DEPARTMENT OF ARTIFICIAL & DATA SCIENCE

ENGINEERING
SUMAN RAMESH TULSIANI TECHNICAL CAMPUS, FACULTY
OF
ENGINEERING, PUNE 410405
SAVITRIBAI PHULE PUNE UNIVERSITY 2023-24

PROJECT REPORT ON HEALTHCARE CHAT-BOT

SUBMITTED TO THE SAVITRIBAI PHULE PUNE UNIVERSITY, PUNE IN THE

PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE AWARD OF THE
DEGREE

(DEPARTMENT OF ARTIFICIAL INTELLIGENCE & DATA SCIENCE

ENGINEERING)

SUBMITTED BY

STUDENT NAME GR No.

Student 1 1
Student 2 2
Student 3 3
Student 4 4
 CERTIFICATE
This to certify that the project report entitles
SUBMITTED BY

STUDENT NAME GR. No.

Student 1 1
Student 2 2
Student 3 3
Student 4 4

is a bonafide student of this institute and the work has been carried out by him/her under the

supervision of Prof.Anushka Joshi and it is approved for the partial fulfilment of the

requirement of Savitribai Phule Pune University, for the award of the degree of Bachelor of

Engineering (ARTIFICIAL INTELLIGENCE & DATA SCIENCE ENGINEERING).

Prof. Anushka Joshi Prof.Dr. Anjali More

Guide Head of Department

Prof. (Dr.) J. B. Sankpal

Principal
 ACKNOWLEDGEMENT

It gives us great pleasure in presenting the preliminary project report on We would like
to take this opportunity to thank our internal guide Prof. Anushka Joshi for giving us all the
help and guidance we needed. We are really grateful to them for their kind support and
motivation throughout. Their valuable suggestions were very helpful.

We are also grateful to Prof. Dr.Anjali More, Head of the Computer Engineering, Suman
Ramesh Tulsiani Technical Campus: Faculty of Engineering , Kamshet ,Pune for her
indispensable support and suggestions.

We are also grateful to, Principal Prof. Jaywant Sankpal ,Suman Ramesh Tulsiani Technical
Campus: Faculty of Engineering , Kamshet ,Pune for his indispensable support and
suggestions.
 ABSTRACT

PRINICIPAL TERMS
• bit width: the number of bits used by a computer or other device to store integer
values or other data.
• character: a unit of information that represents a single letter, number, punctuation
mark, blank space, or other symbol used in written language.
• control characters: units of information used to control the manner in which
computers and other devices process text and other characters.
• hamming distance: a measurement of the difference between two characters or
control characters that effects character processing, error detection, and error
correction.
• printable characters: characters that can be written, printed, or displayed in a
manner that can be read by a human.
 TABLE OF CONTENTS
1. INTRODUCTION
Overview
Motivation
Problem definition & Objective

2. LITERATURE SYRVEY
2.1 Study of literature survey

3. SOFTWARE REQUIREMENT SPECIFICATION

Assumption and Dependence
Functional Requirement
External Interface Requirement
User Interface
Hardware Interface
Software Interface
Non functional Requirements
Performance Requirements
IV. SYSTEM DESIGN
System Architecture
Data Flow Diagram
Entity Relationship Diagrams
UML Diagrams

V. PROJECT PLAN
Project Estimate
Reconciled Estimates
Risk Management
Risk Identification
Risk Analysis
Project Schedule
Project Task set Task
Network
Team Organization
Team Structure
Management reporting and communication

VI. PROJECT IMPLEMENTATION

Overview of Project Modules
Tools and Technologies Used
Algorithm Details

VII. RESULT
Outcomes
Screen Shorts

VIII. CONCLUSIONS
Outcomes
Screen Shorts

APPENDIX: Reference
LIST OF FIGURES
Figure 1 Proposed System Architecture
Figure 2 Data Flow diagram-0
Figure 3 Data Flow diagram-1
Figure 4 ER Diagram
Figure 5 Use Case
Figure 6 Sequence Diagram
Figure 7 Waterfall Model
Figure 8 Literature Diagram
Figure 9 Output Screenshots
 CHAPTER I
INTRODUCTIO
N

The first chatbot ever was developed by MIT professor Joseph Weizenbaum in the 1960s. It was called
ELIZA. You'll read more about ELIZA and other popular chatbots that were developed in the second
half of the 20th century later on. In the year 2009, a company called WeChat in China created a more
advanced Chatbot.

