CertifiCate

This is to certify that this report entitled “Chatbot for query resolution” comprises literature
review carried out by Navdeep Singh [GCS/2030509], Kuldeep Singh [GCS/2030110] and
Mridul Rabha [GCS/2030116] under the supervision of Mr. Sukhpreet Singh, Assistant
Professor [Department of Computer Science, SLIET Longowal. during the period between
January 2023 to May 2023 for the fulfilment of requirements of the bachelor’s degree in
computer science and Engineering from Sant Longowal Institute of Engineering and
Technology, Longowal. The results presented to this have not been submitted previously and
results are authentic.

Date: 17th May, 2023 Mr. Sukhpreet Singh

Assistant Professor
Department of Computer Science
SLIET, Longowal
 Acknowledgement

We would like to acknowledge Sant Longowal Institute of Engineering and Technology,

Longowal for providing us the opportunity to present our work on ‘Sentiment Analysis’ as a
partial fulfilment for bachelor’s degree requirement. We would like to extend our gratitude
towards Mr. Sukhpreet Singh, Assistant Professor, Sant Longowal Institute of Engineering and
Technology, Longowal, Punjab for the guidance during the project.
We would also like to thank our friends for encouragement and assistance they provided
throughout the project.
 Abstract
This abstract introduces a healthcare chatbot developed to provide personalized assistance and
support in the healthcare domain. Built using Python, the chatbot incorporates natural language
processing and machine learning techniques to offer a user-friendly interface for symptom
assessment and doctor recommendations. Users register with the chatbot, then engage in an
interactive questionnaire where they respond to questions about their health condition. By
analysing the responses, the chatbot accurately assesses symptoms and identifies potential
health concerns. The chatbot generates a list of recommended doctors specializing in the
reported health issues, providing users with detailed profiles and contact information for further
consultation. The healthcare chatbot improves access to preliminary medical guidance,
empowering individuals to make informed healthcare decisions. By streamlining symptom
assessment and facilitating connections with healthcare professionals, the chatbot enhances the
overall healthcare experience. The project showcases the effectiveness of Python in developing
intelligent healthcare systems, offering the potential for future enhancements such as
medication reminders and appointment scheduling. Overall, the healthcare chatbot contributes
to improved healthcare outcomes and patient satisfaction.
List of Figures:
Fig 5.1: Programme information flow diagram
Fig 6.1: Welcome screen
Fig 6.2: Registration Screen
Fig 6.3: Successful Registration screen
Fig 6.4: First step to use the chatbot.
Fig 6.5: Chatbot displaying questions.
Fig 6.6: chatbot displaying the disease of Hypoglycaemia and Doctor’s details for
consultation based on symptoms.
Fig 6.7: chatbot displaying the disease of Dengue and Doctor’s details for consultation based on
symptoms.
Chapter No Title Page No.
Certificate i

Acknowledgement ii

Abstract iii

List of figures iv

1 Introduction 1

1.1 Background 1

1.2 Challenges 1

1.3 Why do chatbots failures? 1

1.3.1 How to fix chatbot failures 2

2 Literature Review 3

2.1 Introduction 3

2.2 Literature review 3

3 Problem Statement 4

4 Objective 6

5 Methodology 8

6 Results and Screenshots 10

7 Conclusion 14

References
 Chapter 1: Introduction
Chatbots are also known as chatter bots. A chatbot is developed with the help of AI
(Artificial Intelligence) application. It gives permission to humans to interact with digital
devices as if they were communicating with a human being. AI chatbots employ machine
learning, an AI capability that allows bots to become smarter over time as they are used. AI
chatbots are a natural match for customer service because of this. Chatbots use digital instant
messenger to communicate with people and can be integrated into a variety of applications and
websites.
These websites include:
• B2B: Mobile Monkey.
• Services: Massage Envy.
• Restaurant: Domino's.
• E-commerce: Peloton.

