VISVESVARAYA TECHNOLOGICAL UNIVERSITY

Jnana Sangama, Belagavi - 590 018.

2023-2024

A PROJECT REPORT ON

“College Enquiry Chatbot”

Submitted in partial fulfilment of the requirements for the award of degree of

BACHELOR OF ENGINEERING
In
INFORMATION SCIENCE & ENGINEERING

Submitted by:

AISHWARYA P SAJJAN (1AT21IS006)

ANUSHA (1AT21IS016)
KAVYA U (1AT21IS057)

Under the guidance of:

Mr. Omprakash B
Assistant Professor,
Dept. of ISE, ATRIA I. T.

ATRIA INSTITUTE OF TECHNOLOGY

ASKB Campus, Anand Nagar,
Bengaluru-560024
 ATRIA INSTITUTE OF TECHNOLOGY
Anand Nagar, Bengaluru 560024

Department of Information Science and Engineering

CERTIFICATE

Certified that the project work entitled as “College Enquiry Chatbot” carried out by
AISHWARYA P SAJJAN (USN : 1AT21IS006), ANUSHA (USN : 1AT21IS016)
and KAVYA U(USN:1AT21IS057),a bonafide students of Department of Information
Science and Engineering, Atria Institute of Technology in partial fulfillment for the
award of Bachelor of Engineering in Information Science and Engineering of the
Visvesvaraya Technological University, Belgaum during the year 2023-2024. It is
certified that all corrections/suggestions indicated for Internal Assessment have been
incorporated in the Report deposited in the departmental library. The project report has
been approved as it satisfies the academic requirements in respect of Project work
prescribed for the said Degree.

Guide HOD Principal

Mr. Omprakash B Dr. Deepak N R Dr. Rajesha S

Assistant Professor, ISE Dept. of ISE Atria I.T

External Viva

Name of Examiners Signature with date

1.

2.
 DECLARATION

We, AISHWARYA.P.SAJJAN (1AT21IS006), ANUSHA (1AT21IS016), KAVYA.U

(1AT21IS057)students of 6th semester Bachelor of Engineering, Department of Information
Science and Engineering, Atria Institute of Technology, Bengaluru, would hereby declare that
the project entitled “College Enquiry Chatbot” has been carried out by us at Atria Institute of
Technology, Bangalore, and submitted in partial fulfilment of the course requirement for the award
of degree of Bachelor of Engineering in Information Science and Engineering of Visvesvaraya
Technological University, Belagavi, during the academic year 2023-24.

We further declare that the work embodied in this report has not been submitted to any other
university or institution for the award of any other degree.

Place: Bangalore
Date: Signature Of Students

AISHWARYA.P.SAJJAN

(1AT21IS006)

ANUSHA
(1AT21IS016)

KAVYA.U

(1AT21IS057)

i
 ACKNOWLEDGEMENT

We are grateful to our institution, Atria Institute of Technology, for having provided us with the
facilities to successfully complete this project on “College Enquiry Chatbot”.

We thank Dr. Rajesha S, Principal and Dr. Deepak NR, Professor & HOD, ISE for providing
us all the necessary facilities for the successful completion of our project.

Deadlines play a very important role in the successful completion of the academic project on time,
efficiently and effectively. We take this opportunity to express our deep sense of gratitude to our
guide and coordinator Mr. Omprakash B, Assistant Professor, Department of ISE, Mr.Rahul
Sajjan,Assistant Proffessor,Department of ISE for their valuable guidance and help throughout
the course of the academic project. They have always been patient with us and helped immensely
in completing the task on hand. We also thank them for their immense support, guidance,
specifications & ideas without which seminar would have been completed without full merit.

Last but not least from the Department of Information Science and Engineering, teaching and non-
teaching staffs for their constant encouragement, support, patience, and endurance shown during
the preparation of this report were remarkable. We also thank the management.

Finally, we thank our parents and friends for their motivation, morale and material support.

AISHWARYA P SAJJAN (1AT21IS006)

ANUSHA (1AT21IS016)
KAVYA U (1AT21IS057)

ii
 ABSTRACT

This research presents the development and implementation of a college enquiry

chatbot designed to provide students with rapid and accurate answers to their questions.
Leveraging natural language processing and machine learning techniques, the chatbot is
capable of understanding and responding to a wide range of queries related to college
admissions, courses, fee structures, placements, and other relevant information.By automating
the process of information dissemination, the chatbot aims to enhance student engagement,
reduce administrative burdens, and improve overall student satisfaction. The chatbot's
performance is evaluated based on its accuracy in responding to queries, user satisfaction, and
reduction in query resolution time.

