MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123844 A) filed by Malla Reddy (MR) Deemed to be University; Malla Reddy Engineering College For Women; Malla Reddy College Of Engineering And Technology; Malla Reddy Vishwavidyapeeth; and Malla Reddy University, Medchal-Malkajgiri, Telangana, on Dec. 9, 2025, for 'real-time emotion recognition chatbot for mental health applications.'
Inventor(s) include Mr. Malege Sandeep; Mrs. G Anjali; Dr. Srinivasa Rao Mantri; Vodije Mamatha; and Dr G S Naveen Kumar.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The current invention reveals a highly developed Real-Time Emotion Recognition Chatbot that is specifically designed to be used as a first-line support system in mental health apps. In the modern digital health landscape, the currently used (or suggested) automated conversational agents typically make use of the keyword match or decision tree, which cannot reflect the human emotional state in particular. This drawback often results in generic or disconnected or clinically inappropriate responses which may be off-putting to users in need of psychological service. These shortcomings are overcome with the invention that incorporates a multi-modal emotion recognition engine that dynamically processes linguistic patterns, level of sentiment, and typing behavior to create a dynamic emotional profile of the user. The system works under a developed deep learning system, which uses Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) units to keep track of the context across long conversation threads. This invention has a memory of the emotional flow of the session as compared to standard chatbots which interpret each input individually. Indicatively, in case a user moves out of the state of expressing anxiety to a state of demonstrating the symptoms of a depressive resignation, the chatbot will change its approach to therapy, switching between active methods of relaxing to a sympathetic validation and assessment of risks. This flexibility assures the interaction of fluidity and responsiveness of a human counselor. Moreover, the invention has an expert crisis intervention protocol that operates concurrently with the conversational engine. This protection level continuously checks the chat concerning semantic cues of self-homicide, extreme distress, or mental emergencies. When such high-risk indicators are detected, the system automatically switches to a crisis alert mode after an automated chat mode to have immediate resources and, in the event of authorization, inform emergency contacts or human professionals. This two-layered solution is a compromise between the scalability of AI-driven support and the ethical requirement of safety monitoring in mental care. Lastly, the chatbot has a personalized Therapeutic Alignment module that uses the user feedback and history of interactions to adapt its personality and communication style. The agent is an adaptive being because he/she understands that various individuals react to various therapeutic styles, including Cognitive Behavioral Therapy (CBT) activities and mindfulness induction. It can be used to supplement the social distancing between the sessions of therapy, acting as a constant 24/7 emotional scaffolding that empowers its users to take the initiative of maintaining their mental health even between sessions with the therapist."
Disclaimer: Curated by HT Syndication.
