COLLEGE ENQUIRY CHATBOT

Project Report Submitted

In Partial Fulfillment of the Requirements For the Degree of

BACHELOR OF ENGINEERING IN

COMPUTER SCIENCE AND ENGINEERING

Submitted by

Humayun Sayeed (1604-19-733-117)

COMPUTER SCIENCE AND ENGINEERING DEPARTMENT

MUFFAKHAM JAH COLLEGE OF ENGINEERING &
TECHNOLOGY
(Affiliated to Osmania University)
Mount Pleasant, 8-2-249, Road No.3, Banjara Hills, Hyderabad-342022

i
ii
 DECLARATION

This is to certify that the work reported in the major project entitled “College

Enquiry Chatbot” is a record of the bonafide work done by us in the Department of

Computer Science and Engineering, Muffakham Jah College of Engineering and

Technology, Osmania University. The results embodied in this report are based on

the project work done entirely by us and not copied from any other source.

Humayun Sayeed (1604-19-733-117)

iii
 ACKNOWLEDGEMENT

Our hearts are filled with gratitude to the Almighty for empowering us with courage,
wisdom and strength to complete this project successfully. We give him all the glory,
honor and praise.

We thank our Parents for having sacrificed a lot in their lives to impart the best
education to us and make us promising professionals for tomorrow.

We would like to express our sincere gratitude and indebtedness to our project
supervisor Mrs. Manjusha Kalekuri for her valuable suggestions and interest
throughout the course of this project.

We are happy to express our profound sense of gratitude and indebtedness to Prof.
Dr Syed Shabbeer Ahmed, Head of the Computer Science and Engineering
Department, for his valuable and intellectual suggestions apart from educating
guidance, constant encouragement right throughout our work and making us
successful.

We are pleased to acknowledge our indebtedness to all those who devoted themselves
directly or indirectly to make this project work a total success.

HUMAYUN SAYEED

iv
 Abstract

With the increasing demand for instant answers and convenient communication, chatbots have
become a popular solution for many industries. The education sector is no exception, with many
colleges and universities implementing chatbots to help students and prospective students find
information quickly and easily.

This project aims to develop a college enquiry chatbot that can answer common questions about a
college, such as admissions information, academic programs, campus life, financial aid, and
student support services. The chatbot will provide a personalized experience for users, allowing
them to interact with the college in a way that is natural and intuitive.

To achieve this, the chatbot will be designed to be user-friendly, with a text-based or voice-based
interface that uses natural language processing to understand user input. The chatbot will have
access to a knowledge base of pre-written responses and will be able to generate responses on the
fly as needed. The chatbot will also be able to interpret user intent, using machine learning
algorithms to provide more accurate and relevant responses over time.

The chatbot will be integrated with the college's website and other platforms to provide seamless
access for users. This will ensure that users can access the chatbot from any device, at any time,
without having to navigate away from the college's website or social media channels. The chatbot
will also be able to track user interactions and provide insights into user behavior, allowing the
college to optimize its chatbot strategy over time.

In summary, the college enquiry chatbot project aims to create a personalized and user-friendly
experience for students and prospective students looking for information about a college. By
leveraging the latest advancements in natural language processing and machine learning, the
chatbot will be able to provide accurate and relevant information, while also providing valuable
insights into user behavior and preferences.

v
 CONTENTS
Chapter Page No
TITLE
CERTIFICATE I
DECLARATION II
ACKNOWLEDGEMENT III
ABSTRACT IV
LIST OF FIGURES VII
1. INTRODUCTION 1
1.1. Overview 1
1.2. Problem Statement 2
1.3. Motivation 3
1.4. Objective 3

2. LITERATURE SURVEY 5
2.1. Disadvantages of Chatbot
2.1.1 Limited Conceptual Understanding 5
2.1.2 Dependency on Accurate and up-to-date Information 5
2.1.3 Security and Privacy Concerns 5
2.1.4 Technical Limitations and Technical Support 5
2.2. Existing Approaches of Chatbot
2.2.1 ELIZA: a very basic Rogerian Psychotherapist Chatbot 6
2.2.2 Cleverbot 7
2.2.3 Problems with Cleverbot 7
2.2.4 Chatbot Design Techniques in Speech-Based Conversational Agents 8
2.2.5 Designing Chatbots for E-Commerce 8
2.2.6 Intelligent Conversational Agents in Education 8
2.2.7 Towards Conversational Agents in Education 8
2.2.8 Design and Evaluation of a Campus Chatbot to Improve Student Engagement 8
2.2.9 Conversational Agents in Academic Advising 9

3. SYSTEM ANALYSIS 10
3.1. Existing System
3.1.1 Disadvantages of Existing System 10
3.2. Proposed System
3.2.1 Advantages of Proposed System 10
3.3. Feasibility Study

vi
 3.3.1 Technical Feasibility 11
3.3.2 Operational Feasibility 11
3.3.3 Economic Feasibility 12
3.4. Software and Platforms used
3.4.1 HTML 12
3.4.2 CSS 12
3.4.3 JavaScript 13
3.4.4 Python 13
3.4.5 Models used in Project 13

