lOMoARcPSD|43583645

D-BOT
x

PROJECT REPORT

Submitted by

NARESH S (714023201088)
KOUSHIK KUMAR S (714023201068)
MUKKESH S (714023201085)
MUTHUMUNIYASAMY K (714023201086)

In partial fulfillment for the award of the degree of

BACHELOR OF TECHNOLOGY IN

ARTIFICIAL INTELLIGENCE AND

DATA SCIENCE

SRI SHAKTHI
INSTITUTE OF ENGINEERING AND TECHNOLOGY

An Autonomous Institution, Accredited by NAAC with “A” Grade

ANNA UNIVERSITY: CHENNAI 600025

JUNE 2024

BONAFIDE CERTIFICATE

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Certified that this report titled “Visual aid to assist blind people” is the Bonafide work of
NARESH S (714023201088) , KOUSHIK KUMAR S (714023201068) ,
MUKKESH S (714023201085) , MUTHUMUNIYSAMY K (714023201086) who
carried out the project work under our supervision.

SIGNATURE SIGNATURE

Mr. DHINAHARAN S Mr. TAMIL SELVAN A

HEAD OF THE DEPARTMENT ASSISTANT PROFESSOR
Department of Artificial Intelligence and Department of Artificial Intelligence
Data Science and Data science
Sri Shakthi Institute of Engineering Sri Shakthi Institute of Engineering
And Technology And Technology
Coimbatore-641062 Coimbatore-641062

Submitted for the project work viva voce Examination held on………………….…..

INTERNAL EXAMINER EXTERNAL EXAMINER

ACKNOWLEDGEMENT

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

We sincerely express my deepest gratitude to Dr.S.THANGAVELU, chairman, SSIET for

his continuous encouragement throughout our studies.

We would like to extend my special thanks to Mr.T.DEEPAN, Secretary

Mr.T.SHEELAN, joint secretary and Dr.A.R.RAVIKUMAR, principal for their
magnanimity in allowing us to avail the facilities in this department.

We hereby acknowledge and express my sincere gratitude to Mr.

S.DHINAHARAN, Assistant Professor and head of the AI&DS department for his continuous

support in carrying out the project work.

We would like to thank my beloved project coordinator Ms.G.POOJA ,

Assistant professor of AI&DS Department and my project guide Mr.A.TAMIL SELVAN,
Assistant professor of AI&DS Department for her valuable technical discussion and

guidance during project work.

We acknowledge my thanks to the teaching and non-teaching staffs of our Department,

our beloved parents and our friends, for their help provided during the development of
our project.

ABSTRACT

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

In the realm of personalized nutrition, the Diet Bot emerges as a cutting-edge solution leveraging
artificial intelligence (AI) and natural language processing (NLP) to revolutionize dietary
management. By integrating user-provided data like age, weight, dietary preferences, and health
objectives, this innovative tool generates customized meal plans and nutritional
recommendations. Key functionalities include precise calorie tracking, comprehensive nutrient
analysis, and curated recipe suggestions tailored to individual needs. The Diet Bot aims to
empower users with the knowledge and tools necessary to achieve and maintain optimal health
through informed dietary choices. Its intuitive interface and interactive features make adopting
healthier eating habits more accessible and enjoyable, setting a new standard in digital health and
wellness assistance.

In today's era of personalized nutrition, the Diet Bot represents a groundbreaking advancement in
dietary management through the application of artificial intelligence (AI) and natural language
processing (NLP). By seamlessly integrating user-provided information such as age, weight,
dietary preferences, and health goals, this innovative tool excels in crafting personalized meal
plans and nutritional recommendations. Its core functionalities include meticulous calorie
tracking, in-depth nutrient analysis, and curated recipe suggestions tailored precisely to
individual needs.

The Diet Bot's primary objective is to empower users with the knowledge and tools necessary for
achieving and sustaining optimal health through informed dietary decisions. Its intuitive interface
and interactive features not only simplify the process of adopting healthier eating habits but also
make it a more engaging and enjoyable experience. By setting a new benchmark in digital health
and wellness assistance, the Diet Bot is poised to redefine how individuals approach and
maintain their dietary well-being in the modern age.

