Merged Final 30

College Enquiry Bot
A Major Project – l Report

Submitted in partial fulfillment of the requirement for the award of
Degree of Bachelor of Technology in Electronics & Communication
Submitted to
RAJIV GANDHI PROUDYOGIKI VISHWAVIDYALAYA, BHOPAL (M.P.)
Major Project - l Report
Submitted by
Payal Bharti (0176EC201017) Yash Awasthi (0176EC201030)
Khusboo Jaiswal (0176EC201009) Tanya Sharma (0176EC201025)
Under the supervision of

Prof. Rajdeep Shrivastava Prof. Santosh Kumar Jha
(Project Guide) (Project In - charge)
DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING

LAKSHMI NARAIN COLLEGE OF TECHNOLOGY EXCELLENCE, BHOPAL
SESSION 2023-24
Lakshmi Narain College of Technology Excellence, Bhopal (M.P.)
Department of Electronics & Communication Engineering
VISION OF THE DEPARTMENT
To become reputed in providing technical education in the field of electronics and

communication engineering and produce technocrats working as leaders.
MISSION OF THE DEPARTMENT
1. To provide congenial academic environment and adopting innovative learning

process.
2. To keep valuing human values and transparency while nurturing the young
engineers.
3. To strengthen the department by collaborating with industry and research

organization of repute.
4. To facilitate the students to work in interdisciplinary environment and enhance

their skills for employability and entrepreneurship.
PROGRAM EDUCATIONAL OUTCOME (PEO)
PEO1: Recognize and apply appropriate experimental and scientific skills to solve real
world problems to create innovative products and systems in the field of electronics and
communication engineering.
PEO2: To evolve graduates with ability to apply, analyze, design in Electronics &
Communication Systems.
PEO3: Motivate graduates to become responsible citizens with moral & ethical values
for the welfare of Society.
PEO4: Inculcate the habit of team work with professional quality of leadership to
become successful contributors in industry and/ or entrepreneurship in view of Global
& National status of technology.
PROGRAM SPECIFIC OUTCOME (PSO)
PSO1: Analyze specific engineering problems relevant to Electronics &

Communication Engineering by applying the knowledge of basic sciences,
engineering mathematics and engineering fundamentals.
PSO2: Apply and transfer interdisciplinary systems and engineering approaches to the
various areas, like Communications, Signal processing, VLSI and Embedded system,
PCB Designing.
PSO3: Inculcate the knowledge of Engineering and Management principles to meet

demands of industry and provide solutions to the current real time problems.
PSO4: Demonstrate the leadership qualities and strive for the betterment of
organization, environment and society.
CERTIFICATE
This is to certify that the work embodied in this Project-I Report entitled “College
Enquiry Chatbot” has been satisfactorily completed by Payal Bharti, Yash
Awasthi, Khushboo Jaiswal and Tanya Sharma. It is abona-fide piece of work,
carried out under our supervision and guidance in the Electronics and
Communication, Lakshmi Narain College of Technology Excellence, Bhopal, for
partial fulfillment of the Bachelor of Engineering during the academicyear 2023-
2024.
Under the supervision of
……………………….. …….……………....
Prof. Rajdeep Shrivastava Prof. Santosh Kumar Jha
(Project Guide) (Project In-charge)
Approved by
…………………………
Dr. Abhinav Bhargava

(Professor & Head)

DECLARATION
We, Payal Bharti, Yash Awasthi, Khushboo Jaiswal and Tanya Sharma,
students of Bachelor of Engineering, Electronics and Communication
Engineering,Lakshmi Narain College of Technology Excellence, Bhopal, here-by
declare that the work presented in this Project-I is outcome of our own work, is
bonafide, correct to the best of our knowledge and this work has been carried out
taking care of Engineering Ethics. The work presented does not infringe any
patented work and has not been submitted to any University for the award of any
degree or any professional diploma.
Payal Bharti (0176EC201017)

Yash Awasthi (0176EC201030)
Khushboo Jaiswal (0176EC201009)
Tanya Sharma (0176EC201025)

Acknowledgement
Words shall never be able to pierce through the Gamut's of emotions that are
Suddenly exposed during the routine of our college life. We would like to thank Prof.
Rajdeep Shrivastava, Project Guide for guiding and correcting us at each instant
andfor his continuous motivation. At the same time, we would also like to thank Prof.
Santosh Kumar Jha, Project In-charge of Electronics and Communication
Engineering, for his well-wishes and also to provide his kind support and valuable
knowledge on the subject from time to time.
We express our heart-felt thankfulness to Dr. Abhinav Bhargava, H.O.D. of

Electronics and Communication Engineering, LNCTE, Bhopal for his un-failure
inspiration, whole hearted co-operation and constant encouragement throughout the
process of the dissertation and incisive comments gave immense confidence to
complete the work. Also, we are grateful to Dr. Ashok Kumar Rai, Director
Administration, LNCT Group for providing us a positive learning environment and
Dr. A. K. Saxena, Principal, LNCTE for giving us a chance to fulfill our potential.
Payal Bharti (0176EC201017)
Yash Awasthi (0176EC201030)
Khushboo Jaiswal (0176EC201009)
Tanya Sharma (0176EC201025)

CONTENTS
List of Abbreviations……………………….…………………..……VII
List of Figures…………………………………………………..…...VIII
Photographs of the Project……………………………………..…… IX
About Us………………………………………………………...…... X
Abstract……………………………..……………………………… .XI
Chapter – 1: Introduction
1.1 Introduction…………………………….………… 2
1.2 Motivation……………………….………………. 3
1.3 Objective of the project……..……………………. 4
Chapter – 2: Market Size & Growth
2.1 Market Size………………………………………..6
2.2 Future Growth……………………………………..7
Chapter – 3: Theory…………………..………………………………9
Chapter – 4: Issues & Challenges………..………………………….13
Chapter – 5: Technologies for Chatbot…..………………………….18
5.1 Artificial Intelligence………………………………19
5.2 Elements of Artificial Intelligence…………………20
5.3 Natural Processing Language………………………23
Chapter – 6: Software & Hardware Requirements…………………..26
Chapter – 7: Advantages & Disadvantages
Advantages…………………………….…………….28
Disadvantages……………………………………….29
Chapter – 8: Maintenance…………………..………………………30
Chapter – 9 : Future Scope & Enhancement………………………...34
Chapter – 10: Conclusion………………………………...……...….38
References…………………...…………………………..………....41
v
Source code………………………...………………………..…...….42
Images of Project……………………………………………………..57
Annexure I: Impact on Society……………………………………….59
Annexure II: Environment and Sustainability………………..………61
Annexure III: Presentation Slides…………………………..…..…….63
vi
List of Abbreviations
AI - Artificial Intelligence
ML - Machine Learning
NLP - Natural Language Processing
CMD - Command Prompt
NLDK - Natural Language Toolkit
IDLE - Integrated Development and Learning Environment
IDE - Integrated Development Environment
vii
List of Figure
Figure 1 - Flow Chart for Chatbot………………………………………….23

Figure 2 - Architecture of Chatbot………………………………………….24
Figure 3 – Interface…………………………………………………………57
Figure 4 - Enquiry Generated by Bot(1)……………………………………58
viii
Photograph of the Project
ix
ABOUT US
My name is Payal Bharti. I am pursuing Bachelor of Technology

in Electronics and Communication engineering from Lakshmi
Narain College of Technology Excellence, Bhopal. My current
CGPA is 8.79. I have done my schooling from Delhi Public School,
Saharsa (Bihar). I am an honest and responsible person. I am
dedicated towards my work with all my efforts and discipline.
My name is Yash Awasthi. I am pursuing Bachelor of Technology

in Electronics and Communication engineering from Lakshmi
Narain College of Technology Excellence, Bhopal. My current
CGPA is 8.51. I have done my schooling from Deepak Memorial
Academy (M.P). I am an active and hardworking person trying to
learn new technologies.
My Name is Khusboo Jaiswal. I am pursuing my B.Tech in