Machine learing has influenced how we engage in our every day activities by designing and evaluating
advanced applications and devices, called intelligent agents, which can perform various functions. A
chatbot is an artificial intelligence program and a Human–computer Interaction (HCI) model (Bansal &
Khan, 2018). According to the dictionary, a chatbot is “A computer program designed to simulate
conversation with human users, especially over the Internet” (Chatbot |Definition of chatbot in English by
Lexico Dictionaries, 2019). It uses Natural Language Processing (NLP) and sentiment analysis to
communicate in human language by text or oral speech with humans or other chatbots (Khanna et al.,
2015). Artificial conversation entities, interactive agents, smart bots, and digital assistants are also known as
chatbots.

Apart from imitating human interaction and amusing people, chatbots are useful in various other fields
in education, business and e-commerce, health, and entertainment (Shawar & Atwell, 2007). Productivity is
the most important motivation for chatbot users, although different motivations include entertainment, social
factors, and novelty interaction. Moreover, in business, chatbots have become so common because they
reduce service costs and can handle many customers simultaneously. Chatbots are more friendly and
attractive to users than, for example, the static content search in frequently asked questions (FAQs) lists.
They offer users comfortable and efficient assistance when communicating with them; they provide them
with more engaging answers, directly responding to their problems (Brandtzaeg & Følstad, 2017)
(R. Ranoliya et al., 2017).
Most of the time, users feel chatbots as friendly companions and not just as mere assistants (Costa, 2018).
Forty percent (40%) of user requests are emotional than informative (Xu et al., 2017). It is the evolution
of Machine Learning and sentiment analysis that equipped chatbots with the ability to respond emotionally
to customers (Følstad et al., 2018).
The degree of trust a chatbot gains from its use depends on factors related to its behavior, appearance,
and others related to its manufacturer, privacy issues, and protection (Wallace, 2009). The development of
this relationship of trust is also supported by the level to which the chatbot is human-like, which depends on
the visual characteristics, how closely its name is to a person, its personality, and its efficiency to handle
human language (Go & Sundar, 2019).
Emotion is another essential aspect to humanize a chatbot, and there have been many approaches to
building an emotionally aware chatbot (Pamungkas, 2019).
Developments in AI enhance the abilities of chatbots to mimic human agents in conversation.
However, human–chatbot communication has noticeable differences in the content and quality in
comparison to the human–human discussion. The duration of a human–chatbot conversation is long. People
often use concise language with poor vocabulary or even lousy language (Hill et al., 2015). It is worth
noting, that the crucial difference among chatbots and humans is the perception of empathy, as chatbots are
less capable of conversational understanding than humans are. However, progress is being made, and
chatbots are gradually becoming more fully aware of their interlocutor’s feelings (Fernandes, 2018).
Moreover, human–chatbot communication changes depending on the disclosure or not of the
conversational partner. Undisclosed chatbots are four times more productive than novice sales staff, and
their ability reaches that of specialized consumer shopping employees (Luo et al., 2019). However,
subjective human perception makes people consider disclosed chatbots less informed and emotionally
intelligent. Thus, when customers discover during a conversation that they talk to a chatbot, they get upset
and buy fewer products. Therefore, a method for delayed disclosure of a chatbot was used (Luo et al., 2019).
In Mori et al. (2012), the so-called “uncanny valley theory” examines the uncomfortable feelings that a
person is experiencing when he/she does not know if the interlocutor is a human or a computer program
(Skjuve et al., 2019). Personification and contact in people’s disclosures on sensitive topics, such as social
stressors, have also been examined (Sannon et al., 2018).
Although we live in an age when our interlocutor can be a real person or a chatbot without caring about
his true identity (Dale, 2016), a bias against gender is exposed (Costa, 2018). Most chatbots are typically
used as personal assistants and secretaries to execute activities that mimic traditionally feminine
stereotypes and convey these characteristics through stereotypic behaviors.
In this context, we set the research question of this literature review as follows: What are the evolution
and current state in chatbots’ technology and their applications?