KEYWORDS:

1. Personalized nutrition
2. Diet Bot
3. Artificial intelligence (AI)
4. Natural language processing (NLP)
5. Revolutionize dietary management
6. User-provided data
7. Customized meal plans
8. Nutritional recommendations
9. Precise calorie tracking
10. Comprehensive nutrient analysis
11. Curated recipe suggestions
12. Optimal health
13. Informed dietary choices
14. Intuitive interface
15. Interactive features

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Table of Contents
CHAPTER 1..............................................................................................................................................2
INTRODUCTION.....................................................................................................................................2
1.1 Background................................................................................................................................3
1.2 Challenges........................................................................................................................................3
1.3 Goals and Objectives.......................................................................................................................5
1.4 Solution:...........................................................................................................................................6
1.5 Report Outline:................................................................................................................................6
CHAPTER 1..............................................................................................................................................2. 5
Literature Review......................................................................................................................................11
2.1 Introduction :....................................................................................................................................11

2.2 Literature Review............................................................................................................................8

2.3 Summary........................................................................................................................................22
CHAPTER 3............................................................................................................................................23
REQUIREMENT ANALYSIS................................................................................................................23
3.1 Introduction...................................................................................................................................24
3.2 Problem Scenarios.........................................................................................................................24
3.3 Functional Requirements..............................................................................................................24
3.4 Non-Functional Requirements......................................................................................................25
CHAPTER 4............................................................................................................................................26
SYSTEM DESIGN..................................................................................................................................26
4.1 Introduction...................................................................................................................................27
4.2 Architectural Design......................................................................................................................27
4.3 Detailed Design..............................................................................................................................28
4.4 Data Flow Diagram........................................................................................................................28
4.5 Use case Diagram...........................................................................................................................29
4.6 Activity Diagram............................................................................................................................29
4.7 Website Design:..............................................................................................................................30
References:...............................................................................................................................................33

CHAPTER 1

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

INTRODUCTION

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Introduction:
Chatbots are also known as chatter bots. A chatbot is developed with the help of AI (Artificial
Intelligence) application. It gives permission to humans to interact with digital devices as if they
were communicating with a human being.
AI chatbots employ machine learning, an AI capability that allows bots to become smarter over
time as they are used. AI chatbots are a natural match for customer service because of this.
Chatbots use digital instant messenger to communicate with people and can be integrated into a
variety of applications and websites. These websites include:
• B2B: Mobile Monkey.
• Services: Massage Envy.
• Restaurant: Domino's.
• E-commerce: Peloton. Types of Chatbot:

• Menu/button chatbot
• Linguistic based
• Keyword recognition-based chatbots
• Machine Learning chatbots
• The hybrid models
• Voice bots [1]
1.1 Background
In 1966, MIT's Joseph Weizenbaum invented ELIZA, the first chatbot that came close to
simulating a human. ELIZA will detect keywords in a sentence as well as pattern match them
against a list of pre procedures to generate appropriate responses.
Amazon's Echo and Alexa, Apple's Siri, and Microsoft's Cortana are examples of
modern chatbot. [2 , 3]

1.2 Challenges
Now that you've learned about the advantages of using AI chatbots, one can put its power to
work to improve customer happiness. Whenever it comes to adopting AI chatbots within the
company, unfortunately, there are some major challenges.
• Chatbot security.
• Understanding the emotions and sentiments of your customers.
• They are susceptible to data security breaches.
• They can misunderstand user point of view.
• They can face spoken language problems.  They can interrupt the user experience.
Why do chatbots fails?
Chatbots are programmed by humans and typically follow a decision-tree. The chatbot's
activities are expressly mapped out by the authors based on what a user says. Chatbots fail
because pre-training a chatbots to operate correctly in every case is nearly hard.

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Consider slang, misspellings, intonation, comedy, and syntax when it comes to

communication. I hate to admit it, but I'm a human who sometimes misses sarcasm or comedy in
my own relationships.
As a result, chatbots make mistakes. We see consumers angry or annoyed, brand
reputation harmed, or flat-out negative user feedback for a variety of reasons, which we detail
below.

The top 5 chatbot fails

Chatbot Fail # 1: uxchat.me
Reason: Engaging in inappropriate conversation.
Chatbot uxchat.me does not understand the emotions of the user or customer.
Fix: Don't teach your bot to answer a question it doesn't comprehend or to repeat something
word for word.
Chatbot Fail #2: Poncho
Reason: Not Understanding the Basics
"Please accept my apologies. I'm not sure what you're talking about. "Could you just try again?"
Even if you're following instructions or asking a question that should be within its field of
knowledge, if you've engaged with a simple chatbot, I'm sure you've stumped it.
Fix: Take a significant time to train your customer service chatbot on as many utterances and
situations as possible. Crowd-source to gather additional training data. Monitor engagement to
continuously enhance training.
Chatbot Fail #3: Sprout Social
Reason: Not adapting to the channel
When you are writing a message to your friend you avoid writing long paragraphs. It is difficult
to read for any person because it takes a lot of time to read a message.
Fix: Limit the length of chatbot replies to one or two sentences. [4]

