A

MAJOR PROJECT REPORT

On
CAREER & RESUME ASSISTANT BOT USING AI
Submitted in partial fulfilment for the award of the degree of
BACHELOR OF TECHNOLOGY
in
ARTIFICIAL INTELLIGENCE AND DATA SCIENCE
By
TEAM MEMBERS
1.D.KUSUMA SRI - 22Q91A7208
2.G.HARINI - 22Q91A7211
3.M.MONISHA - 22Q91A7235
4.M.LAVANYA - 22Q91A7237
Under the guidance of
Mrs.K.Sravanthi
Assistant Professor, Dept. of CSE(DS)

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING-

(CSE- ARTIFICIAL INTELLIGENCE & DATA SCIENCE)
MALLA REDDY COLLEGE OF ENGINEERING
(Approved by AICTE-Permanently Affiliated to JNTU-Hyderabad)
Accredited by NBA , Recognized section 2(f) & 12(B) of UGC New Delhi
ISO 9001: 2015 Certified Institution
Maisammaguda, Dhulapally (Post via Kompally), Secunderabad- 500100
2025 - 2026
 MALLA REDDY COLLEGE OF ENGINEERING
(Approved by AICTE-Permanently Affiliated to JNTU-Hyderabad)
Accredited by NBA , Recognized section 2(f) & 12(B) of UGC New Delhi
ISO 9001:2015 Certified Institution
Maisammaguda, Dhulapally (Post via Kompally), Secunderabad- 500100

DEPARTMENT OF ARTIFICIAL INTELLIGENCE & DATA SCIENCE

CERTIFICATE
This is to certify that the Major Project stage -1 report on “CAREER & RESUME ASSISTANT
BOT USING AI” successfully done by the following students of Department of Artificial
Intelligence & Data Science of our college in partial fulfilment of the requirement for the award
of Bachelor of Technology degree in the year 2025-2026. The results embodied in this report have
not been submitted to any other University for the award of any diploma or degree.

TEAM MEMBERS

1.D.KUSUMA SRI - 22Q91A7208

2.G.HARINI - 22Q91A7211
3.M.MONISHA - 22Q91A7235
4.M.LAVANYA - 22Q91A7237

Submitted for the viva voice examination held on : _________________________

INTERNAL GUIDE PROJECT COORDINATOR HOD

Mrs.K.Sravanthi Mrs.S.Naga Sharanya Dr. J. Gladson Mario Britto
Assistant Professor Assistant Professor Professor & Head

Internal Examiner External Examiner

 DECLARATION

We, D.KUSUMA SRI, G.HARINI, M.MONISHA, M.LAVANYA with Regd.No. 22Q91A7208,

22Q91A7211,22Q91A7235,22Q91A7237 are hereby declaring that the major project stage-1 entitled
“CAREER & RESUME ASSISTANT BOT USING AI” has done by us under the guidance of Mrs.
K. Sravanthi Assistant Professor, Department of Computer Science and Engineering (AI&DS) is
submitted in the partial fulfilment of the requirements for the award of degree of BACHELOR OF
TECHNOLOGY in ARTIFICIAL INTELLIGENCE AND DATA SCIENCE.

The result embedded in this project report have not been submitted to any other University or
institute for the award of any degree.

Signatures of the Candidate

1.D.KUSUMA SRI -22Q91A7208

2.G.HARINI -22Q91A7211

3.M.MONISHA -22Q91A7235

4.M.LAVANYA -22Q991A7237

DATE :
PLACE :Maisammaguda
 ACKNOWLEDGEMENT

First and foremost, we would like to express our immense gratitude towards our institution Malla
Reddy College of Engineering, which helped us to attain profound technical skills in the field of
Computer Science & Engineering, there by fulfilling our most cherished goal.

We are pleased to thank Sri Ch. Malla Reddy, our Founder Chairman, MRGI, Sri Ch.
Mahender Reddy, Secretary, MRGI for providing this opportunity and support throughout the
course.

It gives us immense pleasure to acknowledge the perennial inspiration of Dr. M. Ashok our
beloved principal for his kind co-operation and encouragement in bringing out this task.

We would like to thank, Dr. J. Gladson Maria Britto HOD, CSE-DS Department for their
inspiration adroit guidance and constructive criticism for successful completion of our degree.

