VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI – 590018, Karnataka

INTERNSHIP REPORT
ON

“Chatbot for Healthcare System

Using AI”
Submitted in partial fulfilment for the award of degree(21INT49)

BACHELOR OF ENGINEERING IN
Computer Science Engineering
Submitted by:
AASHISH DHAMALA
1BH22CS400

Conducted at
Compsoft Technologies

BANGALORE TECHNOLOGICAL INSTITUTE

(An ISO 9001:2015 Certified Institute)
Near Wipro Corporate Office, Off Bengaluru - Sarjapura Road, Bengaluru-560 035

Internship report 2023-24 1

 BANGALORE TECHNOLOGICAL INSTITUTE
(An ISO 9001:2015 Certified Institute)
Near Wipro Corporate Office, Off Bengaluru - Sarjapura Road, Bengaluru-560 035

CERTIFICATE

This is to certify that the Internship titled “Chatbot for Healthcare System Using AI” carried out
by Mr. AASHISH DHAMALA, a bonafide student of Bangalore Technological Institute, in partial
fulfillment for the award of Bachelor of Engineering, in Department Computer Science Engineering
under Visvesvaraya Technological University, Belagavi, during the year 2022-2023. It is
certified that all corrections/suggestions indicated have been incorporated in the report.

The project report has been approved as it satisfies the academic requirements in respect
of Internship prescribed for the course Internship / Professional Practice (21INT49)

Signature of Guide Signature of HOD Signature of Principal

External Viva:

Name of the Examiner Signature with Date

1)

2)

Internship report 2023-24 2

 DEC LARATIO N

I, Aashish Dhamala, third year student of branch Computer Science Engineering,

Bangalore Technological Institute- 560035, declare that the Internship has been
successfully completed, in Compsoft Technologies. This report is submitted in
partial fulfillment of the requirements for award of Bachelor Degree in Branch
name, during the academic year 2022-2023.

Date :03/12/2023 :
Place : Bangalore

USN : 1BH22CS400
NAME: Aashish Dhamala

Internship report 2023-24 3

 OFFER LETTER

Internship report 2023-24 4

 AC K N OWLE D G E M ENT

This Internship is a result of accumulated guidance, direction and support of several

important persons. We take this opportunity to express our gratitude to all who have helped
us to complete the Internship.

We express our sincere thanks to our Principal, for providing us adequate facilities to
undertake this Internship.

We would like to thank our Head of Dept – branch code, for providing us an opportunity to
carry out Internship and for his valuable guidance and support.

We would like to thank our (Lab assistant name) Software Services for guiding us during the
period of internship.

We express our deep and profound gratitude to our guide, Guide name, Assistant/Associate
Prof, for her keen interest and encouragement at every step in completing the Internship.

We would like to thank all the faculty members of our department for the support extended
during the course of Internship.

We would like to thank the non-teaching members of our dept, for helping us during the
Internship.

Last but not the least, we would like to thank our parents and friends without whose constant
help, the completion of Internship would have not been possible.

NAME: Aashish Dhamala

USN: 1BH22CS400

Internship report 2023-24 5

 ABSTRACT

The evolution of conversational AI has paved the way for innovative applications in various
industries, particularly in healthcare. This abstract presents a comprehensive overview of the
development and implementation of a sophisticated healthcare chatbot using the Rasa framework.
The aim of this project is to create a user-friendly, intelligent, and reliable chatbot that assists
users in accessing healthcare information, scheduling appointments, providing symptom analysis,
and offering general medical guidance.

The project utilizes Rasa, an open-source conversational AI framework known for its flexibility,
natural language understanding capabilities, and easy integration. Leveraging its machine
learning-based dialogue management and natural language processing (NLP) functionalities, the
chatbot is designed to engage users in natural, context-aware conversations.
The development process involves several key stages:

Data Collection and Preprocessing: Gathering a diverse set of healthcare-related data,

including medical literature, FAQs, and user queries, followed by preprocessing to ensure quality
and relevance. This step involves data cleaning, categorization, and structuring for optimal
training.