Chatbot Fail # 4: Humans prefer talking to humans

Chatbot which is authorized by AI and machine learning, chatbots can efficiently interact with
humans and they can answer any type of human queries. Amazon’s Alexa and Google’s voice
assistant are great examples of efficient chatbots present today.
Chatbot Fail # 5: Inability to resolve personalized issues

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Now-a-days, chatbots can easily interact with customers easily because of the continuous
advancement in AI (Artificial Intelligence) and machine learning. They can easily answer
customer’s questions. But they cannot resolve the unique personalized problems of your
customers.

How to Prevent Chatbot Failure?

1. Send a message to a human agent
"Please bear with us while we connect you with our expert."
When it comes to dealing with common client complaints and questions, a chatbot can be useful.
But don't expect these AI-powered bots to work fully independently! Human action is required.
2. Be honest (transparent )
Make it clear to customers that they are speaking with a chatbot rather than a human.
You should not conceal it from your consumers as a brand because it might have a
beneficial impact on them. Surprisingly, using a chatbot can encourage customers to spend more
money.
3. Timely maintenance
Maintaining it on a regular basis entails providing it with up-to-date information and ensuring
that all its functions are operational.
You may have thoroughly prepared your chatbot software, but routine maintenance ensures that
it is up to date and functioning properly, reducing the likelihood of it failing while
communicating with your clients. [5]

1.3 Goals and Objectives

A chatbot can interact with a human being like a human.
You may develop chatbots in any business field such as :
Despite of whether you're a:
• Mill owner
• Senior Manager
• Instant help for students
• Teaching Assistant
• Customize Chatbot

Let’s list down objectives and purpose of chatbots.

Objectives:
• It provides 24/7 availability.

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

• Themes.
• Voice-to-text.
• Language.
• Customize Chatbot.
• Quality of conversation. [6]

1.4 Solution :
Use machine learning to understand the basic questions and emotions of the users and handle
complex queries intelligently.

10

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

CHAPTER 2
Literature Review
2.1 Introduction :
The purpose of this chapter is to provide a literature review of inventory management articles
published in major logistics outlets, identify themes from the literature and provide future
direction for inventory management research. A literature review identifies, estimates and
synthesizes the relevant literature within a specific field of research. At the end we will conduct
the summary of literature review on inventory management system that why this system is
essential for any organization.

2.2 Literature Review

Alan Turing posed the issue, "Can machines think?" in 1950. Turing imagined this issue as a
"mimicking game" (now famous as Turing Test), in which an "interrogator" asked human
artificial candidates queries with the objective of defining the human. They believe the robot
could understand if indeed the people and robot are similar.

The first chatbot ever was developed by MIT professor Joseph Weizen baum 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.

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.

Through its platform, it has made it easy to create very simple chatbots. It has grown to be an
example of the most favored ways for marketers and employers to reduce the work they do as
they interact with customers online.

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. Chumen Wenwen Company, founded in 2012 by a former Google employee, has built
a very sophisticated bot running on WeChat.

Early in 2016, 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.

11

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

The introduction of chatbots into a community has brought us to the time of the conversational
interface. It’s an interface that soon won’t demand a screen or a mouse. The interface will be
entirely conversational, and those communications will be indistinguishable from the
conversations that we have with our friends and relatives.
To fully explain the massiveness of this soon-to-be reality, we’d have to go back to the earliest
days of the computer, when the desire for artificial intelligence technology and a conversational
interface first began.

ELIZA:

Like stated previously, ELIZA was the very first chatbot. It was designed by Joseph
Weizenbaum in 1966 and simulates speech using pattern matching and replacement methods.

The programme was created in such a way that it closely resembles human dialogue. The ELIZA
Chatbot works by entering words into a computer and then matching them to a list of probable
prepared responses. It makes use of a psychotherapist-like script. The screenplay had a big
impact on natural language processing and artificial intelligence, with copies and adaptations
popping up in academies all over the country.

The reaction of users, on the other hand, upset Weizenbaum. ELIZA was supposed to be a
caricature of human dialogue, but users began to confide in it.[13]

In view of the benefits, the following is an overview of several studies conducted by researchers
on using Chabot for tutoring.

A) Customized Learning

Students benefit from individual attention because teachers get understanding of the domain in
which the students are vulnerable. A bigger number of professionals can be conceived if personal
educators are accessible to specific students of various capacities. Students can learn more about
their areas of interest.

