Project Phase 1: Progress 1-Presentation
on
“AI CHATBOT WITH NLP”
STUDENT : Guide name:
Ms. Soumya CS
Krishnacharan Athreyas Asst. Professor, Dept. of CSE, RNSIT
(1RN20CS069)
Department of Computer Science and Engineering
RNS Institute of Technology
2023-24
CONTENTS
• INTRODUCTION
• OBJECTIVES OF PROJECT WORK
• REQUIREMENTS
• BLOCK DIAGRAM
• USEFULNESS OF PROJECT WORK
• IMPLEMENTATION DETAILS
• RESULTS & CONCLUSION
• REFERENCES
Dept. of CSE,RNSIT 2023 - 24 2
INTRODUCTION
Dept. of CSE,RNSIT 2023 - 24 3
INTRODUCTION
Nowadays, we see the chat bots everywhere Chat bots are the
source of answers to the users questions in any particular domain
where it is operating. Chat bots are the source of answers to the
users questions in any particular domain where it is operating. The
most popular example today is the Amazon’s Alexa. Chat bots are
at almost every place, one can see it at every second website they
visit. A bot is helpful in answering queries related to information
which might be unreachable at that website easily. Most of the
websites avail users with chat bots to aid them to go through what
the websites facilitate. They are turning out to be our virtual
assistants in everyday lives.
Dept. of CSE,RNSIT 2023 - 24 4
LITERATURE SURVEY
Chatbots for University related FAQs by Bhavika R Ranoliya, gave us a brief knowledge of
Chatbot Approaches and helped us to choose the appropriate approach for developing Intelligent Bot.
This paper provides the design of a chatbot, which provides an efficient and accurate answer for any
query based on the dataset of FAQs using Artificial Intelligence Markup Language (AIML) and LSA
(Latent Semantic Analysis). Advantages: This chatbot can be used by any University to answer FAQ to
curious students in an interactive fashion. Template based and general questions like welcome/greetings
and general questions will be responded using AIML and other service based questions uses LSA to
provide responses at any time that will serve user satisfaction. Disadvantages:
If we use AIML and LSA, Sometimes the GUIs are not so easy to understand and when the
chatbot logic gets more complex, it becomes hard to handle. They have little or no natural language
processing capabilities. For example, some platforms cannot perform information extraction. Therefore,
given a phrase such as “I’m in Boston” they cannot extract the fact that the city of Boston (location
entity) occurs.
Dept. of CSE,RNSIT 2023 - 24 5
LITERATURE SURVEY
The Research paper "Programming challenges of Chatbot: current and future
prospective" by A M Rahman, also gave us a brief knowledge of chatbot Approaches and
its programming and other challenges we face while building a chatbot. The paper explains
that the Intent classification module identifies the intent of user message. Entity recognition
module extracts structured bits of information from the message.
The candidate response generator is doing all the domain-specific calculations to process
the user request. The response selector just scores all the response candidate and selects a
response which should work better for the user. Advantages: The story concept is very useful
and powerful. Branches lead to better control the conversation also conditions on the actions.
Disadvantages: It is not feasible to handle stories data and even stories are powerful
concepts, there are the cases, where data flow can misunderstand the requests. Chatbot needs
to provide vast logic and linguistic resources which are input, output and entities phrases.
Chatbot with complex queries handling need high attention in using singular and plural
forms, need to take care of synonyms, hyponyms, and finally, the sentimental analysis should
be done careful
Dept. oF CSE,RNSIT 2023 - 24 6
PROBLEM STATEMENT OF PROPOSED PROJECT
•It is evident from the research carried out in the literature review that modern services are constantly
seeking to expand their technologies. This is to gain a competitive edge over other colleges for queries and to
expand its user base. A domain specific chatbot will be implemented to assist users with their college queries.
In order to overcome the user satisfaction issues associated with colleges.
•The chatbot will provide personal and efficient communication between the user and their questions
regarding the problem they are facing and get assistance when needed, such as; answering any queries and
getting the admission date or fees. The chatbot will allow users to feel confident and comfortable when using
this service regardless of the user’s computer literacy due to the natural language used in messages.