Types of Chatbot:
• Menu/button chatbot
• Linguistic based
• Keyword recognition-based chatbots
• Machine Learning chatbots
• The hybrid-models
• Voice bots [1]

1.1 Background
In 1966, MIT's Joseph Weizenbaum invented ELIZA, the first chatbot that came close
to simulating a human. ELIZA will detect keywords in a sentence as well as pattern match them
against a list of pre procedures to generate appropriate responses.
Amazon's Echo and Alexa, Apple's Siri, and Microsoft's Cortana are examples of
modern chatbot. [2,3]

1.2 Challenges
Now that you've learned about the advantages of using AI chatbots, one can put its
power to work to improve customer happiness. Whenever it comes to adopting AI chatbots
within the company, unfortunately, there are some major challenges.
• Chatbot security.
• Understanding the emotions and sentiments of your customers.
• They are susceptible to data security breaches.
• They can misunderstand user point of view.
• They can face spoken language problems.
• They can interrupt the user experience.

1
1.3 Why do chatbots fails?
Chatbots are programmed by humans and typically follow a decision-tree. The chatbot's
activities are expressly mapped out by the authors based on what a user says. Chatbots fail
because pre-training a chatbots to operate correctly in every case is nearly hard. Consider slang,
misspellings, intonation, comedy, and syntax when it comes to communication. I hate to admit
it, but I'm a human who sometimes misses sarcasm or comedy in my own relationships.
As a result, chatbots make mistakes. We see consumers angry or annoyed, brand
reputation harmed, or flat-out negative user feedback for a variety of reasons, which we detail
below.

1.3.1 How to fix these failures.

• Enhance NLP algorithms and context awareness for accurate and relevant responses.
• Expand and update knowledge base for comprehensive information.
• Optimize user experience with intuitive design and guided interactions.
• Personalize interactions based on user preferences and history.
• Thorough testing, iteration, and promotion for improved performance and user
adoption.
Types of Chatbots:
1. Rule-based Chatbots: These chatbots operate on a predefined set of rules and responses.
They follow a specific decision tree or flowchart to provide answers based on keywords
or patterns in user input.
2. AI-Powered Chatbots: These chatbots utilize artificial intelligence (AI) and natural
language processing (NLP) techniques to understand and respond to user input. They
can handle more complex queries and improve their responses over time through
machine learning algorithms.
3. Virtual Assistant Chatbots: These chatbots are designed to assist users with various
tasks and provide personalized recommendations. They can schedule appointments,
make reservations, answer questions, and perform specific functions based on user
requests.
4. Transactional Chatbots: These chatbots are focused on facilitating transactions and
completing specific tasks. They can handle payment processing, order placement,
tracking shipments, or providing customer support for e-commerce businesses.
5. Voice Assistants: Voice assistants, such as Amazon's Alexa, Apple's Siri, or Google
Assistant, are chatbots that interact with users through voice commands. They can
perform tasks, answer questions, and control smart home devices.
6. Domain-Specific Chatbots: These chatbots are tailored for specific industries or
domains, such as healthcare, finance, or customer support. They have specialized
knowledge and capabilities relevant to their specific field.
7. Hybrid Chatbots: Hybrid chatbots combine rule-based and AI-powered approaches to
provide more versatile and accurate responses. They leverage predefined rules but also
employ AI algorithms to handle more complex queries.

