MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202541009543 A) filed by Tejas Networks Limited on February 05, 2025, for Efficient Data Collection And Model Architecture For Ai-Ml Based Positioning.
Inventor includes Vikram Singh.
The application for the patent was published on August 07, 2026, under issue no. 32/2026.
Abstract: The present disclosure relates to artificial-intelligence and machine-learning (AI-ML) based positioning in wireless communication networks, particularly under non- line-of-sight (NLoS) propagation conditions. The disclosure provides a low-overhead positioning framework that enables accurate location estimation while reducing channel information reporting from network nodes. Concise channel information comprising timing information, angle information, line-of-sight or non-line-of-sight confidence indication, and associated quality indicators is received from at least one receiver node. A first AI-ML model reconstructs a virtual complete channel representation from the concise channel information to compensate for missing or degraded channel characteristics caused by limited reporting and NLoS effects. A second AI-ML model then estimates the position of a target node using the reconstructed channel representation, wherein the confidence and quality indicators are used to adapt the positioning estimation. The disclosed framework reduces uplink feedback overhead while maintaining high positioning accuracy and is applicable to two- dimensional and three-dimensional positioning in 5G-Advanced and sixth-generation wireless networks. Figure 1 (publication).
Disclaimer: Curated by HT Syndication.
