10 XI November 2022

https://doi.org/10.22214/ijraset.2022.47554
 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 XI Nov 2022- Available at www.ijraset.com

Conversational AI Assistant
Tarique Ansari1, Pathan Arshad2, Vishal Khetan3, Bhimashankar Bembre 4, Prof. Priyanka Halle5
1, 2, 3, 4
Students, 5Professor, Department of Computer Engineering, SKN Sinhgad Institute of Technology and Science, Kusgaon(BK),
Pune.

Abstract: A conversational assistant is an intelligent conversational computing system designed to mimic human speech to
provide automated online guidance and support. The growing benefits of conversational support have led to widespread adoption
across many industries to provide virtual support to their customers. Conversation assistance uses methods and algorithms from
his two fields of artificial intelligence: natural language processing and machine learning. However, the application has many
challenges and limitations. This research reviews recent advances in conversation support using artificial intelligence and
natural language processing. We highlight the main challenges and limitations of the current work and provide
recommendations for future research investigations.
Keywords: Conversational assistant, natural language, Artificial Intelligence, Technology Mediated Learning, NLP.

I. INTRODUCTION
A conversation assistant is an intelligent conversational computer program that mimics human speech in a natural way.
Conversation assistants can process user input and generate output. Conversation helpers typically take natural language text as
input, and the output should be the one most relevant to the sentence entered by the user. Conversational assistance can also be
defined as "an online human-computer dialogue system in natural language". A conversation assistant therefore represents an
automated dialogue system capable of supporting thousands of potential users simultaneously. Conversational Assistance is
currently applied to a variety of different fields and applications, spanning from education to e-commerce, encompassing healthcare
and entertainment. Therefore, Conversational Assistance can provide both support in different fields as well as entertainment to
users; this is the case for Conversational Assistance such as Mitsuku and Jessie Humani, “small talk” oriented Conversational
Assistance that could provide a sense of social connection. Conversational Assistance appears, in fact, to be more engaging to the
user than the static Frequently Asked Questions (FAQ) page of a website. At the same time, Conversational Assistance can
simultaneously assist multiple users, thus resulting in more productivity and less expensive compared to human customer supports
services. In addition to support and assistance to customers, Conversational Assistance can be used for providing entertainment and
companionship for end users. Nonetheless, the various levels of embodiment of how conversational support is human-like, and
disclosure of how and when the nature of conversational support is revealed to the user, have implications for user engagement and
conversational support. It seems to affect the trust of impact users’ engagement.

II. LITERATURE REVIEW

The Conversational Assistant has been developed utilizing AIML (Artificial Intelligence Mark-up Language) which, is an XML
patter for creating NLS i.e. natural language software that applies the technique of pattern recognition or pattern matching wherever
a test of expression is utilize to work out if it has definite characteristics.
The Dialog Flow technology, sometimes known as Speak-toit, is used to construct catboats, Speak-toit is a Google development
platform for building Natural Language Processing-based human-computer interface solutions.
Personalized attention to students advances their results as the tutors get to knowledge of the domain where the learners are fragile
.the supply of private educators to character college students of different capacities can conceive larger quantity of experts.
Students can acquire deeper knowledge of their interests era Mediated getting to know (TML) is defined as “an environment in
which the learner’s interactions with getting to know substances (readings, assignments, physical activities, and many others.), peers,
and/or instructors are mediated thru superior statistics technologies”. Conversational Assistant mediated learning is also taken into
consideration as a branch of TML where the look at is personalized and students can dynamically use those bots for their studying.
(Thomas, 2020). The Conversational Assistant check the discernment of the students and presents the subsequent lecture. For
instance, the Summit Learning Project uses Conversational Assistant to identify the weak areas of students and adapt to their leaning
style and help them manage the modules. The Conversational Assistant further conducts quizzes and submits the results to the tutors,
who provide immediate feedback to the students.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1169
 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 XI Nov 2022- Available at www.ijraset.com

This is accomplished through digital forums presently, educators generally tend to assess the students through more than one-
preference questionnaires easing their duties. A scholar can be assessed higher based totally on their writing and composition talents
which can be obtained via essay writing. This has been explored thru an automated evaluating machine in which the researchers have
finished unsupervised gadget getting to know on acting robot assessment and have additionally finished an evaluation on the overall
performance of the robotic which changed into analysed the use of an amalgam of aggregate of term frequency inverse-document
characteristic (tfidf) with cosine Euclidean distance. An actual time examination was conducted on fixed subjects of scientific
students, wherein the internet tutoring software extended their test ratings and cognitive efficacy to threefold the dimensions which
was measured in Cohen’s D effect size (95%) and confidence interval (CI).

III. METHODOLOGY
A. Problem Definition
The aim of this mission is to broaden a Chatbot interacting via voice input like famous private assistant apps like Siri and Alexa
through the use of python. we can define it as a laptop application that impersonates human conversations in its natural format..

B. Proposed Solution
To apply NLP for developing a conversational chatbot for educational institutes. enforcing a Chatbot, as proposed in this paintings,
lets in setting up the precise pedagogical model wherein college students address one of a kind subjects and therefore can get reply
from the chatbot
1) Functional Requirements
a) Computer program that impersonates human conversations in its natural format, which may include text (since the advent of
bots) or spoken language using artificial intelligence (AI) techniques such as Natural Language Processing (NLP) and audio
analysis.
b) Well-designed user interfaces and experiences (UI/ UX).
c) Complex dialogues- In addition to understanding and interacting within conversations, our Conversational Assistant software
should have NLU (Natural Language Understanding) functions to analyse the context of a conversation.