We would like to thank Mrs.Naga Sharanya Assistant professor and Project Coordinator for
their vital support in helping with the successful completion of our degree.

We would like to thank Mrs.K.Sravanthi Assistant Professor our internal guide, for her valuable
suggestions and guidance during the exhibition and completion of this project.

Finally, we avail this opportunity to express our deep gratitude to all staff who have contributed
their valuable assistance and support making our project a success.

TEAM MEMBERS

1.D.KUSUMA SRI - 22Q91A7208

2.G.HARINI - 22Q91A7211
3.M.MONISHA - 22Q91A7235
4.M.LAVANYA - 22Q91A7237
CAREER & RESUME ASSISTANT BOT
USING AI
 INDEX

CHAPTER NO. TITLE PAGE NO.

A. ABSTRACT I
B. LIST OF ABBREVIATIONS II
C. LIST OF FIGURES III
1. CHAPTER 1: INTRODUCTION 1
1.1 INTRODUCTION 2
1.2 PURPOSE 3
1.3 SCOPE 3
1.4 PROJECT OVERVIEW 4
2. CHAPTER 2: LITERATURE SURVEY 5
2.1 LITERATURE SURVEY 6
3. CHAPTER 3: PROBLEM DEFINITION 11
3.1 EXISTING SYSTEM 12
3.1.1 DISAVDTANGES 12
3.2 PROPOSED SYSTEM 13
3.2.1 ADVANTAGES 13
3.3 REQUIREMENTS 14
3.3.1 HARDWARE REQUIREMENTS 14
3.3.2 SOFTWARE REQUIREMENTS 14

4. CHAPTER 4: SYSTEM DESIGN 15

4.1 DATA FLOW DIAGRAM 16
4.2. UML DIAGRAMS 17
4.2.1 USE CASE DIAGRAM 18
4.2.2 CLASS DIAGRAM 19
4.2.3 SEQUENCE DIAGRAM 20
4.2.4 ACTIVITY DIAGRAM 21
4.2.5 MODEL DIAGRAM 22
4.3 ARCHITECTURE 23
5. CHAPTER 5: MODULES 24
5.1 USER MODULES 25
5.2 PROCESSING MODULES 25
5.3 OUTPUT MODULE 26
 5.4 STORAGE MODULE 27
5.5 SECURITY MODULE 27
6. CHAPTER 6: REFERENCE 28
6.1 REFERENCES 29
 ABSTRACT
The Career & Resume Assistant Bot is an AI-powered solution designed to streamline and
enhance the process of resume creation, analysis, and career preparation. Built with advanced
Natural Language Processing (NLP) and Machine Learning (ML) models, the system offers
intelligent support to users by generating tailored, professional resumes, reviewing existing ones
for improvements, and providing personalized interview questions and portfolio suggestions. By
analyzing user inputs and aligning them with job descriptions, the bot identifies missing skills,
strengthens resume content, and improves overall job readiness.

Unlike cloud-based tools, this chatbot operates entirely within a local environment, ensuring
complete data privacy and offline accessibility. This makes it especially suitable for academic
institutions, training centers, and individual users who prioritize secure and uninterrupted access.
The bot’s conversational interface allows users to interact naturally, making the experience
intuitive and user-friendly. It guides users step-by-step through resume building, skill
enhancement, and interview preparation, offering constructive feedback and actionable insights.

The Career & Resume Assistant Bot bridges the gap between education and employment by
equipping users with the resources they need to succeed in competitive job markets. Its
integration of AI technologies not only automates repetitive tasks but also delivers personalized
support, making it a valuable asset for students, professionals, and educators alike.

I
 LIST OF ACRONYMS AND ABBREVIATIONS

S.NO ACRONYM DESCRIPTION

1 ATS Applicant Tracking System

2 BERT Bidirectional Encoder

Representations from
Transformers

3 NLP Natural Language Processing

4 API Application Programming

Interface

5 GPU Graphics Processing Unit

6 TF-IDF Term Frequency-Inverse

Document Frequency

7 RoBERTa Robustly Optimized BERT

Pretraining Approach

II
 LIST OF FIGURES

LIST OF FIGURES FIG.NO NAME OF THE PAGE NO.