2
 Chapter 2: Literature Review
2.1 Introduction:
The purpose of this chapter is to provide a literature review of inventory management articles
published in major logistics outlets, identify themes from the literature and provide future
direction for inventory management research. A literature review identifies, estimates, and
synthesizes the relevant literature within a specific field of research. At the end we will conduct
the summary of literature review on inventory management system that why this system is
essential for any organization.
2.2 Literature Review
Alan Turing posed the issue, "Can machines think?" in 1950. Turing imagined this issue
as a "mimicking game" (now famous as Turing Test), in which an "interrogator" asked human
-artificial candidates queries with the objective of defining the human. They believe the robot
could understand if indeed the people and robot are similar.
The first chatbot ever was developed by MIT professor Joseph Weizen baum in the
1960s. It was called ELIZA. You’ll read more about ELIZA and other popular chatbots that
were developed in the second half of the 20th century later.
In the year 2009, a company called WeChat in China created a more advanced Chatbot.
Since its launch, WeChat has conquered the hearts of many users who demonstrate an
unwavering loyalty to it. It is a highly thriving social media platform.
Through its platform, it has made it easy to create very simple chatbots. It has grown to
be an example of the most favoured ways for marketers and employers to reduce the work they
do as they interact with customers online.
Though it has implications and is less performant than today’s messaging apps such as
Facebook Messenger, Slack, and Telegram, it doesn’t mean that you cannot construct a very
smart bot on WeChat. Chumen Wenwen Company, founded in 2012 by a former Google
employee, has built a very sophisticated bot running on WeChat.
Early in 2016, we saw the intro of the first wave of artificial data technology in the
design of chatbots. Social media platforms like Facebook enabled developers to build a chatbot
for their trademark or service so that customers could carry out some of their daily actions from
inside their messaging platform.
The introduction of chatbots into a community has brought us to the time of the
conversational interface. It’s an interface that soon won’t demand a screen or a mouse. The
interface will be entirely conversational, and those communications will be indistinguishable
from the conversations that we have with our friends and relatives.

3
 Chapter 3: Problem Definition
In the healthcare system, the implementation of chatbots poses several challenges.
Firstly, healthcare chatbots may lack accuracy and medical expertise, potentially leading to
incorrect diagnoses or treatment recommendations. Privacy and data security concerns also
arise as chatbots handle sensitive patient information, necessitating robust safeguards to protect
confidentiality. Moreover, chatbots often struggle to provide the human touch and empathy that
patients desire, potentially impacting patient satisfaction and trust. Complex healthcare queries
pose a difficulty for chatbots, as they may have difficulty understanding medical terminology
and interpreting nuanced symptoms. Lastly, ethical, and legal considerations arise regarding
chatbot identity disclosure, responsibility delegation, and transparency of AI algorithms.
Addressing these challenges is crucial to ensure successful integration of chatbots in healthcare,
delivering accurate information while upholding patient privacy, safety, and satisfaction.
The healthcare industry faces several challenges that can be addressed through the
implementation of a chatbot. The problem definition for using a chatbot in healthcare services
includes the following key aspects:

• Limited Access to Timely Healthcare Information: Patients often encounter

difficulties in accessing accurate and timely healthcare information. It can be
challenging to find relevant resources, understand medical jargon, or navigate
through the complex healthcare system, leading to delays in seeking appropriate
care.
• Overwhelmed Healthcare Resources: Healthcare facilities and professionals
often face an overwhelming number of patient inquiries and appointments,
resulting in long waiting times and increased healthcare costs. Limited
resources may hinder the ability to provide timely and efficient healthcare
services to all patients.
• Inefficient Symptom Assessment and Triage: Traditional methods of symptom
assessment and triage may be time-consuming and prone to errors. Patients may
not have access to reliable guidance to evaluate their symptoms and determine
the urgency of their healthcare needs, leading to unnecessary emergency room
visits or delayed interventions.
• Lack of Personalized Healthcare Guidance: Patients may struggle to find
personalized healthcare guidance tailored to their specific symptoms, medical
history, and preferences. The absence of tailored recommendations and
information may lead to suboptimal decision-making and inadequate self-care
practices.
• Insufficient Health Education and Awareness: Many individuals lack proper
health education and awareness, leading to misconceptions, delays in seeking
care, or inadequate preventive measures. There is a need for accessible and
reliable health information to empower individuals to make informed choices
about their health.

4
 By identifying and addressing these challenges, the integration of a chatbot in
healthcare services aims to improve access to timely and accurate healthcare information,
optimize healthcare resource utilization, enhance symptom assessment, and triage efficiency,
provide personalized healthcare guidance, and promote health education and awareness.