Electronics and Communication Engineering from LNCT group of
Colleges, Bhopal. My current CGPA is 8.23 .My career objective is
to leverage my passion for technology and innovation to contribute
significantly in this industry. I believe in the concept of mutual
growth where both me and my organization will leave a lasting
remark in the industry.
My name is Tanya Sharma, I am pursuing Bachelor of Technology

in Electronics and Communication Engineering from Lakshmi
Narain College of Technology, Excellence, Bhopal. My current
CGPA is 7.66. I completed my schooling from Good Shepherd
Convent Sr. Sec. School, Shahdol (M.P.). I am a motivated and
intelligent individual and I try to learn new skills and improve
myself.
x
ABSTRACT
In today’s world computers play an important role in our society? Computers give us
information; they entertain us and help us in lots of manners. A chatbot is a program
designed to counterfeit a smart communication on a text or spoken ground. But this
paper is based on the text only chatbot. Chatbot recognize the user input as well as by
using pattern matching, access information to provide a predefined acknowledgment.
For example, if the user is providing the bot a sentence like “What is your name?” The
chatbot is most likely to reply something like “My name is Chatbot.” or the chatbot
replies as “You can call me Chatbot.” based on the sentence given by the user. When
the input is bringing into being in the database, a response from a predefined pattern
is given to the user. A Chatbot is implemented using pattern comparing, in which the
order of the sentence is recognized and a saved response pattern is acclimatize to the
exclusive variables of the sentence. They cannot register and respond to complex
questions.
xi
College Enquiry Bot
CHAPTER-1
Introduction
1
Department of Electronics and communication Engineering, Lakshmi Narayan College of Technology Excellence, Bhopal
College Enquiry Bot
CHAPTER-1
Introduction
1.1 Introduction
In today’s world computers play an important role in our society? Computers give us
information; they entertain us and help us in lots of manners. A chatbot is a program designed
to counterfeit a smart communication on a text or spoken ground. But this paper is based on
the text only chatbot. Chatbot recognize the user input as well as by using pattern matching,
access information to provide a predefined acknowledgment. For example, if the user is
providing the bot a sentence like “What is your name?” The chatbot is most likely to reply
something like “My name is Chatbot.” or the chatbot replies as “You can call me Chatbot.”
based on the sentence given by the user. When the input is bringing into being in the database,
a response from a predefined pattern is given to the user. A Chatbot is implemented using
pattern comparing, in which the order of the sentence is recognized and a saved response
pattern is acclimatize to the exclusive variables of the sentence. They cannot register and
respond to complex questions, and are unable to perform compound activities [1]. Chatbot is
relatively a new technology. The application of a Chatbot can be seen in various fields in the
future. This paper covers the techniques used to design and implement a Chatbot.
Comparisons are made, findings are discussed and conclusion is drawn at the end. A chatbot
(conversational interface, AI agent) is a computer program that can understand human
language and converse with a user via a website or a messaging app. Chatbots can handle
various tasks online — from answering simple questions and scheduling calls to gathering
customer feedback.
At the most basic level, a chatbot is a computer program that simulates and processes
human conversation (either written or spoken), allowing humans to interact with digital
devices as if they were communicating with a real person a single-line response, or as
sophisticated as digital assistants that learn and evolve to deliver increasing levels of
personalization as they gather and process information.
A chatbot is a computer program that simulates human conversation with an end user.
Though not all chatbots are equipped with artificial intelligence (AI), modern chatbots
2
College Enquiry Bot
increasingly use conversational AI techniques like natural language processing (NLP) to

understand the user’s questions and automate responses to them. Chatbots can make it easy
for users to find information by instantaneously responding to questions and requests—
through text input, audio input, or both—without the need for human intervention or manual
research. Chatbot technology is now commonplace, found everywhere from smart speakers
at home to consumer-facing instances of SMS, WhatsApp and Facebook Messenger to
workplace messaging applications like Slack. The latest evolution of AI chatbots, often
referred to as “intelligent virtual assistants” or “virtual agents,” can not only understand free-
flowing conversation through use of sophisticated language models, but even automate
relevant tasks. Alongside well-known consumer-facing intelligent virtual assistants like
Apple's Siri and Amazon Alexa, virtual agents are also increasingly used to in an enterprise
context to assist customers and employees.
1.2 Motivation
People have multiple motivations, and the purposes for using a chatbot can vary enormously.
As such, there is a need for an appropriate range of use cases in the chatbot context. changing
user behaviour as well as user needs. They are also altering particular user interfaces, creating
new demands in the field of HCI.
As we all know chatbots square measure a really fashionable approach of

communication between the user the system text interface. we have a tendency to wished to
use this system to implement college web site for a additional economical communication
between the coed and administration. Students will use school website chatbot for Queries
rather than about to workplace or authorities directly for info. College web site based mostly
bots square measure accustomed develop effective communication between different
branches and facilitate management to produce innovative solutions. Our Project to create a
university web site chatbot would undoubtedly have a bright scope as this could bring a
modification within the approach of interaction between school and students.
This Project would inspire alternative schools still to develop internet chatbots to Ease the
communication between Management and Students. Traditionally, the chat larva system isn't
renowned to those who don't seem to be additional into the technology. Even if there exist a
talk larva system, it's not abundant correct in proving the solution or solutions. Students got
to manually visit to the school to induce their queries answered by the school facilitate table.
3
College Enquiry Bot
This method consumes ton of your time still as cash because the client required to go to school
if its miles removed from home. Also, this method might cause communication gap
between student and school.
1.3 Objective of the project
Chatbots allow businesses to connect with customers in a personal way without the expense
of human representatives. For example, many of the questions or issues customers have are
common and easily answered. That's why companies create FAQs and troubleshooting
guides.
Educational chatbots are software programmes that replicate human conversation and
provide automated educational help to students and educators by utilizing artificial
intelligence (AI) and natural language processing (NLP) technology. These chatbots are
programmed to interpret the user’s questions and react with relevant and useful information.
Educational chatbots can be used to answer inquiries, provide study tools, provide feedback,
and even provide personalized coaching. They provide a more interesting and interactive
learning environment for students and can help educators save time by automating repetitive
processes. With a trend towards online education and EdTech platforms, many consumers
seek course inquiry and pricing structure. However, no one has enough time to deliver all the
relevant information, which is where a chatbot comes in. In this kind of use case, a chatbot
has answers for almost all course-related information, including fees, curriculum covered,
completion date, etc. Students explore multiple courses before enrolling in one, so supplying
them with the finest is essential. Chatbots in such a use case offer faster query resolutions
resulting in better changes of course sign-ups and promote transparency of information to
foster positive relationships with parents and students.
We also know that free internet tools and services are on the rise, making it difficult
to sell a course or persuade many students to join your college. As a result, it is critical to set
up a course with low prices yet various expertise to offer. Doing so may help you get more
students to enrol if you offer some unique courses at reasonable pricing. And using
educational chatbots, you can learn more about the needs of your students through personal
chats and offer them the courses accordingly. Your chatbot can also help acquire the required
information and work on future finances to meet students’ needs.
4
College Enquiry Bot
CHAPTER-2
Market Size & Growth
5
College Enquiry Bot
CHAPTER-2
Market Size & Growth
2.1 Market Size
The global chatbot market size was accounted at USD 0.84 billion in 2022 and it is expected
to reach around USD 4.9 billion by 2032. What will be the CAGR of global chatbot market?
The global chatbot market is poised to grow at a CAGR of 19.29% from 2023 to 2032.
The Indian chatbot industry, although still in its nascent form, is a $3.1B market,
according to analysts. The market, in the coming years will evolve to a point where interactive
and intuitive AI will become the bare standard for customer service across a variety of sectors.
AI in Insurance will value at $36B by 2026. In 2022, the marketing segment accounted for
the largest market share of about 56%. Chatbots use AI to process language and interact with
humans. Many chatbots have been added to messenger apps like Facebook, Skype, Slack, and
other social media networking sites. Moreover, chatbot programmers incorporate payment
gateways directly with the associate and use these messaging platforms for payment
services. One of the market's significant opportunities is to charge nominal fees as
commission. Furthermore, chatbots are widely used in digital marketing to keep existing
customers informed about new products and services, even though they allow for direct
customer interaction.
2.2 Future Growth
Chatbots that are developed for integration with messaging applications are also expected to
witness significant market demand in the future. Moreover, chatbot are gaining popularity as
the businesses continue to automate their sales and customer services. The use of chatbot
enables organizations to deliver timely services at reduced costs. Today there is a significant
rise in the usage of messaging services, which is expected to surpass the social networking
sites in terms of the number of users. There is also a significant development in the Natural
language processing field, which made the interactions between computer and human
languages more streamlined. The entire ecosystem of the chatbot comprises various cross-
linking features that help in optimum usage of the application.
6
College Enquiry Bot
The users interacting with the customer service interrelate with the chatbot through
the chatbot interface. The chatbot interact with users via webpage or mobile applications or
through SMS etc. The chatbots are deployed on various channels such as standalone, website,
and third-party messenger platforms. In standalone, bots are integrated with the applications
and other software of the enterprises. The users interact with the chatbots deployed to raise
the requests or the complaints to customer service. The chatbot is a messaging service that
was developed by using a set of rules and artificial intelligence that can be interacted via a
chat interface. There are two types of chatbots, one which is developed by a set of rules and
the other which uses artificial intelligence and machine learning algorithms. Some chatbots
also include voice recognition in order to offer an enhanced customer service experience.
Currently, chatbot developers are including analytics into software application in order to get
better insights into customer behavior and buying patterns. Open.AI, an American artificial
intelligence company, released ChatGPT, an AI chatbot that answers every question. It is the
latest series of AI which is referred to as GPT. The chat structure enables the AI to respond
to "follow-up questions, admit its errors, contest false assumptions, and decline unsuitable
requests. With the spread of the coronavirus, various marketing agencies, financial
organizations, and grocery outlets have initialized the full fledge implementation of chatbots
and conversational AI tools to enhance customer service in the crisis. Amid the pandemic,
businesses face challenges in sustaining and are willing to try new technological avenues such
as voice-based assistants and chatbots. Also, chatbots have assisted the medical and healthcare
verticals during the difficult times. Several medical insurance companies and public health
institutions worldwide have deployed chatbots to assist users/patients in providing proper
COVID-19 advice and suggestions.
7
College Enquiry Bot
CHAPTER – 3
Theory
8
College Enquiry Bot
CHAPTER - 3
Theory
In the earlier days, students had to visit the college to enquire about details like courses , fee
structures, admission process and other information about the college which is tiresome and
long process. This is where we thought of using an intelligent bot delivering the information.
College Enquiry Chatbot is a simple python web application which aims to provide the
information regarding college asked by the user. A chatbot is software that simulates human-
like conversations with users via text messages on chat. Its key task is to help users by
providing answers to their questions. This could be a text based (typed) conversation, a spoken
conversation or even a non-verbal conversations. Chat bot is typically perceived as engaging
software entity which humans can talk to . It can be interesting , inspiring and intriguing. It
appears everywhere, from old ancient HTML pages to modern advanced social networking.
College Enquiry Chatbot uses machine learning concepts to have conversations with humans.
The purpose of developing this project is based on an intellectual chat-bot system which will
deal with the academic activities like admission enquiry, fees structure, scholarship details,
time-table of every department, details of the documents required to attach etc. With this chat-
bot system it will be easy for the student to directly clear their queries in less time. Chatbots
typically provide a text-based user interface, allowing the user to type commands and receive
text in order to resolve the query. The Chatbot has information stored in its dataset to identify
the sentences and making a decision itself as response to answer a given question . The
program analyses the user’s query then the bot responds to the query.
The main objective of “College Enquiry Chatbot” is to minimize the time required to
solve the queries of an user, reduce the work load on the college’s office staff, save the time
and strength of an user of visiting and contacting the administration office often , keep the
user fully updated about the ongoing and upcoming events of the college, etc.
There are two main types of chatbots: rule-based and self-learning. Rule-based chatbots
follow a set of predefined rules to determine the correct response to a user’s input. Self-
learning chatbots, also known as AI-based chatbots, use machine learning algorithms to
understand and respond to user input.The most common type of self-learning chatbot is the
9
College Enquiry Bot
Retrieval-based chatbot, which is based on the idea of selecting a response from a set of
predefined responses based on the similarity between the user’s input and the predefined
responses.
Another type of self-learning chatbot is a Generative-based chatbot, which is based

