Project Title here….

Group Members:
1.Ali Raza Bozdar
2.Ali Raza Chandio
3.Ahsan Ali Malik

Supervisor: Dr. Hanif Tunio

2018

Institute of Computer Science,

 Literature Review

 Tools and Technologies

 Results and Discussions

 Future Work

 Conclusion

 References

2
 Introduction
• “SALU AI Enquiry Chatbot is a cutting-edge, 24/7 virtual assistant

that provides instant answers to student and faculty queries. Powered

by artificial intelligence, it enhances communication, simplifies

access to course and academic information, and reduces staff

workload, making the university experience faster, smarter, and

more efficient."
• Benefits for New Students and Outsiders:

• Quick Introduction to the University: Provides immediate answers to common questions

• 24/7 Accessibility: New students and outsiders can get information at any time, ensuring
they don’t have to wait for office hours to receive support.

• Easy Access to Course Information: New students can quickly learn about available
courses, departments, and academic schedules without the need for in-person visits.

• Guided Campus Navigation: Helps new students and visitors understand the layout of the
campus, find departments, and locate facilities with ease.

• Improved First Impressions: Offers a seamless, modern digital experience, showing new
students that the university is innovative and committed to supporting them from the start.
 Literature Review
. This review will cover three key areas: (1) the evolution and application of AI chatbots, (2) the role of chatbots in higher
education and their effectiveness in enhancing administrative services,

This subdomain explores the historical progression and technological advancements in the development of AI chatbots,
from their inception to their modern-day applications. Understanding this evolution is crucial for recognizing the
significance of AI-powered systems like the enquiry chatbot you are developing for your university. The
 Literature Review
Notable Research
• The 1960s-1970s: The Birth of Chatbots the concept of chatbots dates back to the 1960s, with the creation of the
first known chatbot: ELIZA. Developed by Joseph Weizenbaum at MIT in 1966,

• The 1990s: Introduction of NLP and Intelligent Agents The 1990s saw the development of more intelligent
systems that incorporated Natural Language Processing (NLP). NLP, a subfield of AI, is concerned with enabling
machines to understand, interpret, and generate human language.

• GPT (2018-2020): OpenAI's GPT models, especially GPT-3 (released in 2020), marked a milestone in
conversational AI. GPT-3, a massive language model with 175 billion parameters, demonstrated a remarkable ability
to generate human-like text and answer complex queries with minimal input.
 Literature Review
Notable Research

• The 2000s: Emergence of Learning-Based Models The early 2000s marked a significant shift in the development
of chatbots, as researchers began incorporating Machine Learning (ML) techniques into chatbot development.
Unlike rule-based systems, ML-powered chatbots learn from data rather than relying on predefined rules.

• 2010s: The Advent of Deep Learning and Transformer Models The 2010s represented a major leap forward in
chatbot development with the rise of deep learning and the introduction of the transformer architecture.
Transformers are a type of neural network designed to process sequential data and have revolutionized the way AI
models handle language
 Tools and Technologies
• Python
• Purpose: Used as the primary programming language for developing the backend of the chatbot.
• Libraries: Leverages libraries such as Natural Language Toolkit (NLTK) or TensorFlow for natural
language processing and machine learning.
• Flask
• Purpose: A lightweight web framework used to build and handle the web application’s server-side logic.
• Benefits: Flask is easy to use, flexible, and ideal for creating APIs for chatbot communication.
• MySQL
• Purpose: Used as the database to store and manage user data, queries, and responses.
• Benefits: Reliable, widely used relational database that allows efficient data management and retrieval.
• JavaScript
• Purpose: Used to create interactive, dynamic web pages and handle the logic for chatbot responses on the frontend.

• Libraries: jQuery for DOM manipulation, AJAX for asynchronous web requests.

• jQuery
• Purpose: Simplifies HTML document traversal, event handling, animation, and AJAX interactions.

• Benefits: Ensures better compatibility across browsers, speeding up development time.

• HTML/CSS/Bootstrap
• Purpose: Used to structure and style the web pages.

• HTML: Defines the webpage structure and content.

• CSS: Provides styles, layout designs, and responsive behavior.

• Bootstrap: A front-end framework used for responsive, mobile-first web development, ensuring the chatbot

interface looks good on all screen sizes.

• Benefits: Facilitates seamless integration of Python data with HTML templates, enabling dynamic content rendering
on the web page.

• AJAX
• Purpose: Used for making asynchronous requests from the client-side without reloading the entire page.

• Benefits: Ensures smooth, fast, and interactive user experience by dynamically updating the web page with chatbot
responses.
 Conclusion
• The Shah Abdul Latif University AI Enquiry Chatbot project successfully addresses the need for efficient and
accessible communication within educational institutions. By integrating Artificial Intelligence with modern web
technologies, the chatbot provides students, faculty, and staff with instant, accurate responses to a wide range of
queries related to academics, fees, placements, exams, and university facilities.
• Key highlights of the project include:
• 24/7 Availability: Ensures users can access information anytime, eliminating the need for physical visits or reliance on
staff.
• Enhanced User Experience: A user-friendly interface, powered by tools like Flask, MySQL, AJAX, and Bootstrap,
provides a smooth, interactive experience.
• Time and Resource Efficiency: The system reduces administrative workloads, saving time and effort for both students
and staff.
• With Python and Flask as the backbone of the system, the chatbot delivers quick, personalized responses, creating a
streamlined communication process for everyone involved. Moving forward, there is potential to expand the system
to support multiple languages, voice-based queries, and integration with other platforms, making the chatbot more
inclusive and adaptive to the needs of a broader audience.
 Future Work
•Multilingual Support:
•Expand the chatbot to support multiple languages, making it more accessible to a diverse student
base.
•Voice-Based Interaction:
•Implement voice recognition and response capabilities, allowing users to interact with the chatbot
via speech.
•Integration with University Systems:
•Integrate the chatbot with other university systems (e.g., student portals, learning management
systems) to provide real-time information like grades, schedules, and exam results.
•Personalized User Experience:
•Develop personalized responses based on user data and preferences to make interactions more
relevant and helpful.
References
[1]
https://onlim.com/en/the-history-of-chatbots/#:~:text=The%20first%20chatbot%20ever%
20was,created%20a%20more%20advanced%20Chatbot
.
[2] https://www.justthink.ai/blog/the-evolution-and-history-of-ai-chatbots
[3]https://www.researchgate.net/publication/
378149233_History_of_generative_Artificial_Intelligence_AI_chatbots_past_present_an
d_future_development

46
49