Intent Identification and Entity Recognition: Using Rasa NLU (Natural Language
Understanding) components to classify user intents and extract relevant entities from user
messages. This step involves training the model to accurately identify and understand user
intentions, such as appointment booking, symptom inquiry, or medication queries, along with
extracting specific information like dates, symptoms, or medications mentioned.

Dialogue Management: Implementing a robust dialogue management system using Rasa Core to
maintain context, manage conversation flows, and handle multi-turn interactions. This component
ensures coherent and meaningful exchanges between the user and the chatbot, enabling smooth
navigation through various healthcare-related tasks.

Integration with Healthcare Systems: Integrating the chatbot with existing healthcare systems,
such as appointment scheduling platforms or electronic health record (EHR) systems, to enable
functionalities like appointment booking, retrieval of medical records, and seamless information
exchange.

Continuous Learning and Improvement: Employing iterative model training and evaluation to
enhance the chatbot's performance. Incorporating user feedback, monitoring conversation logs,
and retraining the model using Rasa's reinforcement learning capabilities to adapt and improve
the chatbot's responses over time.

The healthcare chatbot developed using Rasa aims to address several challenges, including
improving healthcare accessibility, providing immediate assistance, reducing administrative
burdens on healthcare providers, and promoting health literacy among users. Moreover, emphasis
is placed on ensuring the chatbot complies with healthcare regulations and maintains data privacy
and security standards.

Internship report 2023-24 6

The evaluation of the chatbot involves rigorous testing, including simulated user interactions,
usability assessments, and performance metrics analysis. Metrics such as accuracy in intent
classification, entity extraction precision, response time, and user satisfaction are measured to
gauge the effectiveness and efficiency of the chatbot.
In conclusion, the development of a healthcare chatbot using Rasa showcases the potential of
conversational AI in revolutionizing healthcare delivery by offering personalized, accessible, and
reliable assistance to users. The project aims to contribute to the advancement of AI-driven
solutions in the healthcare domain, emphasizing the importance of ethical considerations, user-
centric design, and continuous improvement.

Internship report 2023-24 7

 Table of Contents

Sl no Description Page no

1 Company Profile 9

2 About the Company 11

3 Introduction 15

4 System Analysis 18

5 Requirement Analysis 22

6 Design Analysis 26

7 Implementation 30

8 Snapshots 32

9 Conclusion 38

10 References 40

Internship report 2023-24 8

 CHAPTER 1
COMPANY PROFILE

Internship report 2023-24 9

 1. COMPANY PROFILE
A Brief History of Compsoft Technologies
Compsoft Technologies, was incorporated with a goal ”To provide high quality and optimal
Technological Solutions to business requirements of our clients”. Every business is a different
and has a unique business model and so are the technological requirements. They understand
this and hence the solutions provided to these requirements are different as well. They focus
on clients requirements and provide them with tailor made technological solutions. They also
understand that Reach of their Product to its targeted market or the automation of the existing
process into e-client and simple process are the key features that our clients desire from
Technological Solution they are looking for and these are the features that we focus on while
designing the solutions for their clients.

Sarvamoola Software Services. is a Technology Organization providing solutions for all web
design and development, MYSQL, PYTHON Programming, HTML, CSS, ASP.NET and
LINQ. Meeting the ever increasing automation requirements, Sarvamoola Software Services.
specialize in ERP, Connectivity, SEO Services, Conference Management, effective web
promotion and tailor-made software products, designing solutions best suiting clients
requirements.

Compsoft Technologies, strive to be the front runner in creativity and innovation in software
development through their well-researched expertise and establish it as an out of the box
software development company in Bangalore, India. As a software development company,
they translate this software development expertise into value for their customers through their
professional solutions.

They understand that the best desired output can be achieved only by understanding the
clients demand better. Compsoft Technologies work with their clients and help them to
defiine their exact solution requirement. Sometimes even they wonder that they have
completely redefined their solution or new application requirement during the brainstorming
session, and here they position themselves as an IT solutions consulting group comprising of
high caliber consultants.

They believe that Technology when used properly can help any business to scale and achieve
new heights of success. It helps Improve its efficiency, profitability, reliability; to put itin one
sentence ” Technology helps you to Delight your Customers” and that is what we want to
achieve.

