US 12,323,210 B2
Techniques for determining channel state information using a neural network model
Qiaoyu Li, Beijing (CN); Yu Zhang, San Diego, CA (US); Liangming Wu, Beijing (CN); Hao Xu, Beijing (CN); Rui Hu, Beijing (CN); Chenxi Hao, Beijing (CN); and Taesang Yoo, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Appl. No. 18/253,427
Filed by QUALCOMM INCORPORATED, San Diego, CA (US)
PCT Filed Jan. 29, 2021, PCT No. PCT/CN2021/074347
§ 371(c)(1), (2) Date May 18, 2023,
PCT Pub. No. WO2022/160235, PCT Pub. Date Aug. 4, 2022.
Prior Publication US 2023/0421223 A1, Dec. 28, 2023
Int. Cl. H04B 7/06 (2006.01); H04B 7/0456 (2017.01); H04B 17/391 (2015.01)
CPC H04B 7/0626 (2013.01) [H04B 7/0456 (2013.01); H04B 17/3913 (2015.01)] 30 Claims
OG exemplary drawing
 
1. A method for wireless communications at a user equipment (UE), comprising:
receiving a first indication of a first number of antenna ports for which the UE is to report channel state information, and a second indication of a second number of antenna ports on which the UE is to measure channel state information reference signals, the second number of antenna ports being less than the first number of antenna ports;
receiving a third indication of one or more neural networks to be used by the UE for determination of the channel state information associated with the first number of antenna ports;
determining the channel state information associated with the first number of antenna ports using the one or more neural networks and using measurements made by the UE on the second number of antenna ports as inputs to the one or more neural networks; and
transmitting a report comprising the channel state information associated with the first number of antenna ports determined via the one or more neural networks.