4. SYSTEM DESIGN 15
4.1. System Architecture 15
4.2. UML Diagrams
4..2.1 Use Case Diagram 15
4.2.2 Sequence Diagram 16
4.2.3 Class Diagram 17
4.2.4 Activity Diagram 17
4.3. Methodology
4.3.1 Requirements Gathering Stage 18
4.3.2 Analysis Stage 19
4.3.3 Designing Stage 20
4.3.4 Development Stage 21
4.3.5 Integration and Test Stage 22
4.3.6 Installation and Acceptance Stage 23
4.3.7 Maintenance 23

5. IMPLEMENTATION 24
5.1. Process to Connect to the Server
5.1.1 Requirements 24
5.1.2 Running the Server 24
5.1.3 Running the Web Application 25
5.2 Code for quick Summary 25

6 TESTING 30
6.1 System Testing 30
6.2 Module Testing 30
6.3 Integration Testing 30
6.4 Acceptance Testing 31

7 SCREENSHOTS 32

vii
 7.1 First Look 32
7.2 Friendly Conversation 32
7.3 General Queries 33

8 CONCLUSION 34

9 FUTURE ENHANCEMENT 35

10 REFERENCES 36

viii
 LIST OF FIGURES
Figure No. Description Page No.

Fig 2.2.1 ELIZA Conversation with a Patient 6

Fig 4.1 Architecture Diagram 15
Fig 4.2.1 Use Case Diagram 16
Fig 4.2.2 Sequence Diagram 16
Fig 4.2.3 Class Diagram 17
Fig 4.2.4 Activity Diagram 17
Fig 4.3.1 Requirements Gathering Stage 19
Fig 4.3.2 Analysis Stage 20
Fig 4.3.3 Designing Stage 21
Fig 4.3.4 Coding Stage 22
Fig 4.3.5 Integration and Testing Stage 22
Fig 4.3.6 Installation 23
Fig 5.1.1 Packages to Install 24
Fig 5.1.2 Running the Server 24
Fig 5.2 Code for quick Summary 25
Fig 7.1 First Look 32
Fig 7.2 Friendly Conversation 32
Fig 7.3 General Queries 33

ix
1. INTRODUCTION
1.1 OVERVIEW
In an era of digital advancements, chatbots have emerged as valuable tools for enhancing
communication and delivering instant information. Colleges and universities recognize the need
to provide quick and accurate responses to queries from students, parents, and prospective
applicants. To address this demand, this project focuses on the development of a college enquiry
chatbot—a conversational agent capable of answering a wide range of questions related to
admissions, academic programs, campus life, financial aid, and student support services.

The primary objective of this project is to create a user-friendly chatbot with an intuitive interface
that accommodates both text-based and voice-based interactions. Leveraging natural language
processing capabilities, the chatbot will comprehend and interpret user input, enabling a seamless
conversational experience. By leveraging a comprehensive knowledge base, the chatbot will
provide prompt and precise responses to common enquiries while also generating dynamic
responses when confronted with unique or specific queries.

The chatbot's scope encompasses various aspects of college life, starting with admissions-related
information. Users will gain insights into admission requirements, application procedures, and
pertinent deadlines. Additionally, the chatbot will furnish details about the college's diverse
academic programs, including available majors, minors, and course requirements, helping users
make informed decisions about their educational pursuits.

Beyond academics, the chatbot will also serve as a gateway to understanding campus life. It will
offer information on student organizations, events, and facilities, facilitating an enriched college
experience. Additionally, the chatbot will cater to queries regarding financial aid, shedding light
on available options and guiding users through the application process.

Throughout the development process, rigorous testing and continuous user feedback will be
integral to fine-tuning the chatbot. Beta testing with a diverse sample of users will provide valuable
insights into the chatbot's performance and usability.

By implementing the college enquiry chatbot, colleges and universities can streamline their
communication channels and improve their responsiveness to inquiries. This project endeavors to
leverage the power of chatbot technology to offer a convenient and accessible means of accessing
information about a college. The ultimate goal is to enhance the user experience and foster
effective communication between educational institutions and their stakeholder.

1
1.2 PROBLEM STATEMENT

Colleges and universities face the challenge of efficiently and effectively providing accurate
information to students, parents, and prospective applicants who have a multitude of questions
regarding admissions, academic programs, campus life, financial aid, and student support services.
The traditional methods of information dissemination, such as websites or manual inquiry
handling, often result in delayed responses, limited availability, and overwhelming staff
workloads. As a result, there is a need to develop a solution that can address these issues and
improve the overall experience for individuals seeking information about the college.

The problem at hand is the absence of a comprehensive and readily accessible platform that can
cater to the diverse queries of college-related topics. Without a dedicated system in place,
individuals may struggle to find accurate and up-to-date information, leading to frustration,
confusion, and potential disengagement with the college. Additionally, the lack of a streamlined
communication channel hinders colleges' ability to efficiently address inquiries, resulting in
wasted resources and missed opportunities to engage with prospective students.

In light of these challenges, the development of a college enquiry chatbot emerges as a viable
solution. By leveraging advancements in natural language processing and artificial intelligence, a
chatbot can serve as a virtual assistant, capable of understanding user queries, accessing relevant
information, and delivering prompt, accurate, and personalized responses. Such a chatbot would
alleviate the burden on staff, improve response times, enhance accessibility, and ensure consistent
and reliable information dissemination to users.