on the idea of generating a response by itself. This type of chatbot uses neural networks like
GPT-3 to generate text that is similar to human text.
In general, chatbots are used to automate tasks such as customer service, information
retrieval, and e-commerce. They can also be used to improve user engagement and
personalize the user experience. However, it’s important to note that chatbots have some
limitations such as the lack of context awareness and common-sense knowledge.
SOME IMPORTANTS PARTS:
1. Chatbots are computer programs that simulate human conversation through text
or voice interactions.
2. There are two main types of chatbots: rule-based and self-learning. Rule-based
chatbots follow a set of predefined rules to determine the correct response to a
user’s input. Self-learning chatbots use machine learning algorithms to
understand and respond to user input.
3. Self-learning chatbots can be further divided into Retrieval-based and

Generative-based chatbots. Retrieval-based chatbots select a response from a set
of predefined responses based on the similarity between the user’s input and the
predefined responses. Generative-based chatbots use neural networks like GPT-
3 to generate text that is similar to human text.
4. Chatbots can be used to automate tasks such as customer service, information
retrieval, and e-commerce. They can also be used to improve user engagement
and personalize the user experience.
5. Chatbots have some limitations such as lack of context awareness and common-
sense knowledge. It’s important to monitor and test chatbots to ensure they
provide accurate and appropriate responses.
10
College Enquiry Bot
A chatbot needs a purpose, and if we consider that if this purpose is to be helpful, it also needs
to gain trust from the users. There is no need to ask a chatbot for help if you don’t trust the
information it gives you. With this in mind we consider the first question to be a bit too
ambiguous and large for us to investigate in this course. We have therefore used this question
as a guideline for what we can actually manage to explore in this course and what we can find
on the existing literature in this field. Trust is an important factor for reliance on and
implementation of technology (Lee & See, 2004). In relationships trust means being reliable,
having confidence in the other person both physically and emotionally (Lewicki & Bunker,
1995). So one can say that trust will also play a role in the interplay between human and
machine. The problem with systems taking control is that it’s often hard for people to rely
upon it appropriately. Because people respond to technology socially, trust influences
dependence in it. So trust will inevitably guide reliance when we are faced with complex and
unanticipated situations. When we use systems to navigate and make decisions about 3 our
health, finances, relationships, and future — they must be trustworthy. In human-technology
interaction trust is an example of the important influence of affect and emotions. Emotional
feedback in technology is not only important for acceptance, but can also make a fundamental
improvement regarding safety and performance (Lee & See, 2004).
Chatbots has emerged as a hot topic in the latest years, and it is used by numerous companies
in various areas - help desk tools, automatic telephone answering systems, e-commerce and
so on. Even though the technology has been around since the 60’s (Atwell & Shawar, 2007).
Why are we suddenly so interested in this technology now? This can likely be explained by
the recent year's advancements in messaging applications and AI technology (Brandtzaeg &
Følstad, 2017). In the article Chatbots: Are they really useful? Atwell and Shawar provide
real-life examples of different chatbots in different contexts. One of the examples is Sophia,
a robot that was developed to assist in mathematics at Harvard by answering students
questions. This turned out to be applicable in many other contexts. Living in Norway you
have probably noticed “Kommune Kari”. A chatbot that many of the municipality have
available on their web-pages. Kari is there to answer “easy” questions like “when will the
garbage truck come?” and “where can I find available jobs?”. Kari’s goal and the job is to
provide information so that you as a user don’t have to navigate the “massive information
flow” (Schibevaag, 2017). This way of using a chatbot is a part of the Question Answering
(QA) field which is a combination between AI and information retrieval (Molla & Vicedo,
11
College Enquiry Bot
2007). QA can be defined as: “... the task whereby an automated machine (such as a computer)
answers arbitrary questions formulated in natural language. QA systems are especially useful
in situations in which a user needs to know a very specific piece of information and does not
have the time—or just does not want—to read all the available documentation related to the
search topic in order to solve the problem at hand”. (Molla & Vicedo, 2007). 4 Sophia and
Kari are examples of chatbots that operate in “very specific” domains. This means that if you
were to ask Kari about math and Sophia about when the garbage truck comes none of them
would know the answer - because the question is outside of their domain. Chatbots have what
is called a natural language user interface and therefore communicate with users via
natural language ㅡ how a human would talk on a regular basis (Brandtzaeg & Følstad, 2017).
Therefore they use what is called natural language processing (NLP) where the chatbot uses
computational techniques to analyze text, where the goal is to produce a human-like answer
based on a linguistic analysis (Hirschberg & Manning, 2015). For a chatbot to be especially
useful to a certain domain some criteria have to be met. Minock (2005) proposes the following
criteria for a domain to be successful in answering domain-specific questions: a domain
should be circumscribed, complex and practical.
12
College Enquiry Bot
CHAPTER - 4
Issues & Challenges
13
College Enquiry Bot
CHAPTER – 4
Issues & Challenges
AI Chatbots are increasingly becoming a fixture of our digital lives, with many of us taking
advantage of the technology to communicate with friends and family online. However, as
with any new technology, there are bound to be some teething problems and issues that need
to be addressed. Here, we take a look at some of the main issues and challenges associated
with AI chatbots.
One of the main issues with chatbots is that they sometimes make up facts. This can
be extremely frustrating for users, who may find themselves unable to get the information
they need due to the chatbot’s lack of accuracy. In addition, chatbots are also often biased on
many topics, which can again lead to users not getting the information they need. Another
challenge associated with chatbots is that they can often fail to answer basic questions. This
is often due to the fact that chatbots are not yet as sophisticated as human beings and so are
not able to understand all of the nuances of human language. This can be extremely frustrating
for users who may find themselves having to explain their question in great detail in order to
get a response.
No protection against hacking
As artificial intelligence continues to evolve, so too do the ways in which hackers can exploit
it. Because of their popularity, chatbots are also becoming a more common target for hackers.
There are a few ways in which hackers can exploit chatbots. One of the most common is by
simply trying to guess the bot’s answers to common questions. This can be done by looking
at the bot’s code or by using a process of elimination. Another way to exploit a chatbot is to
flooding the bot with requests. This can cause the chatbot to lag or even crash. Finally, hackers
can try to take control of the chatbot by hijacking the account that is associated with it. This
can be done by guessing the password or by taking advantage of a security flaw in
the chatbot’s code. All of these methods can be used to exploit chatbots and cause serious
problems for businesses that use them. As artificial intelligence continues to evolve, it is
important for businesses to be aware of these dangers and take steps to protect themselves.
14
College Enquiry Bot
Web traffic
One of the key issues facing AI chatbots is the issue of web traffic. As chatbots become more
popular and more advanced, there is a risk that they will increasingly be used as a replacement
for traditional web browsing. This could lead to a decline in web traffic, as users opt to use
chatbots to access information instead of visiting websites. Now it is profitable for any site to
get into the search results because the user will follow the link to it and bring traffic with him.
But what to do when the chatbot can give such an answer that the user no longer needs to go
to the site? Let’s imagine an apocalyptic scenario in which sites gradually die, since no one
else visits them, but at the same time, the chatbot dies, since it has nowhere to get information
from.
Fake news and propaganda
Another issue facing AI chatbots is the challenge of fake news. Due to the fact that chatbots
can generate and share content, there is a risk that fake news or misinformation could be
spread via chatbots. This could have serious consequences, as chatbots have the potential to
reach a large audience very quickly.
One of the issues with chatbots is that they can be used to spread misinformation. This is
because chatbots are often designed to mimic human conversation. As such, they can be used
to create false narratives or to propagate misinformation.
This is a particularly relevant issue in the current political climate. For example, during the
2016 US presidential election, chatbots were used to spread fake news stories and to influence
public opinion. This issue was also relevant during the Brexit referendum in the UK. Another
issue with chatbots is that they can be used to exploit vulnerable people. This is because
chatbots can be designed to target people who are vulnerable to certain types of exploitation.
For example, there have been cases of chatbots being used to target people with gambling
addiction.
Data privacy
Finally, another challenge associated with AI chatbots is the issue of data privacy. As chatbots
collect data from users, there is a risk that this data could be mishandled or shared without the
user’s consent. This could lead to serious privacy breaches and could damage the reputation
15
College Enquiry Bot
of chatbots. Chatbots can also be used to invade people’s privacy. This is because chatbots
can be designed to collect personal information from people. This information can then be
used to target advertisements or to sell to third-party companies.
Ethical questions
As artificial intelligence (AI) increasingly enters the mainstream, developers are facing
important ethical questions about how to design AI chatbots. In particular, they must decide
which topics are appropriate for chatbots to joke about, and which topics are off-limits. This
is not an easy task, as chatbots are often developed for global audiences and must therefore
take into account the sensitivities of people from diverse cultures and religions. There have
already been a number of scandals involving AI chatbots. In India, for example, people were
offended that ChatGPT could joke about Krishna but not about Muhammad or Jesus. This
highlights the challenges that developers face in trying to create AI chatbots that are respectful
of all religions and cultures. The question of what topics are appropriate for chatbots to joke
about is a difficult one to answer. On the one hand, chatbots should be allowed to joke about
any topic that is not likely to offend or hurt anybody. On the other hand, there are some topics
that are so sensitive that even the most innocent joke could be interpreted as offensive. For
example, jokes about the Holocaust are generally considered to be in bad taste and would
likely offend many people.
The best way to avoid offending anyone with an AI chatbot is to carefully consider
the chatbot’s audience and to avoid jokes about sensitive topics. In addition, developers
should provide users with the ability to report offensive jokes so that they can be removed
from the chatbot’s database.
Similar to business ideals and objectives, there could be a misalignment in the success
metrics of chatbot development. There is no long-term engagement strategy as most of the
metrics planned are suited for short-term campaigns, such as a promotion drive for lead
generation.
Side Note: Speaking of lead generation, content marketers looking to define their
linking leads and SEO strategy should incorporate link building.
Websites like linkbuildinghq.com provide detailed information and guidance on how