Technology Mediated Learning (TML) is defined as "an environment in which

intelligent data technologies mediate the learner's interactions with learning resources (readings,
assignments, exercises, etc.), peers, and/or instructors." Chatbot mediated learning is another
branch of TML in which the study is personalized, and students can use the bots to learn in real
time.

12

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Comparison between different Chatbots:

1) BI Norwegian Business School

The different chatbot employed at BI Norwegian Business School brings together students with
similar cases so that they will be never judged based on initial queries, and reminders are made
for their continuous participation. The chatbots evaluate their students' judgement and deliver the
appropriate teaching. For example, the Summit Learning Project employs chatbots to identify
students' weak areas, adapt to their learning styles, and assist them in managing their modules.
The chatbots also conduct tests and report the findings to the tutors, who respond to the students
right away. This is achieved using digital platforms. Botsify exemplifies the same attitude.

2) Wizard-Of-Oz Paradigm

In the Wizard-Of-Oz Paradigm, a real person acts as that of the virtual teacher that examines
their learners to use the Intelligent Tutoring System (ITS) and IM Bots named as Open

Learner Modelling. The experiment was carried out within live time with 30 students from the
University of Birmingham.

3) Anne G. Neering

Anne G. Neering is another automated conversational agent created by a group young

engineering students which distribute course content and ideas while also encouraging students
to have fun while learning.

B) Spaced Interval Learning:

Students could use spaced interval learning to analyze what they've learned so far. The kids can
recollect the information they have learned. Super Memo is a system that aware the children
when they are about to forget something. It monitors the frequency mode in which learning
occurs and repeats things that have already been covered using an algorithm.
C) Assessment of composition skills:

Currently, instructors choose to test students using multiple-choice surveys, which makes their
jobs easier. A student's writing and composition skills, that could be acquired via essay writing,
can help them be better judged. This has been investigated just use an automated evaluating

13

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

system where the researchers had to use unsupervised machine learning to perform robotic
evaluation as well as an analysis of the robot's performance, that was finished using a mixture of
Term Frequency Inverse Document Function (TFIDF) and cosine Euclidean distance.

A real-time study on a group of medical students found that the web tutoring system raised their
test scores and cognitive efficacy by three times the size, as measured by Cohen's D effective
dose (95%) and confidence interval.

An actual investigation was conducted at University of Salerno for a set of computer science
students where Latent Dirichlet Allocation (LDA) algorithm was used in the operation of
managing queries. This produced a satisfactory outcome.

Teachers who believe that chatbots would take their jobs and they will be laid off are
making a mistake. It simply makes jobs easier for them by assisting pupils with common
questions and evaluating them individually. Throughout their free time, teachers can stay up to
date on the newest research. One of the first educators to employ such strategy was Ashok Goel,
who created his own chatbot, Jill Watson. Jill attempted to respond to the students via an online
forum, disseminating all accessible information as well as technical questions.

Research was conducted to determine teachers' attitudes on the use of talk bots in their curricula,
and it was shown that they would have an emotion overall rating (mean) of 3572, indicating that
they were positive about the technology. They also advised that chatbots should include a search
feature like that of a web search.

F) Integration of chatbots to classrooms:

Apart from self-supporting chatbots, there has been an increase in the combination of these
chatbots in social platforms such as Facebook, Google classroom, Twitter and so on. Based on
the category, language and development platform chatbots used for education in Facebook has
been studied in and the success has been evaluated. Quality allocation was tabulated using
Analytic Hierarchy Process (AHP).
G) Appealing methods of online education:
The effectiveness of chatbots in teaching is also determined by their appealing design. In their
study, Reeves, B., and Nass, C. (1996) found that many people identify social media platforms
such televisions, laptops, and the web like fellow beings and treat them with more respect. Few
researchers were inspired by this discovery to come up with novel ways to transmit knowledge
like a dignitary or prominent figure from the past. To elaborate, a talk bot called Freud bot were

14

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

created in 2014 utilizing non-proprietary software called AIML (Artificial Intelligence Markup
Language) with ELIZA-like control mechanisms. Freud bot's standout feature was that it
interacted with students as though he were a famous historical figure.