Therefore, the primary objective of this project is to develop an intelligent and user-friendly
college enquiry chatbot that addresses the limitations of traditional information channels. The
chatbot will serve as a single point of contact for users, providing comprehensive and up-to-date
information on admissions, academic programs, campus life, financial aid, and student support
services. Through its implementation, the aim is to enhance the user experience, streamline
communication, and foster efficient engagement between colleges and their stakeholders.

2
1.3 MOTIVATION

The development of a college enquiry chatbot is motivated by several factors that aim to address
the existing challenges and improve the overall experience for students, parents, and prospective
applicants.

Firstly, the motivation lies in enhancing accessibility. Traditional methods of accessing

information about colleges, such as navigating websites or relying on manual inquiry handling,
may pose barriers to accessibility for individuals with limited technological literacy or physical
abilities. By implementing a chatbot, colleges can provide a user-friendly and inclusive platform
that allows individuals to access information easily and conveniently.

Another key motivation is to provide instant and timely responses to user queries. Waiting for
responses to inquiries can be frustrating and time-consuming, especially during peak periods. With
a chatbot, colleges can deliver prompt responses, eliminating the need for individuals to wait for
staff availability or navigate complex websites. This enhances the user experience and allows for
quick access to the information they seek.

1.4 OBJECTIVE

The main objective of this project is to develop a college enquiry chatbot that offers a user-friendly
and comprehensive platform for accessing information related to colleges and universities. The
chatbot will leverage natural language processing and artificial intelligence to deliver accurate and
personalized responses to users' queries regarding admissions, academic programs, campus life,
financial aid, and student support services. The following are the specific objectives of the project:

 To design and develop a user-friendly chatbot interface that accommodates both text-based
and voice-based interactions.

 To implement natural language processing capabilities to enable the chatbot to comprehend

and interpret user input accurately and efficiently.

 To build a comprehensive knowledge base that encompasses various aspects of college

life, including admissions-related information, academic programs, campus life, financial
aid, and student support services.

 To ensure the accuracy and relevance of information by integrating the chatbot with the
college's website and other platforms, thereby accessing up-to-date information.

3
  To provide prompt and precise responses to common enquiries while also generating
dynamic responses when confronted with unique or specific queries.

 To enhance the chatbot's efficacy through rigorous testing and continuous user feedback,
leveraging beta testing with a diverse sample of users and ongoing monitoring and analysis
of user interactions.

 To streamline communication channels and improve responsiveness to inquiries, leading

to more efficient and effective engagement with students, parents, and prospective
applicants.

 To foster a positive user experience, providing convenient and accessible means of

accessing information about a college, and enhancing the institution's reputation as a tech-
savvy and forward-thinking educational institution.

Overall, the objective of this project is to develop a robust and intelligent college enquiry chatbot
that can serve as a virtual assistant, delivering accurate and personalized responses to user queries
and enhancing communication and engagement between colleges and their stakeholders.

4
2. LITERATURE SURVEY

2.1 DISADVANTAGES OF CHATBOT

2.1.1 Limited Conceptual Understanding

Chatbots primarily rely on natural language processing algorithms to interpret and respond to user
queries. However, they may struggle to understand complex or nuanced queries that require deep
contextual understanding. This limitation can result in inaccurate or irrelevant responses, leading
to user frustration and dissatisfaction.

2.1.2 Dependency on Accurate and up-to-date Information

To provide accurate responses, a college enquiry chatbot relies on a comprehensive and up-to-date
knowledge base. If the information within the chatbot's database is incomplete, outdated, or
incorrect, it can result in misleading or erroneous responses. Maintaining and updating the
knowledge base requires continuous effort and resources.

2.1.3 Security and Privacy Concerns

Chatbots handle sensitive user information, such as personal details and academic records. It is
crucial to ensure robust security measures are in place to protect user data from unauthorized
access or breaches. Additionally, clear privacy policies should be communicated to users to
address any concerns they may have about data collection and usage.

2.1.4 Technical Limitations and Technical Support

Chatbots may encounter technical issues or downtime, which can disrupt user interactions and
hinder the information-seeking process. Additionally, users may require technical support or
assistance in navigating the chatbot interface or understanding its capabilities. Providing adequate
technical support and ensuring system stability is essential for a positive user experience.

2.2 EXISTING APPROACHES OF CHATBOT

2.2.1 ELIZA: a very basic Rogerian psychotherapist chatbot

ELIZA is an early natural language processing computer created from 1964 to 1966 at MIT by
joseph Weizenbaum Created to explore communication between humans and machines, ELIZA
simulated conversation by using pattern matching and substitution methodology that gave users
an illusion of understanding on the part of the program, but had no representation that could be

5
considered really understanding what was being said by either party. Whereas the ELIZA program
itself was written (originally) in MAD-SLIP, the pattern matching directives that contained most
of its language capability were provided in separate "scripts", represented in a lisp-like
representation.
ELIZA makes the use of primitive natural language processing. It operates on user’s responses to
scripts, in which the most famous was the DOCTOR, a simulation of psychotherapist. It provided
a basic human-like interaction with almost no information about human thought or emotion. It was
written at MIT between 1964 and 1966.