•It also provides a very accessible and efficient service as all interactions will take place within the one
chat conversation negating the need for the user to navigate through a site.
Dept. oF CSE,RNSIT 2023 - 24 7
EXISTING SYSTEM AND THEIR LIMITATIONS
•The existing method for chatbots are simply querying with the person behind the screens who answers
all the questions asked by the users on a particular domain or rule-based chatbots are present. For doing so,
a large team of people as well as continuous monitoring is required, which costs very high when we do
with websites having large number of users. Interaction with a simple chatbot feel robotic rather than
conversational. They cannot learn on their own which means improvements need to be made manually.
•In some conditions, people answer the queries asked by the user which can be very tiring and also
they are not available 24/7. An AI chatbot is powered by NLP. So, unlike with a rule-based chatbot, it
won’t use keywords to answer, but it will try to understand the intent of the guests. The more it interacts
with guests, the better it will become at understanding the intent, and the better it will become at answering
requests.
Dept. oF CSE,RNSIT 2023 - 24 8
EXISTING SYSTEM AND THEIR LIMITATIONS
Limitations Of Existing System
The implementation still lacks in accuracy of result in some cases. More
optimization is needed.
Prior information is needed for segmentation.
Database extension is needed in order to reach the more accuracy.
Any improvements need to be made manually
No person can be available for 24/7 for answering the queries. Shift
changes are required which can be little tiring.
Dept. oF CSE,RNSIT 2023 - 24 9
OBJECTIVES OF PROJECT WORK
.
This application's objectives include analysing
and comprehending user queries, offering
efficient responses to college inquiries,
saving users time, keeping students informed
about college activities, and ensuring
enhanced security through Google Two-
Factor Authentication, which involves
generating unique codes via the Google
Authenticator app for account access.
Dept. of CSE,RNSIT 2023 - 24 10
REQUIREMENTS
Hardware requirements :-
• PC running Linux-Ubuntu to act as server to host chatbot locally
• Processor – Intel core i5
Software requirements :-
• Operating System : Windows 7, 10 or Higher Versions
• Platform : Oracle VM Virtual box
• Front End : Python Tkinter, html, css, php
• Back End : Python and Files
• Programming Language :Python
Dept. of CSE,RNSIT 2023 - 24 11
BLOCK DIAGRAM
User Interface (UI)
- Chat Window
- Voice Interface
- User Input Collection
|
|
V
Natural Language Processing
- Text Tokenization
- Stop-word Removal
- Intent Recognition
- Entity Recognition
- Dialog Management
- Response Generation
|
|
V
Backend Server
- NLP Model Integration
- Data Preprocessing
- Model Training
- Continuous Learning
- Data Security & Privacy Measures
|
|
Dept. of CSE,RNSIT 2023 - 24 12
|
|
v
Integration & Deployment
- Communication Channels (Web, Mobile)
- Cloud Deployment (e.g., AWS, Azure)
- User Authentication & Authorization
|
|
V
Monitoring & Analytics
- User Interaction Tracking
- Issue Identification
- Performance Metrics
Dept. of CSE,RNSIT 2023 - 24 13
DATA FLOW DIAGRAM
Dept. of CSE,RNSIT 2023 - 24
14
USEFULNESS OF THE PROJECT
• This application demonstrates a high level of innovativeness and usefulness in several key aspects.
Firstly, its ability to analyze and understand user queries using Natural Language Processing (NLP),
POS tagging, and entity recognition through Dialogflow sets it apart. This ensures that the chatbot can
interpret user messages effectively, providing precise and relevant answers to their inquiries. This not
only saves users valuable time by eliminating the need for them to physically visit the college for
information but also enhances the overall user experience by delivering responses akin to a real
person's interaction through an effective GUI.
• Moreover, the incorporation of Google Two-Factor Authentication adds a crucial layer of security,
ensuring the protection of users' personal data and sensitive information. By generating unique codes
sent to users' mobile devices, this feature safeguards their accounts from unauthorized access,
especially important when dealing with personal banking information. This innovative security
measure enhances the trustworthiness of the application, making it a dependable and secure platform
for users.
