MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202641050481 A) filed by Mrs. Bhavithira V; Mr. Kart Hick B; Mr. Jersil G M; Mr. Dharshan K J; and Mr. Abishek M on April 21, 2026, for Autonomous Research Assistant.
Inventors include Mrs. Bhavithira V; Mr. Abishek M; Mr. Dharshan K J; Mr. Jersil G M; and Mr. Karthick B.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: FitGenie is an AI-powered personalized fashion assistant system designed to streamline wardrobe management and outfit decision-making through integration of computer vision, machine learning, and large language models. The system collects user-specific attributes including age, gender, skin tone, and body type via a React.js interface, processes uploaded clothing images using a fine-tuned Vision Transformer model to extract garment attributes, and indexes resulting feature vectors into a F AISS vector database for fast similarity· retrieval. A Retrieval-Augmented Generation (RAG) pipeline constructs a situational context profile using real-time weather data, calendar events, and user preferences, then injects retrieved wardrobe items and fashion trends into a Large Language Model to generate ranked outfit recommendations with natural language rationale. A virtual try-on module powered by a latent diffusion model enables photorealistic simulation of selected garments on user _images, while a continuous feedback mechanism updates a User Preference Matrix in PostgreSQL to improve recommendations over time. Additional features include outfit history tracking, closet gap analysis, and calendar-based scheduling, collectively delivering a scalable, adaptive, and sustainable personal fashion intelligence platform.
Disclaimer: Curated by HT Syndication.