Internship report 2023-24 10

 CHAPTER 2
ABOUT THE COMPANY

Internship report 2023-24 11

 2. ABOUT THE COMPANY

Compsoft Technologies is a Technology Organization providing solutions for all web design
and development, MYSQL, PYTHON Programming, HTML, CSS, ASP.NET and LINQ.
Meeting the ever increasing automation requirements, Compsoft Technologies specialize in
ERP, Connectivity, SEO Services, Conference Management, effective web promotion and
tailor-made software products, designing solutions best suiting clients requirements. The
organization where they have a right mix of professionals as a stakeholders to help us serve
our clients with best of our capability and with at par industry standards. They have
young, enthusiastic, passionate and creative Professionals to develop technological
innovations in the field of Mobile technologies, Web applications as well as Business and
Enterprise solution. Motto of our organization is to “Collaborate with our clients to provide
them with best Technological solution hence creating Good Present and Better Future for our
client which will bring a cascading a positive effect in their business shape as well”.
Providing a Complete suite of technical solutions is not just our tag line, it is Our Vision for
Our Clients and for Us, We strive hard to achieve it.

Products of Compsoft Technologies.

Android Apps

It is the process by which new applications are created for devices running the Android
operating system. Applications are usually developed in Java (and/or Kotlin; or other such
option) programming language using the Android software development kit (SDK), but other
development environments are also available, some such as Kotlin support the exact same
Android APIs (and bytecode), while others such as Go have restricted API access.

The Android software development kit includes a comprehensive set of development tools.
These include a debugger, libraries, a handset emulator based on QEMU, documentation,
sample code, and zutorials. Currently supported development platforms include computers
running Linux (any modern desktop Linux distribution), Mac OS X 10.5.8 or later, and
Windows 7 or later. As of March 2015, the SDK is not available on Android itself, but
softwaredevelopment is possible by using specialized Android applications.

Web Application

It is a client–server computer program in which the client (including the user interface and
client- side logic) runs in a web browser. Common web applications include web mail, online

Internship report 2023-24 12

 retail sales, online auctions, wikis, instant messaging services and many other functions. web
applications use web documents written in a standard format such as HTML and
JavaScript,which are supported by a variety of web browsers. Web applications can be
considered as a specifific variant of client–server software where the client software is
downloaded to the client machine when visiting the relevant web page, using standard
procedures such as HTTP. The Client web software updates may happen each time the web
page is visited. During the session, the web browser interprets and displays the pages, and
acts as the universal client for any web application. The use of web application frameworks
can often reduce the number of errors in a program, both by making the code simpler, and by
allowing one team to concentrate on the framework while another focuses on a specifified use
case. In applications which are exposed to constant hacking attempts on the Internet, security-
related problems can be caused by errors in the program.

Frameworks can also promote the use of best practices such as GET after POST. There are
some who view a web application as a two-tier architecture. This can be a “smart” client that
performs all the work and queries a “dumb” server, or a “dumb” client that relies on a “smart”
server. The client would handle the presentation tier, the server would have the database
(storage tier), and the business logic (application tier) would be on one of them or on both.
While this increases the scalability of the applications and separates the display and the
database, it still doesn‟t allow for true specialization of layers, so most applications will
outgrow this model. An emerging strategy for application software companies is to provide
web access to software previously distributed as local applications. Depending on the type of
application, it may require the development of an entirely different browser-based interface,
or merely adapting an existing application to use different presentation technology. These
programs allow the user to pay a monthly or yearly fee for use of a software application
without having to install it on a local hard drive. A company which follows this strategy is
known as an application service provider (ASP), and ASPs are currently receiving much
attention in the software industry.

Security breaches on these kinds of applications are a major concern because it can involve
both enterprise information and private customer data. Protecting these assets is an important
part of any web application and there are some key operational areas that must be included in
the development process. This includes processes for authentication, authorization, asset
handling, input, and logging and auditing. Building security into the applications from the
beginning can be more effective and less disruptive in the long run.

