10 III March 2022

https://doi.org/10.22214/ijraset.2022.40830
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue III Mar 2022- Available at www.ijraset.com

Chatbot for Children Assistance

Ankita Dadaso Raskar1, Akshata Santosh Dongare2, Afrin Salim Inamdar3, Rutuja Bharat Kamble4, Pranali Laxman
Patil5, Dr. S V Balshetwar6

Abstract: Children of age 3 to 7 are unaware of language and they face trouble while learning new things so this chatbot
application is designed for them to make their start towards learning easy and in interactive way. This application will help them
to learn basic things required in daily life and also will entertain them. This application is helpful to enhance their skills. This is
designed to provide an interactive learning medium which results in fast progress of child.
A chatbot is artificial intelligence (AI) software that can simulate a conversation (or a chat) with a user in natural language
through messaging applications, websites, mobile apps or through the telephone. A chatbot is often described as one of the most
advanced and promising expressions of interaction between humans and machines. Machine Learning and artificial intelligence
are fast growing technologies and are used in any area to make human activities easy and fast. Chatbots are way more than
simple conversational agents. They can be connected to various APIs which will for example enable them to deal with a wider
range of children requests.
Multifunctional chatbot assistance built using this technology will help children in day to day activity. During 19 pandemic some
issues are raised as big concern one of them is children health and growth. Parents are unable to give their proper attention to
their child due to work pressure, work from home.
Chatbot assistance will help them out in daily activities and give guidelines which will beneficial to their health and growth.
Chatbot will work as a their study partner.

I. INTRODUCTION
During Covid 19 Pandemic for online study of primary school students Government of Maharashtra developed a whatsapp chat
assistance called “Convegenius”. It was beneficial for student during weekly test as it was interactive. Students got familiar with it
easily. There is no any other such application available for students below age of seven which help them in study and their daily
activity. So we propose making of a voice chatbot for children of age group 3 to 7 to assist them in their activity and bind them to
study with entertainment. And the main motivation we found that the majority of a chatbot users it gives a motivation for using a
chatbot. It was very effective and efficient to use. Machine Learning and artificial intelligence are fast growing technologies and are
used in any area to make human activities easy and fast. Multifunctional chatbot assistance built using this technology will help
children in day to day activity.
Children assistant is very useful for children and it is very innovative for them. It facilitates help to do daily work of children and
their studies also. This is help children to solve their different questions and also solve health issues between them .It is also helpful
for their parents to overcome the care for their children. At present , children are also familier with the every technology so,our
project is very helpful for them to make their intertainment medium helpful

II. LITERATURE REVIEW

Today virtual assistance are boosting technology and are used in various field. They are easy to install and access so used widely
due to their flexibility. While studying Chatbot system we found that it would be beneficial for children as they love interactive
sessions. So we studied different research paper on various chatbot applications to understand basic concepts and terms related to
chatbot.
As per [1] Author has developed smart college chatbot using machine learning and python as a channel for information distribution.
This project will investigate how advancements in Artificial Intelligence and Machine Learning technology are being used to
improve many services. For human language processing they used Natural Language Processing (NLP) (“NLP: ability of computer
to understand, analyze, manipulate, and potentially generate human language.”). For some features they have also focused on
Artificial Intelligence Markup Language (AIML) (“AIML: AIML is an XML dialect for creating natural language software
agents”).
As per [2] author has focused on design and development of an intelligent voice recognition chatbot. The paper presents a
technology demonstrator to verify a proposed framework required to support web based bots. This online chat system follows client
server approach. Voice recognition process has two parts capturing and analysis of input signal which allows the server to generate
response faster.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1307
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue III Mar 2022- Available at www.ijraset.com

