Conversational AI Powered Chatbot Using Lex and AWS

International Journal of Trend in Scientific Research and Development (IJTSRD)
Volume 6 Issue 3, March-April 2022 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470
@ IJTSRD | Unique Paper ID – IJTSRD49722 | Volume – 6 | Issue – 3 | Mar-Apr 2022 Page 1622
Conversational AI Powered Chatbot Using Lex and AWS
Pradyumna Saini, Mohd Tajammul
School of Computer Science and IT, Jain University, Jayanagar, Bangalore, Karnataka, India
ABSTRACT
Artificial intelligence-based application for their treatment. Thus,
telehealth will rapidly and radically transform in-person care to
remote consultation of patients. Because of this, it developed a
Multilingual Conversational Bot based on Natural Language
Processing (NLP) to provide free primary healthcare education,
information, advice to chronic patients. The study introduces a novel
computer application acting as a personal virtual doctor that has been
opportunely designed and extensivelytrained to interact with patients
like human beings. This application is related to a server less
architecture and it aggregates the services of a doctor by providing
preventive measures, home remedies, interactive counseling sessions,
healthcare tips, and symptoms covering the most prevalent diseases
in rural India. The paper proposes a conversational bot for delivering
telehealth in India to increase the patient's access to healthcare
knowledge and leverage of artificial intelligence to bridge the gap of
demand and supply of human healthcare providers. This AI
application has resulted in reducing the barriers for access to
healthcare facilities and intelligent consultations remotely to allow
time to time care and quality treatment, thereby effectively assisting
the society.
KEYWORDS: chatbot Alexa; conversational technology, digital
health Amazon Web Services; Internet of Things
How to cite this paper: Pradyumna Saini
| Mohd Tajammul "Conversational AI
Powered Chatbot Using Lex and AWS"
Published in
International Journal
of Trend in
Scientific Research
and Development
(ijtsrd), ISSN: 2456-
6470, Volume-6 |
Issue-3, April 2022,
pp.1622-1627, URL:
www.ijtsrd.com/papers/ijtsrd49722.pdf
Copyright © 2022 by author (s) and
International Journal of Trend in
Scientific Research and Development
Journal. This is an
Open Access article
distributed under the
terms of the Creative Commons
Attribution License (CC BY 4.0)
(http://creativecommons.org/licenses/by/4.0)
I. INTRODUCTION
The major challenges that India faces is to cater to
good quality and affordable healthcare industry to its
growing population. The World Health Report issued
by World health Organization has ranked India’s
healthcare system at 112 out of 190 countries.
Same time are not cost-efficient and well-matched to
their medical needs. To seek more ways to provide
timely medical care, access and quality treatment to
the patient, the role comes into play which connects
patients with healthcare providers.
In the current growing age of Artificial Intelligence
(AI) powered chatbots are playing a leading role by
exemplifying the function of a virtual assistant that
could manage a conversation via speech. use of voice
queries to get answers, perform actions and
recommendations according to users needs. They are
adaptable to the user's individual language usages,
searches , and preferences with continuing use.
applications to access and record the patient's data. At
the patient's side, it is a cheaper alternative; AI-
enabled virtual assistants that can render 24x7 care to
a wide variety of patients. Many people are suffering
from chronic diseases, disabled patients, and patients
living in areas would benefit most from such
powerful virtual assistants’ tools. Advantages of these
System: reduced time on the part of physicians,
improved security of patient data.
The healthcare domain is facing a range of challenges
due to increasing service demand. Shortage of trained
professionals and their limited availability while
providing treatment to the patients is a major
challenge. The main reason for the problem is that
healthcare practitioners have to overcome
organizational, temporal and geographical barriers to
assist the patients. The availability of trained
professionals to provide an authentic treatment within
the appropriate time is important for disease
diagnosis, assisting patients having cholesterol, blood
pressure, diabetes or other severe diseases and for the
treatment of pregnant women. Mobile Health services
resolve these concerns, helping patients with
authentic healthcare accessible from remote locations
irrespective of time and space. Traditional mHealth
IJTSRD49722