This abstract presents the design and implementation of a college enquiry chatbot,
aimed at streamlining and enhancing the communication between prospective students and
educational institutions. By automating information dissemination, the chatbot aims to enhance
student engagement, reduce administrative burden, and improve overall student satisfaction.
The chatbot's performance is assessed based on its ability to comprehend and respond to
complex queries, as well as its impact on query resolution time and user experience.

iii
 TABLE OF CONTENTS

DECLARATION.......................................................................................................................... i

ACKNOWLEDGEMENT........................................................................................................... ii

ABSTRACT ............................................................................................................................... iii

TABLE OF CONTENTS ........................................................................................................... iv

LIST OF FIGURES .................................................................................................................... vi

LIST OF ACRONYMS ............................................................................................................. vii

CHAPTER 1.................................................................................................................................. 1
INTRODUCTION......................................................................................................................... 1
1.1 Introduction ............................................................................................................................ 2

CHAPTER 2.................................................................................................................................. 3
LITERATURE SURVEY............................................................................................................. 3
2.1 Current system ....................................................................................................................... 4
2.2 Proposed system..................................................................................................................... 4
2.3 Methodology .......................................................................................................................... 5

CHAPTER 3.................................................................................................................................. 6
SYSTEM REQUIREMENT SPECIFICATION ........................................................................ 6
3.1 Analysis/Feasibility study ...................................................................................................... 7
3.2 Hardware Requirement Specification..................................................................................... 8
3.3 Software Requirement Specification .................................................................................... 11

CHAPTER 4................................................................................................................................ 13
DESIGN AND IMPLEMENTATION....................................................................................... 13
4.1 System Architecture ............................................................................................................. 14
4.2 Class Diagram ...................................................................................................................... 15
4.3 Sequence Diagram ............................................................................................................... 15
4.4 Activity Diagram.................................................................................................................. 16

iv
CHAPTER 5................................................................................................................................ 17
IMPLEMENTATION AND TESTING .................................................................................... 17
5.1 General Implementation Discussions ................................................................................... 18
5.2 Software testing ................................................................................................................... 18

CHAPTER 6 ............................................................................................................................... 19
RESULTS AND DISCUSSIONS ............................................................................................... 19
6.1 query based intent ................................................................................................................ 20
6.2 implementing necessary libraries ......................................................................................... 20
6.3 coding................................................................................................................................... 21
6.4 Chatbot ouput 1 .................................................................................................................... 21
6.5 chatbot output 2.................................................................................................................... 22
6.6 chatbot output3……………………………………………………………………………... 22

CHAPTER 7…………………………………………….. . ………………………………………. 23

CONCULSION…………………………………………………………………………………24
7.1 Scope for Future Enhancement…………………………………………………………….24
REFERENCES…............................................................................................................................25

v
 LIST OF FIGURES

Figure 3.1 Intel Core i5 ............................................................................................................... 8

Figure 3.2 RAM 8 GB ................................................................................................................ 9
Figure 3.3 Hard Disk Drive ........................................................................................................ 10
Figure 4.1 System Architecture .................................................................................................. 14
Figure 4.3 Class Diagram ........................................................................................................... 15
Figure 4.4 Sequence Diagram..................................................................................................... 15
Figure 4.5 Activity Diagram ....................................................................................................... 16
Figure 6.1 query based intent ..................................................................................................... 20
Figure 6.2 implementing necessary libraries.............................................................................. 20
Figure 6.3 coding ....................................................................................................................... 21
Figure 6.4 Chatbot ouput 1......................................................................................................... 21
Figure 6.5chatbot output 2 ......................................................................................................... 22
Figure 6.6 chatbot output3…………………………………………………………… ..……... 22