When comes to health generating response is more crucial and needs the high accuracy in [3] we studied the chatbot system for
conversational healthcare service. In project the way they have distributed tasks and deep analyzing of data was quite impressive.
They have made the module to understand user which is beneficial in response generation.
As per [4] author has focused on dialog management approaches and tools with respect to the different aspects like capability of
creating natural, robust and complex dialogs, convenience for developers, scalability, reusability. On analysing these goals they had
proposed the dimensions of analysis such as dialog structure, learning, error handling, dependencies, control, domain independence,
and tool availability.
As per [5] author has outlined interpersonal assistants as a promising model that conversational agents may evolve. They also
mentioned some elicited key functional elements for always-on services running on resource-scare devices. This helped to
understand how to keep our assistant always active in proper manner.
As per [6] - this paper illustrate a web based infrastructure of architecture for conversational agents equipped with a modular
knowledge base. It focuses on the enhancement of the agent interaction capabilities. From paper we study about web based chatbot
and their infrastructure.
As per [7] author G. Pilato, A. Augello and S. Gaglio, in paper "A Modular Architecture for Adaptive ChatBots," has illustrated
architecture for a conversational agent based on a modular knowledge representation. This paper focus on accurate response for
query in effective manner to make conversation more attractive.
As per [8] automatic chatbot knowledge acquisition method from online forums is presented in this paper. It includes a classification
model based on rough set and the theory of ensemble learning is combined to make decision.
As per [9] this paper presents a survey on similarities, differences, and limitations of the existing chatbots, it also presents a survey
on existing chatbots and techniques applied on it. This gives the clear idea of continuous evolution of chatbot assistant. This paper
helps us to understand current limitations of chatbot system. Also we got the knowledge various technology used in different types
of chatbots.
This paper [10] "Review on Implementation Techniques of Chatbot," provides a critical review of chatbots and the current strategies
are executively explored and talked discussed. This paper is also based on comparison of different chatbots implementation
techniques. From paper we get idea for better implementation of chatbot.

Table 1. Comparison Table

Sr. Paper Name Publisher Techniques Merits Demerits

No.
1 Smart Collage H.K.K, A .K. Here artificial 1. This paper provide more This paper only show
Chatbot using ML Palakurthi , V intelligence, user interactive as it that user can ask any
and Python .Putnala , Dr. Ashok machine responds to the user queries. numbers of queries to
Kumar K learning, natural 2. As the paper the feedback chatbot system
language is stored in the database regarding collage.
processing which can used by collage
techniques are to know how efficiently
used chatbot is answering user
queries.
2 An intelligent Web- S.J.du Preez,Student Here Artificial This paper shows This paper shows that
Based voice chatbot Member,IEEE,M.La Intelligence,XM environmental facilitating all modules can not
ll2.S.Sinha3,MIEEE L transparent and high running off one
,MSAIEE ,JAVA,AIML,A performance of the overall system.
LICE system
techniques are
used

3. Chatbot as Mladan Jovanovic, Here shared The paper shows that how The paper only
Conversational Marcos Baez, Fabio design metaphor chatbot easily interact with provide medication
Healthcare Services Casati technique used human/patient. reminder not a
medicines to a
patients.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1308
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue III Mar 2022- Available at www.ijraset.com

4 Approaches for J. Harms, P. Hera automatic 1. This paper provides an This paper shows
Dialog Management Kucherbaev, A. speech overview of the state-of- memory network
in Conversational Bozzon and G. recognition, the-art of commercial as research is not mature
Agents Houben, artificial well as research tools. enough yet to explore
intelligence, 2. This paper shows domain independence.
machine opportunities for future
learning are research directions.
techniques used
5 Towards Inseok Hwang, Here shared 1. It trains the parents and 1. This paper provides
Interpersonal Chulhong Min design metaphor develops the language of prominence of micro
Assistant: Next Youngki Lee , techniques used child. structural properties is
Generation Dangsun Yim, and Artificial 2. Frequently changing not limited to a
Conversational Chungkuk yoo John Intelligence are speech characteristics as particular example of
agent Kim. use they grow, and insufficient interpersonal
speech carpus specialized in assistants.
children.
6 A Modular A. Augello, M. Here This paper provides the The test script have
Framework for Scriminaci, S. conversational information about test data embedded in
Versatile Gaglio and G. Pilato agents, modular architecture and how to them, which will
Conversational KB, ontology exploit different modules become problem
Agent Building reasoning, suited for specific dialogue when updating the
semantic spaces requirements. code
techniques are
used
7 A Modular G. Pilato, A. Here artificial This paper provides Speech acts are
Architecture for Augello and S. intelligence, intelligent conversational detected through a
Adaptive Chatbots Gaglio Corpus agents with a dynamic and simple rule-based
Callosum Hexible behaviour. speech act classifier
techniques are whose description
used goes beyond the scope
of this paper.
8 Automatic Chatbot Y. Wu, G. Wang, Here Forum, This paper shows high Approaches are not
Knowledge W. Li and Z. Li Multiple rough recognition efficiency to capable of extracting
Acquisition from set techniques related replies and the knowledge for
Online Forum via are used combination of ensemble specific domain.
Rough Set and learning improve the result.
Ensemble Learning
9 A Survey on M. Nuruzzaman Here Neural This paper provides Existing chatbot do
Chatbot and O. K. Hussain Network, Peep sequential attention not have an
Implementation in learning, mechanism in deep interactive user
Customer Service Natural recurrent neural networks. interface and maintain
Industry through language poor documentation.
Deep Neural processing,
Networks Dialogue
system
techniques are
used
10 Review on S. Nithuna and C. Hare AIML, In this paper critical review Hard to understand
Implementation A. Laseena ALICE,DNN, of chatbot and current the framework
Techniques of machine strategies are explored. effectively with no
Chatbot learning, natural rules to visitors.
language
processing
techniques are
used

