MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202611051695 A) filed by Sharda University, Greater Noida, Uttar Pradesh, on April 23, for 'spatio-temporal eta and ride fare prediction system.'
Inventor(s) include Bhaven Shah; Md Altaf Raza; Ashu Goyal; Aashika Singh; and Nishant Upadhyay.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "Disclosed is a system for joint prediction of estimated time of arrival (ETA) and ride fare in an urban ride-sharing system. The system comprises at least one remote server configured to receive trip-related data, traffic-related data, temporal data, and geographic data, partition an urban geographic area into hexagonal indexed geographic regions, generate a graph representation with corresponding nodes and directional edge classes, assign regional features to the corresponding nodes, generate spatial embeddings using a spatio-temporal graph neural network (ST-GNN), generate temporal embeddings using a Transformer-based temporal encoder comprising multi-head self-attention, fuse the spatial embeddings and the temporal embeddings, and generate a predicted ETA and a predicted ride fare for use in ride-request processing within the urban ride-sharing system."
Disclaimer: Curated by HT Syndication.