Dept. of CSE,RNSIT 2023 – 24 15
USEFULNESS OF THE PROJECT
• Furthermore, the application's commitment to keeping students updated about
college activities showcases its usefulness in fostering engagement and
communication within the college community. This feature not only meets the
information needs of students but also enhances their overall college experience
by providing timely updates on events, announcements, and important news.
• In summary, this application stands out for its innovative use of NLP and AI-
driven technologies, time-saving capabilities, security enhancements, and its
role in promoting effective communication within the college community. It
addresses multiple user needs while ensuring a secure and user-friendly
experience, making it a valuable and versatile tool for both students and the
institution
Dept. of CSE,RNSIT 16
2023 – 24
IMPLEMENTATION DETAILS
Developing an AI chatbot with Natural Language Processing (NLP) involves a series of technical steps and
considerations. To begin, you'll need to choose a programming language for development, such as Python or
JavaScript. Next, select an NLP framework or library that suits your needs, like NLTK, spaCy, or Dialogflow.
Gathering a relevant dataset or text corpus is crucial for training and testing NLP models. Data preprocessing
tasks, such as tokenization and stop-word removal, should be performed. Depending on your chatbot's tasks,
such as intent and entity recognition, deep learning models like RNNs or Transformer-based models may be
used. Training these models on your preprocessed data is essential. The chatbot should include intent
recognition, entity recognition, dialog management, and response generation components. Integration with
communication channels, UI design, rigorous testing, and continuous learning mechanisms are also crucial.
Security and privacy measures, as well as monitoring and analytics, should be integrated. Finally,
comprehensive documentation and support are vital for users and developers. Building an AI chatbot with NLP
is a multifaceted process that demands a deep understanding of NLP techniques, machine learning, and
software development, ultimately aiming to provide users with an efficient and intelligent
conversational experience.
Dept. of CSE,RNSIT 2023 - 24 17
RESULTS & CONCLUSION
To conclude, College Enquiry Chatbot is helpful in guiding students with correct and
most upto date sources of information .It is advantageous for international applicants for
queries such as fee payment and academic matters. Students can get the information at their
finger tips rather than visiting college office. It improves efficiency by taking over tasks for
which humans are not essential.
Sentiment analysis implemented in College Enquiry Chatbot correctly recognizes the
user’s query such as positive, negative, and neutral by storing all the conversations in the
database. However, the system was partially successful in adding empathy since scope of
these queries is vast and the system requires more rigorous data to handle all the questions
which are out of script. Nevertheless, active learning helps to improve the bot performance for
handling off-script queries.
Dept. of CSE,RNSIT 2023 - 24 18
REFERENCES/BIBLIOGRAPHY
1) Smart Answering Chatbot based on OCR and Over generating Transformations and Ranking S. Jayalakshmi,
Dr.AnanthiSheshasaayee 978- 1-5090-5960-7/17 2017 IEEE 2017 An automated answering Chatbotsystem to respond to
users question using text article from digital document file.
2) Artificial Intelligence Technologies for Personnel Learning Management Systems NaydenNenkov, YuriyDyachenko IEEE
8th International Conference on Intelligent Systems 2016. These agents in the form of chatbots have to automate the
interaction between the student and the teacher within the frames of Moodle learning management system.
3) Chatbot Using A Knowledge in Database Human-to-Machine Conversation Modeling BayuSetiaji
,FerryWahyuWibowo 2166-0670/16 2016 IEEE 2016 The machine has been embedded knowledge to identify the sentences
and making a decision itself as response to answer a question
4) Towards an efficient voice-based chatbot J. Quintero Student Member IEEE, and R. Asprilla, Member, IEEE 2015 IEEE
THIRTY FIFTH CENTRAL AMERICAN AND PANAMA CONVENTION 2015 The development and integration of
technologies used in an experimental natural conversation system designed to run on a humanoid robot.
5) Schantz, Herbert F, The history of OCR, optical character recognition, Recognition Technologies Users Association,
Manchester Center, VT ,1982.
Dept. of CSE,RNSIT 2023 - 24 19
SUGGESTIONS….!
Dept. of CSE,RNSIT 2023 - 24 20
THANK YOU!!!
Dept. of CSE,RNSIT 2023 - 24 21