H) Competent in language:
There are apps that assist users in learning new languages. Its integration with chatbots is still
being tested. A study was performed specifically targeting Language learning, in which the
chatbot was built and integrated into an established English Practice software. Users may
improve their linguistic skills via quizzes, grammar tests, spoken language tests, vocabulary
assessments, etc. If users are idle for an extended length of time, the application will remind
them.
Jia and Chen conducted research into ways to motivate learners in the English language
industry. The research was carried across a six-month time and was integrated into an English
high school classroom. According to the findings, students felt more self-assured and had the
capacity to improve their learning abilities. Duolingo is a language-learning app that employs
bots. [8-13]

Chatbots in Business Field

Businesses are using chatbots to increase sales and improve customer service. To demonstrate
the broad range of pricing and abilities there in chatbot field, they created the top AI chatbot
system comparison and reviews list. This is a progressive collection that will be updated on a
regular basis.
The table below includes three categories: Type, Platform, and Fees.
Type:
The user's interaction with the AI chatbot system is defined by the kind. All systems have
conversation chatbots that are using AI and/or logic, and some can transition to a human
individual in such a chat session.
There are four types of chatbots which re as follows:
• Rule-Based Chatbot
• AI Chatbot
• Live Chat
• Voice
1. Rule-Based Chatbot
Without using AI, a rule-based chatbot uses a tree-like flow to assist guests with their
questions. This means that the chatbot will lead the guest through a series of follow-up
questions in order to arrive at the proper solution. Because the structures and responses are
all pre-determined, you have complete control over the discourse.

15

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

2. AI Chatbot
Chatbots are also known as chatterbots. It is a form of Artificial Intelligence (AI) which is
used in messaging apps. This too helps add convenience for clients. They are automated
programs that interact with clients like a human would and cost little to nothing to capture
with.
3. Live Chat
Live chat is a discussion between two people that involves sending messages over the
internet, especially to get or give information about a company’s product. The furniture
companies hire 20’ ’design consultants” who offer advice by phone, email, and live
chat.
4. Voice-based
Voice chatbots are chatbots that can communicate using vocal input and output. You can talk
to the bot out loud, like you would a person. In turn, it will respond with a voice of its own.
Chatbots of any kind are software programs that interact via conversation. Usually, this
works through text-based input and output.

Platform:
Platform defines what platform the chatbot works on, and the list may not include all
platforms.
• Website
Interfaces on a desktop and mobile website
• Facebook
Facebook is a social networking website where we create our profile, share
photos and videos with each other, and respond or link to the information posted by
others. An online social marketing website is an example of Facebook.
• SMS Text
It uses SMS mobile texting.
• Slack, Kik, Twitter, WhatsApp and other networks
System works on other social and communication network.
E-commerce platforms
Systems that work on or integrate with an ecommerce platform.
Fees
Fees are the chatbots costs shown on each company’s website on the date when this
table was created.

16

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Comparison of different chatbots

Company Type Platform Fees

Ochatbot Text, Live chat Websites, ecommerce Free, $69, $109, $495
(Shopify,
BigCommerce,
Magento,
WooCommerce, and
others), Facebook
and others, 80+
LeadBots templates
on all platforms
IBM Watson Text, voice Websites, Facebook, Requires contact
SMS, Slack,
WhatsApp
Intercom Text, Live chat Websites, Facebook, $67, Support,
Slack Customer
Engagement,
Marketing require
contact
Smooch Text, Live chat Websites, Facebook Requires contact

AIVO Text, voice Websites, Facebook, $99, $499, Business

SMS and Enterprise
require contact
ChatFuel Text, Live chat Facebook Free, $9.99. $39.99,
$124.99, Established
Business requires

17

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

18

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

SMS, Slack, Alexa

1. Ochatbot
Ochatbot is a true AI chatbot platform which is designed for e-commerce, sales,
marketing and support while allowing a life-like experience for shoppers through its
natural, friendly, and interactive textual discussion capabilities.
2. Chatfuel
Chatfuel is a Facebook Messenger chatbot for marketing, sales, and support. It features a
library of bot templates that may be used to create a Facebook Messenger chatbot
without requiring any coding knowledge. When the chatbot is unable to answer a
question, it provides a method for transferring the conversation to a human.
3. Engati
Engati has a chatbot also live chat. It could stop a chatbot response and permits a person
to take over the conversation. It is available in multiple languages that work on social
websites. It's a chatbot that does not require any programming. Over 50 languages are
supported by Engati.