Web design

It is encompasses many different skills and disciplines in the production and maintenance of
websites. The different areas of web design include web graphic design; interface design;
authoring, including standardized code and proprietary software; user experience design; and

Internship report 2023-24 13

 search engine optimization. The term web design is normally used to describe the design
process relating to the front-end (client side) design of a website including writing mark up.
Web design partially overlaps web engineering in the broader scope of web development.
Web designers are expected to have an awareness of usability and if their role involves
creating mark up then they are also expected to be up to date with web accessibility
guidelines. Web design partially overlaps web engineering in the broader scope of web
development.

Departments and services offered

Compsoft Technologies plays an essential role as an institute, the level of education,
development of student’s skills are based on their trainers. If you do not have a good mentor
then you may lag in many things from others and that is why we at Compsoft Technologies
gives you the facility of skilled employees so that you do not feel unsecured about the
academics. Personality development and academic status are some of those things which lie
on mentor’s hands. If you are trained well then you can do well in your future and knowing
its importance of Compsoft Technologies always tries to give you the best.

They have a great team of skilled mentors who are always ready to direct their trainees in the
best possible way they can and to ensure the skills of mentors we held many skill
development programs as well so that each and every mentor can develop their own skills
with the demands of the companies so that they can prepare a complete packaged trainee.

Services provided by Compsoft Technologies.

• Core Java and Advanced Java

• Web services and development

• Dot Net Framework

• Python

• Selenium Testing

• Conference / Event Management Service

• Academic Project Guidance

• On The Job Training

• Software Training

Internship report 2023-24 14

 CHAPTER 3

INTRODUCTION

Internship report 2023-24 15

 3. INTRODUCTION

Introduction to ML
Machine Learning is a subfield of artificial intelligence (AI) that focuses on the development of
algorithms and models that enable computers to learn from data and make predictions or
decisions without being explicitly programmed. The core idea behind machine learning is to
allow systems to automatically learn and improve from experience.

There are three main types of machine learning:

1. Supervised Learning: In supervised learning, the algorithm is trained on a labelled dataset,

where the input data is paired with corresponding output labels. The model learns to map
inputs to outputs, and its performance is evaluated on how well it can generalize to new,
unseen data.

2. Unsupervised Learning: Unsupervised learning involves working with unlabelled data. The
algorithm tries to find patterns or relationships within the data without explicit guidance on
what to look for. Common techniques include clustering, dimensionality reduction, and
association rule learning.

3. Reinforcement Learning: Reinforcement learning involves an agent that learns to make

decisions by interacting with an environment. The agent receives feedback in the form of
rewards or penalties, allowing it to learn the optimal actions to take in different situations.

Problem Statement
A problem statement in the context of machine learning defines the specific issue or task that the
ML model is designed to address. It provides a clear description of the problem, the goals of the
model, and the expected outcomes. A well-defined problem statement is crucial for guiding the
entire machine learning project.

Here is an example problem statement:

Problem: Predictive Maintenance for Manufacturing Equipment

Description:
In a manufacturing facility, unexpected equipment failures result in costly downtime and
maintenance expenses. The goal is to develop a machine learning model that predicts potential
equipment failures before they occur, enabling proactive maintenance. The dataset includes
historical sensor data from various machines, along with labels indicating whether a failure
occurred within a specific time window. The model should be able to classify equipment
conditions as normal or indicative of an impending failure.

Internship report 2023-24 16

Objectives:

1. Develop a predictive maintenance model using supervised learning techniques.

2. Evaluate the model's performance based on metrics such as precision, recall, and F1 score.
3. Implement the model in a real-time monitoring system to provide timely alerts for
maintenance.
Expected Outcome:
Reduced downtime, increased efficiency, and cost savings through proactive maintenance,
ultimately improving the overall reliability of manufacturing equipment.

This problem statement outlines the context, goals, and expected impact of the machine learning
project, providing a roadmap for the development and deployment of the predictive maintenance
model.