International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
applications were limited to basic functions such as
recording exercise activities or counting calories
burnt. However, mobile health applications are
becoming more adaptive and complex, providing
advanced features like disease diagnosis and assistive
patient treatment. Chatbots or conversational agents
come under the modern category of mHealth services.
They use natural languages and voice- based
interaction while communicating with the patients,
through a ‘question-answer oriented’ interface model.
II. BACKGROUND AND RELATED WORK
A. Smart Phone apps
AirStrip offers a mobile, interoperable platform that
allows care coordination between multiple devices
and multiple care settings. Data from an tech health
records, health information exchanges, medical
devices, and other monitoring solutions can be
accessed bysmartphones, tablets, and computers from
hospitals, post-acute care centers, and community-
based care organization. The AirStrip platform gives
providers a tool to all data into one platform that can
be accessed via telemedicine, and integrates with
other vendor systems.
This patient-faces mobile app allows patients to
directly find information on their health conditions
and gives them step-by-step guide to treat conditions
in the most effective way possible.
B. Chatbot features and implementation
standards
The authors also mention the principles to modify
healthcare applications. These implementation
standards can be used as a reference while structuring
and designing chatbot applications. The standards
meets four parameters- user experience/ adherence,
data safety, data privacy, data integration, and
effectiveness. The authors have also described
challenges to handle these parameters.
C. Existing solutions
Instant messaging platforms have been widely
adopted as one of the main technologies to
communicate and exchange information. Nowadays,
most of them provide built-in support for integrating
chatbot applications, which are automated
conversational agents capable of interacting with
users of the platform. Chatbots have proven useful in
many other contexts to automate tasks and improve
the user experience, such as automated customer
services, education, and e-commerce. Moreover,
existing reports emphasize that chatbot design will
become a key ability in IT hires in the near future.
The global chatbot market is projected to reach 2
billion dollars by 2024, growing at a CAGR
(compound annual growth rate) of 29.7%.
This interest and demand for chatbot applications has
emphasized the need to be able to quickly build
complex chatbot applications supporting AI-based
natural language processing in order to be able to
fluently chat with the user. Furthermore, any non-
trivial chatbot requires accessing an orchestration of
internal and external services in order to perform the
requested user actions.
As such, chatbots are becoming complex software
artifacts that require a high-level of expertise in a
variety of technical domains, ranging from NLP to a
deep understanding of the APIs of the targeted instant
messaging platforms and third-party services to be
integrated.
The research use primary data, which was collected
using structured questionnaire. The sample size for
the study that consists of 100 respondents. The
questionnaire has prepared in such a way so as to
gather data from the respondents, which will be
helpful in attaining the objectives of the study. The
collected data has been carefully scrutinized,
tabulated and analyzed using simple statistical
techniques like percentages. and support to translate
more than 30 languages. The cognitive service
‘Language Understanding Intelligent Service’ (LUIS)
has been used in
the design; for creating HTTP endpoints to return
JavaScript Object Notation (JSON) responses,
developing new models and while training the
language model with sample utterances. The design
uses the Telegram messaging app. It performs
message encryption and offers a free, open-source
and secure platform. The chatbot tracks user location
through Google Maps Application Programming
Interface.
Many articles and research papers have underlined
the increasing popularity and acceptance of
pregnancy companion mobile apps. The chatbot is
effective than a smartphone app as it provides a voice
interface through a personalized platform. Current
chatbot designs provide suggestions and tips on many
topics like lifestyle, personal wellbeing, healthy diet,
and others. However, some additional aspects are
necessary to make these chatbots more relevant for
users. In [14-27], authors have given a number of
solutions for security mechanism in cloud computing.

