SMART INTERVIEW SYSTEM
Nikita Kailasnath Rasal
Bhagyashree Vilas Shinde
Snehal Mahesh Ghorpade
Amaan Afraj Tamboli
Under the Guidance of
Prof. R.K.Taware
2023-2024
Table of Contents
1 Introduction
2 Problem Statement
3 Purpose ,Objective and Scope
4 System Requirements
5 Existing System
6 Proposed System
7 System Architecture
8 Use-Case Diagram
9 Class Diagram
10 Activity Diagram
11 Sequence Diagram
12 Component Diagram
13 DFD Level-0 Diagram
14 DFD Level-1 Diagram
15 DFD Level-2 Diagram
16 Algorithms
17 Conclusion
18 Bibliography
Introduction
Information technology is one of the fastest areas that are
growing around the world.
The automation of these interview phases can help companies
streamline their recruitment processes, reduce human bias,
and save time.
Currently most companies follow traditional interviewing
processes with human involvement.
Problem Statement
Traditional interviewing processes usually take more time,
because everything within the traditional interviewing process
is operated and organized by a selected group of humans.
Purpose ,Objective and Scope
The main objective is to propose and develop a smart
interviewing system that automates the traditional
interviewing process using NLP techniques and modern
machine learning approaches.
The system aims to benefit interviewers and HR management
employees in different organizations who conduct
technology-related interviews.
The ultimate goal of the smart interviewing system is to help
organization find the best-suited candidates for their job
positions in a competitive job market.
System Requirements
Software Requirements Hardware Requirements
Operating System : Windows 10 Processor : i3 or i5
Platform : Android Studio /VS code Processor speed : 2.0GHz
Database : System In-built Disk Space : 5 GB
Technologies : Flutter, Dart, Python RAM : 8 GB
Existing System
In today’s scenario, there are many online platforms to give
and take interviews but it only considers the knowledge base
as the judging parameter for the candidate.
The current AI-based interview system is select the candidates
on their video recording.
Employs pre-defined criteria to score and rank candidates.
Even though the pandemic is over 82 percent of recruiters are
hiring via online interviews.
Proposed System
AI-based mock interview system with voice assistance.
User-friendly platform using natural language processing and
speech recognition.
Customizable interview scenarios and questions for users.
Realistic interview simulations.
Assess and provide feedback on users’ responses. Adapt
questions and difficulty levels based on user feedback.
Empowers individuals to improve interview skills for real-world
success.
System Architecture
Figure: System Architecture
Use-Case Diagram
Figure: Use-Case Diagram
Class Diagram
Figure: Class Diagram
Activity Diagram
Figure: Activity Diagram
Sequence Diagram
Figure: Sequence Diagram
Component Diagram
Figure: Component Diagram
DFD Level-0 Diagram
Figure: DFD Level-0 Diagram
DFD Level-1 Diagram
Figure: DFD Level-1 Diagram
DFD Level-2 Diagram
Figure: DFD Level-2 Diagram
Algorithms
Voice Recognition Algorithm
Voice Recognition Most modern systems of voice recognition
rely on the Hidden Markov (HMM) model.
Speech Recognition Package Speech Recognition takes audio
data and makes it very easy to locate this data.
Keyword Matching Basically, keyword matching is focusing
select most suitable candidates for current job requirement.
Random Forest Algorithm
Random Forest is an ensemble learning method that combines
the predictions of multiple decision trees to make more
accurate and robust predic-tions.
Decision Trees The basic building block of a Random Forest is
the decision tree.
Conclusion
Smart Interviewing System automates traditional interviews
with NLP and deep learning.
The proposed AI-based mock interview system on voice
assistance will function as a user-friendly platform designed to
enhance interview preparation.
This innovative solution aims to empower job seekers and
students with a valuable tool for honing their interview skills,
boosting their confidence, and ultimately increasing their
chances of success in the competitive job market.
Bibliography
Integrating Faireness in the Software Design Process:An
Interview Study with HCL and ML Experts,march 2023 artical.
”Automate Traditional Interviewing Process Using Natural
Language Processing and Machine Learning”2021.
THANKYOU