5
 Chapter 4: Objective
The objective of our project is to develop a healthcare chatbot that enhances the accessibility
and efficiency of healthcare services. The chatbot will employ advanced natural language
processing (NLP) algorithms to engage with users and provide personalized assistance. Upon
receiving user input regarding symptoms, the chatbot will intelligently present relevant options
for further exploration. It will leverage a comprehensive database of doctors to provide users
with a curated list of healthcare professionals who specialize in addressing their specific
symptoms. By combining the power of technology and medical expertise, our aim is to
streamline the process of seeking appropriate medical care and empower users to make
informed healthcare decisions.
Proposed Work:
The proposed work for our healthcare chatbot project includes the following key components:
1. System Design: We will design the architecture and user interface of the healthcare
chatbot, ensuring a user-friendly and intuitive experience. The chatbot will be built
using advanced NLP techniques to understand and process user input effectively.
2. Symptom Assessment Module: We will develop a sophisticated symptom assessment
module that will prompt users with relevant questions based on their responses. The
chatbot will intelligently present options related to the reported symptoms, aiding users
in better understanding their healthcare needs.
3. Doctors Database Integration: We will integrate a comprehensive database of doctors,
including their specialties, experience, and availability. The chatbot will utilize this
database to provide users with a curated list of healthcare professionals who are well-
suited to address their specific symptoms.
4. Integration with Appointment Scheduling: To further streamline the process, we will
integrate the chatbot with appointment scheduling functionality. Users will have the
option to book appointments directly through the chatbot, ensuring a seamless
experience from symptom assessment to securing a doctor's appointment.
5. Testing and Refinement: Throughout the development process, we will conduct
rigorous testing to validate the chatbot's functionality, accuracy, and user experience.
User feedback will be gathered and incorporated into iterative refinements to enhance
the chatbot's performance and address any identified issues.

By implementing these proposed tasks, we aim to create a healthcare chatbot that assists
users in symptom assessment, provides relevant options, and connects them with suitable
doctors for effective healthcare management.

6
 The objective of integrating a chatbot in healthcare services is to enhance the efficiency,
accessibility, and quality of patient care. By leveraging artificial intelligence and natural
language processing, the chatbot aims to achieve the following objectives:
➢ Improve Access to Healthcare: The chatbot enables users to seek healthcare
information and assistance conveniently from their preferred devices, eliminating
geographical and time barriers. It provides 24/7 availability, empowering users to
access healthcare resources and guidance whenever needed.
➢ Streamline Symptom Assessment: The chatbot facilitates an interactive and
systematic symptom assessment process, allowing users to provide information
about their health condition. This enables the chatbot to analyse symptoms
accurately and provide relevant insights, helping users make informed decisions
about their health.
➢ Personalized Recommendations: Through intelligent algorithms, the chatbot offers
personalized recommendations based on the user's symptoms, medical history, and
preferences. It provides tailored advice, doctor recommendations, and treatment
options, guiding users towards appropriate healthcare interventions.
➢ Efficient Healthcare Navigation: The chatbot assists users in navigating the
complex healthcare system by providing information about healthcare facilities,
services, and specialties. It helps users find suitable doctors, clinics, or hospitals,
facilitating efficient and informed decision-making.
➢ Health Education and Awareness: The chatbot serves as an educational resource,
offering accurate and reliable healthcare information to users. It can provide
preventive care tips, answer common health-related queries, and promote health
awareness, empowering individuals to take proactive steps towards better health.
➢ Support Healthcare Professionals: The chatbot can assist healthcare professionals
by automating routine tasks, such as appointment scheduling, triage, or data
collection. This allows healthcare providers to focus more on direct patient care and
complex medical decision-making.
By achieving these objectives, the integration of a chatbot in healthcare services aims to
enhance the overall patient experience, promote health literacy, optimize healthcare resource
utilization, and contribute to improved health outcomes.