III. DESIGN AND METHODOLOGY
A. Technology Acceptance Survey
The authors explain the ‘Unified Theory of
Acceptance and Use of Technology’ () system to
analyze the user acceptance of technology and the
application use context. The advanced ver. deals with
the technology application in private contexts. can be
considered as a reference while analyzing the impact
of a chatbot in many applications. Researchers have
already used the model in the context of mHealth
applications. It focuses on aspects such as Effort
expectations, Performance expectations, Facilitating
conditions, Social influences, Price values Hedonic
motivations and Habits. A set of questions were
framed to verify the primary familiarity of the user
with the smartphone or chatbots and to predict how
frequently they are using them. Multiple questions
were asked to record user opinions while accepting
the chatbot as a assistant and as a replacement tool for
the traditional smartphone interaction.
Fig 1 Survey summary-
Almost all users were having a primary exposure for
technology, but some of them accepted that they
don’t use chatbots more frequently. As most of the
interviewees often feel the need for a doctor’s advice
in a day, they admitted that sometimes they can’t
raise their queries or questions with someone.
Although they prefer using a search engine like
Google to get the answers; they were in favor of a
chatbot to replace it. Users were asked to provide
their consent for the parameters on the scale of 1-5
(strongly disagree, disagree, neutral, agree, strongly
agree) while looking at the feasibility of a chatbot.
Figure 1 shows a statistical summary of the survey,
which highlights the positive user inclination towards
a Health chatbot.
The survey analysis interpreted from factors resulted
in a fairer analysis of the technology acceptance. The
responses from the users were helpful in structuring
the chatbot design features, making it a relevant and
engaging tool for the users.
B. Design and Block diagram
Alexa is a popular virtual voice assistant application
developed by Amazon. Devices like Amazon Echo
Plus, Echo Studio or Echo dot are enabled with
Alexa. Amazon Alexa provides multiple function like
real-time data extraction, voice interaction, weather
forecast, broadcasting, smart audio-video streaming,
tasks list management, home-automation control and
other. Third-party users can also configure these
functionalities by designing and installing a custom
‘skill’ on Alexa enabled smart speaker. The skill, just
like a mobile phone application allows the user to
perform certain defined tasks that involve features
such as service assistance or voice interaction. Alexa
has become a popular tool in realizing the concept of
intelligent and interactive chatbots.
Designing a chatbot on top of a custom Alexa skill
allows developers to utilize a range of Amazon Web
Services like AWS Lambda, Simple Email Service
(SES), Simple Notification Service (SNS) and
DynamoDB.
AWS Lambda is a cloud computing platform that
allows users running code without managing or
provisioning the cloud servers. The developer is
charged only for the compute time consumed- no
charge when the code doesn’t run. The Lambda
function codes are run on a computing infrastructure
having high-availability. It also manages the
administration of cloud computing resources, capacity
provisioning and automatic scaling, maintenance of
the server and operating system, code logging and
monitoring. The developer just supplies the Lambda
function code in one of the supported languages, and
the other services are handled by AWS Lambda.
AWS DynamoDB is a NoSQL database service
providing higher scalability and quick performance.
Developers don’t have to worry about the
management of hardware provision, replication,
software patching, setup, and configuration, or cluster
scaling as this is handled by DynamoDB. It also
secures the sensitive data by encrypting it at rest,
reducing the burden on the developer. It allows the
creation and maintenance of any amount of data.
More on, DynamoDB serves incoming requests are
any traffic level.
AWS SNS is a cloud-based notification service that
can be used for generating message notifications from
serverless and distributed applications. It is a durable

and secure platform that offers higher throughput
with higher availability.
AWS SES is a cloud-based service that can be
configured for generating email notifications,
transactional or marketing emails. SES is a reliable,
cost-effective, flexible and highly-scalable service
useful for multiple use cases serving different
requirements.
AWS Lex enables you to build applications using
a speech or text interface powered by the same
technology that powers Amazon Alexa.
Lex bot interactions with AWS Lambda In Lex
you now create a single Lambda function per
language per bot, which must be able to support
both types of Lex interaction:
Initialization/Validation - Lambda is called at
every turn of the converation. This allows you to
initialise, validate or override slot data values.
Amazon Connect - An easy-to-use omnichannel
cloud contact center that helps you provide
superior customer service at a lower cost. Over
ten years ago, Amazon’s retail business needed a
contact center that would give our customers
personal, dynamic, and natural experiences.
Figure 2 displays the integrated system block
diagram. Voice communication can be observed
between the pregnant woman and the Alexa enabled
Echo dot device. Alexa Skills Kit (ASK) handles user
requests captured in as an audio signal. It converts the
audio input into the equivalent text to detect the
‘intent’ or context of the request. Corresponding to
the detected intent, the associated Lambda function
event gets evoked. Request response interaction
between the Lambda function and ASK takes place in
the JSON format. Suitable actions are performed by
Lambda for the raised request, such as extraction of
the data or generation of a response. The Lambda
function interacts with AWS DynamoDB for data
storage or data retrieval. ASK translates the responses
sent by the Lambda function to audio output for the
user. SNS and SES are triggered through the Lambda
function to generate short text notifications or emails
in case of certain events.
Fig 2 system block diagram
C. Data source selection
An authentic and reliable data source is needed to
extract the backend data which is used for the chatbot
design. Considering these features a platform
recommended by healthcare practitioners, the
National Health Service (NHS) website was selected
as a dataset source. NHS is the national healthcare
system in the United Kingdom. The website has
information content about pregnancy such as weekly
guide, recommendation, and also suggestions about
relevant miscellaneous topics.
IV. IMPLEMENTATION AND
VERIFICATION
A. Implementation aspects
AWS Developer account and AWS Management
console account are needed to configure an Alexa
skill with Amazon Web Services. ASK Developer
Console enables the programmer to configure and
publish a custom Alexa skill. On the other side, the
AWS Management console enables the programmer
to utilize multiple AWS services, monitor cloud
services, user and roles management, handle costing
and billing and execution requirement.
In this growing world of AI, consumers are getting
technological help in all facets of their lives. The data
provides various ways to get information and has
radically changed the way of communication.
Innovation has enhanced our lives with more
opportunities, and everything is quite simple for us.
Everybody likes to collaborate and expect quick
answers without much delay. You can use online
networking platforms or websites regularly for
various reasons to connect with others.
A chatbot is a program or service that easily connects
with us to help solve our queries/problems. The
services that a chatbot can deliver are quite diverse,
from providing important life-saving health messages
to checking the weather. While interacting with
chatbots, you should feel as if you are talking with a
real person only.
From my perspective, chatbots or smart assistants
with artificial intelligence are dramatically changing
businesses. There is a wide range of chatbot building
platforms that are available for various enterprises,
such as e-commerce, retail, banking, leisure, travel,
healthcare, and so on.