19

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

4. Drift
Drift is a term used in predictive analytics and machine learning that explain how the
statistical features of the target variable that the model is attempting to forecast vary over
time in unpredicted ways. This raises issues just because days passes, such forecasts
become less accurate.
5. ManyChat
ManyChat is a platform to develop Facebook Messenger Bots for marketing, sales, and
customer service. You can use their visual Flow Builder too make entire bots, and you
can build a dozen different methods for people to interact with your Messenger Bot.
6. Dexter
Dexter lets you compose the chatbot dialogue in a text editor, allowing you to quickly
update and test it. Rich media can be incorporated into templates, and it connects to a
variety of APIs. Dexter is aimed for businesses and agencies.
Dexter provides AI-based forecasting-as-a-service to helps electricity retailers avoid
power system instability and save up to 35% on instability costs. The services optimize
energy retailers' portfolios by properly predicting energy loads and network imbalances.
7. LivePerson
Through reliable Conversational AI, LivePerson makes life easier for people and brands
all over the world. Rather than wasting so much time on wait and otherwise exploring
websites, our Conversational Public cloud allows customers to message their favorite
brands, just like they do with friends and relatives.
For specialized industries, LivePerson is just a tool in marketing, sales, and
contact center activities. With each industry use case, they offer ready-to-use bot designs
and pre-configured intentions and conversations that interact with back-end systems.
8. BotCore
BotCore can be installed inside or outside the cloud, and it connects with enterprise apps
and legacy systems. A variety of chat channels are available, including voice, text, and
custom channels. Microsoft Bot Framework is in charge of multi-channel assistance.
BotCore is a platform that allows businesses to create bespoke conversational
bots that are driven by artificial intelligence. It can use any AI service that is currently
available and will expand for future services. It's completely deployable on Microsoft
Azure and takes advantage of several of the platform's features.
9. AI Assist by Coversica
AI Assist is a virtual sales assistant for prospecting, lead generation, and nurturing for the
finance industry. The assistant communicates with the leads via email, collects fresh or
updated phone numbers, and forwards the information to a sales representative for
follow-up.

20

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

10. AIVO
Agentbot creates omnichannel experiences on any voice or text channel. It has
middleware that interacts with each application such as Zendesk, Salesforce, and Zapier.
It uses natural language processing to learn from each conversation.

11. Dialog flow

Dialog flow incorporates Google’s machine learning expertise and products such as
Google Cloud Speech-to-Text and is optimized for Google Assistant. This bot supports
over 20 languages.
12. Autochat
Autochat assists e-commerce businesses in interacting with their customers during the
buying process. It has Woo Commerce, Magento, Shopify, and Big Commerce
platform connections.
13. Avaamo
Avaamo has an AI support desk assistant that can conduct multi-turn discussions. For the
healthcare, insurance, financial services, retail, and telecommunications industries, there
are more than 150 prebuilt and custom interfaces.
14. Clustaar
Clustaar includes a visual drag-and-drop builder and lets you import a ready-to-use
template to assist with bot training. The conversation is started by the bot, but a real chat
agent can take over at any point.
15. FlowXo
FlowXO is a lead generation chatbot that can transition to live chat when necessary. It
can accept payments during a conversation and connects the user to a secure payment
portal to complete the transaction.

16. Botanic Technologies

Botanic provides a comprehensive set of conversational systems for businesses that
speak, see, hear, and converse in multiple ways. Customers can also construct their
custom bots using its proprietary conversational interfaces.
17. Digital Genius
Digital Genius is a customer care automation software that employs predictive
technology to help agents find the optimal solution. The solution was automatic whereas
if prediction has a high level of confidence.
18. Helpshift

21

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Helpshift is a business-oriented in-channel customer service bot. Bots are accessible in

eleven different languages. Without support of a developer, you could create your own
bot or edit ones that has already been created.
19. IBM Watson
IBM Watson AI Assistant is a software that incorporates a variety of conversation
technology. The Assistant may be utilized on mobile devices, messaging networks, and
robotics, among other things.
20. Intercom
Intercom is a sales, marketing, and support chatbot with a web chat feature which links
with eCommerce as well as social networks. Conversations from social media can be
included into a customer relationship management system (CRM).
21. BotsCrew
BotsCrew is a chatbot company that specializes in the hospitality, legal, customer
service, banking, eCommerce, entertainment, other personal service industries. Chatbots
are available for websites, messaging, SMS, and voice assistants such as Alexa and
Google Home.
22. ItsAlive
ItsAlive is a Facebook Messenger chatbot system using drag-and-drop rules and a
folderbased method for organizing decision trees.
23. Kore.ai
Kore.ai is an enterprise-grade end-to-end conversational chatbot platform that meets the
enterprise's demanding use case needs. It can be installed on-premises, in the cloud, or in
a hybrid configuration. It's an all-in-one platform.
24. Landbot
Landbot is a service that turns websites and landing pages into interactive conversations.
25. Mobile Monkey
Mobile Monkey is a webchat Facebook Messenger and Instagram marketing bot maker.
It caters to agencies, marketers, small businesses, and content providers.
26. Netomi
Netomi is a helpline AI chatbot that can response to emails sent to it. There are also
inapp, online chat, audio, SMS, and social integrations, as well as the ability for such a
people to control over such a chat session.
27. NextIT
NextIT is an enterprise-grade integrated AI solution with intelligent virtual assistants for
customer engagement and workforce support for the enterprise.