this system works. Coming back to chatbots, think of them as serving a much bigger purpose
16
College Enquiry Bot
and one that needs to be approached with a purposeful and long-term strategy to be
successful. That frequently necessitates the creation of a dedicated team to be in charge of
monitoring trial results and enhancing performance over time in a learn-and-test approach.
There is presently no monetization strategy for developers who create chatbots for
Messenger. In other words, unless they establish chatbots for a third party, chatbot developers
have no way of making money from their bots.
That is not to say that one of the powerful platforms will not implement an enticing
monetization method in the coming years. Customers might have to pay a subscription fee for
premium apps on the app store, similar to how they do now. Chatbots may not offer direct
value to developers. Still, they may be helpful for large corporations seeking to engage with
more users and thus increase revenue.
17
College Enquiry Bot
CHAPTER 5
Technologies for Chatbot
18
College Enquiry Bot
CHAPTER - 5
Technologies for Chatbot
5.1 Artificial Intelligence -
Artificial intelligence (AI) is the ability of a computer program or a machine to think and
learn. It is also a field of study which tries to make computers "smart".
Businesses are becoming smarter with time. Every business expects intelligence in the
system. Businesses are looking for a system on which they can trust, they can depend on them
for customer support, the system which can make important decisions or perform vital actions
on behalf of humans with an engaging experience. This can be possible with the AI Chatbots.
Artificial Intelligence gives a human touch to every conversation. The bot understands the
user’s query and triggers an accurate response.
Taking the bionic approach as a basis, the article discusses the main concepts of the
theory of artificial intelligence as a field of knowledge, which studies the principles of creation
and functioning of intelligent systems based on multidimensional neural-like growing
networks. The general theory of artificial intelligence includes the study of neural-like
elements and multidimensional neural-like growing networks, temporary and long term
memory, study of the functional organization of the “brain” of the artificial intelligent
systems, of the sensor system, modulating system, motor system, conditioned and
unconditioned reflexes, reflexes arc (ring), motivation, purposeful behaviour, of “thinking”,
“consciousness”, “subconscious and artificial personality developed as a result of training and
education”.
Artificial intelligence, defined as “a system's ability to correctly interpret external

