Intellectual Property India Publishes Patent Application for A System And Method For Machine Learning-Based Human-Computer Interaction And Personalized Digital Assistance Platform

MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641078257 A) filed by Vardhaman College Of Engineering on June 25, 2026, for A System And Method For Machine Learning-Based Human-Computer Interaction And Personalized Digital Assistance Platform.

Inventors include Dr. Srinivasulu Gogula; Mr. Madasu Ashwan Kumar; Mr. Bijaya Kumar Sethi; Ms. Farhana Begam; Dr. Kathirisetty Nikhila; and Ms. M Keerthana.

The application for the patent was published on July 03, 2026, under issue no. 27/2026.

Abstract: ABSTRACT A System and Method for Machine Learning-Based Human-Computer Interaction and Personalized Digital Assistance Platform The present disclosure relates to a system and method for machine learning based human computer interaction and personalized digital assistance The system includes a multimodal interaction acquisition module that is used to gather interaction information from voice input, text communication, facial expressions, gestures, wearable sensors, application environment, and context. A cross-modal synchronization engine outputs unified contextual representations, and a cognitive digital twin generation module dynamically builds and updates a behavioral model of a user. A behavioral drift detection module identifies change of behavior of users and adapts the personalization strategies based on this detection. A emotion-aware intent fusion module to infer users’ intent and cognitive state. A contextual memory evolution engine to automatically update contextual knowledge structures. A predictive intent forecasting module predicts future user needs, and a neuro-symbolic reasoning engine produces explainable assistance decisions. The system also includes federated adaptive learning and cryptographic fingerprinting to allow for privacy- preserving personalization. Personalized assistance actions are then executed to improve the interaction accuracy, contextual awareness, predictive intelligence, user productivity and overall digital assistance performance.

Disclaimer: Curated by HT Syndication.