Internship report 2023-24 17

 CHAPTER 4

SYSTEM ANALYSIS

Internship report 2023-24 18

4. SYSTEM ANALYSIS

System analysis is a crucial phase in the development lifecycle of any technological solution,
including machine learning systems. It involves a comprehensive study of the existing system,
understanding its strengths and weaknesses, and defining the requirements for the proposed
system. The primary goal is to identify the problems in the current system, explore opportunities
for improvement, and lay the groundwork for the design and implementation of the new system.

Key Components of System Analysis:

1. Understanding Requirements:
• Identify and document the specific requirements of the system.
• Interview stakeholders, end-users, and subject matter experts to gather insights.
• Define functional and non-functional requirements, considering both technical and
business aspects.
2. Study of Existing System:
• Evaluate the strengths and weaknesses of the current system.
• Identify manual processes, bottlenecks, and areas for improvement.
• Analyze data flow, input-output processes, and feedback mechanisms in the existing
system.
3. Feasibility Study:
• Conduct a feasibility study to assess the practicality and viability of the proposed
system.
• Evaluate technical, operational, and economic feasibility.
• Determine if the proposed system aligns with organizational goals and resources.
4. System Design Considerations:
• Define the architecture and high-level design of the proposed system.
• Consider scalability, reliability, security, and other design principles.
• Identify technology stacks and tools that align with the project's requirements.
5. Risk Analysis:
• Identify potential risks associated with the proposed system.
• Assess the impact and likelihood of each risk.
• Develop mitigation strategies to address identified risks.
6. User Involvement:
• Involve end-users and stakeholders throughout the analysis phase.

Internship report 2023-24 19

 • Gather feedback and insights from users to ensure the proposed system meets their
needs.
• Consider user experience and usability aspects in system design.
7. Cost-Benefit Analysis:
• Evaluate the costs associated with developing and implementing the new system.
• Compare the costs against the anticipated benefits to determine the project's return on
investment.
Importance of System Analysis in Machine Learning Projects:
In the context of machine learning projects, system analysis is particularly important because it
helps in:
• Understanding the nature of the problem the machine learning model aims to solve.

• Defining clear objectives and requirements for the machine learning system.
• Assessing the quality and relevance of available data for training the model.
• Identifying potential challenges and constraints that may impact the success of the project.
• Ensuring that the proposed machine learning solution aligns with the overall
organizational strategy and goals.
A thorough system analysis lays the foundation for a successful machine learning
implementation, guiding subsequent phases such as system design, development, and
deployment. It helps ensure that the machine learning solution addresses real-world problems
effectively and delivers tangible value to the stakeholders.

1. Existing System
In the existing system, there may be manual or traditional methods in place for managing the
process or problem addressed by the machine learning solution. For example, in the context
of the predictive maintenance problem mentioned earlier, the existing system might rely on
reactive maintenance practices, where equipment is repaired or replaced only after a failure
occurs. This approach can result in increased downtime, higher maintenance costs, and
reduced overall efficiency.

2. Proposed System
The proposed system introduces the machine learning solution to address the limitations of
the existing system. In the case of predictive maintenance, the proposed system involves
implementing a machine learning model that can analyze historical sensor data to predict
potential equipment failures. The system may include real-time monitoring capabilities, alert
mechanisms, and integration with the existing maintenance workflow to enable proactive
maintenance.

3. Objective of the System

The main objectives of the proposed system are:
• Improve Efficiency: By predicting equipment failures in advance, the proposed system
aims to reduce downtime and improve the overall efficiency of the process or system.

Internship report 2023-24 20

 • Cost Savings: Proactive maintenance, guided by machine learning predictions, can lead
to significant cost savings by minimizing unplanned downtime and optimizing
maintenance schedules.
• Enhanced Reliability: The system aims to enhance the reliability of the process or
equipment by preventing failures before they occur, ultimately improving overall
performance.
• Real-time Monitoring: Implementing real-time monitoring capabilities ensures that the
system can provide timely alerts and insights, allowing for quick response to potential
issues.
• Integration: The proposed system should seamlessly integrate with existing workflows
and systems to facilitate a smooth transition and ensure practical usability.
• Accuracy and Precision: Develop a machine learning model with high accuracy and
precision in predicting potential failures, evaluated using appropriate performance
metrics.
• User-Friendly Interface: If applicable, the system should have a user-friendly interface
that allows users to interact with and interpret the results of the machine learning model
effectively.
By achieving these objectives, the proposed system aims to overcome the limitations of the
existing system and provide a more effective and efficient solution to the problem at hand. The
system analysis phase sets the stage for the design and development of the machine learning
solution, guiding the project toward successful implementation and deployment.