7
 Chapter 5: Methodology

Fig 5.1: Programme information flow diagram

• Sample space design:
In chatbot testing, sample space design involves creating diverse test cases covering input
variations, intent coverage, error handling, contextual scenarios, boundary/edge cases,
integration testing, and performance/load testing to ensure comprehensive evaluation of the
chatbot's functionality and performance.
• Receiving inputs:
At this stage, the user will be able to provide necessary inputs in the form of Yes or No. The
bot will provide questionnaire to the user and the user will have to choose accordingly. And
particularly, the chatbot used in the healthcare services must be easy to feed the information.
• Input Processing:
Input processing in a healthcare chatbot involves analysing and interpreting user inputs, which
can be text or voice-based, using natural language processing (NLP) techniques. The chatbot
extracts relevant information, identifies the user's intent, and generates appropriate healthcare-
related responses.
• Presenting the requested output:
The output of a healthcare chatbot includes providing users with relevant and accurate
healthcare information, recommendations, symptom assessments, appointment scheduling, and
connecting them with appropriate healthcare professionals, ultimately assisting users in making
informed healthcare decisions.

8
Methods of working of a chatbot:
1. Requirement Gathering: We will conduct comprehensive research and engage with
healthcare professionals to gather requirements and understand user expectations. This
will help us define the scope and objectives of the healthcare chatbot project accurately.
2. System Design: Based on the gathered requirements, we will design the architecture
and user interface of the chatbot. We will select appropriate technologies and
frameworks for development, ensuring scalability, security, and seamless integration
with existing systems.
3. Data Collection and Preparation: We will collect and curate a diverse dataset of medical
symptoms, associated conditions, and corresponding doctor specialties. The dataset will
be carefully prepared, ensuring accuracy and relevance to facilitate accurate symptom
assessment and doctor recommendations.
4. Development of NLP Models: We will develop, and train NLP models using machine
learning techniques to understand and interpret user input accurately. These models will
enable the chatbot to process user queries, extract relevant information, and provide
appropriate options based on the reported symptoms.
5. Integration with Doctors Database: We will integrate the developed chatbot with a
comprehensive database of doctors. This integration will involve mapping doctors'
specialties to specific symptoms and conditions to ensure accurate and relevant
recommendations for users.
6. Testing and Evaluation: We will conduct extensive testing of the chatbot, including
functional testing, usability testing, and performance testing. User feedback and test
results will be gathered and analysed to identify any issues or areas of improvement.
7. Refinement and Iteration: Based on the testing results and user feedback, we will refine
the chatbot's algorithms, user interface, and symptom assessment module. Iterative
development cycles will be conducted to enhance the accuracy, usability, and overall
user experience of the chatbot.
8. Deployment and User Feedback: Once the chatbot is refined and deemed ready for
deployment, we will make it available to users. User feedback will continue to be
gathered to monitor the chatbot's performance, identify any further enhancements, and
address any user concerns.

By following this methodology, we aim to develop a robust and user-centric healthcare

chatbot that effectively assesses symptoms, presents relevant options, and connects users with
appropriate doctors, ultimately improving access to healthcare services and empowering users
to make informed healthcare decisions.

9
 Chapter 6: Results and Screenshots
The project aimed to develop a healthcare chatbot using the Python programming language.
The chatbot implementation successfully incorporated key features, resulting in an efficient
and user-friendly healthcare assistance system.
The first step in utilizing the chatbot required user registration. Users were prompted to
provide their personal information, including name, age, and contact details. This registration
process ensured a personalized experience for users and allowed the chatbot to maintain user
records securely.
Once registered, users could engage with the chatbot to seek healthcare guidance. The
chatbot employed an interactive questionnaire approach, presenting users with a series of
questions related to their health condition. Users were expected to respond with either "yes" or
"no" to provide relevant information for symptom assessment.
Based on the user's responses, the chatbot performed symptom analysis. By utilizing
sophisticated algorithms, the chatbot accurately assessed the reported symptoms and identified
potential health concerns. This step enabled the chatbot to understand the user's health status
and provide appropriate recommendations.
One of the key outcomes of the project was the provision of doctor recommendations. After
analysing the user's symptoms, the chatbot generated a list of suitable doctors who specialized
in addressing the reported health issues. Users were provided with details of the recommended
doctors, including their specialties, qualifications, and contact information. This feature
facilitated seamless access to healthcare professionals for further consultation.
Overall, the developed healthcare chatbot proved to be an effective tool for users seeking
preliminary medical guidance. By streamlining the process of symptom assessment and
providing actionable information, the chatbot empowered users to make informed decisions
about their healthcare. The project's successful outcome demonstrated the feasibility and
potential benefits of utilizing Python in developing healthcare chatbots.
Furthermore, the project highlighted the importance of user registration, as it allowed for
personalized interactions and enhanced data security. The interactive questionnaire approach
ensured an engaging user experience, while the accurate symptom analysis and doctor
recommendations improved the efficiency and effectiveness of the chatbot.
In conclusion, the developed healthcare chatbot served as a valuable resource for users,
providing reliable symptom assessment and connecting them with appropriate healthcare
professionals. The project's result showcased the potential of Python in creating intelligent
healthcare systems that contribute to improved healthcare access and decision-making.