FIGURE NO FIGURE
4.1 4.1 DATA FLOW 16
DIAGRAM
4.2.1 4.2.1 USE CASE DIAGRAM 18
4.2.2 4.2.2 CLASS DIAGRAM 19
4.2.3 4.2.3 SEQUENCE DIAGRAM 20
4.2.4 4.2.4 ACTIVITY DIAGRAM 21
4.2.5 4.2.5 MODEL DIAGRAM 22
4.3 4.3 ARCHITECTURE 23

III
 CHAPTER-1

INTRODUCTION

1
1.1 INTRODUCTION

In the evolving landscape of recruitment and talent acquisition, Artificial Intelligence (AI) has
emerged as a transformative force, streamlining tasks that were traditionally manual, repetitive,
and error-prone. A prominent application of AI lies in automated resume generation and
career guidance systems, where precision, personalization, and scalability are critical. Manual
resume creation often suffers from inconsistencies such as non-standard formatting, missing
skill alignment, and semantic mismatches with job descriptions. The proposed Career &
Resume Assistant Bot mitigates these challenges by leveraging Natural Language Processing
(NLP) and transformer-based models to interpret user inputs, extract relevant competencies,
and generate ATS-optimized resumes tailored to specific roles. Through its conversational
interface, the system delivers real-time feedback, identifies skill gaps, and recommends
enhancements, thereby improving the candidate’s professional profile. Furthermore, the bot
extends its functionality to include context-aware interview question generation and portfolio
content suggestions, offering a holistic, end-to-end solution for career development. Its
modular architecture, offline deployment, and privacy-preserving design make it suitable for
academic environments and secure professional use cases. By integrating advanced NLP
pipelines and transformer-based models such as BERT or RoBERTa, the system ensures
semantic accuracy in skill extraction and job-role matching. This enables the bot to not only
generate resumes but also evaluate their relevance against dynamic job descriptions, enhancing
employability. The conversational interface is designed to be intuitive and user-friendly,
allowing even non-technical users to navigate the resume-building process with ease.
Additionally, the system’s offline capability ensures that sensitive user data remains secure,
making it ideal for deployment in academic institutions, training centers, and privacy-conscious
organizations. Its modular design allows for future expansion, including features like job
tracking, feedback analytics, and multilingual support, positioning it as a scalable solution for
diverse career development needs.

2
1.2 PURPOSE

The aim of the Career & Resume Assistant Bot is to develop a locally deployed, AI-powered
system that simplifies and enhances the process of resume creation, analysis, and career
preparation. By integrating Natural Language Processing (NLP) and Machine Learning (ML)
models, the bot enables users to generate tailored resumes, match them with job descriptions,
identify missing skills, and receive personalized interview questions and portfolio suggestions.
Unlike existing cloud-based tools, this system operates entirely offline, ensuring user privacy and
accessibility in academic or secure environments. It aims to provide an end-to-end career support
solution through a conversational interface that is intuitive, efficient, and context-aware.

1.3 SCOPE

The scope of the Career & Resume Assistant Bot encompasses the design, development, and
deployment of a locally hosted AI system that supports end-to-end career preparation. The
system is built using Python, Flask, and MongoDB, SQLite, and integrates Natural Language
Processing (NLP) and Machine Learning (ML) models to automate resume generation, job-role
matching, resume analysis, and interview question creation. It is designed to function both online
and offline, ensuring data privacy and accessibility in academic, institutional, and low-
connectivity environments. The bot supports dynamic resume creation based on user input and
job descriptions, using transformer-based models from Hugging Face for skill extraction and
semantic matching. It analyzes existing resumes to identify formatting issues, missing skills, and
content gaps, and provides actionable feedback. The system generates personalized interview
questions aligned with the user’s resume and target job role, helping users prepare effectively.
The bot also guides users in presenting their projects and achievements professionally through
portfolio generation. Its modular architecture allows easy integration of future features such as
job tracking, feedback collection, and multilingual support. The scope includes usability for
students, job seekers, training centers, and academic institutions, making it a versatile tool for
both educational and professional career development.