Our objective is through a descriptive investigation of the research question to organize critical
information that is a necessary background for further research activity in the field of chatbots. In this
context, we present the evolution history of chatbots and state out drawbacks at each stage; we also
present the different approaches for chatbot construction and discuss chatbots applications and
industrial use cases.

The main contribution of our work consists of:

● We enhanced the chatbots classification system proposed by (Nimavat & Champaneria, 2017)
by adding the ’Permissions’ category, which distinguishes chatbots to Open Source or
commercial and extending the ’Communication channel’ category by adding the image input.

● We propose an architectural design for chatbots that is general, includes sufficient details, and
complete compared to other related works.
● We point out the drawbacks of today’s chatbots and comment out how one can mitigate them.

● We highlight critical issues that every developer should take into account before the chatbot
design.

● We state our view on the direction that technology should take for chatbots to meet the needs
of human communication through speech.
● The rest of the paper is structured as follows. In Section 2, we take a historical look back from
the beginning of chatbot creation to the present day, pointing out the scientific community’s
interest. Then, in Section 3, we propose a classification of existing chatbots. Pattern-matching
and machine learning approaches are described in Section 4. In Section 5, we suggest a general
chatbot architecture, while in Section 6, we discuss issues related to chatbot development. In
Section 7, the weaknesses and threats of chatbots are addressed, while in Section 8, some
chatbots applications are presented. Finally, in Section 9, we report the limitations of this
study, discuss its implications, and present our view on the direction the technology should
take.
 MOTIVATIONS

We designed Chatbot to assist patients and avoid issues that may arise during normal business hours, such
as waiting on hold for a long time or scheduling appointments that don’t fit into their busy schedules.
With 24/7 accessibility, patients have instant access to medical assistance whenever they need it.

PROBLME DEFINATION AND OBJECTIVES

1) Design & implement Healthcare Chatbot using Machine learning
2)Analysis ,Design ,develop system for Medical sector
3) to design system such that communication between patient and intelligent chatbot will be there
& it should be online system.
4) Assist people with minor issues , assist them what precaution they have to take, and this system
display patient’s disease as per input symptoms.
 CHAPTER II

LITERATURE REVIEW

In this section we outline the following main aspects of chatbots based on our finding from the
literature review: implementation approaches, available public database used in previous data-driven
approaches to chatbot implementation, the main evaluation methods for measuring the performance of
chatbots and the application of chatbots in different domains.
 4.1. Implementation Approaches to Chatbots

Title of Paper Year Author Key Points

An AI-Based 6 December SANJAY Artificial intelligence,

Medical Chatbot 2022 CHAKRABORTY, chatbot, LSTM algorithm,
Model for HRITHIK machine learning, natural
Infectious Disease IEEE Journal PAUL 2 , SAYANI language processing,
Prediction GHATAK 2 , query processing.
SAROJ
KUMAR PANDEY
3,
ANKIT KUMAR 3
, KAMRED
UDHAM
SINGH 4 , AND
MOHD ASIF
SHAH
Conversation- January 14, 2022 GIOVANNI Chatbot, virtual assistant,
Driven Approach ALMEIDA content management,
for Chatbot Springer SANTOS,GUILHE conversation-driven
Management Journal RME GUY DE development,
ANDRADE,RAFA humansupervised learning
EL TIMÓTEO DE
SOUSA, JR
Health Assistant June 8, 2020, MARCO Intelligent virtual assistan
Bot: A Personal POLIGNANO , eHealth, conversational
Health Assistant IEEE Journal FEDELUCIO systems, healthcare,
for the Italian NARDUCCI , recommender systems,
Language ANDREA IOVINE health, dialog, chatbot,
1, machine learning.
(Graduate Student
Member,

I
n this section, we will give an overview of chatbots’ implementation methods. We will distinguish
between Rule-based chatbots, and Artificial Intelligence (AI) based chatbots. Within AI-based
chatbots, we will further distinguish among Information-Retrieval chatbots and Generative Chatbots.
We will also discuss drawbacks and limitations of each implementation approach, as well as recent
improvements.
 4.2. Rule-Based Chatbots
The very first attempts at chatbots’ implementation were rule-based. Rule-based models are
usually easier to design and to implement, but are limited in terms of capabilities, since they have
difficulties answering complex queries. Rule-based chatbots answer users’ queries by looking for
patterns matches; hence, they are likely to produce inaccurate answers when they come across a
sentence that does not contain any known pattern. Furthermore, manually encoding pattern matching
rules can be difficult and time consuming.Furthermore, pattern matching rules are brittle,
highlydomain specific, and do not transfer well from one problem to the other.
 CHAPTER III

