	US 11,870,609 B2
	Selecting a joint equalization and decoding model
Seyedomid Taghizadeh Motlagh, Oberursel (DE); Sher Ali Cheema, Ilmenau (DE); Ali Ramadan Ali, Munich (DE); Ankit Bhamri, Rödermark (DE); Hyejung Jung, Northbrook, IL (US); Hossein Bagheri, Urbana, IL (US); Vijay Nangia, Woodridge, IL (US); and Razvan-Andrei Stoica, Essen (DE)
Assigned to Lenovo (Singapore) Pte. Ltd., New Tech Park (SG)
Filed by Lenovo (Singapore) Pte. Ltd., New Tech Park (SG)
Filed on Sep. 22, 2021, as Appl. No. 17/482,148.
Prior Publication US 2023/0086078 A1, Mar. 23, 2023
Int. Cl. H04L 25/02 (2006.01); H04L 1/00 (2006.01); H04L 1/06 (2006.01); H04L 5/00 (2006.01); H04L 25/03 (2006.01)

CPC H04L 25/0204 (2013.01) [H04L 1/0016 (2013.01); H04L 1/0643 (2013.01); H04L 5/0023 (2013.01); H04L 25/03331 (2013.01)]

20 Claims

1. A User Equipment (“UE”) for wireless communication, comprising:

at least one memory; and

at least one processor coupled with the at least one memory and configured to cause the UE to:

receive, from a network device, a first configuration indicating at least one of: a set of resources for model training, a type of intended model training, a type of a model to be used, or a combination thereof;

receive an indication of a wireless channel condition, wherein the indication comprises an index of a first codebook of predetermined channel condition parameters;

select a joint channel equalization and decoding (“JED”) model from a second codebook of predefined models based on the indication of the wireless channel condition and the received first configuration; and

train the selected JED model using the first configuration.