A simple conversation example:

User: My head hurts.
DOCTOR: Why do you say your head hurts?
User: My mother hates me.
DOCTOR: Who else in the family hates you?
The creator of ELIZA never expected to create a fully working model consisting of NLP, it was
rather a simple toy. What DOCTOR actually did was that it used a lot of data from the statements
from the humans in order to compose the responses by using simple templates. It actually used an
if-else pattern of using a certain template for a certain trigger. It was first implemented on SLIP
language (an extension to FORTRAN).

Figure 2.2.1: ELIZA conversation a patient

6
2.2.2 Cleverbot

Cleverbot is also a web application which converses with humans and uses artificial intelligence
algorithms. It was created be British scientist Rollo Carpenter. The difference between Eliza and
Cleverbot is that its unique algorithm learns from humans and remembers words within its AI.

There is also a point to note that the bot’s responses are programmed. It learns from human input;
The UI of my project is somewhat similar to Cleverbot where the human types into the box below
the logo of Cleverbot and finds all the matching keywords or phrases matching the input. It
responds to the input of the human by searching its saved conversations. It also responds to the
particular input by finding how a human responded to that input when it was asked, but that
happens in part or in full.

Because of its complex algorithm structure, it is constantly learning. It’s data size is also
increasing. Due to this it appears to display a degree of “intelligence”. It’s software updates are
constantly checked and in 2014 it was upgraded to use GPU serving techniques.

Cleverbot also participated in a Turing Test in 2011 organized by IIT Guwahati. Cleverbot was
judged to be 59.3% human. The software which participated in the test had to process 1 or 2
simultaneous requests, but it was noted that Cleverbot handled 80000 people at once.

2.2.3 Problems with Cleverbot

Despite the complex algorithm of Cleverbot some problems were noted:

It does not take anyone too many sentences for it to fail a Turing test, and figure out it was
saying things that had been said to it many times.
It can't reference back than a single sentence. It has no core identity.
It often answers a "why" question with a "where" answer.

The reason for this is that the CleverBot stores the responses that people give to it in return for
that it says. It is also noted that it simply says the answers to someone else and records their
answer.

The condition for a machine to hold a proper conversation with anyone is that it would need to
design a system that "understands" what its hearing and saying properly so that it can hold a co-
operative conversation. Making that happen is hard. The greatest obstacle to it is unraveling the
jumbled-up mess of complexity that words and ideas are made up of.

7
2.2.4 Chatbot Design Techniques in Speech-Based Conversational Agents
This comprehensive survey explores various design techniques and technologies used in speech-
based conversational agents, including chatbots. It delves into natural language processing (NLP),
dialogue management, user experience, and different types of chatbot architectures. The paper
provides valuable insights into the technical aspects of developing a college enquiry chatbot,
emphasizing the importance of robust NLP algorithms and effective dialogue management
strategies.

2.2.5 Designing Chatbots for E-Commerce

While focusing on e-commerce, this literature review offers insights into chatbot design principles
and techniques applicable to a college enquiry chatbot. It discusses user interaction patterns,
personalization strategies, trust-building mechanisms, and customer satisfaction evaluation. The
review emphasizes the need for context-awareness and intelligent dialogue generation to enhance
user engagement and conversion rates, which are valuable considerations for developing an
effective college enquiry chatbot.

2.2.6 Intelligent Conversational Agents in Education

This systematic review investigates the effectiveness and usability of intelligent conversational
agents, including chatbots, in educational contexts. It examines the impact of chatbots on student
learning outcomes, engagement, and satisfaction. The review identifies the key factors
contributing to successful chatbot implementation, such as adaptive feedback, personalized
recommendations, and adaptive learning support, which can be valuable considerations for a
college enquiry chatbot.

2.2.7 Towards Conversational Agents in Education

This review explores the current state-of-the-art, challenges, and future trends in developing
conversational agents for educational environments. It covers topics such as natural language
understanding, dialogue management, personalization, and pedagogical considerations. The
review emphasizes the need for intelligent and adaptive conversational agents that can cater to
individual learning styles and preferences, which can inform the design and development of a
college enquiry chatbot with educational functionality.

2.2.8 Design and Evaluation of a Campus Chatbot to Improve Student Engagement

This research paper presents the design and evaluation of a campus chatbot implemented in a
university setting. It discusses the features, functionality, and user feedback on the chatbot's
performance. The study emphasizes the importance of user-centered design, responsiveness,
accurate information delivery, and proactive engagement strategies in improving student
engagement and satisfaction. The findings provide practical insights for designing an effective
college enquiry chatbot.

8
2.2.9 Conversational Agents in Academic Advising
This review explores the applications of conversational agents, including chatbots, in academic
advising. It discusses the benefits and challenges of using chatbots to support advising processes,
such as course selection, degree planning, and career guidance. The review highlights the potential
for chatbots to enhance advising efficiency, improve student.

9
3. SYSTEM ANALYSIS

3.1 EXISTING SYSTEM

In the earlier days students had to visit the college to enquire about details like courses, fee
structure, admission process as well as long process for both parents as well as students. Now a
days there are many changes occurred in the education system with help of advanced technology.
Everything is happening over the internet without any trouble. In those days for enquiring about
courses we must visit the college, but as the days are passing away its completely changing.
Collecting the course details, fee structure manually will be a big procedure and it also needs a
manpower. For reducing that manpower and avoid such difficulties and time consuming many
devices or systems were emerged day by day

3.1.1 Disadvantages of Existing System

More time consuming
Delay in response
In the existing system we have only limited number of predefined queries.
It cannot understand specific problems and cannot perform task for the client.