SOFTWARE REQUIREMENT SPECIFICATION:

SOFTWARE INTERFACES AND HARDWARE INTERFACES

● Browser- Chrome/edge/ firefox– Any latest version
● Operating System - Ubuntu 20.04 / windows 10 or above
● Database - File system (.CSV)
● Text Editor - Google Colab / Jupyter notebook
● Server- Google cloud servers
● GPU- NVIDIA T4 Tensor Core by Google
● Programming language: Pytho

SAFETY REQUIREMENT
The application is designed in modules where errors can be detected and fixed easily. This makes
it easier to install and update new functionality if required

SOFTWARE QUALITY ATTRIBUTES

Software Quality Attributes are features that facilitate the measurement of performance of a
software product by Software Testing professionals, and include attributes such as availability,
interoperability, correctness, reliability, learnability, robustness, maintainability, readability,
extensibility, testability
 CHAPTER IV
SYSTEM DESIGN
SYSTEM ARCHITECTURE
 CHAPTER V

PROJECT PLAN
● The Chatbot (HealthBot) will try to solve or provide an answer to health-related issues or
queries that the user is asking for. We are implementing ML to improve the efficiency of the
chatbot.

● Healthcare chatbots are the next frontier in virtual customer service as well as planning and
management in healthcare businesses. A chatbot is an automated tool designed to simulate an
intelligent conversation with human users.

PROJECT SCHEDULE
PROJECT TASK SET
A task set is a collection of software engineering work tasks, milestones, and deliverables
that must be accomplished to complete a particular project. The task set to be chosen must
provide enough discipline to achieve high software quality. Major Tasks in the Project
stages are:
• Task 1: correctness

• Task 2: availability

• Task 3: integrity

TEAM ORGANIZATION
The team consists of 5 members and proper planning mechanisms are used and the roles of each
member are defined based on skill-sets and expertise.

1. TEAM STRUCTURE
The team structure for the project is identified. There are a total of 5 members in our team and
roles are defined. All members are contributing in all the phases of the project.

2. MANAGEMENT REPORTING AND

Well, planning mechanisms are used for progress reporting, and inter/intra team communication
is identified as per the requirements of the project.
 CHAPTER VI
PROJECT IMPLEMENTATION
TOOLS AND TECHNOLOGIES SOFTWARE
REQUIREMENTS:
• Operating system: 64bit Windows 7 and on words
• Coding Language: Python
• Google colab
 CHAPTER
VIII
CONCLUSION

● Using the Healthcare chatbot application, Patients will find many conveniences which will
change the way people react in emergencies.
● Rather than being panic, people may find a fast and effective thanks to solving with the
assistance of this application . within the future, we hope to figure extensively on this to develop it
to a replacement level for the betterment of individuals, especially the poor.
● We also are looking forward to using AI in helping people detecting diseases- supported symptoms
more accurately. This way, it's hoped that a health care system is going to be a useful part and
parcel of the everyday in everyone's life.
 CHAPTER
VIII

Output Screenshots
REFERENCES

● https://www.researchgate.net/publication/229064004_A_Systematic_Review_of
_ Healthcare_Applications_for_Smartphones

● An AI-Based Medical Chatbot Model for Infectious Disease Prediction (IEEE journal)
● HealthAssistantBot: A Personal Health Assistant for the Italian Language (IEEE
journal)
● A Conversation-Driven Approach for Chatbot Management (Springer journal)

● https://www.researchgate.net/publication/328724242_Healthcare_Application_Develop
ment_in_Mobile_and Cloud_Environments

SPECIAL THANKS :
special thanks to Prof.Anushka Joshi to guide us to make the assignment of programming and
problem solving . They help us to Perform our assignment. Also thanks for giving us
opportunity to make this assignment.
So, we should like to express our sincere