Internship report 2023-24 21

 CHAPTER 5

REQUIREMENT ANALYSIS

Internship report 2023-24 22

 5. REQUIREMENT ANALYSIS

Hardware Requirement Specification

The hardware requirements for a healthcare chatbot using Rasa, or any conversational AI system,
are generally moderate. The specific hardware components depend on factors such as the
expected user load, the complexity of the chatbot, and any additional functionalities integrated
into the system. Below is a basic outline of the hardware requirements:
1. Server/Cloud Infrastructure:
• A server or cloud infrastructure to host the chatbot system.
• The choice of cloud provider (e.g., AWS, Azure, Google Cloud) will depend on
organizational preferences and requirements.
2. Processing Power:
• Sufficient CPU resources to handle natural language processing (NLP) tasks
efficiently.
• Multi-core processors are recommended for parallel processing of user queries.
3. Memory (RAM):
• Adequate RAM to store and process the chatbot's knowledge base, models, and
handle concurrent user interactions.
• The exact RAM requirement depends on the size and complexity of the chatbot.
4. Storage:
• Storage space for storing chat logs, user data, and any additional multimedia
content (if applicable).
• SSD storage is preferred for faster data retrieval.
5. Network Infrastructure:
• A reliable network connection with sufficient bandwidth to handle incoming and
outgoing requests.
• Integration with external APIs (if any) may require additional consideration for
network connectivity.
6. Backup and Redundancy:
• Implement backup systems and redundancy to ensure data integrity and system
availability.
• Regularly back up the chatbot's knowledge base and user data.

Internship report 2023-24 23

 Software Requirement Specification
The software requirements for a healthcare chatbot using Rasa involve specifying the necessary
software components and tools required for both development and deployment.
1. Development Environment:
• Programming Language: Python (Rasa is primarily built using Python).
• Integrated Development Environment (IDE): Any Python-compatible IDE such
as PyCharm, VSCode, or Jupyter Notebooks.
2. Rasa Framework:
• Rasa Open Source: The core framework for building conversational AI
applications.
• Rasa NLU (Natural Language Understanding): A component for intent
recognition and entity extraction.
• Rasa Core: A dialogue management library for managing the flow of
conversations.
3. Dependencies and Libraries:
• Installation of required Python libraries, including but not limited to TensorFlow,
spaCy, and scikit-learn.
4. NLP Models:
• Pre-trained language models (e.g., spaCy models) for natural language processing
tasks.
• Depending on the healthcare domain, specialized models or medical ontologies
may be incorporated.
5. Database:
• A database system (e.g., MongoDB, PostgreSQL) to store user data, chat logs, and
any relevant information.
6. Web Server:
• A web server (e.g., Flask, Django) to host the chatbot as a web service.
• SSL certificates for secure communication (especially if handling sensitive health
data).
7. Version Control:
• Version control system (e.g., Git) for tracking changes in the codebase.
8. Deployment Platforms:
• Compatibility with the chosen deployment platforms, whether on-premises or
cloud-based (AWS, Azure, Google Cloud).
9. Integration Tools:

Internship report 2023-24 24

 • Any additional tools or APIs required for integrating the chatbot with healthcare
systems, databases, or external services.
10. Testing Frameworks:
• Testing tools and frameworks to ensure the reliability and correctness of the
chatbot's responses.
11. Documentation:
• Comprehensive documentation for the chatbot's setup, usage, and maintenance.
12. Security Measures:
• Implementation of security best practices, including secure API communication,
encryption, and user authentication.
By specifying these hardware and software requirements, the development and deployment of the
healthcare chatbot using Rasa can proceed systematically, ensuring that the system meets the
desired functionality, performance, and security standards.