data, to learn from such data, and to use those learnings to achieve specific goals and tasks
through flexible adaptation” (Kaplan and Haenlein, 2019, p. 17), can be categorized into three
types: analytical, human-inspired, and humanized (Kaplan and Haenlein, 2019). Analytical
AI has characteristics consistent with cognitive intelligence only. Human-inspired AI has
elements of cognitive and emotional intelligence, i.e., understanding human emotions, in
addition to cognitive elements, and uses these in its decision making. Humanized AI exhibits
19
College Enquiry Bot
characteristics of all types of competencies (i.e., cognitive, emotional, and social intelligence),
and is able to be self-aware in its interactions.
AI's spring, i.e., its birth, can be traced to Alan Turing's article “Computing Machinery and
Intelligence” (1950) that provided the mechanism for testing a machine's intelligence.
However, the term “artificial intelligence” was not coined until 1956 at the Dartmouth
Summer Research Project on Artificial Intelligence (DSRPAI) organized by John McCarthy
and Marvin Minsky. What followed were a few AI “summers” and “winters”, metaphorically
the subsequent ups and downs of AI: While general optimism, hype, and intensive AI funding
reigned during its summers, the opposite was the case during AI winters (Haenlein and
Kaplan, 2019).
AI's autumn, or its harvest period, arrived only recently. Its “Year One” is usually
considered 2015, when Google's AlphaGo AI system managed to beat the human champion
in the very complex board game Go. Previously believed impossible, this event marked a
turning point in the history of artificial intelligence. Previously, computational processing was
not powerful enough to handle the (big) data necessary for AI systems being able to learn.
Artificial intelligence needs lots of data to train algorithms, and this is where social media
comes into play, as they contain massive quantities of data.
5.2 Elements of Artificial Intelligence (AI)
Artificial Intelligence uses two important elements that help the chatbot to find a perfect
response.
Machine Learning
Machine learning is an algorithm that helps the chatbot to learn from queries and the data
provided by you during bot training. Artificial intelligence requires to interact with the
machine in a natural language that could be easily understood by the system. Here machine
learning comes in a role. The main aim of machine learning is to provide a brief answer to the
user’s question.
The area of Machine Learning deals with the design of programs that can learn rules
from data, adapt to changes, and improve performance with experience. In addition to being
one of the initial dreams of Computer Science, Machine Learning has become crucial as
20
College Enquiry Bot
computers are expected to solve increasingly complex problems and become more integrated
into our daily lives. Writing a computer program is a bit like writing down instructions for an
extremely literal child who just happens to be millions of times faster than you. Yet many of
the problems we now want computers to solve are no longer tasks we know how to explicitly
tell a computer how to do. These include identifying faces in images, autonomous driving in
the desert, finding relevant documents in a database (or throwing out irrelevant ones, such as
spam email), finding patterns in large volumes of scientific data, and adjusting internal
parameters of systems to optimize performance. That is, we may ourselves be good at
identifying people in photographs, but we do not know how to directly tell a computer how
to do it. Instead, methods that take labeled training data (images labeled by who is in them,
or email messages labeled by whether or not they are spam) and then learn appropriate rules
from the data, seem to be the best approaches to solving these problems. Furthermore, we
need systems that can adapt to changing conditions, that can be user-friendly by adapting to
needs of their individual users, and that can improve performance over time.
Consider the general principle of “Occam’s razor”, that simple explanations should be
preferred to complex ones. There are certainly many reasons to prefer simpler explanations
— for instance, they are easier to understand — but can one mathematically argue for some
form Occam’s razor from the perspective of performance? In particular, should computer
programs that learn from experience use some notion of the Occam’s razor principle, and how
should they measure simplicity in the first place? One of the earliest results in Computational
Learning Theory is that there is indeed a reason as a policy to seek out simple explanations
when designing prediction rules. In particular, for measures of simplicity including
description length in bits, Vapnik-Chervonenkis dimension which measures the effective
number of parameters, and newer measures being studied in current research, one can convert
the level of simplicity into a degree of confidence in future performance. While some of these
theoretical results are quite intricate, at a high level the intuition is just the following: there
are many more complicated explanations possible than simple ones. Therefore, if a simple
explanation happens to fit your data, it is much less likely this is happening just by chance.
On the other hand, there are so many complicated explanations possible that even a large
amount of data is unlikely to rule all of them out, and even some that have nothing to do with
the task at hand are likely to 2 still survive and fool your system. This intuition can then be
turned into mathematical guarantees that can guide machine learning algorithms. Another
21
College Enquiry Bot
highlight of Computational Learning Theory is the development of algorithms that are able
to quickly learn even in the presence of large amounts of distracting information. Typically,
a machine learning algorithm represents its data in terms of features: for example, a document
might be represented by the set of words it contains, and an image might be represented by a
list of various properties it has. The learning algorithm processes this information to make
some prediction (Is this document of interest? Who is the person in this image?). However, it
is up to the algorithm designer to decide on what these basic features should be, and the
designer may not know in advance what features will turn out to be the most useful. Thus,
one would like the designer to be able to pour as many features as possible into the learning
algorithm and have the algorithm itself quickly focus in on those that are actually needed. An
exciting early result in Computational Learning Theory was the development of algorithms
that in many cases have provably only a logarithmic dependence in their convergence rate on
the number of distracting features: this means that every time you double the amount of
information available, it at worst can hurt the algorithm by a small additive amount. So,
designers do not have to be stingy in providing information to the algorithm. Moreover,
recently there has been substantial work on how learning algorithms can automatically change
their input representation through what are known as kernel functions, which themselves can
be learned from data. Machine Learning Theory also has a number of fundamental
connections to other disciplines. In cryptography, one of the key goals is to enable users to
communicate so that an eavesdropper cannot acquire any information about what is being
said. Machine Learning can be viewed in this setting as developing algorithms for the
eavesdropper. In particular, provably good cryptosystems can be converted to problems one
cannot hope to learn, and hard learning problems can be converted into proposed
cryptosystems. Moreover at the technical level, there are strong connections between
important techniques in Machine Learning and techniques developed in Cryptography. For
example, Boosting, a machine learning method designed to extract as much power as possible
out of a given learning algorithm, has close connections to methods for amplifying
cryptosystems developed in cryptography. Machine Learning Theory also has close
connections to issues in Economics. Machine learning methods can be used in the design of
auctions and other pricing mechanisms with guarantees on their performance. Adaptive
machine learning algorithms can be viewed as a model for how individuals can or should
adjust to changing environments. Moreover, the development of especially fast-adapting
algorithms sheds light on how approximate equilibrium states might quickly be reached in a
22
College Enquiry Bot
system, even when each individual has a large number of different possible choices. In the
other direction, economic issues arise in Machine Learning when not only is the computer
algorithm adapting to its environment, but it also is affecting its environment and the
behaviour of other individuals in it as well. Connections between these two areas have become
increasingly strong in recent years as both communities aim to develop tools for modeling
and facilitating electronic commerce.
5.3 Natural Language Processing
Natural Language Processing is known as NLP, which provides assistance to the bot to
understand and interpret the information. The main goal of NLP is to interpret, recognize, and
understand user requests. When you send “Hello” to the chatbot, it is the NLP that lets the
chatbot know that you are sending greetings, It allows the bot to leverage its AI capabilities
to come up with a proper response.
Fig 1:-Flow Chart diagram for College Enquiry Chatbot
23
College Enquiry Bot
Fig 2:-Architecture of College Enquiry ChatBot
24
College Enquiry Bot
CHAPTER - 6
Software & Hardware Requirements
25
College Enquiry Bot
CHAPTER - 6
Software & Hardware Requirements
6.1 Software Requirements:
➢ Windows 10, Windows 11

➢ Visual Studio 2010
➢ CMD
➢ Python
6.2 Hardware Components:
➢ Processor – i5
➢ Hard Disk – 5 GB
➢ Memory – 4GB RAM
➢ Android device
26
College Enquiry Bot
CHAPTER - 7
Advantages & Disadvantages
27
College Enquiry Bot
CHAPTER - 7
Advantages & Disadvantages
7.1 Advantages
• Provide fast, 24/7 customer service.

• Offer more personalized experiences.
• Deliver multilingual support.
• Ensure more consistent support.
• Offer convenient self-service options.
• Provide proactive customer service.
• Deliver omnichannel support.
• Improve service with every interaction.
• Collect customer feedback.
• Reduce customer request.
• Detect customer intent for added context.
• Boost Customer engagement.
• Streamline service with routing and triage.
• Boost sales.
• Increase lead generation.
• Enhance conversational commerce and marketing
28
College Enquiry Bot
7.2 Disadvantages
• Extent of Resolving Queries.

• Cannot Handle Angry Customers Subtly.
• Higher Complexity Results in Higher Costs.
• Not Suitable for All Businesses and Applications.
• Do not Provide Accurate Solutions Always.
29
College Enquiry Bot
CHAPTER - 8
Maintenance
30
College Enquiry Bot
CHAPTER - 8
Maintenance
Most chatbots these days rely on AI technology which is changing and evolving at a rapid
rate. Regular maintenance can keep the chatbot updated with new technology and
information. And when the chatbot is up-to-date, it can handle queries of any complexity with
ease and add value to users at any stage of the journey with a brand.
A chatbot may need maintenance for a variety of reasons, including –
• Improved accuracy – Chatbots are prone to giving incorrect and irrelevant responses
if not maintained regularly with the latest queries and content. So, they need to be
trained with the latest database and conversational strands to offer relevant responses
to queries. Not training on this can greatly affect the quality of engagement and user
experience a bot can deliver.
• Better engagement – No matter how advanced a chatbot is, after a while, it will cease
to deliver accurate responses due to a lack of maintenance. And this can hugely affect
its ability to engage with users.
• Efficiency and promptness – An updated chatbot will obviously show more

efficiency toward user queries. Most of the time, such tools also deliver quick answers
and therefore ensure improved satisfaction levels among customers.
• A seamless user experience – A chatbot can provide a seamless experience to

users only when it’s optimized and kept free of minor issues. The more you take care
of the maintenance, the more enjoyable experience you can deliver to users.
• Cost savings – Chatbot maintenance can not only improve its performance but can
also make your support agents more productive as well. A trained bot can also offer
accurate responses 24×7 or they can also answer questions when agents are not
available. All this can help businesses optimize support costs. Chatbot maintenance is
often an ongoing process. Your bot may need maintenance long after it has been
developed and deployed. And you can enhance the user experience with your brand
only when the chatbot is maintained on a regular basis.
31
College Enquiry Bot
Imagine that you are a service engineer at an industrial enterprise. A huge industrial
enterprise. Every day, you deal with very sophisticated and – let’s face it – very
expensive equipment. Moreover, you have a couple of dozens of different units that
have different service and maintenance procedures. Servicing complex equipment
requires solid knowledge of its user guides and maintenance manuals. Lots of
parameters, settings, values, sequences, safety precautions – and they may be
different for each unit. Ofcourse, you can always carry a smartphone or tablet with
all guides and manuals stored within.
However, in a situation when you need to find the corresponding manual,

