Scribd
Upload
13 views19 pages

CCVT Sem7 Group17 MidTermPPT

The document presents 'InterviBot: Ace Every Interview', a cloud-based AI tool designed to enhance job interview preparation through real-time feedback and personalized guidance. It addresses the limitations of traditional interview preparation methods by utilizing facial analysis, natural language processing, and a user-friendly interface. The project outlines its objectives, technology stack, methodology, and implementation strategies to improve candidates' performance in interviews.

Uploaded by

aryanranjan.cse
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as KEY, PDF, TXT or read online on Scribd
13 views19 pages

CCVT Sem7 Group17 MidTermPPT

The document presents 'InterviBot: Ace Every Interview', a cloud-based AI tool designed to enhance job interview preparation through real-time feedback and personalized guidance. It addresses the limitations of traditional interview preparation methods by utilizing facial analysis, natural language processing, and a user-friendly interface. The project outlines its objectives, technology stack, methodology, and implementation strategies to improve candidates' performance in interviews.

Uploaded by

aryanranjan.cse
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as KEY, PDF, TXT or read online on Scribd
You are on page 1/ 19

Major Project

Title:
InterviBot: Ace Every Interview
Cloud based AI Tool

Presented by: Guided by:


Aryan Ranjan (500095595) Dr. Swati Rastogi
Khushi Nimawat (500095624) School of Computer
Science
Content

1. Introduction
2. Problem Statement
3. Objectives
4. Tech Stack
5. Methodology
6. Algorithms
7. SWOT Analysis
8. Implementation
9. Conclusion
10. References
1. Introduction

Importance of Interviews: In the modern


job market, securing a desirable job requires
not only strong qualifications but also
performing well in interviews.
Challenges in Preparation: Many
candidates struggle with effective
preparation for interviews.
Limitations of Traditional Methods:
Traditional preparation methods, like using
static practice questions and generalized
feedback, have limitations.
Dynamic Nature of Real Interviews:
Conventional approaches may not
adequately prepare candidates for the
dynamic and unpredictable nature of real
interviews.
2. Problem Statement
Effective job interview preparation is challenging because traditional methods,
like generic practice questions and mock interviews, lack adaptability and real-
time feedback. They don't provide personalized guidance or consider non-verbal
cues such as facial expressions and vocal tone, which are crucial in interviews.

1. General practice questions and mock


interviews lack adaptability.
2. Do not offer real-time feedback.
3. Non-verbal cues like facial expressions and
vocal tone, which are vital in interviews,
are often overlooked.
4. No personalized guidance tailored to
specific job roles or skills.
3. Objectives
1. Real-Time Response Evaluation and feedback with Facial Analysis and User-
Friendly Interface:
Analyze facial expressions.
Design a user-friendly interface for easy interaction and practice.
2. NLP for generating contextual interview questions and feedbacks on Speech
Analysis:
Customize questions based on user profiles and job roles.
Provide detailed feedback on content, structure, and delivery for Improvement.
3. Cloud-Based Solution:
Deploy on the cloud for scalability and performance.
Optimize for cost efficiency and continuous monitoring.
4. Technology Stack
Frontend: Machine Learning and NLP:
React.js, HTML/CSS For building and training deep
WebRTC(real-time video and audio learning models for NLP and facial
capture, for facial and speech analysis) expression analysis.
Backend: Hugging Face Transformers: For
Express.js (Node.js), Python(For leveraging pre-trained NLP models
implementing machine learning models, like BERT or GPT for question
NLP processing, and facial and speech generation and response evaluation.
analysis algorithms) OpenCV: For facial expression
Database: detection and analysis.
MongoDB SpeechRecognition: For speech-to-
Version Control text conversion and analysis of user
responses.
CI/CD GitHub
SDLC Model
Agile
5. Methodology
InterviBot: Ace Every
Interview
Generates contextual
questions
Evaluates responses
Analyzes facial and
speech patterns.
Offer personalized
feedback on both verbal
and non-verbal aspects
Enhance interview
preparation, by improving
their performance and
success rate.
6. Algorithms
6. Algorithms
7. SWOT Analysis
8. Implementation
8. Implementation
8. Implementation
8. Implementation
8. Implementation
9. Conclusion
9. Conclusion
10. References
[1] Mrs. P. Swetha, B. Gowthami, Ch. Sreemam, G. Amruth, “AI-Based Mock Interview
Evaluator: An Emotion and Confidence Classifier Model,” IEEE Xplore, 2023.
[2] Prof. H. R. Agashe, Dhanashri Anwat, Prajakta Derle, Payal Nagare, Siddhi Dhavale,
“AI-Based Mock Interview Evaluator and Analysis: To Analyze Emotion, Confidence, and
Knowledge” IJARSCT 2023.
[3] Aditi S. More, Samiksha S. Mobarkar, Siddhita S. Salunke, Reshma R. Chaudhari,
“Smart Interviews Using AI” VIVA Institute of Technology ISSN 2022.
[4] B. C. Lee, Ph.D. Candidate, Seoul Business School, Seoul School of Integrated
Sciences and Technologies (aSSIST), Seoul, South Korea, “Development of an AI-Based
Interview System for Remote Hiring,” IAEME 2021.
[5] Shashank Rai, Alisha Miranda, Samiya Jagirdar, Prof. Nidhi Chitalia, “Skillup Bot: An
AI-Driven Mock Interview Platform” IRJMETS 2022.
[6] Prof. Taware R.K., Bhagyashree Shinde, Nikita Rasal, Snehal Ghorpade, “Smart
Interview System Using AI Technology” IRJMETS 2021.
Thank You

You might also like