3
1.4 PROJECT OVERVIEW

The Career & Resume Assistant Bot Using AI is a locally deployed, intelligent system designed
to automate and enhance the process of resume creation, analysis, and career preparation. Built
using Python, Flask, and MongoDB, SQLite the bot integrates Natural Language Processing
(NLP) and Machine Learning (ML) techniques to understand user input, extract relevant skills,
and tailor resumes to specific job descriptions. It employs transformer-based models from
Hugging Face for semantic matching and skill gap detection, ensuring contextual accuracy. The
chatbot interface allows users to interact naturally, generate customized resumes, receive
analytical feedback, and access personalized interview questions and portfolio suggestions.
Operating both online and offline, the system ensures data privacy and is optimized for academic
and professional use. Its modular architecture supports extensibility, making it a scalable and
secure career development tool.

4
 CHAPTER 2

LITERATURE SURVEY

5
2.1 LITERATURE SURVEY

TITLE 1: NLP-Based Resume Screening

Authors: Arvind Kumar Sinha, Md. Amir Khusru Akhtar, Ashwani Kumar

Publication: Resume Screening Using Natural Language Processing and Machine Learning: A
Systematic Review (Springer, 2021).

Objective:

This study presents a comprehensive review of how Natural Language Processing (NLP) and
Machine Learning (ML) are transforming resume screening in recruitment. The authors argue
that traditional keyword-based filtering methods are limited in their ability to understand the
context and semantics of candidate profiles. Instead, NLP techniques such as named entity
recognition, semantic similarity, and contextual embeddings allow systems to interpret resumes
more like human recruiters.

The paper highlights the use of deep learning models, including word embeddings (Word2Vec,
GloVe) and transformer-based architectures (BERT), to extract meaningful features from
resumes. These models enable systems to match candidate qualifications with job descriptions
more accurately. The authors also discuss challenges such as unstructured resume formats,
domain-specific terminology, and bias in training data.

A key contribution of this work is its emphasis on the shift from rule-based parsing to intelligent,
context-aware screening. The authors propose a hybrid framework that combines NLP with
supervised learning to classify resumes and rank candidates. They also explore evaluation
metrics such as precision, recall, and F1-score to measure system performance.

6
TITLE 2: AI-Driven Chatbots for HR Automation

Authors: K. Sharma, P. Verma

Publication: AI-Driven Chatbots for Human Resource Automation (2022).
Objective :
The role of AI-powered chatbots in automating HR tasks, with a focus on recruitment and
candidate engagement. Their research emphasizes the use of transformer-based models such as
BERT and GPT for enabling personalized, context-aware conversations between bots and users.

The study outlines how chatbots can handle tasks like resume collection, candidate screening,
interview scheduling, and feedback collection. By integrating NLP and ML, these bots can
understand user queries, extract relevant information, and respond intelligently. The authors
highlight the importance of conversational AI in improving user experience and reducing HR
workload.

One of the key findings is the effectiveness of transformer models in maintaining context across
multiple turns of conversation. This allows chatbots to simulate human-like interactions and
provide tailored responses. The paper also discusses integration challenges, including data
privacy, scalability, and training requirements.

The authors propose a modular chatbot architecture that includes intent recognition, entity
extraction, and response generation. They recommend using open-source libraries like spaCy and
Hugging Face Transformers to build lightweight, customizable bots.

This survey supports the proposed project’s use of transformer-based NLP models for building a
local, privacy-preserving career assistant bot.

7
TITLE 3: Resume Parser APIs and ATS Systems

Authors: Dr. D. Lakshmi Padmaja, Ch. Vishnuvardhan, G. Rajeev, K. Nitish Sanjeev Kumar
Publication : Automated Resume Screening Using Natural Language Processing (JETIR,
2023)
Objective :
This paper examines the evolution of resume parsing technologies and their integration into
Applicant Tracking Systems (ATS). The authors review several commercial Resume Parser APIs,
noting their reliance on cloud infrastructure and proprietary algorithms. While these systems
offer high accuracy, they often lack transparency and flexibility.

The study identifies key components of resume parsers, including section detection, skill
extraction, and experience mapping. It discusses how NLP techniques like tokenization, part-of-
speech tagging, and dependency parsing are used to structure resume data. The authors also
explore the use of ML classifiers to categorize resumes based on job fit.

A major concern raised is the dependence on cloud-based services, which may pose privacy risks
and limit offline accessibility. The authors advocate for open-source alternatives that can be
deployed locally, such as spaCy for parsing and Scikit-learn for classification.