22

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

28. Octane AI
Octane AI is a Facebook Messenger bot that connects with eCommerce platforms to
communicate with customers directly, track their behavior, and report revenue.
29. Pandorabots
Conversational agents for the eCommerce, customer service, voice, B2C, marketing, and
entertainment industries are known as Pandorabots. They provide anything from do-
ityourself chatbots to fully turnkey chatbot creation services.
30. Pypestream
Pypestream is a conversational AI technology designed to automate customer care.
Consumers can use encrypted B2C exchanges to make payments, file claims, and
arrange appointments.
31. Quriobot
Quriobot is a tool that allows you to create your own bot using templates and a drag-
anddrop designer. It comes with a conversation designer that can be used on most social
media platforms, as well as websites and landing pages.
32. Kustomer
Kustomer is a customer service bot framework with insurance, travel & hospitality, and
consumer electronics companies. It connects to major CRMs, social media platforms, and
websites.
33. Sales Machine
Sales machine is a Slack bot and customer service solution that notifies you when a
customer requires assistance. Keep track of your customers' health and be notified if
something changes.
34. Selekt
Selekt provides sales and marketing chatbots for real estate, eCommerce, hospitality,
airlines, television broadcasting, and human resources.
35. Semantic Machines
Semantic Machines is a conversational AI interface for Siri, Google, and Cortana for
ecommerce and business.
36. Smooch
Smooch maintains all your messaging channels with a single API. It has a bot-to-human
handoff feature that sends the conversation history and context to a live agent.
37. Snatchbot

23

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

Snatchbot is a chatbot driven by artificial intelligence that can be used on mobile devices,
web apps, and popular chat platforms. Without even any coding skills, one can construct
an artificial bot or even a user mixed chatbot.
38. Twyla
Twyla is an AI chatbot trainer discussion design software. It is a chatbot CMS with flow
features it automates chat and voice.
39. Web Spiders
For customer service and HR, Web Spiders offers a web, social, and mobile activity
chatbot and a leads engagement sales chatbot.
40. Wit.ai
Wit.ai allows you to build speech and text-based bots that humans can communicate with
using their favorite messaging platform.
41. Wizeline
Wizeline offers customer service, marketing, events, and conference chatbots, as well as
Alexa and Google voice bots. It is integrated with Google Maps and Yelp.
42. Customize Chatbot
Customer service queries could be effectively answered and responded to using custom
chatbots. Custom chatbots can live on your website as a chat widget, inviting customers
to chat at any time of day or night. [14]

2.3 Summary
From my perspective, chatbots or smart assistants with artificial intelligence are
dramatically changing businesses. There is a wide range of chatbot building platforms
that are available for various enterprises, such as e-commerce, retail, banking, leisure,
travel, healthcare, and so on. Chatbots can reach out to a large audience on messaging
apps and be more effective than humans. They may develop into a capable
informationgathering tool soon.

CHAPTER 3
REQUIREMENT
ANALYSIS

24

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

3.1 Introduction
Requirement's analysis, also called requirements engineering, is the process of determining
user expectations for a new or modified product. These features, called requirements, must be
quantifiable, relevant and detailed. Requirement's analysis is an important aspect of project
management.

3.2 Problem Scenarios

In addition to understanding and interacting within conversations, an outstanding chatbot
software has NLP functions (Natural Language Processing) to analyze the context of a
conversation. It can identify the intent of a question to provide an accurate answer and suggest
options to confirm or resolve the issue.