section, paragraph quickly, and you need both hands to work on the equipment, you
will very well wish to have a third hand to manage your smartphone or tablet.But
why would you need an extra hand when you have your voice? That’s right. If you
cannot search and read your manual, you can talk to it. Naturally, to do so, you
need one more thing – a voice chatbot. A voice chatbot will be your voice assistant
providing the necessary information when and where you need it leaving your hands
free to operate the machine.Basically, we have outlined the problem already – in
their everyday work, service engineers are expected to deal with several different
equipment units, each with own specifics. Besides, the work of a service engineer,
operator or technician often requires both hands to be busy which makes it next
to impossible to browse the printed manual.
Therefore, the challenge was to find a way for the technician or engineer
to obtain the information they need to operate the machine without using their
hands. Another aspect was to get the information that is relevant at that very
moment, and quickly.
32
College Enquiry Bot
CHAPTER - 9
Future Scope & Enhancement
33
College Enquiry Bot
CHAPTER - 9
Future Scope & Enhancement
Future of Chatbots is very bright. With so much advancement in Artificial Intelligence sector,
chatbots are the future with zero doubt. Yes, the current chatbots which we are using are not
the future I am talking about. I am talking about Chatbot which will be built by using modern
technologies like Machine Learning, Natural Language Processing, Artificial Intelligence,
Speech Recognition, etc. The future chatbot will not be just a Customer Support agent, it will
be an advance assistant for both the business and consumer. We as human are not fond of
doing repetitive boring tasks. So in the future companies will hire AI Chatbot for the tasks
which are repetitive and doesn’t require creativity. Also, Human doesn’t like storing up
contents (mugging up) in their mind. And today with the Internet they can leverage that part.
So tasks which require storing the information (data) can be transferred to AI Chatbot. And
with AI Chatbot taking over repetitive boring tasks, Companies will utilize their human
resources for more creative tasks. With this, we can expect more amazing things coming up
to us in the future. At present, there is a mixed review in users (consumer) of Chatbot.
Majority of users are appreciating chatbots and its feature. Today with a chatbot, users get a
lot of amazing features like Instant Replies, Shopping Bot, Shipment Tracking, etc. all that at
one place, a single messenger platform.
We see a lot potential of the AI Chatbot in the future. To make a product or technology
successful, it needs public support and chatbot is getting that. With Advance modern
technology coming up we can expect more astonishing features from a chatbot. With ongoing
developments in artificial intelligence and natural language processing, chatbots have a broad
and bright future. Here are some crucial areas where chatbots are anticipated to make a big
difference.
Customer service and support: Chatbots are already used to answer questions from
customers, offer assistance, and fix problems. Chatbots will probably become considerably
more advanced and context-aware in the future, with the ability to handle complicated
interactions and, in many circumstances, replace the need for human engagement.
34
College Enquiry Bot
Personal Assistants: Chatbots have the potential to develop into highly customized virtual
assistants that aid users in organizing their daily duties, schedules, and activities. To offer a
seamless and effective user experience, these assistants might interface with a variety of
devices and apps.
Healthcare: Chatbots may be able to provide information to help healthcare workers.

With consumers’ needs increasing for around-the-clock communication, companies are
adapting to find ways to meet customers’ needs through automated response systems. But
knowing when and how to use chatbots is key to successful integration into your business
strategy. Since 36% of consumers think that chatbot’s accuracy could make efforts to improve,
it’s essential to figure out where to incorporate chatbots and where human interaction is still
necessary. So, let’s break down different ways to use chatbots so you can learn how to
incorporate them to better support your brand and alleviate some tasks off your employee’s
plates.
Chatbots are also referred to as virtual assistants. It is a rudimentary form of artificial
intelligence software that can mimic human conversation. The Chatbots can be analyzed and
improved. It can be used in various fields such as education, business, online chatting etc. It
can be used in the field of education as a learning tool. The information necessary for
education can be stored in the data base and can be retrieved any time by querying the bot. In
business field, it can be used to provide business solutions in an efficient way. When the
solutions are efficient, the business can be improved and the growth of the organization will
be increased. This Chatbot can be used in online chatting for entertainment purpose. People
can chat with these bots online when they are bored for the purpose of entertainment. These
bots can also be used to learn different kinds of language. The language that has to learnt can
be stored in the database and can be learnt by asking questions to the bot. They can also be
used in the field of medical to solve health related problems. Chatbots are going to explode
and can be really dominating in future. Chatbots can provide a new and flexible way for users.
They are giving AI something better to do. Chatbots results in smart conversation and is
advancing at an unprecedented rate with each new development. ChatBot usually store
contextual data which can be used in the detection of geo location or a state (which data is
needed for which step when communicating with a bot?). This could also be a telephone
number or other private data, and no one knows whether the data is encrypted before it gets
saved to a database. Since Chatbot predicts and provides accurate response to a posed
35
College Enquiry Bot
question, it is hard to imagine the future without a Chatbot. This Chatbot is very simple and
user friendly. It is not very complicated like other Chatbots. The working of the Chatbot is
simple and can be easily understood by any person. In other Chatbots, the working is very
complicated. Many classes are used which is difficult to understand. In this program, only
one class is used to make it simple and obtain the expected output. This Chatbot uses simple
pattern matching to represent the input and output whereas other Chatbots uses input rules,
keyword patterns and output rules to generate a response. If the input is not found in the
database, a default response is generated. The input and output can be customized according
to the user. Based on the developer or the user, the required requests and responses can be
stored in the database. Since own database can be created, it allows the user to understand
how the response is generated. This Chatbot can be used for the entertainment purpose.
Whenever a person is bored, he can chat with the bot for entertainment. It can also be used to
provide information by modifying the program as needed by the user.
36
College Enquiry Bot
CHAPTER - 10
Conclusion
37
College Enquiry Bot
CHAPTER - 10
Conclusion
A chatbot is one of the simple ways to transport data from a computer without having to think
for proper keywords to look up in a search or browse several web pages to collect information;
users can easily type their query in natural language and retrieve information. In this paper,
information about the design, implementation of the chatbot has been presented. From the
survey above, it can be said that the development and improvement of chatbot design grow at
an unpredictable rate due to variety of methods and approaches used to design a chatbot.
Chatbot is a great tool for quick interaction with the user. They help us by providing
entertainment, saving time and answering the questions that are hard to find. The Chatbot
must be simple and conversational. Since there are many designs and approaches for creating
a chatbot, it can be at odds with commercial considerations. Researchers need to interact and
must agree on a common approach for designing a Chatbot. In this project, we looked into
how Chatbots are developed and the applications of Chatbots in various fields. In addition
comparison has been made with other Chatbots. General purpose Chatbot must be simple,
user friendly, must be easily understood and the knowledge base must be compact. Although
some of the commercial products have recently emerged, improvements must be made to find
a common approach for designing a Chatbot.
A chatbot is one of the simple ways to transport data from a computer without having
to think for proper keywords to look up in a search or browse several web pages to collect
information; users can easily type their query in natural language and retrieve information. In
this paper, information about the design, implementation of the chatbot has been presented.
From the survey above, it can be said that the development and improvement of chatbot design
grow at an unpredictable rate due to variety of methods and approaches used to design a
chatbot. Chatbot is a great tool for quick interaction with the user. They help us by providing
entertainment, saving time and answering the questions that are hard to find. The Chatbot
must be simple and conversational. Since there are many designs and approaches for creating
a chatbot, it can be at odds with commercial considerations. Researchers need to interact and
must agree on a common approach for designing a Chatbot. In this project, we looked into
38
College Enquiry Bot
how Chatbots are developed and the applications of Chatbots in various fields. In addition
comparison has been made with other Chatbots. General purpose Chatbot must be simple,
user friendly, must be easily understood and the knowledge base must be compact. Although
some of the commercial products have recently emerged, improvements must be made to find
a common approach for designing a Chatbot.
As a result of the rapid technological development and the development of the chatbot
concept and the time and effort it can save. Many specialized frameworks have emerged to
undertake chatbot creation and development. By relying on artificial intelligence, the chatbot
has integrated machine learning within it, and it has become more comprehensive and wider
for various technological fields. Therefore, we will create a chatbot for the University's
Admission and Registration, the project aims to build a chatbot to facilitate the process of
accessing information related to students' inquiries towards admissions, Registration and the
university itself. The motivation for the work of this project is that there is no university-level
equivalent from previous graduation projects, as this project mainly targets all palestinian
tawjihi students and other palestinians, non palestinian students . As a conclusion, it lies in
answering frequent and common questions by people and providing the answer to these
questions at any time the person wants.
This bot was built to respond to the inquiries of the Tawjihi students regarding each
of the university's faculties and their specializations, with extracted information for each
specialization, familiarizing students with the level exams that students submit about their
enrollment in the university, introducing the educational qualification diploma program and
the mechanism for joining it. Giving students notes on the electronic enrollment application
package, the locations of approved banks, and how to fill out the application. Introduce Bagrut
students to the conditions and notes that must be taken into account in the event of joining
Palestine
Polytechnic University and the mechanism for calculating grades. Introduce students
to the procedures followed to reserve a seat and what documents are required after the student
is accepted. Introducing students to the system of transferring to Palestine Polytechnic
University from another university on the undergraduate system. Informing students of the
university’s teaching system and language. Introducing students to the student exchange
system with other universities. Introducing students to the system of grants, exemptions, and
39
College Enquiry Bot
financial aid provided to students. Informing students of cases in which the student loses his
university seat. Introducing students to the installment refund system for new students and its
conditions. Challenges: We faced many challenges, and the biggest challenge during the work
was the arrest of my colleague Ali Jboor, a month before the deadline for the project. Dealing
with the framework is one of the biggest challenges, as it is new and not widespread. And
also the challenge of learning the necessary Python language to complete the construction of
this bot. We can say that the current health situation contributed to creating communication
problems between team members and problems related to slow internet and power outages
during work. We also mention the challenge we faced, so we divided the work into two parts,
part for the admin panel and a part to follow up on the work on the bot. Unfortunately, Ali
was arrested and I had to do the project alone in his absence, especially after we agreed on a
day to share the results of the work, but that day Ali was arrested.
40
College Enquiry Bot
References
1. https://en.wikipedia.org/wiki/Chatbot
2. https://www.youtube.com/watch?v=ukzFI9rgwfU
3. https://www.businessinsider.com/what-is-chatbot-talking-ai-robot-chat-
simulators-2017-10
4. https://chatbotsmagazine.com/a-visual-history-of-chatbots-8bf3b31dbfb2
5. The Power of Conversation by John McTear
6. "Chatbots - Artificial Solutions." Chatbots | Conversational AI Platform for
Enterprise - Teneo. Accessed 8 Nov. 2020.
7. "How Do Bots and Chatbots Work." https://www.cxtoday.com/contact-
centre/how-do-bots-and-chatbots-work/
8. "Building Chatbots - A comparison of Rasa-NLU and Dialogflow." 17 Apr.
2018, Building Chatbots - A comparison of Rasa-NLU and Dialogflow.
Accessed 8 Nov. 2020.
9. "Jonathan Wheat" Jonathan Wheat - DEV Community. Accessed 10 Nov. 2020.
10. Understanding the Basics of Rasa - Open source conversational AI
https://smazee.com/blog/basics-of-rasa 6. Rasa Architecture Overview
https://rasa.com/docs/rasa/arch-overview/
11. An Architecture for Dynamic Conversational Agents for Citizen Participation
and Ideation by: Saifeldin Ahmed (PDF) An Architecture for Dynamic
Conversational Agents for Citizen Participation and Ideation (researchgate.net)
12. Installation: https://rasa.com/docs/rasa/installation 9. How to test a chatbot.
Accessed May 31-2021: https://apphawks.com/blog/a-compelling-guide-on-
chatbot-testin
41
College Enquiry Bot
Source Code –
import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
import json
import pickle
import random
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation, Dropout
from tensorflow.keras.optimizers import SGD
# Load and preprocess the data
words=[]
classes = []
documents = []
ignore_words = ['?', '!']
data_file = open('intents.json').read()
intents = json.loads(data_file)
for intent in intents['intents']:
for pattern in intent['patterns']:
42
College Enquiry Bot
#tokenize each word
w = nltk.word_tokenize(pattern)
words.extend(w)
#add documents in the corpus
documents.append((w, intent['tag']))
# add to our classes list
if intent['tag'] not in classes:
classes.append(intent['tag'])
# lemmatize and lower each word and remove duplicates
words = [lemmatizer.lemmatize(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))
# sort classes
classes = sorted(list(set(classes)))
# documents = combination between patterns and intents
print (len(documents), "documents")
# classes = intents
print (len(classes), "classes", classes)
# words = all words, vocabulary
print (len(words), "unique lemmatized words", words)
pickle.dump(words,open('words.pkl','wb'))
43
College Enquiry Bot
pickle.dump(classes,open('classes.pkl','wb'))
# create our training data
train_x = [] # List for bag of words
train_y = [] # List for output rows
# training set, bag of words for each sentence
for doc in documents:
# initialize our bag of words
bag = []
# list of tokenized words for the pattern
pattern_words = doc[0]
# lemmatize each word - create base word, in attempt to represent related words
pattern_words = [lemmatizer.lemmatize(word.lower()) for word in pattern_words]
# create our bag of words array with 1, if word match found in current pattern
for w in words:
bag.append(1) if w in pattern_words else bag.append(0)
# output is a '0' for each tag and '1' for current tag (for each pattern)
output_row = [0] * len(classes)
output_row[classes.index(doc[1])] = 1
train_x.append(bag) # Append bag of words to train_x
train_y.append(output_row) # Append output row to train_y
44
College Enquiry Bot
# Convert train_x and train_y to NumPy arrays
train_x = np.array(train_x)
train_y = np.array(train_y)
# Build and compile the model
model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]), activation='softmax'))
sgd = SGD(learning_rate=0.01, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
# Train the model and save it
hist = model.fit(train_x, train_y, epochs=200, batch_size=5, verbose=1)
model.save('chatbot_model.h5', hist)
print("Model created and saved")
import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
import pickle
import numpy as np
45
College Enquiry Bot
from tensorflow.keras.models import load_model
model = load_model('chatbot_model.h5')
import json
import random
intents = json.loads(open('intents.json').read())
words = pickle.load(open('words.pkl','rb'))
classes = pickle.load(open('classes.pkl','rb'))
def clean_up_sentence(sentence):
# tokenize the pattern - split words into array
sentence_words = nltk.word_tokenize(sentence)
# stem each word - create short form for word
sentence_words = [lemmatizer.lemmatize(word.lower()) for word in