This literature reinforces the need for a local, open-source implementation in the proposed
project, ensuring data privacy and academic usability.

8
TITLE 4: NLP Techniques for Skill Extraction

Authors: Deeptha R, Abirup Dey, Gowtham G.S.G.R, Abhishek Tripathi

Publication : Resume Screening Using NLP (iManager Publications, 2024)

Objective:

This study focuses on the application of NLP for extracting skills and qualifications from
resumes. The authors describe how semantic analysis and keyword extraction can be used to
identify relevant competencies. They emphasize the importance of context in distinguishing
between similar terms (e.g., “Java” as a programming language vs. “Java” as a location).

The paper reviews various NLP methods, including TF-IDF, named entity recognition, and word
embeddings. It also discusses the use of pretrained models like BERT for understanding resume
content at a deeper level. The authors propose a pipeline that includes resume preprocessing,
skill tagging, and job-role matching.

One of the key contributions is the evaluation of different skill extraction techniques using
benchmark datasets. The authors compare rule-based, statistical, and deep learning approaches,
highlighting the trade-offs between accuracy and computational cost.

This literature supports the use of lightweight NLP models in the proposed project, enabling
efficient skill extraction without relying on heavy cloud infrastructure.

9
TITLE 5: Privacy-Preserving Resume Assistants Using Local NLP
Frameworks

Authors: R. K. Mishra, S. Bansal, A. Jain

Publication: International Journal of Artificial Intelligence and Applications, Vol. 13, Issue 2,
2023
Objecttive :
This study explores the development of resume screening systems that prioritize user privacy by
avoiding cloud-based processing. The authors argue that while many commercial resume parsers
and career bots rely on cloud infrastructure, this raises concerns about data security, especially in
academic and government settings. To address this, the paper proposes a locally hosted resume
assistant built using open-source NLP frameworks such as spaCy, Scikit-learn, and Hugging
Face Transformers.

The system architecture described in the paper includes modules for resume parsing, skill
extraction, job-role matching, and interview question generation. The authors emphasize the use
of lightweight NLP models that can run efficiently on local machines without requiring GPU
acceleration or internet access. They demonstrate how spaCy’s entity recognition and
dependency parsing can be used to extract structured information from unformatted resumes,
while Hugging Face’s transformer models are leveraged for semantic understanding and
contextual matching.

A key contribution of the paper is its evaluation of privacy-preserving design principles. The
authors compare local NLP performance with cloud-based APIs and show that, while cloud
models may offer slightly higher accuracy, local models provide sufficient performance for most
academic and small-scale recruitment needs. They also highlight the importance of transparency,
reproducibility, and user control in AI systems used for career development.

10
 CHAPTER 3

PROBLEM DEFINITION

11
3.1 EXISTING SYSTEM
Most current resume creation tools and online platforms rely heavily on fixed templates, which
restrict customization and lack the ability to understand user context. These systems often fail to
adapt resumes to specific job roles or highlight unique user strengths. Cloud-based Applicant
Tracking Systems (ATS) and resume analyzers, while technically advanced, pose privacy
concerns and require constant internet access, making them unsuitable for offline or secure
environments. Additionally, many existing chatbots are designed for narrow tasks and do not
offer a complete solution that includes resume generation, analysis, and interview preparation in
one unified system. A major drawback of these platforms is their reliance on external APIs,
which can lead to slower performance and limit accessibility in academic settings or areas with
limited connectivity. These challenges highlight the need for a locally deployed, privacy-focused,
and context-aware career assistant that provides end-to-end support without external
dependencies.

3.1.1 DISADVANTAGES:

No personalization: Generic templates fail to highlight strengths relevant to job roles.

Inconsistent feedback: Manual proofreading or third-party services produce varied results.
Data exposure risks: Uploading resumes to online platforms can compromise personal data.
Lack of adaptability: Cannot tailor resumes dynamically based on job descriptions.
High cost of advanced tools: Many professional resume analyzers require paid
subscriptions.
Fragmented workflow: Users must switch between multiple tools for different
functionalities.

