MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202641088172 A) filed by Karpaga Vinayaga College Of Engineering And Technology; Dr. A. B. Hajira Be; Ms. Devadharshini. B; Ms. Nivitha B; Mr. Lakshmipathi N; and Mr. Janarthanan S on July 20, 2026, for Design And Implementation Of A Cloud-Based Intelligent E-Gardening Management System Using Machine Learning Thereof.
Inventors include Dr. A. B. Hajira Be; Ms. Devadharshini. B; Ms. Nivitha B; Mr. Lakshmipathi N; and Mr. Janarthanan S.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: The invention discloses a cloud-based, data-driven intelligent e-gardening management system and method designed to optimize residential botany, urban agriculture, and domestic plant care through an integrated machine learning architecture. The system establishes a secure digital infrastructure starting with an automated user authentication layer that initializes independent database partitions for personal garden properties. Users interact with a centralized, multi-page web application that serves as an inventory system where plant records can be dynamically created, updated, or removed. This inventory system supports localized image media hosting for visual tracking of individual specimens, categorizing flora into specific structural domains based on species classifications and environmental configurations. At its operational core, the platform integrates an asynchronous activity log and predictive notification system that maps historical cultivation workflows, such as precision watering timestamps and fertilizer application intervals. Rather than relying on rigid, fixed-timer countdowns, the scheduling engine calculates moisture depletion patterns using a predictive Random Forest machine learning model trained on localized ambient parameters, throwing adaptive visual warnings and seasonal reminders across the user interface when imminent dehydration or nutritional deficiency is detected. Simultaneously, the system integrates a dedicated computer vision pipeline for real-time biological protection. Home gardeners can capture and upload digital images of distressed plant foliage directly to the application, where a pre-trained convolutional neural network (CNN) model parses the image data to isolate, detect, and classify distinct plant diseases, including leaf rust and powdery mildew. Upon accurate classification, the system cross-references an indexed treatment database to instantly display organic and chemical recovery steps.
Disclaimer: Curated by HT Syndication.