vi
 LIST OF ACRONYMS

ACRONYMS FULL FORMS

SMOTE Synthetic Minority Oversampling Technique

APK Android Package Kit

API Application Programming Interface

RF Random Forest

KDD Knowledge Discovery and Data Mining

FP- GROWTH Frequent Pattern – Growth

CNN Convolutional Neural Network

XGBOOST eXtreme Gradient Boosting

SVM Support Vector Machines

KNN K Nearest Neighbors

vii
 CHAPTER 1
INTRODUCTION
 College Enquiry Chatbot 2023-24

CHAPTER 1
INTRODUCTION

In today's fast-paced world, students looking to join colleges often need quick answers to
their questions about admissions, courses, fees, and campus facilities. Traditional methods like
phone calls, emails, or in-person visits can be slow and inconvenient. To make this process easier,
many colleges are now using chatbots. These chatbots can be accessed through college websites,
mobile apps, or social media, providing a convenient way for students to get help whenever they
need it. By using machine learning, the chatbots get better at answering questions over time,
providing more accurate and personalized information.
The rapid growth of technology has transformed the way information is accessed and
consumed. In the realm of higher education, prospective students are increasingly relying on digital
platforms for seeking information about colleges and universities. To meet this evolving demand,
the development of intelligent systems capable of providing timely and accurate information has
become imperative. A college enquiry chatbot, leveraging advancements in natural language
processing (NLP) and machine learning, emerges as a promising solution to address the information
needs of prospective students.
A college enquiry chatbot serves as a virtual assistant, providing prospective students with
24/7 access to information about admissions, academics, placements, and campus life. By offering
instant responses, personalized recommendations, and a user-friendly interface, it enhances the
student experience and streamlines the college selection process. Simultaneously, it reduces
administrative workload for the institution, improves student engagement, and offers valuable
insights into student preferences.
Objectives
The primary objective of this research is to develop a robust and user-friendly college enquiry
chatbot capable of providing accurate and timely information to prospective students. Specifically,
the chatbot aims to:
Provide an efficient and convenient platform for students to access college-related information.
Reduce the workload of admissions staff by handling routine inquiries.
Foster a positive interaction between the college and prospective students.
Collect data on student queries and preferences to inform institutional decisions.
Make college information available to a wider audience, including students with disabilities.

Dept. of ISE, Atria IT Page 2

 CHAPTER 2
LITERATURE SURVEY
 College Enquiry Chatbot 2023-24

CHAPTER 2
LITERATURE SURVEY

2.1 Current system

In most colleges today, handling student enquiries is largely a manual and inefficient
process. Prospective students typically use phone calls, emails, in-person visits, college websites,
and social media to get information. Phone calls often lead to long wait times, especially during
peak application periods, and require significant staff time to handle each call individually. Emails
can be slow, depending on staff availability to read and reply, and often involve repetitive questions.
In-person visits are helpful but time-consuming and inconvenient, particularly for students who live
far away or have scheduling conflicts. College websites provide information but can be difficult to
navigate, making it hard for students to find specific answers. Social media is effective for
disseminating information but still requires real-time monitoring and responses from staff..

2.2 Proposed system

The proposed system is an AI-driven college enquiry chatbot designed to streamline and
enhance the process of handling student enquiries.
• Real time Responses: The chatbot provides immediate answers to student questions, eliminating
wait times and providing 24/7 support.
• Accessibility: Students can interact with the chatbot through multiple channels, including the
college website, mobile apps, and social media platforms, ensuring easy access regardless of the
student's location or device.
• Consistent and Accurate Information: The chatbot provides consistent answers, reducing the risk of
misinformation and ensuring that all students receive the same accurate information.
• Personalized Interactions: Using machine learning, the chatbot can learn from past interactions and
personalize responses based on the user's history and preferences, enhancing the user experience.

Dept. of ISE, Atria IT Page 4

College Enquiry Chatbot 2023-24

2.3 Methodology
The development and implementation of the AI-driven college enquiry chatbot involve several
key steps, including requirement analysis, design, development, testing, deployment, and
continuous improvement. Below is a detailed outline of the methodology:
1.Requirement Analysis:
• Use Case Identification: Identify and document the various use cases for the chatbot, such as
admissions queries, course information, fee details, and campus facilities.

2.Design:

• User Interface (UI) Design: Design the user interface for different platforms, ensuring it is
intuitive and user-friendly.
• Natural Language Processing (NLP) Model Selection: Choose the appropriate NLP model that
can accurately understand and process user queries.