12
3.2 PROPOSED SYSTEM:
The proposed Career & Resume Assistant Bot Using AI offers a comprehensive and privacy-
focused solution for career development by integrating resume creation, job description matching,
resume analysis, and interview preparation into a single system. Developed using Python for
core logic, Flask for the web interface, and MongoDB for data storage, the bot ensures secure
and efficient local execution without relying on external cloud services. It utilizes Natural
Language Processing (NLP) pipelines to understand user input and detect semantic similarity
between resumes and job descriptions, enabling accurate content alignment. Transformer-based
models from Hugging Face are employed to extract relevant skills and match user profiles with
specific job roles, enhancing the personalization and effectiveness of the generated resumes. The
chatbot interface allows users to interact naturally, guiding them through resume generation,
providing analytical feedback, and offering personalized interview questions based on their
profile. Key advantages of this system include improved accuracy in resume-job matching, full
offline functionality for academic and secure environments, strong data privacy due to local
deployment, and modular extensibility that allows easy adaptation for various educational and
professional use cases. This makes the bot a practical and intelligent tool for end-to-end career
support.

3.2.1 ADVANTAGES:

Automation: Reduces manual effort in resume writing, analysis, and improvement.

Personalization: Dynamically tailors resumes based on job descriptions and extracted skills.
Integrated System: Combines multiple functionalities—resume building, analysis, Q&A
generation, skill recommendation and portfolio creation—into one platform.
Offline Functionality: Runs locally, removing dependency on external servers or internet
connectivity.

13
Enhanced Privacy: Ensures user data remains secure within the local environment.
Customizable Templates: Provides editable, professional resume formats
Lightweight and Fast: Optimized using FastAPI for efficient API communication and low
latency.
User-Friendly Interface: Simplifies interaction through a clean web-based front end

3.3 REQUIREMENTS

3.3.1 HARDWARE REQUIREMENTS:

 Processor - Intel Core i5 or equivalent
 RAM - 8 GB minimum
 Storage - 10 GB free space
 Display - 1366x768 resolution or higher
 GPU (optional) - GPU for faster NLP inference

3.3.2 SOFTWARE REQUIREMENTS:

 Operating System : Windows 10 or later / Ubuntu 20.04+
 Coding Language : PYTHON 3.10 or higher
 Front-End : HTML5, CSS3, JavaScript
 Back –End : FastAPI, Python
 Data Base : SQLite, MongoDB
 Development Tools : Visual Studio Code

14
 CHAPTER 4
SYSTEM DESIGN

15
4.1 DATA FLOW DIAGRAM
1. The data flow diagram is also called as bubble chart. It is a simple graphical formalism
that can be used to represent a system in terms of input data to the system, various
processing carried out on this data, and the output data is generated by this system.
2. The data flow diagram is one of the most important modeling tools. It is used to model
the system components. These components are the system process, the data used by the
process, an external entity that interacts with the system and the information flows in the
system.
3. Data flow diagram shows how the information moves through the system and how it is
modified by a series of transformations. It is a graphical technique that depicts
information flow and the transformations that are applied as data moves from input to
output.
4. Data flow diagram is also known as bubble chart. A data flow diagram may be used to
represent a system at any level of abstraction. Data flow diagram may be partitioned into
levels that represent increasing information flow and functional detail.

16
 Fig 4.1

4.2 UML DIAGRAMS

UML stands for Unified Modeling Language. UML is a standardized general-purpose modeling
language in the field of object-oriented software engineering. The standard is managed, and was
created by, the Object Management Group.
The goal is for UML to become a common language for creating models of object oriented
computer software. In its current form UML is comprised of two major components: a Meta-
model and a notation. In the future, some form of method or process may also be added to; or
associated with, UML.
The Unified Modeling Language is a standard language for specifying, Visualization,
Constructing and documenting the artifacts of software system, as well as for business modeling
and other non-software systems.
The UML represents a collection of best engineering practices that have proven successful in the
modeling of large and complex systems.
The UML is a very important part of developing objects oriented software and the software
development process. The UML uses mostly graphical notations to express the design of
software projects.

17
GOALS:
The Primary goals in the design of the UML are as follows:
1. Provide users a ready-to-use, expressive visual modeling Language so that they can
develop and exchange meaningful models.
2. Provide extendibility and specialization mechanisms to extend the core concepts.
3. Be independent of particular programming languages and development process.
4. Provide a formal basis for understanding the modeling language.
5. Encourage the growth of tools market.
6. Support higher level development concepts such as collaborations, frameworks, patterns
and components.
7. Integrate best practices.