3.3 Functional Requirements

Chatbots aid in the improvement of customer experiences by assisting or guiding customers
during critical choices. Above all, chatbots offer a plethora of automation possibilities that can
drastically speed up services. Not all chatbot software solutions, however, are created equal.
Specific restrictions have a significant impact on possible savings and consumer benefits.
Chatbots assist customers in making better selections by providing support or advice.
Above all, chatbots offer a plethora of automation possibilities that can greatly speed up service
delivery. All chatbot software solutions, however, are not treated equally. There are several
restrictions that have a significant impact on possible savings and consumer benefits.
If you are looking for a chatbot software but are not sure yet which features are
necessary, this article will help! We’ll investigate the most important requirements and features
of a chatbot software for enterprises.
The most important requirements of chatbot software:
Complex dialogues

• In addition to understanding and interacting within conversations, an outstanding chatbot

software has NLP (Natural Language Processing) to analyze the context of a
conversation.
• It can identify the intent of a question to provide an accurate answer and suggest options
to confirm or resolve the issue.
The best chatbots have advanced conversation features and can proactively search for
information and ask clarifying questions even if the conversation is not linear.

 Training of our bot

25

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

We should train our bot and it gives answer after understanding the queries.
• Mode:
The customer can change the mode according to his/her choice. Modes like dark or light
mode.
• Voice to text
In chatbot applications, voice bots are chatbots that communicate in an automated way
using vocal input and output. You can talk to the bot out loud like you would to a
person. In turn, it will respond with a voice of its own without the need for human
interaction on its end. [15]

3.4 Non-Functional Requirements

Nonfunctional requirements include the following:
(1) Security:
Unauthorized users should have no access to the system.
(2) Usability:
The proposed system should be easy for the user to operate, enter data, and
interpret the output.
(3) Scalability :
The system should always perform adequately regardless of updates.
(4) Compatibility :
The proposed system should be compatible with all web browsers. [16]

CHAPTER 4
SYSTEM DESIGN
4.1 Introduction
A chatbot is a natural language-based human-computer communication system. As a result, a
person can converse naturally with a machine or system. The chatbot must be able to converse
with the user and comprehend what they are saying, you could call this a comprehension
function. Intent and entity recognition are included in this comprehension.

26

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

4.2 Detailed Design

4.3 Data Flow Diagram

27

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

4.5 Use case Diagram

28

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

4.6 Activity Diagram

4.7 Website Design :

1. Front page

2. Chatbot

29

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

3. Customize Chatbot Features

4. Languages

30

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

5. Speech-to-text References:
1) https:// www.engati.com/
blog/types-of- chatbots-and-their-

applications? utm_content=types-
of-chatbots-and- their-applications
2) 4 reasons for enterprise chatbot
failure and how to overcome them using
a multi- bot approach. (2020).

https://servisbot.com/four-reasons-for-enterprise-chatbot-failure/. (Retrieved 30 September

2020).
3) 5 core considerations for choosing your chatbot | by Ruth Zive | chatbots mange. (2020).
https://chatbotsmagazine.com/5-core-considerations-for-choosing-your-chatbot4
f4bb0856ead. (Retrieved 30 September 2020).
4) https://www.netomi.com/the-worst-chatbot-fails-and-how-to-avoid-them 5)
https://helplama.com/chatbots-fail/
6) https://chatbots-life.com/purpose-and-objective-of-chatbots-4f2ed7f35227
7) https://onlim.com/en/the-history-of-chatbots/
8) A, S., & John, D. (2015). Survey on chatbot design techniques in sp Garcia Brustenga, G.,
Fuertes-Alpiste, M., Molas Castells, N. (2018). Briefing paper: chatbots in education.
Barcelona: eLearn Center. University Obertade Catalunya.
9) Alavi, M., & Leidner, D. E. 2001. Review: Knowledge Management and Knowledge
Management Systems: Conceptual Foundations and Research Issues. MIS quarterly, 25(1):
107.
10) A, S., & John, D. (2015). Survey on chatbot design techniques in speech conversation
systems. International Journal of Advanced Computer Science and Applications, 6,
http://dx.doi.org/10.14569/IJACSA.2015.060712.
11) AbuShawar, B., & Atwell, E. (2015). ALICE Chatbot: Trials and outputs. Computación y
Sistemas, 19, http://dx.doi.org/10.13053/cys-19-4-2326.

31

Downloaded by msk ([email protected])

 lOMoARcPSD|43583645

12) Ada: Your health companion. (2020). Ada website: https://ada.com/. (Retrieved 8 June
2021)
13) Amazon lex – build conversation bots. (2019). Amazon Web Services, Inc. website:
https://aws.amazon.com/lex/. (Retrieved 25 November 2019).
14) https://www.ometrics.com/blog/chatbot-platform-comparison-reviews/
15) https://onlim.com/en/top-requirements-for-chatbot-software/
16) https://github-wiki-see.page/m/WaldurChatbot/Waldur-Chatbot/wiki/Non-functional
requirements.

32

Downloaded by msk ([email protected])