Samsung Prism Hackathon Team Pythonic

Transcript

1. 1 P Y T H O N I C S A M S U N G
2. 2 AIM P U R P O S E ? • Simplification • Improve user experience • Show smartness and suggestion user things they are not aware of In the ideal future, smart home devices maintain’s the house by themselves
3. 3 HOW DOES THIS MAKE USERS LIFE EASIER? T H E I M P Q U E S T I O N ! • Convenience • Personalised experience • Remote control • Real time monitoring • More time for family/work
4. 4 FEATURES W H A T D I D W E C R E A T E • P e r s o n a l a s s i s t a n t S A M • S u g g e s t i o n s ( l o c a t i o n , t i m e , h a b i t s ) • S a f e t y f e a t u r e s • E a s e o f a d d i n g d e v i c e s a n d r o u t i n e s • P o w e r s a v i n g • M u l t i p l e p e r s o n a s • L o c a t i o n a n d r o o m s
5. 5 OUR SOLUTION T H E T E C H S T A C K ADDING A NEW DEVICE • LLM - codelamma 7B (open source) • DataBase - JSON files (for POC) • Frontend - Gradio, NextJS 14, tailwindCSS • Backend - Python, JavaScript • API - Samsung’s SmartThings official docs
6. 6 SUGGESTIONS H O W D O E S T H I S W O R K ?
7. 7 HOW DO WE KNOW WHEN TO PUSH SUGGESTIONS Q U E S T I O N T O B E A S K E D Graph of user’s activity over the weekdays and weekends averaged out over a week’s time, throughout the day. U S E R ’ S PA S T H A B I T S ! !
8. 8 FUTURE WORK W H A T I S Y E T T O B E D O N E DOIGN THESE WILL MAKE IT MORE SCALABLE AS WELL • Adding authentication (Samsung ID) • Hosting the database on Supabase • Using a multilingual LLM • Improving on the suggestions system • Learning from users responses • Multiple variations of suggestions • Using Samsung sensors • Adding devices via Bluetooth and WIFI • User analytics
9. 9 CONTROL?? H O W M U C H
10. 10 OUR TEAM T H E P Y T H O N I C S FEEL FREE TO REACH OUT TO ANY OF US FOR ANY QUERIES :) A M A N G . S U B H P. S A M I K S .