3.2 PROPOSED SYSTEM

The objective of this application is to propose a chatbot enquiry for students to communicate with
the colleges. By using artificial intelligence, the system answers the queries asked by the students.
The chatbot mainly consists of core and interface, where it mainly accesses the core in Natural
language processing technologies are here used for parsing, tokenizing, stemming and filtering the
content of the complaint.
To further develop the proposed system- college chatbot we can use any programming language
that supports object-oriented concept, but we use python as it is the most happening language and
user friendly. Software we use python compiler. we develop the artificial neural network algorithm
in the python language on python compiler. And further integrate it with database using python
compiler...

3.2.1 Advantages of Proposed System

• Faster processing when compared to existing one.
• It takes less time to respond.
• It gives response in the form of queries rather than options.
• It provides 24/7 service

10
3.3 Feasibility Study
Preliminary investigation examines project feasibility; the likelihood the system will be useful to
the organization. The main objective of the feasibility study is to test the Technical, Operational
and Economical feasibility for adding new modules and debugging old running system. All
systems are feasible if they are given unlimited resources and infinite time. There are aspects in
the feasibility study portion of the preliminary investigation:

 Technical Feasibility
 Operation Feasibility
 Economic Feasibility

3.3.1 Technical Feasibility

The technical issue usually raised during the feasibility stage of the investigation includes the
following:
 Does the necessary technology exist to do what is suggested?
 Do the proposed equipments have the technical capacity to hold the data required to use
the new system?
 Will the proposed system provide adequate response to inquiries, regardless of the number
or location of users?
 Can the system be upgraded if developed?
 Are there technical guarantees of accuracy, reliability, ease of access and data security?

3.3.2 Operational Feasibility

User-friendly
Customer will use the forms for their various transactions i.e. for adding new routes, viewing the
routes details. Also the Customer wants the reports to view the various transactions based on the
constraints. These forms and reports are generated as user-friendly to the Client.
Reliability
The package wills pick-up current transactions on line. Regarding the old transactions, User will
enter them in to the system.
Security
The web server and database server should be protected from hacking, virus etc
Portability
The application will be developed using standard open source software (Except Oracle) like Java,
tomcat web server, Internet Explorer Browser etc these software will work both on Windows and
Linux o/s. Hence portability problems will not arise.
Availability
This software will be available always.

11
Maintainability
The system uses the 2-tier architecture. The 1st tier is the GUI, which is said to be front-end and
the 2nd tier is the database, which uses My-SQL, which is the back-end.
The front-end can be run on different systems (clients). The database will be running at the server.
Users access these forms by using the user-ids and the passwords.

3.3.3 Economic Feasibility

The computerized system takes care of the present existing system’s data flow and procedures
completely and should generate all the reports of the manual system besides a host of other
management reports.
It should be built as a web-based application with separate web server and database server. This is
required as the activities are spread throughout the organization customer wants a centralized
database. Further some of the linked transactions take place in different locations.

3.4 SOFTWARE AND PLATFORMS USED

3.4.1 HTML
The HyperText Markup Language or HTML is the standard markup language for documents
designed to be displayed in a web browser. Web browsers receive HTML documents from a web
server or from local storage and render the documents into multimedia web pages.

3.4.2 CSS
Cascading Style Sheets (CSS) is a style sheet language used for describing the presentation of a
document written in a markup language such as HTML or XML (including XML dialects such
as SVG, MathML or XHTML). CSS is designed to enable the separation of content and
presentation, including layout, colors, and fonts.

12
3.4.3 JavaScript
JavaScript is a scripting or programming language that allows you to implement complex features
on web pages — every time a web page does more than just sit there and display static information
for you to look at — displaying timely content updates, interactive maps, animated 2D/3D
graphics, scrolling video jukeboxes, etc. — you can bet that JavaScript is probably involved.

3.4.4 Python
Python is an interpreted, object-oriented, high-level programming language with dynamic
semantics. Its high-level built in data structures, combined with dynamic typing and dynamic
binding, make it very attractive for Rapid Application Development, as well as for use as a
scripting or glue language to connect existing components together.

3.4.5 Models used in Project

TensorFlow
TensorFlow is a free and open-source software library for dataflow and differentiable
programming across a range of tasks. It is a symbolic math library, and is also used for machine
learning applications such as neural networks. It is used for both research and production at
Google.
TensorFlow was developed by the Google Brain team for internal Google use. It was released
under the Apache 2.0 open-source license on November 9, 2015.

NumPy
NumPy is a general-purpose array-processing package. It provides a high-performance
multidimensional array object, and tools for working with these arrays.
It is the fundamental package for scientific computing with Python. It contains various features
including these important ones:
 A powerful N-dimensional array object
 Sophisticated (broadcasting) functions
 Tools for integrating C/C++ and Fortran code

13
  Useful linear algebra, Fourier transform, and random number capabilities
Besides its obvious scientific uses, NumPy can also be used as an efficient multi-dimensional
container of generic data. Arbitrary data-types can be defined using NumPy which allows NumPy
to seamlessly and speedily integrate with a wide variety of databases.