3.Development:

• NLP Training: Train the selected NLP model using a dataset of frequently asked questions and
answers, along with variations in phrasing.
• Integration: Integrate the chatbot with the college's existing information systems, such as the
admissions database, course catalog, and student information system.

4.Testing:

• Unit Testing: Test individual components of the chatbot to ensure they function correctly.
• Integration Testing: Test the integration of the chatbot with existing systems to ensure seamless
data exchange.
• User Acceptance Testing (UAT): Conduct testing with a group of prospective students and staff
to gather feedback and make necessary adjustments.

5.Continuous Improvement:

• Regular Updates: Update the NLP model and chatbot features regularly to improve accuracy and
expand the range of queries it can handle.

Dept. of ISE, Atria IT Page 4

 CHAPTER 3
SYSTEM REQUIREMENT
SPECIFICATION
 College Enquiry Chatbot 2023-24

CHAPTER 3

SYSTEM REQUIREMENT SPECIFICATION

System Requirement Specifications provide a Software requirement would encompass the

programming languages, frameworks, and libraries essential for building and deploying the
machine learning models. Specific versions and dependencies may be outlined to ensure
compatibility and reproducibility. The SRS may also detail the integration of real-time
adaptability mechanisms, emphasizing the need for continuous learning and timely updates to
the system's knowledge base.

3.1 Analysis / Feasibility study

Analysis and feasibility study of involves a thorough examination of the project's viability,
potential challenges, and benefits before committing to its development. The feasibility study
encompasses various aspects, starting with a technical analysis to assess the capabilities and
suitability of machine learning algorithms for college enquiry chatbot.

In this phase, the technical feasibility involves evaluating the availability of necessary
resources, including computing power, datasets, and machine learning tools. It aims to determine
if the technology and methodologies chosen for the project align with the project's objectives and
can effectively address the complexities of college enquiry chatbot.

Financial feasibility is another crucial aspect, assessing the budget requirements for acquiring
resources, conducting research, and implementing the proposed solution. This includes
estimating costs related to hardware, software, data acquisition, and potential personnel or
expertise required for the project's successful execution.

Operational feasibility considers how well the proposed system aligns with the existing
infrastructure and operational processes. It examines the practicality of integrating the Android
malware detection system into real-world scenarios, considering factors such as compatibility.
Analysis of existing literature and research demonstrates a strong foundation of methodologies
and techniques relevant to feature extraction, machine learning algorithms.Ultimately, the
feasibility study aims to provide a comprehensive understanding of the project's potential risks,
benefits, and challenges. It assists decision-makers in determining whether the Android
malware detection project is viable, aligns with organizational goals, and can be realistically
executedwithinthedefinedconstraints.
Dept. of ISE, Atria IT Page 7
 College Enquiry Chatbot 2023-24

3.1 Hardware Requirement Specification

Hardware Requirements

• Processor Type : Intel CoreTM–i5

• Speed : 2.4 GHZ

• RAM : 8 GB RAM
• Hard disk : 80 GB HDD
3.1.1 CPU- INTEL CORE i5

Fig 3.1 INTEL CORE i5

Intel Core is a brand name that Intel uses for various mid-range to high-end consumer and
business microprocessors. As of 2015 the current lineup of Core processors included the Intel
Core i7, Intel Core i5, and Intel Core i3. 5th generation Intel® Core™ i5 processors.

Empower new innovations like Intel® Real Sense™ technology—bringing you features such as
gesture control, 3D capture and edit, and innovative photo and video capabilities to your
devices. Enjoy stunning visuals, built-in security, and an automatic burst of speed when you need
it with Intel® Turbo Boost Technology 2.0.

The CPU, specifically an Intel Core i5 processor, plays a crucial role in executing various
computational tasks related to analysis. The Intel Core i5 processor is chosen for its balance of
performance, power efficiency, and affordability, making it a popular choice for research and
development projects like this. Intel Core is a brand name that Intel uses for various mid-range
to high-end consumer and business microprocessors. As of 2015 the current lineup of Core
processors included the Intel Core i7, Intel Core i5, and Intel Core i3. 5th generation Intel®
Core™ i5 processors.