Internship report 2023-24 25

 CHAPTER 6
DESIGN ANALYSIS

Internship report 2023-24 26

 6. DESIGN & ANALYSIS

System Design:
The design of a healthcare chatbot using Rasa involves both architectural considerations and the
detailed design of individual components. Here, we outline the key aspects of system design:
1. Architecture:
• The chatbot architecture should be modular, scalable, and capable of handling
concurrent user interactions.
• Components include Rasa NLU for natural language understanding, Rasa Core for
dialogue management, and any additional modules for healthcare-specific
functionalities.
2. User Interface (UI):
• Design an intuitive and user-friendly chat interface for seamless interactions.
• Consider incorporating multimedia elements, such as images or buttons, to
enhance user experience.
3. Natural Language Processing (NLP):
• Configure Rasa NLU to recognize user intents and extract entities related to
healthcare queries.
• Integrate pre-trained language models or specialized medical ontologies for
accurate understanding of medical terms.
4. Dialogue Flow:
• Design the dialogue flow to ensure coherent and context-aware conversations.
• Use Rasa Core to manage the flow of interactions, handle user queries, and
provide informative responses.
5. Integration with Healthcare Systems:
• If applicable, design integration points with healthcare databases or external
systems to retrieve or update patient information.
• Implement secure and compliant data handling practices.
6. Personalization:
• Incorporate personalization features to adapt the chatbot's responses based on user
history or preferences.
• Design mechanisms for user authentication if accessing sensitive healthcare
information.
7. Multilingual Support:
• If the chatbot is intended for a diverse audience, design the system to support
multiple languages.

Internship report 2023-24 27

 • Configure language-specific models and responses.
8. Security Measures:
• Implement security protocols such as HTTPS for secure communication.
• Ensure that sensitive data is handled securely and that user privacy is maintained.
9. Error Handling:
• Design robust error-handling mechanisms to gracefully handle unexpected user
inputs or system failures.
• Implement a fallback mechanism for handling queries that the chatbot may not
understand.
10. Scalability:
• Design the system with scalability in mind to handle increasing user loads.
• Consider load balancing and efficient resource management.
Analysis:

The analysis phase involves evaluating the effectiveness and performance of the healthcare
chatbot. Key aspects of analysis include:
1. Performance Metrics:
• Measure the accuracy of intent recognition and entity extraction using appropriate
metrics.
• Evaluate the overall response time and system responsiveness.
2. User Feedback:
• Collect user feedback to understand user satisfaction and identify areas for
improvement.
• Analyze user queries and interactions to refine the chatbot's capabilities.
3. Integration Testing:
• Conduct thorough testing of integration points with healthcare systems to ensure data
accuracy and reliability.
• Verify the secure handling of healthcare information.
4. Scalability Testing:
• Assess the system's ability to scale with an increasing number of concurrent users.
• Identify and address performance bottlenecks.
5. Usability Testing:
• Evaluate the usability of the chatbot's interface and interactions.
• Ensure that users can easily navigate through the healthcare-related functionalities.

Internship report 2023-24 28

 6. Compliance and Regulations:
• Ensure that the chatbot complies with healthcare regulations, privacy laws, and data
protection standards.
• Conduct audits to verify compliance with relevant healthcare policies.
7. Continuous Improvement:
• Analyze usage patterns and user feedback to identify opportunities for continuous
improvement.
• Regularly update the chatbot's knowledge base and models to enhance performance.
By conducting a thorough analysis, the healthcare chatbot can be refined iteratively, addressing
any identified issues and improving its overall performance, usability, and compliance with
healthcare standards. The design and analysis phases are critical for ensuring the success and
effectiveness of the healthcare chatbot in providing valuable support to users in the healthcare
domain.

Internship report 2023-24 29

 CHAPTER 7

IMPLEMENTATION

Internship report 2023-24 30

 7. IMPLEMENTATION
Implementation is the stage where the theoretical design is turned into a working system. The
most crucial stage in achieving a new successful system and in giving confidence on the new
system for the users that it will work efficiently and effectively.

The system can be implemented only after thorough testing is done and if it is found to work
according to the specification. It involves careful planning, investigation of the current
system and it constraints on implementation, design of methods to achieve the change over
and an evaluation of change over methods a part from planning.

