MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641086158 A) filed by Koneru Lakshmaiah Education Foundation on July 14, 2026, for Integrated Cognitive Learning Architecture For Autonomous Development Of Engineering Writing Competencies.
Inventors include M. Hepsiba George; and Dr. Kranthi Priya Oruganti.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention relates to an Integrated Cognitive Learning Architecture for Autonomous Development of Engineering Writing Competencies, designed to enhance technical writing skills through an intelligent and adaptive educational framework. The proposed architecture integrates Large Language Models (LLMs), Explainable Artificial Intelligence (XAI), Engineering Knowledge Graphs, Digital Twin-based learner modelling, Natural Language Processing (NLP), Machine Learning, and Adaptive Learning Analytics into a unified cognitive ecosystem. The system continuously acquires learner-generated engineering documents, constructs dynamic cognitive learner profiles, evaluates multidimensional writing competencies, predicts future competency progression, and generates personalized learning pathways through transparent AI-assisted recommendations. A synchronized Digital Twin maintains a virtual representation of each learner, enabling continuous competency monitoring and adaptive educational intervention. Explainable AI techniques provide interpretable assessment outcomes, while the Engineering Knowledge Graph supports domain-specific semantic reasoning and technical writing guidance. The proposed invention significantly improves engineering writing proficiency, competency-based assessment, personalized learning, educational decision-making, and autonomous skill development, thereby advancing next-generation intelligent engineering education systems. Keywords: Engineering Writing Competencies; Large Language Models (LLMs); Explainable Artificial Intelligence (XAI); Digital Twin-Based Learner Modeling; Adaptive Learning Analytics.
Disclaimer: Curated by HT Syndication.