Pandas
Pandas is an open-source Python Library providing high-performance data manipulation and
analysis tool using its powerful data structures. Python was majorly used for data munging and
preparation. It had very little contribution towards data analysis. Pandas solved this problem. Using
Pandas, we can accomplish five typical steps in the processing and analysis of data, regardless of
the origin of data load, prepare, manipulate, model, and analyze. Python with Pandas is used in a
wide range of fields including academic and commercial domains including finance, economics,
Statistics, analytics, etc.

Matplotlib
Matplotlib is a Python 2D plotting library which produces publication quality figures in a variety
of hardcopy formats and interactive environments across platforms. Matplotlib can be used in
Python scripts, the Python and IPython shells, the Jupyter Notebook, web application servers, and
four graphical user interface toolkits. Matplotlib tries to make easy things easy and hard things
possible. You can generate plots, histograms, power spectra, bar charts, error charts, scatter plots,
etc., with just a few lines of code. For examples, see the same plots and thumbnail gallery.
For simple plotting the pyplot module provides a MATLAB-like interface, particularly when
combined with IPython. For the power user, you have full control of line styles, font properties,
axes properties, etc, via an object oriented interface or via a set of functions familiar to MATLAB
users.

Scikit – learn
Scikit-learn provides a range of supervised and unsupervised learning algorithms via a consistent
interface in Python. It is licensed under a permissive simplified BSD license and is distributed
under many Linux distributions, encouraging academic and commercial use.

14
 4. SYSTEM DESIGN

4.1 SYSTEM ARCHITECTURE

The purpose of the design phase is to arrange an answer of the matter such as by the necessity
document. This part is that the opening moves in moving the matter domain to the answer
domain. The design phase satisfies the requirements of the system. The design of a system is
probably the foremost crucial issue warm heartedness the standard of the software package. It’s a
serious impact on the later part, notably testing and maintenance.

Figure 4.1: Architecture diagram

4.2 UML DIAGRAMS

The Unified Modeling Language allows the software engineer to express an analysis model using
the modeling notation that is governed by a set of syntactic semantic and pragmatic rules.

4.2.1 USE CASE DIAGRAM

A use case diagram at its simplest is a representation of a user's interaction with the system and
depicting the specifications of a use case. A use case diagram can portray the different types of
users of a system and the various ways that they interact with the system. This type of diagram is
typically used in conjunction with the textual use case and will often be accompanied by other
types of diagrams as well.

15
 Figure 4.2.1: Use Case Diagram

4.2.2 SEQUENCEDIAGRAM

A sequence diagram is a kind of interaction diagram that shows how processes operate with one
another and in what order. It is a construct of a Message Sequence Chart. A sequence diagram
shows object interactions arranged in time sequence. It depicts the objects and classes involved in
the scenario and the sequence of messages exchanged between the objects needed to carry out the
functionality of the scenario. Sequence diagrams are typically associated with use case realizations
in the Logical View of the system under development. Sequence diagrams are sometimes called
event diagrams, event scenarios, and timing diagrams.

Figure 4.2.2: Sequence diagram

16
4.2.3 CLASS DIAGRAM

In software engineering, a class diagram in the Unified Modeling Language (UML) is a type of
static structure diagram that describes the structure of a system by showing the system's classes,
their attributes, operations (or methods), and the relationships among the classes. It explains
which class contains information.

Figure 4.2.3: Class Diagram

4.2.4 ACTIVITY DIAGRAM

Activity diagrams are graphical representations of workflows of stepwise activities and actions
with support for choice, iteration and concurrency. In the Unified Modeling Language, activity
diagrams can be used to describe the business and operational step-by-step workflows of
components in a system. An activity diagram shows the overall flow of control.

Figure 4.2.4: Activity Diagram

17
4.3 METHODOLOGY

4.3.1 Requirements Gathering Stage

The requirements gathering process takes as its input the goals identified in the high-level
requirements section of the project plan. Each goal will be refined into a set of one or more
requirements. These requirements define the major functions of the intended application, define
operational data areas and reference data areas, and define the initial data entities. Major functions
include critical processes to be managed, as well as mission critical inputs, outputs and reports. A
user class hierarchy is developed and associated with these major functions, data areas, and data
entities. Each of these definitions is termed a Requirement. Requirements are identified by unique
requirement identifiers and, at minimum, contain a requirement title and textual description.

Figure 4.3.1: Requirements Gathering stage

These requirements are fully described in the primary deliverables for this stage: the Requirements
Document and the Requirements Traceability Matrix (RTM). The requirements document contains
complete descriptions of each requirement, including diagrams and references to external
documents as necessary. Note that detailed listings of database tables and fields are not included
in the requirements document.
The title of each requirement is also placed into the first version of the RTM, along with the title
of each goal from the project plan. The purpose of the RTM is to show that the product components
developed during each stage of the software development lifecycle are formally connected to the
components developed in prior stages.

4.3.2 Analysis Stage

The planning stage establishes a bird's eye view of the intended software product, and uses this to
establish the basic project structure, evaluate feasibility and risks associated with the project, and

18
describe appropriate management and technical approaches.

Figure 4.3.2: Analysis stage

The most critical section of the project plan is a listing of high-level product requirements, also
referred to as goals. All of the software product requirements to be developed during the
requirements definition stage flow from one or more of these goals. The minimum information for
each goal consists of a title and textual description, although additional information and references
to external documents may be included. The outputs of the project planning stage are the
configuration management plan, the quality assurance plan, and the project plan and schedule, with
a detailed listing of scheduled activities for the upcoming Requirements stage, and high level
estimates of effort for the out stages.