2) Non-Functional Requirements
a) Conversational Assistant should communicate seamlessly across multiple channels such as websites used by phones or laptops
b) Accuracy: The overall accuracy of the web API’s response will be measured using a developer-made testing set.

C. Architecture
It incorporates of 4 parts first is front-stop second is know-how-base 0.33 is back-give up and corpus that are schooling facts. The
communique with the user is finished on the front stop element. NLU (herbal language expertise) is used to apprehend the context
and intent of the user enter. An appropriate response is generated from user. The expertise base determines the chatbots information,
that's done with the NLU and supported at the back-give up. The back-end produces the knowledge base by making use of the
domains corpus. input is given to the chatbot inside the form of speech or text. The input is given to the dialog management system
which defines an appropriate response and asks the assistant to perform the required action. The responses are produced in the form
of text and speech each.

Fig1. Workflow

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1170
 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 XI Nov 2022- Available at www.ijraset.com

D. System Design
We use Generative and Selective strategies in recruitment chatbot which needs a general conversational conversation machine. The
Machine Learning principle is a core philosophy for both these approaches: Build it, Train it, and Test it. By using bot
characteristics, constraints, dialogue dataset, access flow, and Sequence tokens this model is built.

Fig2. Data-driven Dialogue System

E. Mathematical Model
Natural language processing (NLP) is a subfield of linguistics, computer technological know-how, and synthetic intelligence
involved with the interactions among computer systems and human language, especially a way to application computers to method
and examine massive quantities of natural language facts.. The purpose is a laptop able to "information" the contents of documents,
together with the contextual nuances of the language within them. The era can then as it should be extract statistics and insights
contained in the documents as well as categorize and organize the documents themselves.

Fig3. Proposed Model

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1171
 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 XI Nov 2022- Available at www.ijraset.com

IV. CONCLUSION
This Conversational Assistant with the conclusion which looks at the research questions and the aim, and summarizes the found
answers and the key points of the discussion. The aim of the research was to further the development of educational Conversational
Assistant by reviewing what had been done and summarizing this knowledge. This would be done by finding out what capabilities
the Conversational Assistant might have in an educational context and if it could stand on its own or if it required extra generation to
add pedagogical value in training. it's far a flexible and numerous tool, simultaneously simple and complicated, constrained best
through the inventiveness of its author. It can work well on its own and provide educational value, but may reach even better results
when combined with other technology. A more specific answer might be that a Conversational Assistant can be used as a tutor, a
student evaluator, for questions and answers, to communicate with a teacher or simply for natural conversation. The Conversational
Assistant capabilities can be expanded by including it in other systems such as e-learning systems, virtual environment or library
systems (or other database heavy systems) or by augmenting eras like text-to-speech technology, linguistic gear or animation. A real
case has been investigated developing a Conversational Assistant for the students of Fundamentals of Computer Science and
Computer Networks courses. The future research can be divided into two more fields. The first aim is to focus on the developers
support to create and offer tools that allow any teacher to integrate Conversational Assistant into their classes without difficulty, and
provide educational Conversational Assistant guidelines to successfully support coaching methods and students learning.

V. ACKNOWLEDGEMENT
The authors would like to acknowledge the support and guidance provided by management and guides of SKN Sinhgad Institute of
Technology and Science, Lonavala for providing the necessary support and guidance in carrying out this work.

REFERENCES
[1] Yogi Wisesa Chandraa Suyanto (2019) “Indonesian Chatbot of Uni- versity Admission Using a Question Answering System Based on SequencetoSequence
Model”, 4th International Conference on Computer Science and Computational Intelligence, Elsevier BV, 2019.
[2] Pavel Smutny, Petra Schreiberova “Chatbots for learning: A review of educational chatbots for the Facebook Messenger”, Research and Development of
Advanced Methods in the Area of Machines and Process Control supported by the Ministry of Education, Youth and Sports, Czechia 2019.
[3] Omar Zahour, El Habib Benlahmar, Ahmed Eddaoui, Hafsa Ouchra, Oumaima Hourrane “A system for educational and vocationalguidance in Morocco:
Chatbot E-Orientation” International Workshop on Artificial Intelligence and Internet of Things (A2IoT), August 9-12, 2020, Leuven, Belgium.
[4] Yushendri, Jefri Hanif, Alvian Siswadi, Anneke Musa, Purnawar- man Kusuma, Tubagus Prasetyo, Eri“A speech intelligence conversation bot for interactive
media information”” Research Gate,1- 6.10.1109/IAC.2017.8280651,2017.
[5] Francesco Colace, Massimo De Santo, Marco Lombardi, Francesco Pascale, and Antonio Pietrosanto“Chatbot for ELearning: A Case of Study”International
Journal of Mechanical Engineering and Robotics, Research Vol.7,No.5,September 2018.
[6] Samuel, Isaac Ogunkeye, Fiyinfoba Olajube, Ayobami Awelewa, Ayokunle.“Development of a Voice Chatbot for Payment Using Amazon Lex Service with
Eyowo as the Payment Platform, 104- 108.10.1109/DASA51403.2020.9317214,2020.
[7] Punith,Chaitra,Veeranna Kotagi,Chethana R:“Research Paper on Chatbot for Student Admission Enquiry”.
[8] Sandu,Raj.“Adoption of AI-Chatbots to Enhance Student Learning Ex- perience in Higher Education in India.
[9] Ravi, R 2018. Intelligent Chatbot for Easy Web-Analytics Insights. International Conference on Advances in Computing, Communications and Informatics
(ICACCI), IEEE, (pp. 2193-2195).
[10] Dr. Kevin Curran, Dr. Daniel Kelly. Task-based Interaction Chatbot. EEE521 final year project Report school of computing, Engineering & Intelligent System.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 1172