Two major tasks of preparing the implementation are education and training of the users and
testing of the system. The more complex the system being implemented, the more involved
will be the system analysis and design effort required just for implementation.

The implementation phase comprises of several activities. The required hardware and
software acquisition is carried out. The system may require some software to be developed.
For this, programs are written and tested. The user then changes over to his new fully tested
system and the old system is discontinued.

TESTING
The testing phase is an important part of software development. It is the Information zed
system will help in automate process of finding errors and missing operations and also a
complete verification to determine whether the objectives are met and the user requirements
are satisfied. Software testing is carried out in three steps:

1. The first includes unit testing, where in each module is tested to provide its correctness,
validity and also determine any missing operations and to verify whether theobjectives
have been met. Errors are noted down and corrected immediately.

2. Unit testing is the important and major part of the project. So errors are rectified easily in
particular module and program clarity is increased. In this project entire system is
divided into several modules and is developed individually. So unit testing is conducted
to individual modules.

3. The second step includes Integration testing. It need not be the case, the software whose
modules when run individually and showing perfect results, will also show perfect
results when run as a whole.

Internship report 2023-24 31

 CHAPTER 8
SNAPSHOTS

Internship report 2023-24 32

 8. SNAPSHOTS

FIG 1: BOT RESPONSES

Internship report 2023-24 33

 FIG 2: Chat UI html

Internship report 2023-24 34

 FIG 3: Flask App Implementaion And Integration Of Rasa Chatbot Api

Internship report 2023-24 35

 FIG 4: Training Stories

Internship report 2023-24 36

 FIG 5: Web App Implementation

Internship report 2023-24 37

 CHAPTER 9
CONCLUTION

Internship report 2023-24 38

 9. CONCLUTION
The package was designed in such a way that future modifications can be done easily. The
following conclusions can be deduced from the development of the project:

❖ Automation of the entire system improves the efficiency

❖ It provides a friendly graphical user interface which proves to be better when compared
to the existing system.

❖ It gives appropriate access to the authorized users depending on their permissions.

❖ It effectively overcomes the delay in communications.

❖ Updating of information becomes so easier

❖ System security, data security and reliability are the striking features.

❖ The System has adequate scope for modification in future if it is necessary.

Internship report 2023-24 39

 10. REFERENCE

Rasa Documentation and Tutorials:

1. Official Rasa Documentation: A great starting point for understanding Rasa's capabilities
and how to build chatbots using Rasa. Rasa Documentation
2. Rasa Masterclass: Rasa provides a series of video tutorials called the Masterclass, which
covers various aspects of building chatbots with Rasa. Rasa Masterclass

Healthcare Chatbot Development:

1. Rasa Healthcare Starter Pack: Rasa offers a starter pack that includes a basic healthcare
bot example. It's a good starting point for understanding how to structure a healthcare-
oriented chatbot. Rasa Healthcare Starter Pack
2. Blog Posts on Healthcare Chatbots with Rasa: Check out blog posts and articles related to
healthcare chatbot development using Rasa. Websites like Medium, Towards Data Science,
or Rasa's official blog might have relevant articles.

Healthcare Data and APIs:

1. Medical APIs: Integrate with medical APIs or databases to fetch information about
symptoms, diseases, medications, etc. Some popular APIs include Infermedica and
Symptomate.
2. Medical Datasets: Look for publicly available healthcare datasets that could be used to
train your chatbot. Websites like Kaggle often have datasets related to healthcare.

Community and Forums:

1. Rasa Community Forum: Join the Rasa community forum to ask questions, find solutions,
and connect with other developers building healthcare chatbots. Rasa Community Forum
2. Stack Overflow: Search for questions and answers related to Rasa and healthcare chatbot
development on Stack Overflow. It's a great resource for troubleshooting specific issues.

Books:
"Building Chatbots with Rasa" by Kevin McGrath and Rasa Technologies: This book
provides practical examples and insights into building chatbots using Rasa, which can be adapted
for healthcare applications.

Internship report 2023-24 40