MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641081794 A) filed by Dr. T. Raja Sekhar, Professor Head Department Of English, Babu Jagjivan Ram Government Degree College A.; Dr. Tadi Vijaya Kalyani, Assistant Professor Guest Faculty Department Of English, Andhra University, Visakhapatnam, A. P.; Rathna Kalyani Erpula, Associate Professor Department Of English, Babu Jagjivan Ram Government Degree College A.; Lokanandi Jyothi, Associate Professor Department Of English; Dr. C. S. Srinivas, Assistant Professor Of English Department Of M&h, Mahatma Gandhi Institute Of Technology A.; Karumuri Sunil, Assistant Professor Guest Faculty; and Dr. Raajitha Rachuri, Assistant Professor Pt Department Of English, Veeranari Chakali Ilamma Women'S University. on July 02, 2026, for Multimodal Attention And Emotion Recognition Framework For Personalized Adaptive Learning In English Language Teaching Environments.
Inventors include Dr. T. Raja Sekhar, Professor Head Department Of English; Dr. Tadi Vijaya Kalyani, Assistant Professor Guest Faculty; Rathna Kalyani Erpula, Associate Professor Department Of; Lokanandi Jyothi, Associate Professor Department Of English, Babu Jagjivan Ram Government Degree College A.; Dr. C. S. Srinivas, Assistant Professor Of English Department Of M&h, Mahatma Gandhi Institute Of Technology A.; Karumuri Sunil, Assistant Professor Guest Faculty Department Of English, Andhra University, Visakhapatnam, A. P.; and Dr. Raajitha Rachuri, Assistant Professor Pt Department Of English, Veeranari Chakali Ilamma Women'S University..
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: Abstract The present invention discloses a multimodal attention and emotion recognition framework (the MAER-PAL Framework) for personalized adaptive learning in English Language Teaching environments. The framework captures facial, vocal, textual, and behavioural signals from a learner during English language tasks and processes them through an attention recognition module, which computes a continuous Attention Index, and an emotion recognition module, which estimates learning- relevant affective states including engagement, confusion, boredom, frustration, anxiety, and confidence. A multimodal fusion module applies dynamic confidence weighting to produce a unified Learner Affective Attentional State (LAAS), and an adaptive learning engine maps this state in real time to pedagogical actions such as adjusting difficulty, switching modality, providing scaffolding, re-teaching, and pacing. A longitudinal learner model personalizes adaptation to each individual over successive sessions. The framework sustains learner engagement, regulates affect, and improves measurable English language proficiency, addressing the gap left by conventional non-adaptive and unimodal systems.
Disclaimer: Curated by HT Syndication.
