetermined options and the
customer can choose from the options until they get answers to their query. The chatbot
will not make any inferences from its previous interactions. These chatbots are best suited
for straightforward dialogues. They are very simple to build and train.

When a customer interacts with a chatbot to order food, the flow of the conversation is
set. Just like an operator asks for your order over the phone, the chatbot will pose the
questions in the same way. Starting from the size of the food, to the crust, toppings and
amount of cheese. It will then request the address and payment method. The steps are
logical and only requires the customer to click through to complete their order.

A.E.C, C.S.E. 4 chatbots

 Fig 4.1:simple chatbots

4.2 SMART CHATBOTS:

AI-enabled smart chatbots are designed to simulate near-human interactions with

customers. They can have free-flowing conversations and understand intent, language,
and sentiment. These chatbots require programming to help it understand the context of
interactions. They are much harder to implement and execute and need a lot of data to
learn.

Virtual assistants are a modified version of smart chatbots. Siri, for instance, learns from
every human interaction. It can also engage in small talk which is an added benefit of
smart chatbots. While smart chatbots are trained to give the most relevant response with
the help of an open domain resource, they learn best by collecting information in real-time.
Note that companies are yet to build a bot to the extent to which virtual assistants work
because it requires massive data. But theoretically, smart chatbots would work like virtual
assistants within web apps.

A.E.C, C.S.E. 5 chatbots

 Fig 4.2:Smart chatbots

4.3 HYBRID CHATBOTS:

They are a combination of simple and smart chatbots. Both simple and smart chatbots are
extremes in the chatbot spectrum. There will constantly be a need for simple chatbots to
be smarter and smart chatbots to be simpler. Hybrid chatbots meet that middle ground.
Hybrid chatbots have some rule-based tasks, and they can understand intent and context.
This makes them a balanced tool for businesses to interact with customers.

Chatbots that help with a medical diagnosis combine the capabilities of both simple and
smart chatbots. Visitors will be able to voice their health-related questions and the bot can
narrow down possible conditions by asking for symptoms in a rule-based format. Visitors
will be able to go back and forth, choose different options and give more details until the
bot narrows down on their condition and prescribes remedies for the same.

A.E.C, C.S.E. 6 chatbots

 Fig 4.3:hybrid chatbots

A.E.C, C.S.E. 7 chatbots

 V.TOOLS OF CHATBOTS

5.1 DIALOGFLOW:
Dialogflow is a conversational platform that lets you design and builds chatbots and voice
apps Google Actions and Amazon Alexa Skills. Dialogflow is backed by Google and is
the most widely used tool to build Actions for more than Google Assistant devices. It
supports all the major messaging channels such as Facebook Messenger, Slack, Skype,
Kik, Line, Telegram, Twitter, Viber. Dialogflow supports Natural Language Processing
languages.

Dialogflow is probably the best tools to build omnichannel chatbots with less coding.
Dialogflow provides the REST API which can be used to integrate the chatbot to your
own application or with custom conversational interfaces.

Fig 5.1:Dialogflog

A.E.C, C.S.E. 8 chatbots

5.2 AMAZON LEX:
Amazon Lex is a service for building conversational interfaces into any application using
voice and text. Amazon Lex is the same technologies that power Amazon Alexa. As a
fully managed service, Amazon Lex scales automatically, so you don’t need to worry
about managing infrastructure. With Amazon Lex, you can build, test, and deploy your
chatbots directly from the Amazon Lex console itself.Amazon Lex bots can be published
to messaging platforms like Facebook Messenger, Slack, Kik, and Twilio SMS. Amazon
Lex provides SDKs for iOS and Android for building bots for your mobile apps.

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.

Fig 5.2:Amazon lex

5.3 BOTKIT:
Botkit is an open source chatbot framework, recently acquired by Microsoft. Botkit is the
leading developer tool for building chatbots, apps and custom integrations for major
messaging platforms. BotKit is NodeJs based SDK which supports publishing the chatbots
on messaging channels such as Slack, Cisco WebEx, Cisco Jabber, Microsoft Teams,
Facebook Messenger Twilio SMS, Twilio IPM, Microsoft Bot Framework, Google
Hangouts Chat.

A.E.C, C.S.E. 9 chatbots

Botkit also provides a web chat plugin which you can embed on any websites. With
BotKit, you have to host the chatbot on your own server. BotKit can be easily used with
all the major NLP platforms.
Bootkits are designed to not only load from the master boot record but also remain active
in the system memory from protected mode through the launch of the operating
system and during the computer’s active state.

A.E.C, C.S.E. 10 chatbots

 VI.APPLICATIONS OF CHATBOTS

6.1 MESSAGING APPS:

Many companies chatbots run on messaging apps or simply via sms. They are used
to customer service, sales and marketing.

In 2016, Facebook Messenger allowed developers to place chatbots on their platform.

There were 30,000 bots created for Messenger in the first six months, rising to 100,000 by
September 2017. Since September 2017, Airlines KLM and Aeroméxico both announced
their participation in the testing both airlines had previously launched customer services
on the Facebook Messenger platform.