CONCLUSION AND FUTURE SCOPE
The chatbot solution offers suggestions and
recommendations Health care ; such as patient care
medical check experienced emotional feelings,
observed symptoms, suggestions, and
recommendations about other relevant topics. The
design also addresses one more limitation of the
existing solutions, providing mobile message and
email notification service in the case of an
emergency. The chatbot records daily sleep duration
and regular exercise activities, by maintaining a diary
log which is useful while consulting the doctor. It also
provides tips and information about multiple topics
that are relevant to medicine.
The paper presents a proof of concept model to
analyze the multiple possible services, which a health
care chatbot system can provide. The primary
objective was the implementation of the probable use
cases by applying a suitable technology. The
proposed solution is not a full-proof solution;
however, it is possible to further extend its features
and the technology application demonstrations to
structure a
The proposed approach of recording sleep time and
exercise activities from the user conversation can be
replaced with the help of smart fitness devices or
body wearable’s to record them automatically. Smart
healthcare devices that monitor personal health
parameters such as blood oxygen level,
Electrocardiogram readings, heart rate, and body
temperature; can be used along with the chatbot
system to identify the emergency.
REFERENCES
[1] https://ai-chatbot.sustainablelivinglab.org/
[2] https://ieeexplore.ieee.org/document/9137944D
evelop ment of a Voice Chatbot for Payment
Using Amazon Lex Service with Eyowo as the
Payment Platform | IEEE Conference
Publication | IEEE Xplore
[3] https://ieeexplore.ieee.org/document/9105762
[4] Personal robotic assistants: a proposal based on
the intelligent services of the IBM cloud and
additive manufacturing | IEEE Conference
https://ieeexplore.ieee.org/document/9271971
[5] Ticketing Chatbot Service using Serverless
NLP Technology | IEEE Conference
https://ieeexplore.ieee.org/document/8576921
[6] https://aws.amazon.com/events/aws-
innovate/data/
[7] Amazon Web Services (AWS), (2018). “What
Is AWS Lambda? Documentation”
[8] https://docs.aws.amazon.com/lambda/latest/dg/
welco me.html [Accessed 24 July 2019]
[9] Amazon Web Services (AWS), (2018). “What
Is Amazon DynamoDB? Documentation”.
[online] Available from
https://docs.aws.amazon.com/amazondynamod
b/latest/ developer guide/Introduction.html
[Accessed 04 July 2019]
[10] Amazon Web Services (AWS), (2018).
“Amazon Simple Notification Service,
Overview”. https://aws.amazon.com/sns/
[11] Amazon Web Services (AWS), (2018).
“Amazon Simple Email Service, Overview”.
https://aws.amazon.com/ses/
[12] https://aws.amazon.com/partners/training/path-
tech-pro/
[13] https://build.amazonalexadev.com/Alexa-for-
Business-Confirmation.html?aliId=eyAWS
Management Console (amazon.com)
[14] Alam T., Tajammul M., Gupta R. (2022)
Towards the Sustainable Development of Smart
Cities Through Cloud Computing. In: Piuri V.,
Shaw R.N., Ghosh A., Islam R. (eds) AI and
IoT for Smart City Applications. Studies in
Computational Intelligence, vol 1002.
[15] Tajammul, M., Shaw R.N., Ghosh A., Parveen
R. (2021) Error Detection Algorithm for Cloud
Outsourced Big Data. In: Bansal J.C., Fung
L.C.C., Simic M., Ghosh A. (eds) Advances in
Applications of Data-Driven Computing.
Advances in Intelligent Systems and
Computing, vol 1319.
[16] Tajammul, M, Parveen, R., “Cloud Storage in
Context of Amazon Web Services”,
International Journal of All Research Education
and Scientific Methods, vol. 10, issue 01, pp.
442-446, 2021.
[17] Tajammul, M., Parveen, R., “Auto Encryption
Algorithm for Uploading Data on Cloud
Storage”, BIJIT - BVICAM’s International

