SERVER-TO-BASE-STATION CONFIGURATION OF A NEURAL NETWORK FOR FEATURE PROCESSING FOR POSITIONING
Patent Information
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- QUALCOMM INC
- Filing Date
- 2022-03-23
- Publication Date
- 2026-05-27
AI Technical Summary
Existing wireless communication systems, particularly in the context of 5G, face challenges in accurately estimating the location of user equipment (UE) without GPS functionality, with existing methods relying on deep learning-based approaches that may not achieve optimal coverage and efficiency.
A method involving a network node that receives parameters for a neural network, performs measurements on reference signals, generates statistics, and reports these to estimate the UE's location, utilizing a network entity with a memory, transceiver, and processor to execute this positioning method.
Enhances the accuracy and efficiency of UE location estimation by leveraging neural networks to process reference signal statistics, improving positioning capabilities in 5G networks.