The bots usually appear as one of the user's contacts, but can sometimes act as participants
in a group chat. Many banks, insurers, media companies, e-commerce companies, airlines,
hotel chains, retailers, health care providers, government entities and restaurant chains
have used chatbots to answer simple questions, increase customer engagement, for
promotion, and to offer additional ways to order from them. A 2017 study showed 4% of
companies used chatbots.

6.2 CHATBOT SEQUENCES:

Used by marketers to script sequences of messages, very similar to an Autoresponder

sequence. Such sequences can be triggered by user opt-in or the use of keywords within
user interactions. After a trigger occurs a sequence of messages is delivered until the next
anticipated user response. Each user response is used in the decision tree to help the
chatbot navigate the response sequences to deliver the correct response message.

6.3 COMPANY INTERNAL PLATFORMS:

Other companies explore ways they can use chatbots internally, for example for Customer
Support, Human Resources, or even in Internet-of-Things projects. has reportedly
launched a chatbot named Mila to automate certain simple yet time-consuming processes
when requesting for a sick leave. Other large companies such as Lloyds Banking
Group, Royal Bank of Scotland, Renault and Citroen are now using automated online

A.E.C, C.S.E. 11 chatbots

assistants instead of call centres with humans to provide a first point of contact. A chatbot
business ecosystem has been steadily growing since the Conference when
Facebook's Mark Zuckerberg unveiled that Messenger would allow chatbots into the
app.In large companies, like in hospitals and aviation organizations, IT architects are
designing reference architectures for Intelligent Chatbots that are used to unlock and share
knowledge and experience in the organization more efficiently, and reduce the errors in
answers from expert service desks significantly. These Intelligent Chatbots make use of all
kinds of artificial intelligence like image moderation and natural language
understanding NLU, natural language generation NLG, machine learning.

6.4 CUSTOMER SERVICE:

Many high-tech banking organizations are looking to integrate automated AI-based

solutions such as chatbots into their customer service in order to provide faster and cheaper
assistance to their clients who are becoming increasingly comfortable with technology. In
particular, chatbots can efficiently conduct a dialogue, usually replacing other
communication tools such as email, phone, or sms. In banking, their major application is
related to quick customer service answering common requests, as well as transactional
support. Several studies report significant reduction in the cost of customer services,
expected to lead to billions of dollars of economic savings in the next 10 years.

when Facebook allowed businesses to deliver automated customer support, e-commerce

guidance, content and interactive experiences through chatbots, a large variety of chatbots
were developed for the Facebook Messenger platform.

6.5 HEALTHCARE:

Chatbots are also appearing in the healthcare industry. A study suggested that physicians
in the United States believed that chatbots would be most beneficial for scheduling doctor
appointments, locating health clinics, or providing medication information.

Certain patient groups are still reluctant to use chatbots. A mixed-methods study showed
that people are still hesitant to use chatbots for their healthcare due to poor understanding
of the technological complexity, the lack of empathy and concerns about cyber-
security. The analysis showed that while 6% had heard of a health chatbot and 3% had
experience of using it, 67% perceived themselves as likely to use one within 12 months.

A.E.C, C.S.E. 12 chatbots

The majority of participants would use a health chatbot for seeking general health
information. booking a medical appointment and looking for local health services 80%.
However, a health chatbot was perceived as less suitable for seeking results of medical tests
and seeking specialist advice such as sexual health. The analysis of attitudinal variables
showed that most participants reported their preference for discussing their health with
doctors 73% and having access to reliable and accurate health information. While 80%
were curious about new technologies that could improve their health, 66% reported only
seeking a doctor when experiencing a health problem and 65% thought that a chatbot was
a good idea. Interestingly, 30% reported dislike about talking to computers, 41% felt it
would be strange to discuss health matters with a chatbot and about half were unsure if
they could trust the advice given by a chatbot. Therefore, perceived trustworthiness,
individual attitudes towards bots and dislike for talking to computers are the main barriers
to health chatbots.

6.6 POLITICS:
The chatbot SAM short for made by Nick Gerritsen of Touchtech has been developed. It
is designed to share its political thoughts, for example on topics such as climate change,
healthcare and education, etc. It talks to people through Facebook Messenger.

A.E.C, C.S.E. 13 chatbots

 VII. OPPORTUNITIES OF CHATBOTS

 Increasing pressure on contact centers.

 Technological advances in AI and NLP.
 Rising demand for self-service.
 Chatbot platforms maturing.

A.E.C, C.S.E. 14 chatbots

 VIII. CONVERSATIONS
ChatterBot supports the ability to have multiple concurrent conversations. A
conversations is where the chat bot interacts with a person, and supporting multiple
concurrent conversations means that the chat bot can have multiple different
conversations with different people at the same time.
8.1 Conversation scope:
If two chabots instances are created, each will have conversations separate from each

other. An adapter can access any conversation as long as the unique identifier for the
conversation is provided.

ChatterBot. In this method, the unique identifiers for each chat session are being stored in
Django’s session objects. This allows different users who interact with the bot through
different web browsers to have separate conversations with the chat bot.

A.E.C, C.S.E. 15 chatbots

 VI.CONCLUSION

A.E.C, C.S.E. 16 chatbots

 BIBLIOGRAPHY

BOOKS:
1. Book Name-Edition-Author Name-Publisher
2.
3.

WEBSITES:
1. www.abc.com
2.
3.

A.E.C, C.S.E. 17 chatbots