US 12,489,506 B2
Method, apparatus, and device for selecting parameters of channel state information, and storage medium
Jiacheng Chen, Shenzhen (CN); Jingbo Liu, Shenzhen (CN); and Haibo Zhou, Shenzhen (CN)
Assigned to PENG CHENG LABORATORY, Shenzhen (CN)
Filed by PENG CHENG LABORATORY, Shenzhen (CN)
Filed on Jun. 17, 2025, as Appl. No. 19/241,282.
Application 19/241,282 is a continuation of application No. PCT/CN2024/123983, filed on Oct. 10, 2024.
Claims priority of application No. 202410042195.X (CN), filed on Jan. 10, 2024.
Prior Publication US 2025/0317184 A1, Oct. 9, 2025
Int. Cl. H04B 7/06 (2006.01)
CPC H04B 7/0639 (2013.01) [H04B 7/0632 (2013.01)] 6 Claims
OG exemplary drawing
 
1. A method for selecting parameters of channel state information, comprising:
acquiring sampling data at a target location point at different times, wherein the target location point is a location point of a parameter to be selected, and the location point that needs to be sampled among geographical location points within a base station coverage area;
determining a target data stream number of the target location point based on the sampling data;
determining a target precoding matrix of the target location point based on the target data stream number and a preset neural network model; and
determining a channel quality indicator of the target location point based on the target precoding matrix, wherein the data stream number, the precoding matrix, and the channel quality indicator are parameters of channel state information,
wherein the preset neural network model includes a variational autoencoder (VAE), and the determining the target precoding matrix of the target location point based on the target data stream number and the preset neural network model comprises:
in response to the target location point being a known location point, determining an optimal precoding matrix set corresponding to the target data stream number; and
encoding and reconstructing the optimal precoding matrix set based on the VAE to obtain the target precoding matrix of the target location point, wherein the VAE is obtained by training a first neural network model to be trained using the optimal precoding matrix set corresponding to each data stream number as input and the precoding matrix of the position point corresponding to each data stream number as output.