Data transmission method, data transmission apparatus and data transmission device
AssigneeDatang Mobile Communications Equipment Co., Ltd.
InventorsXianjun Yang, Shiqiang Suo
Life of this patent
Estimating the term…
Abstract
A data transmission method, a data transmission apparatus, and a data transmission device are provided, where the method on the terminal side includes: obtaining, by the terminal, an ACK/NACK sequence to be fed back; selecting, by the terminal, a machine learning model applied to the ACK/NACK sequence; compressing, by the terminal, the ACK/NACK sequence through the machine learning model to obtain an indication sequence; and transmitting, by the terminal, the indication sequence to the network device.
Claims20
A data transmission method, performed by a terminal, comprising:
- obtaining, by the terminal, an acknowledgment/negative acknowledgment ACK/NACK sequence to be fed back;
- selecting, by the terminal, a machine learning model applied to the ACK/NACK sequence, wherein the machine learning model comprises an autoencoder;
- compressing, by the terminal, the ACK/NACK sequence through the machine learning model to obtain an indication sequence;
- and
- transmitting, by the terminal, the indication sequence to a network device.
A training and distributing method of machine learning model, performed by a network device side, comprising:
- obtaining, by the network device, an ACK/NACK sequence to be trained, and storing the ACK/NACK sequence to be trained;
- grouping, by the network device, the stored ACK/NACK sequence, performing machine learning model training, and generating a plurality of groups of machine learning models, wherein the machine learning models comprise an autoencoder;
- storing, by the network device, the machine learning models;
- distributing, by the network device, the stored machine learning models to the terminals through an RRC signaling or an MAC CE or a physical layer signaling.
A data transmission method, performed by a network device, comprising:
- obtaining, by the network device, an acknowledgment/negative acknowledgment ACK/NACK sequence to be fed back;
- selecting, by the network device, a machine learning model applied to the ACK/NACK sequence, and transmitting indication information of the selected machine learning model to a terminal, wherein the machine learning model comprises an autoencoder;
- compressing, by the network device, the ACK/NACK sequence through the machine learning model to obtain an indication sequence;
- and
- transmitting, by the network device, the indication sequence to the terminal.
Dependencies are inferred from the claim text.