Journal of Information Technology, vol. 12,
Issue 3, pp. 831-837, 2020.
[18] Tajammul, M., Parveen, R., “Key Generation
Algorithm Coupled with DES for Securing
Cloud Storage,” International Journal of
Engineering and Advanced Technology
(IJEAT) ISSN: 2249-8958, Volume-8 Issue-5,
June 2019 no. 5, pp. 1452–1458, 2019.
[19] Tajammul M., Parveen R., “Two Pass
Multidimensional Key Generation and
Encryption Algorithm for Data Storage
Security in Cloud Computing”, International
Journal of Recent Technology in Engineering,
Vol. 8, Issue-2, pp. 4152–4158, 2019.
[20] Tajammul M., Parveen R., “Algorithm for
Document Integrity Testing Pre-Upload and
Post- Download from Cloud Storage”,
International Journal of Recent Technology in
Engineering, Vol. 8, Issue-2S6, pp. 973– 979,
2019.
[21] Tajammul, M., Parveen, R., “Auto Encryption
Algorithm for Uploading Data on Cloud
Storage”, BIJIT - BVICAM’s International
Journal of Information Technology, vol. 12,
Issue 3, pp. 831-837, 2020.
[22] Tajammul, M., Parveen, R., and M.
Shahnawaz, “Cloud Computing Security Issues
and Methods to Resolve: Review,” Journal of
Basic Applied Engineering and Research, vol.
5, no. 7, pp. 545–550, 2018.
[23] Tajammul, M., Parveen, R., Delhi, N. (2018).
Comparative Study of Big Ten Information
Security Management System Standards,
International Journal of Engineering Research
in Computer Science and Engineering
(IJERCSE) Vol 5, Issue 2, pp. 5-14, 2018.
[24] M. Tajammul, R. Parveen, N. K. Gaur and S.
D, "Data Sensitive Algorithm Integrated with
Compression Technique for Secured and
Efficient Utilization of Cloud Storage," 2021
IEEE 4th International Conference on
Computing, Power and Communication
Technologies (GUCON), 2021, pp. 1-9, doi:
10.1109/GUCON50781.2021.9573648.
[25] Tajammul, M., Parveen, R., (2017).
Comparative Analysis of Big Ten ISMS
Standards and Their Effect on Cloud
Computing, 978-1-5386-0627
8/17/31:00c2017IEEE; 9001; 362367.
[26] Tajammul, M., and R. Parveen, "To Carve out
Private Cloud with Total Functionality," 2020
2nd International Conference on Advances in
Computing, Communication Control and
Networking (ICACCCN), 2020, pp. 831-835,
doi: 10.1109/ICACCCN51052.2020.9362826.
[27] M. Tajammul, R. Parveen and I. A. Tayubi,
"Comparative Analysis of Security Algorithms
used in Cloud Computing," 2021 8th
International Conference on Computing for
Sustainable Global Development (INDIA
Com), 2021, pp. 875-880,
doi:10.1109/INDIACom51348.2021.00157.

Conversational AI Powered Chatbot Using Lex and AWS

More Related Content

Similar to Conversational AI Powered Chatbot Using Lex and AWS (20)

More from ijtsrd (20)

Recently uploaded (20)

Conversational AI Powered Chatbot Using Lex and AWS