4.3.3 Designing Stage

The design stage takes as its initial input the requirements identified in the approved requirements
document. For each requirement, a set of one or more design elements will be produced as a result
of interviews, workshops, and/or prototype efforts. Design elements describe the desired software
features in detail, and generally include functional hierarchy diagrams, screen layout diagrams,
tables of business rules, business process diagrams, pseudo code, and a complete entity-
relationship diagram with a full data dictionary. These design elements are intended to describe
the software in sufficient detail that skilled programmers may develop the software with minimal
additional input.

19
 Figure 4.3.3: Designing stage

When the design document is finalized and accepted, the RTM is updated to show that each design
element is formally associated with a specific requirement. The outputs of the design stage are the
design document, an updated RTM, and an updated project plan.

4.3.4 Development (Coding) Stage

The development stage takes as its primary input the design elements described in the approved
design document. For each design element, a set of one or more software artifacts will be produced.
Software artifacts include but are not limited to menus, dialogs, data management forms, data
reporting formats, and specialized procedures and functions. Appropriate test cases will be
developed for each set of functionally related software artifacts, and an online help system will be
developed to guide users in their interactions with the software.

20
 Figure 4.3.4: Coding stage

4.3.5 Integration & Test Stage

During the integration and test stage, the software artifacts, online help, and test data are migrated
from the development environment to a separate test environment. During this stage, reference
data is finalized for production use and production users are identified and linked to their
appropriate roles. The final reference data (or links to reference data source files) and production
user list are compiled into the Production Initiation Plan.

21
 Figure 4.3.5: Integration and Testing Stage

4.3.6 Installation & Acceptance Test

During the installation and acceptance stage, the software artifacts, online help, and initial
production data are loaded onto the production server. At this point, all test cases are run to verify
the correctness and completeness of the software. Successful execution of the test suite is a
prerequisite to acceptance of the software by the customer.
After customer personnel have verified that the initial production data load is correct and the test
suite has been executed with satisfactory results, the customer formally accepts the delivery of the
software.

Figure 4.3.6: Installation

4.3.7 Maintenance
Outer rectangle represents maintenance of a project, Maintenance team will start with requirement
study, understanding of documentation later employees will be assigned work and they will
undergo training on that assigned category.

22
5. IMPLEMENTATION

5.1 PROCESS TO CONNECT TO THE SERVER

5.1.1 Requirements
After the installation of python, install the required packages from the terminal using the syntax
pip install <Package name>
The required packages and models are:

Figure 5.1.1: Packages to install

5.1.2 Running the Server

To run the server, first open the terminal where you have to type the command in order for it to
generate a local server
py main.py runserver
By typing this command in the terminal it generates a IP Address like shown in figure 5.1.2

Figure 5.1.2: Running the server

23
5.1.3 Running the web application
After it generates an IP Address open it in your desktop’s web browser. You will be at the College
Enquiry Chatbot Webpage where you can ask all of your queries in the text box given on the
screen. It gets updated regularly for better performance.

5.2 CODE FOR QUICK SUMMARY

1)

Template of the web-app

24
2)

Javascript

3)

25
Model Training

26
4)

Creating web app

27
5)

Dataset

28
6. Testing

Testing is the process where the test data is prepared and is used for testing the modules
individually and later the validation given for the fields. Then the system testing takes place which
makes sure that all components of the system property functions as a unit. The test data should be
chosen such that it passed through all possible condition. The following is the description of the
testing strategies, which were carried out during the testing period.

6.1 SYSTEM TESTING

Testing has become an integral part of any system or project especially in the field of information
technology. The importance of testing is a method of justifying, if one is ready to move further,
be it to be check if one is capable to with stand the rigors of a particular situation cannot be
underplayed and that is why testing before development is so critical. When the software is
developed before it is given to user to user the software must be tested whether it is solving the
purpose for which it is developed. This testing involves various types through which one can
ensure the software is reliable. The program was tested logically and pattern of execution of the
program for a set of data are repeated. Thus, the code was exhaustively checked for all possible
correct data and the outcomes were also checked.

6.2 MODULE TESTING

To locate errors, each module is tested individually. This enables us to detect error and correct it
without affecting any other modules. Whenever the program is not satisfying the required function,
it must be corrected to get the required result. Thus all the modules are individually tested from
bottom up starting with the smallest and lowest modules and proceeding to the next level. Each
module in the system is tested separately. For example the job classification module is tested
separately. This module is tested with different job and its approximate execution time and the
result of the test is compared with the results that are prepared manually. Each module in the
system is tested separately. In this system the resource classification and job scheduling modules
are tested separately and their corresponding results are obtained which reduces the process
waiting time.

6.3 INTEGRATION TESTING

After the module testing, the integration testing is applied. When linking the modules there may
be chance for errors to occur, these errors are corrected by using this testing. In this system all
modules are connected and tested. The testing results are very correct. Thus the mapping of jobs
with resources is done correctly by the system.

29
6.4 ACCEPTANCE TESTING
When that user fined no major problems with its accuracy, the system passers through a final
acceptance test. This test confirms that the system needs the original goals, objectives and
requirements established during analysis without actual execution which elimination wastage of
time and money acceptance tests on the shoulders of users and management, it is finally acceptable
and ready for the operation.