Dept. of ISE, Atria IT Page 8

 College Enquiry Chatbot 2023-24

3.1.2 RAM

Fig 3.2 RAM 8 GB

When you load up an application on to your computer it loads into your available RAM
memory. It is very quick type of memory. The more programs you load up, the more RAM is
taken up. At the point where you have loaded up enough apps to take up all your free available
physical RAM, your OS will create a swap-file on your hard drive. This file is used as a reserve
for all additional apps you run.

RAM (Random Access Memory) plays a vital role in facilitating the analysis of malware
samples and the execution of various computational tasks. RAM serves as temporary storage
for data and instructions that are actively being used by the CPU and other components of the
system. The amount and quality of RAM directly influence the performance and efficiency of
malware analysis processes.
One of the primary functions of RAM in this project is to store and manipulate data related
to malware samples during analysis. As malware samples are loaded into memory for
examination, RAM provides the necessary space for storing executable code, file structures,
metadata, and other relevant information.
Additionally, RAM facilitates the execution of machine learning algorithms and data
processing tasks involved in identifying patterns and features indicative of malware
behavior. By storing training data, feature vectors, and intermediate computations in
memory, RAM enables rapid processing and analysis of large datasets, leading to more
accurateandefficientmalwaredetection

Dept. of ISE, Atria IT Page 9

 College Enquiry Chatbot 2023-24

3.1.3 HARD DISK

Fig 3.3 Hard Disk Drive

A hard disk drive (HDD), hard disk, hard drive or fixed disk is a data storage device used for
storing and retrieving digital information using one or more rigid ("hard") rapidly rotating disks
(platters) coated with magnetic material. The platters are paired with magnetic heads arranged
on a moving actuator arm, which read and write data to the platter surfaces.
The hard disk serves as a foundational component for storing data essential to malware analysis.
It acts as the primary repository where various files, directories, system configurations, and
other digital artifacts reside. The hard disk's role is multifaceted, encompassing both the storage
and organization of data pertinent to understanding and combating malware.
Moreover, the hard disk holds crucial system artifacts and metadata that are instrumental in
malware analysis. This includes file system structures, such as the Master Boot Record (MBR),
file allocation tables, and directory hierarchies, which provide insights into how files are
organized and accessed within the system.

The hard disk may contain system logs, registry entries, and configuration files that record
system events and changes over time. By analyzing these artifacts, researchers can identify
indicators of compromise (IOCs) and devise strategies for detecting malware threats.
Researchers may perform static analysis by examining the file structure, metadata, and content
of malware samples directly from the hard disk without executing them. Dynamic analysis, on
the other hand, involves executing malware samples in a controlled environment, such as a
virtual machine, to observe their behavior and interactions with the system.

Dept. of ISE, Atria IT Page 10

 College Enquiry Chatbot 2023-24

3.2 SOFTWARE REQUIREMENTS

• Operating System : Windows 64-bit

• Technology : Machine learning

• IDE : tagi

• Tools : pycharm
• Python Version : Python 3.6

3.2.1 Python:

Python is an interpreted, high-level, general-purpose programming language. Created by Guido

van Rossum and first released in 1991, Python has a design philosophy that emphasizes code
readability, notably using significant whitespace. It provides constructs that enable clear
programming on both small and large scales. Van Rossum led the language community until
stepping down as leader in July 2018.

Python features a dynamic type system and automatic memory management. It supports
multiple programming paradigms, including object-oriented, imperative, functional and
procedural, and has a large and comprehensive standard library.Python interpreters are
available for many operating systems. CPython, the reference implementation of Python, is
open source software[30] and has a community-based development model, as do nearly all of
Python's other implementations. Python and CPython are managed by the non-profit Python
Software Foundation.
Python is a multi-paradigm programming language. Object-oriented programming and
structured programming are fully supported, and many of its features support functional
programming and aspect-oriented programming (including by meta programming and
metaobjects (magic methods)). Many other paradigms are supported via extensions, including
design by contract and logic programming.

Python's design offers some support for functional programming in the Lisp tradition. It has
filter(), map(), and reduce() functions; list comprehensions, dictionaries, and sets; and generator
expressions. The standard library has two modules (itertools and functools) that implement

Dept. of ISE, Atria IT Page 11

 College Enquiry Chatbot 2023-24

functional tools borrowed from Haskell and Standard ML.