sentence_words]
return sentence_words
# return bag of words array: 0 or 1 for each word in the bag that exists in the sentence
def bow(sentence, words, show_details=True):
# tokenize the pattern
sentence_words = clean_up_sentence(sentence)
# bag of words - matrix of N words, vocabulary matrix
bag = [0]*len(words)
46
College Enquiry Bot
for s in sentence_words:
for i,w in enumerate(words):
if w == s:
# assign 1 if current word is in the vocabulary position
bag[i] = 1
if show_details:
print ("found in bag: %s" % w)
return(np.array(bag))
def predict_class(sentence, model):
# filter out predictions below a threshold
p = bow(sentence, words,show_details=False)
res = model.predict(np.array([p]))[0]
ERROR_THRESHOLD = 0.25
results = [[i,r] for i,r in enumerate(res) if r>ERROR_THRESHOLD]
# sort by strength of probability
results.sort(key=lambda x: x[1], reverse=True)
return_list = []
for r in results:
return_list.append({"intent": classes[r[0]], "probability": str(r[1])})
return return_list
def getResponse(ints, intents_json):
tag = ints[0]['intent']
list_of_intents = intents_json['intents']
47
College Enquiry Bot
for i in list_of_intents:
if(i['tag']== tag):
result = random.choice(i['responses'])
break
return result
def chatbot_response(msg):
ints = predict_class(msg, model)
res = getResponse(ints, intents)
return res
#Creating GUI with tkinter
import tkinter
from tkinter import *
def send():
msg = EntryBox.get("1.0",'end-1c').strip()
EntryBox.delete("0.0",END)
if msg != '':
ChatLog.config(state=NORMAL)
ChatLog.insert(END, "You: " + msg + '\n\n')
48
College Enquiry Bot
ChatLog.config(foreground="#442265", font=("Verdana", 12 ))
res = chatbot_response(msg)
ChatLog.insert(END, "Bot: " + res + '\n\n')
ChatLog.config(state=DISABLED)
ChatLog.yview(END)
base = Tk()
base.title("EduChat")
base.geometry("400x500")
base.resizable(width=FALSE, height=FALSE)
#Create Chat window
ChatLog = Text(base, bd=0, bg="white", height="8", width="50", font="Arial",)
ChatLog.config(state=DISABLED)
#Bind scrollbar to Chat window
scrollbar = Scrollbar(base, command=ChatLog.yview, cursor="heart")
ChatLog['yscrollcommand'] = scrollbar.set
#Create Button to send message
SendButton = Button(base, font=("Verdana",10,'bold'), text="Send", width="12",

height=5,
bd=0, bg="#25cdf7", activebackground="#3c9d9b",fg='#ffffff',
command= send )
#Create the box to enter message
49
College Enquiry Bot
EntryBox = Text(base, bd=0, bg="white",width="29", height="5", font="Arial")
#Place all components on the screen
scrollbar.place(x=376,y=6, height=386)
ChatLog.place(x=6,y=6, height=386, width=370)
EntryBox.place(x=128, y=401, height=90, width=265)
SendButton.place(x=6, y=401, height=90)
base.mainloop()
"intents":[
"tag":"greeting",
"patterns":[
"Hi there",
"How are you",
"Is anyone there?",
"Hey",
"Hola",
"Hello",
"Good day"
],
"responses":[
"Hello, thanks for asking",
"Good to see you again",
"Hi there, how can I help?"
50
College Enquiry Bot
],
"context":[
""
},
"tag":"goodbye",
"patterns":[
"Bye",
"See you later",
"Goodbye",
"Nice chatting to you, bye",
"Till next time"
],
"responses":[
"See you!",
"Have a nice day",
"Bye! Come back again soon."
],
"context":[
""
},
"tag":"thanks",
51
College Enquiry Bot
"patterns":[
"Thanks",
"Thank you",
"That's helpful",
"Awesome, thanks",
"Thanks for helping me"
],
"responses":[
"Happy to help!",
"Any time!",
"My pleasure"
],
"context":[
""
},
"tag":"noanswer",
"patterns":[
],
"responses":[
"Sorry, can't understand you",
"Please give me more info",
"Not sure I understand"
52
College Enquiry Bot
],
"context":[
""
},
"tag":"options",
"patterns":[
"How you could help me?",
"What you can do?",
"What help you provide?",
"How you can be helpful?",
"What support is offered"
],
"responses":[
"I am a college Enquiry bot, I'll help you to find top colleges"
],
"context":[
""
},
"tag": "Top_colleges",
"patterns": ["Can you suggest top engineering colleges in Bhopal?",
"Top 5 Engineering college of Bhopal?",
53
College Enquiry Bot
"Tell me about engineering colleges in Bhopal"],
"responses": ["Sure, here are the top 5 engineering colleges in Bhopal:\n1.