4.2.1 USE CASE DIAGRAM:

A use case diagram in the Unified Modeling Language (UML) is a type of behavioral
diagram defined by and created from a Use-case analysis. Its purpose is to present a graphical
overview of the functionality provided by a system in terms of actors, their goals
(represented as use cases), and any dependencies between those use cases. The main purpose
of a use case diagram is to show what system functions are performed for which actor. Roles
of the actors in the system can be depicted.

18
 Fig: 4.2.1

4.2.2 CLASS DIAGRAM:

In software engineering, a class diagram in the Unified Modeling Language (UML) is a type
of static structure diagram that describes the structure of a system by showing the system's
classes, their attributes, operations (or methods), and the relationships among the classes. It
explains which class contains information.

19
 Fig 4.2.2

4.2.3 SEQUENCE DIAGRAM:

UML A sequence diagram in Unified Modeling Language (UML) is a kind of interaction
diagram that shows how processes operate with one another and in what order. It is a
construct of a Message Sequence Chart. Sequence diagrams are sometimes called event
diagrams, event scenarios, and timing diagrams.

20
 Fig 4.2.3

4.2.4 ACTIVITY DIAGRAM:

Activity diagrams are graphical representations of workflows of stepwise activities and actions
with support for choice, iteration and concurrency. In the Unified Modeling Language, activity
diagrams can be used to describe the business and operational step-by-step workflows of
components in a system. An activity diagram shows the overall flow of control.

21
 Fig: 4.2.4

4.2.5 MODEL DIAGRAM

A model diagram represents the overall architecture and workflow of a system. It visually
illustrates how different components or modules interact with each other, showing the flow of
data and control between them. This diagram helps in understanding the system’s structure,
dependencies, and communication paths in a clear and organized manner. It serves as a blueprint
for developers and stakeholders to analyze, design, and implement the project effectively.
22
 Fig 4.2.5

4.3 ARCHITECTURE

23
Fig 4.3

24
 CHAPTER 5
MODULES

5.1 USER MODULE:

Resume Input and Job Description Module

25
  Accept resume content, job descriptions, or career-related queries via chatbot interface.
 Enable dynamic input for personalized career assistance.
Input Parsing and Intent Detection Module
 Use NLP techniques (e.g., spaCy) to parse text and extract entities.
 Identify user intent for resume generation, analysis, or interview preparation.
Skill Extraction and Role Matching Module
 Apply transformer-based models to extract relevant skills.
 Match resume content with job roles for semantic alignment.
Resume Generation and Interview Preparation Module
 Create ATS-optimized resumes tailored to job descriptions.
 Generate personalized interview questions based on user profile and target role.
Portfolio Content Mapping Module
 Suggest project summaries and map tools/technologies from resume data.
 Help users present achievements professionally for career portfolios.
Local Storage and Privacy Module
 Store processed data, resumes, and session logs securely in MongoDB.
 Support offline access and ensure user data privacy in academic and low-connectivity
environments.

5.2 PROCESSING MODULE:

Input Parsing and Intent Detection Module
 Use NLP techniques (e.g., spaCy) to tokenize and analyze user input.
 Detect user intent for resume generation, analysis, or interview preparation.
Semantic Matching and Skill Extraction Module
 Apply transformer-based models to extract relevant skills from resumes and job
descriptions.
 Match extracted skills with job role requirements for alignment.
Job Role Analysis Module

26
  Analyze job descriptions to identify key responsibilities and required competencies.
 Maintain a dynamic role-skill mapping for accurate recommendations.

5.3 OUTPUT MODULE:

Resume Generation Module
 Create ATS-friendly resumes tailored to job descriptions and user profiles.
 Format resumes with consistent structure, grammar, and keyword optimization.
Interview Question Generation Module
 Generate personalized interview questions based on resume content and target roles.
 Support mock interview preparation and self-assessment.
Portfolio Content Builder Module
 Suggest project summaries and map tools/technologies from resume data.
 Help users present achievements professionally for career portfolios.
Skill Recommendation Module
 Identifies missing or underrepresented skills by comparing user resumes with relevant job
descriptions.
 Recommends online courses, certifications, or tutorials (from platforms like Coursera or
Udemy)to help users fill those gaps.
 Continuously updates the skill database for dynamic industry relevance.
ATS Score Generation Module
 Calculates the Applicant Tracking System (ATS) score by evaluating resume alignment
with job keywords, skills, and structure.
 Provides a detailed breakdown showing strong and weak sections of the resume.
 Offers improvement suggestions to maximize the ATS score for better job shortlisting
potential.