10
 The following screenshots provide a glimpse into the user interface and functionality of the
healthcare chatbot developed as part of this project. These screenshots showcase the
registration process, interactive questionnaire, symptom analysis, and doctor
recommendations. They illustrate the seamless user experience and the chatbot's ability to
provide personalized healthcare assistance. These visuals offer a tangible representation of the
project's successful implementation, highlighting the user-centric design and the effectiveness
of the chatbot in aiding users with their healthcare needs.

Fig 6.1: Welcome screen

Fig 6.2: Registration Screen

11
Fig 6.3: Successful Registration screen

Fig 6.4: First step to use the chatbot.

Fig 6.5: Chatbot displaying questions.

12
 Fig 6.6: chatbot displaying the disease of Hypoglycaemia and Doctor’s details for consultation
based on symptoms..

Fig 6.7: chatbot displaying the disease of Dengue and Doctor’s details for consultation based on
symptoms.

13
 Chapter 7: Conclusion
The integration of chatbots in healthcare services has shown great promise in addressing
various challenges and improving patient care. By leveraging natural language processing,
artificial intelligence, and personalized recommendations, chatbots have the potential to
enhance accessibility, streamline symptom assessment, and provide valuable healthcare
guidance. The development and implementation of chatbots in the healthcare industry have
demonstrated their ability to improve patient engagement, optimize resource utilization, and
provide personalized care recommendations.
However, there are still areas for improvement and future work. Firstly, further research
and development are needed to enhance the accuracy and reliability of symptom analysis
performed by chatbots. This includes refining algorithms, integrating more extensive medical
databases, and incorporating real-time data to ensure precise and up-to-date assessments.
Secondly, the incorporation of advanced technologies such as machine learning and
predictive analytics can enable chatbots to continuously learn and improve. By analysing large
volumes of healthcare data, chatbots can adapt to changing trends, enhance their decision-
making capabilities, and provide increasingly accurate recommendations.
Thirdly, the integration of chatbots with electronic health records (EHRs) can enhance the
overall patient experience and facilitate seamless information exchange. This integration would
allow chatbots to access relevant patient data, medical history, and laboratory results, providing
a more comprehensive and personalized healthcare service.
In conclusion, the utilization of chatbots in healthcare services has the potential to
revolutionize the way patients access healthcare information, receive symptom assessment, and
make informed decisions about their health. The ongoing advancements in artificial
intelligence, natural language processing, and data analytics provide a strong foundation for
further research and development in this field. By addressing the challenges and exploring the
future possibilities, chatbots can become integral tools in improving healthcare delivery,
enhancing patient outcomes, and transforming the healthcare experience for individuals
worldwide.

14
References
[1] https://www.engati.com/blog/types-of-chatbots-and-their- applications?
utm_content=types-of-chatbots-and-their-applications
[2] 4 reasons for enterprise chatbot failure and how to overcome them using a multi- bot
approach. (2020). https://servisbot.com/four-reasons-for-enterprise-chatbot-failure/.
(Retrieved 30 September 2020).
[3] https://www.netomi.com/the-worst-chatbot-fails-and-how-to-avoid-them
[4] https://chatbots-life.com/purpose-and-objective-of-chatbots-4f2ed7f35227
[5] https://onlim.com/en/top-requirements-for-chatbot-software
[6] https://medium.com/analytics-vidhya/building-a-simple-chatbot-in-python-using-nltk-
7c8c8215ac6e

15