Lakshmi Narain College of Technology (LNCT)\n2. Maulana Azad National Institute
of Technology (MANIT)\n3. Technocrats Institute of Technology (TIT)\n4. IES
College of Technology (IES)\n5. Sagar Institute of Science and Technology, Bhopal."],
"context":[
""
},
"tag": "lnct_courses",
"patterns": ["Tell me about courses available at Lakshmi Narain College of

Technology (LNCT)",
"What courses does LNCT offer?",
"Can you give me information about LNCT courses?"],
"responses": ["Lakshmi Narain College of Technology (LNCT) offers various

courses including:\n1. B.Tech in Computer Science\n2. B.Tech in Mechanical
Engineering\n3. B.Tech in Civil Engineering\n4. B.Tech in Electronics and
Communication Engineering\n5. B.Tech in Electrical Engineering\n\nFor detailed
information, you can visit the official website of LNCT."],
"context":[
""
},
"tag": "lnct_campus",
"patterns": ["Tell me about the campus of Lakshmi Narain College of

Technology (LNCT)",
"What is the campus like at LNCT?",
54
College Enquiry Bot
"Can you give me information about LNCT campus?"],
"responses": ["The Lakshmi Narain College of Technology (LNCT) campus is

spread over a vast area and provides a conducive learning environment for students.
The campus features modern classrooms, well-equipped laboratories, a central library,
sports facilities, and a cafeteria. LNCT also has a lush green campus with gardens and
open spaces for students to relax and engage in extracurricular activities."],
"context":[
""
},
"tag": "manit_courses",
"patterns": ["Tell me about courses available at Maulana Azad National

Institute of Technology (MANIT)",
"What courses does MANIT offer?",
"Can you give me information about MANIT courses?"],
"responses": ["Maulana Azad National Institute of Technology (MANIT) offers

various undergraduate and postgraduate courses in engineering, including:\n1. B.Tech
in Computer Science\n2. B.Tech in Mechanical Engineering\n3. B.Tech in Civil
Engineering\n4. B.Tech in Electronics and Communication Engineering\n5. B.Tech in
Electrical Engineering\n\nFor detailed information, you can visit the official website of
MANIT."],
"context":[
""
},
"tag": "manit_campus",
"patterns": ["Tell me about the campus of Maulana Azad National Institute of

Technology (MANIT)",
55
College Enquiry Bot
"What is the campus like at MANIT?",
"Can you give me information about MANIT campus?"],
"responses": ["The Maulana Azad National Institute of Technology (MANIT)

campus is situated on a sprawling area and is known for its serene and vibrant
atmosphere. The campus boasts state-of-the-art infrastructure, advanced laboratories,
well-equipped classrooms, and recreational facilities. MANIT also has a central
library, sports complex, and hostels for students. The campus provides a conducive
environment for both academic and extracurricular activities."],
"context":[
""
56
College Enquiry Bot
Image of Project
Fig 1 – Interface
57
College Enquiry Bot
Fig 2- Enquiry Generated by Bot
58
College Enquiry Bot
ANNEXURE I
Impact On Society
59
College Enquiry Bot
ANNEXURE I
Impact On Society
The proposal of “ College Enquiry Chatbot” is very useful to our society. The
proposed system helps us to know the complete details about the college. In this we
can search information related to the top college and it displays Stanley college. In
this it displays information regarding departments. We can know about Director,
Principal and HOD of departments. It also displays about faculty, infrastructure and
facilities provided in that particular college. It understands the query posed by the
user and reacts accordingly. It shows the celebrations of that particular college. We
can also know the number of Phd’s, Doctrates, number of labs in that college. It also
displays the professional bodies associated with departments.
60
College Enquiry Bot
ANNEXURE II
ENVIROMENTAL AND
SUSTAINABILITY
61
College Enquiry Bot
ANNEXURE II
ENVIROMENTAL AND SUSTAINABILITY
The project College Enquiry Chatbot is not only environment friendly but also fulfils
long term requirements. This project is eco-friendly, does not produce much of e-
waste, as, it is a software product. This also provides more efficiency as it is easy to
add or remove information from the database thus saves a huge amount of money.
Since this is a software product so it’s one time investment. This application saves
the time of both students and teachers.
62
College Enquiry Bot
ANNEXURE-III
PRESENTATION SLIDES
63
College Enquiry Bot
ANNEXURE-III
PRESENTATION SLIDES
64
College Enquiry Bot
65
College Enquiry Bot
66
College Enquiry Bot
67
College Enquiry Bot
68
College Enquiry Bot
69

Merged Final 30

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Merged Final 30

Uploaded by

Copyright:

Available Formats

College Enquiry Bot

A Major Project – l Report

RAJIV GANDHI PROUDYOGIKI VISHWAVIDYALAYA, BHOPAL (M.P.)

Major Project - l Report

Payal Bharti (0176EC201017) Yash Awasthi (0176EC201030)

Khusboo Jaiswal (0176EC201009) Tanya Sharma (0176EC201025)

Under the supervision of

DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING

VISION OF THE DEPARTMENT

To become reputed in providing technical education in the field of electronics and

MISSION OF THE DEPARTMENT

1. To provide congenial academic environment and adopting innovative learning

3. To strengthen the department by collaborating with industry and research

4. To facilitate the students to work in interdisciplinary environment and enhance

PROGRAM EDUCATIONAL OUTCOME (PEO)

PROGRAM SPECIFIC OUTCOME (PSO)

PSO1: Analyze specific engineering problems relevant to Electronics &

PSO3: Inculcate the knowledge of Engineering and Management principles to meet

Under the supervision of

(Project Guide) (Project In-charge)

Dr. Abhinav Bhargava

Lakshmi Narain College of Technology Excellence, Bhopal (M.P.)

Payal Bharti (0176EC201017)

Khushboo Jaiswal (0176EC201009)

Tanya Sharma (0176EC201025)

We express our heart-felt thankfulness to Dr. Abhinav Bhargava, H.O.D. of

Payal Bharti (0176EC201017)

Yash Awasthi (0176EC201030)

Khushboo Jaiswal (0176EC201009)

Tanya Sharma (0176EC201025)

NLP - Natural Language Processing

CMD - Command Prompt

NLDK - Natural Language Toolkit

IDLE - Integrated Development and Learning Environment

IDE - Integrated Development Environment

Figure 1 - Flow Chart for Chatbot………………………………………….23

My name is Payal Bharti. I am pursuing Bachelor of Technology

My name is Yash Awasthi. I am pursuing Bachelor of Technology

My Name is Khusboo Jaiswal. I am pursuing my B.Tech in

My name is Tanya Sharma, I am pursuing Bachelor of Technology

increasingly use conversational AI techniques like natural language processing (NLP) to

As we all know chatbots square measure a really fashionable approach of

1.3 Objective of the project

Market Size & Growth

Market Size & Growth

2.1 Market Size

2.2 Future Growth

Another type of self-learning chatbot is a Generative-based chatbot, which is based

SOME IMPORTANTS PARTS:

3. Self-learning chatbots can be further divided into Retrieval-based and

Issues & Challenges

Issues & Challenges

No protection against hacking

Fake news and propaganda

Websites like linkbuildinghq.com provide detailed information and guidance on how

Technologies for Chatbot

Technologies for Chatbot

5.1 Artificial Intelligence -

Artificial intelligence, defined as “a system's ability to correctly interpret external

5.2 Elements of Artificial Intelligence (AI)

5.3 Natural Language Processing

Fig 1:-Flow Chart diagram for College Enquiry Chatbot

Fig 2:-Architecture of College Enquiry ChatBot

Software & Hardware Requirements