3.2.2 Machine Learning

Machine Learning (ML) is a branch of artificial intelligence that focuses on creating

algorithms and statistical models that enable computers to perform tasks without explicit
instructions, instead learning and improving from experience. By analyzing data, ML systems
develop models that can make predictions or decisions, refining their accuracy over time as
they process more information. ML encompasses various types, including supervised learning,
where models are trained on labeled data to make predictions; unsupervised learning, which
involves finding patterns in unlabeled data; semi-supervised learning, combining small
amounts of labeled data with large amounts of unlabeled data; and reinforcement learning,
where models learn by interacting with an environment and receiving rewards or penalties.
Key algorithms and techniques include linear regression, decision trees, neural networks,
support vector machines, and k-nearest neighbors. ML is widely applied across many domains
such as healthcare for predicting disease outcomes, finance for fraud detection and credit
scoring, retail for recommendation systems and sales forecasting, and transportation for
autonomous vehicles and route optimization. Popular tools and libraries for ML include Scikit-
Learn, TensorFlow, PyTorch, and Keras, which facilitate the development and deployment of
machine learning models. The continuous advancement of ML technologies drives innovation
and enhances data-driven decision-making across various industries.

At its core, ML involves training algorithms on data to identify patterns and make predictions
or decisions. These algorithms can be classified into different types, including supervised
learning, which uses labeled datasets to train models for tasks like classification and
regression; unsupervised learning, which discovers hidden patterns or structures in unlabeled
data through techniques like clustering and dimensionality reduction; semi-supervised
learning, which leverages both labeled and unlabeled data to improve model accuracy; and
reinforcement learning, which teaches models to make a sequence of decisions by receiving
feedback in the form of rewards or penalties.

Dept. of ISE, Atria IT Page 12

 CHAPTER 4
SYSTEM DESIGN
 College Enquiry Chatbot 2023-24

Chapter 4
SYSTEM DESIGN
4.1 System Architecture:

Fig 4.1 System architecture

The system architecture consist of 4 main parts: Users,Admin,Chatbot System. 4. Corpus A User can
enter a query related to the college in text format. The query is then sent to the Corpus, the corpus
consist of all the information related to the college in an encoded format , via use of sequence-to-
sequence model in the Chatbot System. The Result for Query is searched.

4.2 Class Diagram:

A class diagram is a static structural diagram in software engineering that describes the structure of a
system by showing the system's classes, their attributes, operations (or methods), and the
relationships amongIn simpler terms, it's a blueprint of a software system, showing the different
components (classes) and how they interact with each other.

Dept. of ISE, Atria IT Page 14

 College Enquiry Chatbot 2023-24

Fig 4.2 : Class Diagram

4.3 Sequence Diagram

A sequence diagram, a fundamental component of the Unified Modeling Language (UML), offers a
dynamic representation of interactions between objects within a software system. It provides a visual
blueprint of the chronological flow of messages exchanged among objects during the execution of a
specific scenario or use case.

Fig 4.3 : Sequence Diagram

Dept. of ISE, Atria IT Page 15

 College Enquiry Chatbot 2023-24

4.4 Activity Diagram

An activity diagram is a type of behavioral diagram in the Unified Modeling Language (UML) that
illustrates the flow of control or activities within a system. It provides a graphical representation of
the dynamic aspects of a system, focusing on the sequence of actions or steps that occur in a process,
use case, or workflow. In an activity diagram, activities are represented by rounded rectangles, while
transitions between activities are depicted by arrows indicating the flow of control.

The diagram includes several key elements such as the Initial State, which is the starting point before
an activity occurs, represented by a filled black circle. The Action or Activity State represents the
execution of an action on or by objects, depicted using a rectangle with rounded corners.

