US 11,916,611 B2
Neural network model sharing with zone identifier
Hamed Pezeshki, San Diego, CA (US); Tao Luo, San Diego, CA (US); and Sony Akkarakaran, Poway, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Mar. 15, 2021, as Appl. No. 17/201,318.
Prior Publication US 2022/0294548 A1, Sep. 15, 2022
Int. Cl. H04B 17/391 (2015.01); H04W 4/021 (2018.01); G06N 3/08 (2023.01); H04W 72/542 (2023.01)
CPC H04B 17/3913 (2015.01) [G06N 3/08 (2013.01); H04W 4/021 (2013.01); H04W 72/542 (2023.01)] 26 Claims
OG exemplary drawing
 
1. A method of wireless communication at a base station, comprising:
receiving, from a first user equipment (UE), an indication of a first zone identifier (ID) associated with sidelink communication and one or more machine learning (ML) model parameters based on the first zone ID that identifies a first geographical zone, the one or more ML model parameters being associated with the first zone ID, wherein the first zone ID is derived based on current location of the first UE with reference to coordinates (0, 0) of a World Geodetic System 84 (WGS84) model; and
providing, from the base station, the one or more ML model parameters to a second UE based on the second UE being located in the first geographic zone indicated by the first zone ID associated with the sidelink communication.