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1309
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 10 Issue III Mar 2022- Available at www.ijraset.com

III. CONCLUSION
Chatbot assistant or virtual assistant are fast growing technologies having large impact on different industries. We have variety of
virtual assistant available in market which helps to reduce the human efforts as they are self-learners from conversation and
automated. There is no need to invest our time in their tasks as once it started learning it start becoming better and better.
While building a chatbot first we have to create proper sequence of conversation as it is the heart of system. With proper flow of
dialog system becomes more attractive. Choosing correct technology is crucial part of building a chatbot. We have make our system
with respect to current technology used in industry and update its functionality to make it compatible with respect to time. Also the
starting and ending of conversation is important to make impression on user. We have to focus on requirement of end user and try to
fulfill them. Adding feelings and improve relevant answers is must to make chatbot appear as real person.

REFERENCES
[1] H. K. K., A. K. Palakurthi, V. Putnala and A. Kumar K., "Smart College Chatbot using ML and Python," 2020 International Conference on System,
Computation, Automation and Networking (ICSCAN), 2020, pp. 1-5, doi: 10.1109/ICSCAN49426.2020.9262426.
[2] S. J. du Preez, M. Lall and S. Sinha, "An intelligent web-based voice chat bot," IEEE EUROCON 2009, 2009, pp. 386-391, doi:
10.1109/EURCON.2009.5167660.
[3] M. Jovanović, M. Baez and F. Casati, "Chatbots as Conversational Healthcare Services," in IEEE Internet Computing, vol. 25, no. 3, pp. 44-51, 1 May-June
2021, doi: 10.1109/MIC.2020.3037151.
[4] J. Harms, P. Kucherbaev, A. Bozzon and G. Houben, "Approaches for Dialog Management in Conversational Agents," in IEEE Internet Computing, vol. 23,
no. 2, pp. 13-22, 1 March-April 2019, doi: 10.1109/MIC.2018.2881519.
[5] I. Hwang, Y. Lee, C. Yoo, C. Min, D. Yim and J. Kim, "Towards Interpersonal Assistants: Next-Generation Conversational Agents," in IEEE Pervasive
Computing, vol. 18, no. 2, pp. 21-31, 1 April-June 2019, doi: 10.1109/MPRV.2019.2922907.
[6] A. Augello, M. Scriminaci, S. Gaglio and G. Pilato, "A Modular Framework for Versatile Conversational Agent Building," 2011 International Conference on
Complex, Intelligent, and Software Intensive Systems, 2011, pp. 577-582, doi: 10.1109/CISIS.2011.95.
[7] G. Pilato, A. Augello and S. Gaglio, "A Modular Architecture for Adaptive ChatBots," 2011 IEEE Fifth International Conference on Semantic Computing,
2011, pp. 177-180, doi: 10.1109/ICSC.2011.68.
[8] Y. Wu, G. Wang, W. Li and Z. Li, "Automatic Chatbot Knowledge Acquisition from Online Forum via Rough Set and Ensemble Learning," 2008 IFIP
International Conference on Network and Parallel Computing, 2008, pp. 242-246, doi: 10.1109/NPC.2008.24.
[9] M. Nuruzzaman and O. K. Hussain, "A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks," 2018 IEEE 15th
International Conference on e-Business Engineering (ICEBE), 2018, pp. 54-61, doi: 10.1109/ICEBE.2018.00019.
[10] S. Nithuna and C. A. Laseena, "Review on Implementation Techniques of Chatbot," 2020 International Conference on Communication and Signal Processing
(ICCSP), 2020, pp. 0157-0161, doi: 10.1109/ICCSP48568.2020.9182168.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1310