30
7. SCREENSHORTS

7.1 FIRST LOOK

Figure 7.1: First look

7.2 FRIENDLY CONVERSATION

Figure 7.2: Friendly conversation

31
7.3 GENERAL QUERIES

Figure 7.3: General queries

32
8. CONCLUSION

What we can conclude from the above situation and usage is that greater the database and more
the models and use cases, the better is the reaction produced for the client. In any case, the issues
are many. For adjusting more uses, the scope changes from the investigation of AI to language
examine.

We additionally need to recollect that we are taking a shot at a cell phone. The NLP is very broad
and maybe utilizing them on a server and isolating this application into customer and server side
application can fathom the speed issue as when we do that the speed of the program won’t be
restricted to the equipment.

We live in a time of intelligent technology. Our watches let us know the time, however they
likewise remind us to work out. Our telephones prescribe the best places to eat, and our PCs foresee
our inclinations, helping us to do our everyday work all the more productively.

In conclusion, our implementation of the college enquiry chatbot has demonstrated its potential to
streamline the information retrieval process, improve user engagement, and provide efficient
support to college-related queries. The successful deployment and positive feedback received from
users underscore the value and impact of our chatbot in the educational domain. We are confident
that our college enquiry chatbot lays the foundation for future advancements in conversational AI
and stands as a testament to the power of technology in enhancing educational services.

33
9. FUTURE ENHANCEMENT

 Regularly update the knowledge base to reflect any changes or additions to college policies,
programs, or resources.
 Enable the chatbot to send proactive notifications or reminders to users regarding important
dates, deadlines, or announcements.
 Implement personalized recommendation features that suggest relevant courses, events, or
resources based on the user's interests, academic program, or past interactions with the
chatbot.
 Explore the integration of voice-based interaction capabilities, allowing users to interact
with the chatbot through voice commands.
 Implement mechanisms to gather user feedback and insights on the chatbot's performance
and user experience.
 Enhance the chatbot's capabilities by adding support for multiple languages.

34
10. REFERENCES
1. Ms.Ch.Lavanya Susanna, R.Pratyusha, P.Swathi, P.Rishi Krishna, V.Sai Pradeep,
“College Enquiry Chatbot”, International Research Journal of Engineering and Technology
(IRJET), e-ISSN: 23950056, p-ISSN: 2395-0072, Volume: 07 Issue: 3 Mar 2020 pp
784788.
2. Assistant Prof Ram Manoj Sharma, “Chatbot based College Information System”,
RESEARCH REVIEW International Journal of Multidisciplinary, ISSN: 2455-3085
(Online), Volume-04, Issue03, March-2019, pp 109-112.
3. P.Nikhila, G.Jyothi, K.Mounika, Mr. C Kishor Kumar Reddy and Dr. B V Ramana Murthy
on , “Chatbots Using Artificial Intelligence”, International Journal of Research and
Development, Volume VIII, Issue I, January/2019, ISSN NO:22366124, pp 1-12.
4. Payal Jain, “College Enquiry Chatbot Using Iterative Model”, International Journal of
Scientific Engineering and Research (IJSER),ISSN (Online): 2347-3878, Volume 7 Issue
1, January 2019, pp 80-83.
5. Sagar Pawar, Omkar Rane, Ojas Wankhade, Pradnya Mehta, “A Web Based College
Enquiry Chatbot with Results”, International Journal of Innovative Research in Science,
Engineering and Technology, ISSN(Online): 2319-8753, ISSN (Print): 2347-6710, Vol. 7,
Issue 4, April 2018, pp 3874- 3880.
6. Harsh Pawar , Pranav Prabhu, Ajay Yadav, Vincent Mendonca , Joyce Lemos, “College
Enquiry Chatbot Using Knowledge in Database”, International Journal for Research in
Applied Science & Engineering Technology (IJRASET), ISSN: 2321-9653; IC Value:
45.98, SJ Impact Factor: 6.887, Volume 6, Issue IV, April 2018, pp 2494- 2496.
7. Prof.K.Bala, Mukesh Kumar ,Sayali Hulawale, Sahil Pandita, “Chatbot For College
Management System Using A.I”, International Research Journal of Engineering and
Technology (IRJET) eISSN: 2395-0056, p-ISSN: 2395-0072, Volume: 04 Issue: 11 | Nov
-2017, pp 2030-2033.
8. Nitesh Thakur, Akshay Hiwrale, Sourabh Selote, Abhijeet Shinde and Prof. Namrata
Mahakalkar, “Artificially Intelligent Chatbot”, Universal Research Reports , ISSN : 2348
– 5612, Volume : 04 , Issue : 06, July - September 2017, pp 43-47.
9. Amey Tiwari, Rahul Talekar, Prof.S.M.Patil, “College Information Chat Bot System”,
International Journal of Engineering Research and General Science, ISSN 2091-2730,
Volume 5, Issue 2, MarchApril, 2017, pp 131-137.
10. Malusare Sonali Anil, Kolpe Monika Dilip, Bathe Pooja Prashant, “Online Chatting
System for College Enquiry using Knowledgeable Database”, Savitribai Phule Pune
University, Preliminary Project Report, pp 1-53,2017.

35