Fig 4.4 : Activity Diagram

Dept. of ISE, Atria IT Page 16

 CHAPTER 5
IMPLEMENTATION AND
TESTING
College Enquiry Chatbot 2023-24

Chapter 5
IMPLEMENTATION AND
SOFTWARE TESTING

5.1 General Implementation Discussions

• Define Objectives:Set goals for the chatbot to provide accurate, instant responses on
admissions, courses, and financial aid, and operate 24/7.
• Data Collection:Gather historical inquiries, FAQs, and relevant college information. Prepare
and clean this data for model training.
• Model Development:
• NLTK for NLP Tasks:Use NLTK for preprocessing text, including tokenization, part-of-
speech tagging, and named entity recognition.
PyTorch for Model Training:Develop and train a deep learning model in PyTorch to recognize
user intents and extract entities. Utilize pre-trained models for better performance if needed.
• Develop Chatbot Interface:
• Flask for Backend:Create a Flask application to handle API requests, integrate with the ML
model, and serve responses.
• Frontend Integration:Build a user-friendly chat interface for web or mobile platforms that
connects to the Flask backend.
• Deploy and Test:Host the Flask application on a cloud platform like AWS or Google Cloud.
Test the chatbot with real users to refine responses and ensure accuracy.
• Monitor and Optimize:Track performance, gather user feedback, and update the chatbot
regularly to improve accuracy and user satisfaction.

5.2 Software Testing

• Software testing for a college inquiry chatbot using ML involves
• Functionality Testing:Ensuring response accuracy and relevance.
• Performance Testing:Testing load handling and response times under various conditions.
• Usability Testing :Evaluating user experience and interaction ease.
• Security Testing :Ensuring data protection and secure interactions.
• Compatibility Testing :Checking cross-platform functionality and integration with existing
systems.

Dept. of ISE, Atria IT Page 18

CHAPTER 6
RESULTS
 College Enquiry Chatbot 2023-24

Chapter 6
RESULTS

6.1 Creating query-based intents for the dataset

Fig 6.1: query-based intents

6.2 Importing necessary
libraries

Fig 6.2: importing necessary libraries

Dept. of ISE, Atria IT Page 20

 College Enquiry Chatbot 2023-24

6.3 Coding

Fig 6.3 coding

6.4 Chatbot output 1

Fig 6.4: Chatbot output 1

Dept. of ISE, Atria IT Page 21

 College Enquiry Chatbot 2023-24

6.5 Chatbot output 2:

Fig 6.4: Chatbot output 2

6.6 Chatbot output 3:

Fig 6.6: Chatbot output 3

Dept. of ISE, Atria IT Page 22

CHAPTER 7
CONCLUSION
 College Enquiry Chatbot 2023-24

Chapter 7
CONCLUSION
The development of a college enquiry chatbot represents a significant step towards enhancing
the student experience and optimizing administrative processes. By leveraging advancements in
natural language processing, machine learning, and knowledge representation, this chatbot
offers a robust solution for addressing the information needs of prospective students.

The chatbot's ability to provide instant, accurate, and personalized responses to a wide range of
queries demonstrates its potential to significantly reduce the workload of admissions staff while
improving student satisfaction. Additionally, the chatbot's capacity to gather valuable insights
into student preferences and behaviors offers opportunities for data-driven decision-making
within the institution.

While this research has laid a strong foundation, there is ample scope for further exploration and
refinement. Incorporating advanced natural language understanding capabilities, expanding the
chatbot's knowledge base, and integrating with other campus systems are potential avenues for
future development. Ultimately, the successful implementation of a college enquiry chatbot can
serve as a catalyst for innovation and improved student engagement within the higher education
landscape.

7.1 Scope for Future Enhancement

The college enquiry chatbot, while demonstrating significant potential, offers ample
opportunities for further development and refinement. Key areas for future enhancement
include:

• Enhanced Natural Language Understanding

• Expanded Knowledge Base
• Personalized Interactions
• Multilingual Support
• Integration with Other Systems
• Sentiment Analysis
• Voice Interaction

Dept. of ISE, Atria IT Page 24

College Enquiry Chatbot 2023-24

REFERENCES

• A review on college enquiry chatbot: https://ieeexplore.ieee.org/document/10063053

(accessed: 20 March 2023)
• AI And Web-Based Interactive College Enquiry Chatbot:
https://ieeexplore.ieee.org/document/9515065 (accessed:23 August 2021)
• College Enquiry Chatbot: https://ieeexplore.ieee.org/document/10156978 (accessed: 26 June
2023)
• Smart Chatbot for College Information Enquiry Using Deep Neural Network:
https://ieeexplore.ieee.org/document/10112919 (accessed: 05 May 2023)
• A support system for formal college students: A case study of a community-based app
augmented with a chatbot: https://ieeexplore.ieee.org/document/9759796 (accessed: 25 April
2022)
• ChatGpt:-https://chatgpt.com/c/1960127e-bc86-4a73-96de-546ab3fd03bf

Dept. of ISE, Atria IT Page 25