5.4 STORAGE MODULE:

Local Database Management Module

27
  Store resumes, session logs, and processed data securely using MongoDB.
 Ensure offline access and privacy for academic and low-connectivity
environments.
Session Tracking and History Module
 Maintain user-specific logs of resume edits, feedback, and generated content.
 Enable continuity and version control across multiple sessions.
5.5 SECURITY MODULE
Authentication & Authorization
 Uses secure login protocols (like OAuth and hashed passwords) to verify and control
access to system resources.
 Differentiates roles and privileges for users, admins, and other authorized entities to
prevent misuse.
Data Encryption
 Applies cryptographic hashing (SHA or bcrypt) to secure user passwords and sensitive
data.
 Ensures secure data transmission and prevents unauthorized data manipulation.
Privacy Preservation
 Processes and stores all user data locally, preventing exposure to third-party servers.
 Adheres to privacy-by-design principles, ensuring compliance with academic and ethical
standards.
Backup & Recovery
 Maintains automated backups of user resumes, configurations, and logs for reliability.
 Enables quick data restoration in case of corruption, hardware failure, or accidental loss.

28
 CHAPTER-6
REFERENCES

6.1 REFERENCES

29
1. Lee and J. Kim (2020). Intelligent Resume Analysis Using Deep Learning and NLP
Techniques. ACM Digital Library.
2. Zhang, J., & Yang, M. (2020). Deep Learning for Resume Classification and Ranking.
Journal of Artificial Intelligence Research.
3. Kumar, A., & Roy, M. (2020). Smart Recruitment Using NLP and Machine Learning.
International Journal of Advanced Research in Computer Science.
4. Wolf, T., et al. (2020). Transformers: State-of-the-Art Natural Language Processing.
Proceedings of EMNLP.
5. Nguyen, T. S., et al. (2021). NLP-Based Resume Screening for Smart Recruitment
Systems. IEEE Access.
6. Gupta, R., & Mehta, A. (2021). Semantic Role Labeling for Resume-Job Matching. ACL
Workshop on NLP in Recruitment.
7. Wang, L., & Zhou, H. (2021). Resume Parsing Using Named Entity Recognition and
POS Tagging. IEEE Transactions on Computational Intelligence.
8. Li, C., & Chen, Y. (2021). Conversational Agents for Employment Support. ACM
Transactions on Interactive Intelligent Systems.
9. Sharma, L. K., & Verma, P. (2022). AI-Driven Chatbots for Human Resource
Automation. International Journal of Computer Science Trends.
10. Patel, K., & Desai, S. (2022). Transformer-Based Models for Skill Extraction in
Recruitment Systems. International Journal of Computer Applications.
11. Banerjee, T., & Singh, R. (2022). Offline AI Assistants for Low-Connectivity
Environments. International Conference on Intelligent Systems.
12. Das, M., & Iyer, S. (2022). Skill Gap Analysis Using AI in Resume Screening. Journal of
Human-Centered AI.
13. Lakshmi Padmaja, D., et al. (2023). Automated Resume Screening Using Natural
Language Processing. Journal of Emerging Technologies and Innovative Research.
14. Ramesh, V., & Sinha, P. (2023). Privacy-Preserving AI Systems for Career Guidance.
Journal of Secure Computing.
15. Thomas, B., & Rao, N. (2023). Design of Modular AI Systems for Career Counseling.
Journal of Educational Technology and AI.

30
16. Sharma, P., & Jain, R. (2023). End-to-End Resume Evaluation Using BERT and
RoBERTa. International Journal of Machine Learning and Computing.
17. Ragul Saran, A. P., et al. (2025). AI-Powered Resume Screening and Feedback System.
International Journal of Scientific Development and Research.
18. Ramchandani, S., et al. (2025). AI Resume Analyzer: A Review and Case Study of an
NLP-Driven Recruitment System. International Journal of Science, Engineering and
Technology.

31