MUMBAI, India, Feb. 13 -- Intellectual Property India has published a patent application (202641007898 A) filed by Vellore Institute Of Technology, Chennai, Tamil Nadu, on Jan. 27, for 'system for generating personalized product recommendations and method thereof.'
Inventor(s) include Karthika Sk; Neel Dhaygude; Brian Bobby Joe; and Diya Elizabeth Kurian.
The application for the patent was published on Feb. 13, under issue no. 07/2026.
According to the abstract released by the Intellectual Property India: "A system (102) and a method (200) for generating product recommendations includes client device (102) and centralized server (116) is disclosed. Client device (102) includes image acquisition unit (104), voice acquisition unit (106), and input acquisition unit (108) to acquire visual, audio, and textual user inputs. Feature extraction unit (110) converts visual and audio inputs into facial action feature vectors and prosodic audio feature vectors, which are synchronized by time alignment unit (112). Inference engine (114) processes synchronized multimodal frames and textual inputs to generate a session mood vector and extracted keywords within a predefined latency bound. Centralized server (116) stores tokenized product records in product database (118) and generates ranked product identifiers. Description grading unit (122) evaluates review sentiment, auto-update unit (124) modifies product descriptions based on threshold conditions, and model aggregation unit (126) distributes aggregated model updates. User interface unit (128) presents ranked product recommendations with updated descriptions."
Disclaimer: Curated by HT Syndication.
