# US 2026/0073305 A1 · Communication method and device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073305 A1
- Document ID: US20260073305A1
- Status: Published application
- Kind: A1
- Application number: 19/387,264
- Filed: 2025-11-12
- Published: 2026-03-12
- Earliest claimed: 2023-05-15
- Assignees: Guangdong Oppo Mobile Telecommunications Corp., Ltd.
- Applicants: Guangdong Oppo Mobile Telecommunications Corp., Ltd.
- Inventors: Dexin LI
- Web page: https://patentgrep.com/patent/US20260073305A1

## CPC

- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 20/00: Machine learning
- G06N 3/02: Neural networks
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/048: Activation functions
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/063: using electronic means
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G06N 3/094: Adversarial learning
- G06N 3/098: Distributed learning, e.g. federated learning
- G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present application relates to a communication method and device. The method includes: a first communication device receives model quantization configuration information from a second communication device; and the first communication device executes a model quantization related operation according to the model quantization configuration information.

## Claims

### Claim 1

A communication method, comprising:
receiving, by a first communication device, model quantization configuration information from a second communication device; and
performing, by the first communication device, an operation related to model quantization based on the model quantization configuration information.

### Claim 2 (depends on 1)

The method of claim 1, wherein the model quantization configuration information comprises target precision information.

### Claim 3 (depends on 2)

The method of claim 2, wherein the target precision information comprises one or more of: a target quantization precision of an activation parameter, a target quantization precision of a bias parameter, or a target quantization precision of a weight parameter.

### Claim 4 (depends on 2)

The method of claim 2, wherein performing, by the first communication device, the operation related to the model quantization based on the model quantization configuration information comprises one of:
when the first communication device comprises a first model corresponding to the target precision information, transmitting the first model and/or a parameter of the first model to the second communication device;
when the first communication device comprises no first model corresponding to the target precision information, converting a second model to the first model based on the target precision information, and transmitting, by the first communication device, the first model and/or a parameter of the first model to the second communication device.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
transmitting, by the first communication device, a model quantization configuration request to the second communication device.

### Claim 6 (depends on 1)

The method of claim 1, wherein a model quantization precision supported by the first communication device comprises one or more of: a quantization precision of an activation parameter, a quantization precision of a bias parameter, or a quantization precision of a weight parameter.

### Claim 7 (depends on 4)

The method of claim 4, wherein
the first model is obtained based on a model trained by the first communication device or a sub-model of the model trained by the first communication device; and/or
the first communication device is a network device, and the second communication device is a terminal device, the first model is an encoder model of a channel state information (CSI) model, and the CSI model is trained on the network device and is deployed on the network device and/or the terminal device.

### Claim 8

A first communication device, comprising:
a processor;
a memory for storing a computer program executable on the processor; and
a transceiver;
wherein the processor is configured to execute the computer program to:
control the transceiver to receive model quantization configuration information from a second communication device; and
perform an operation related to model quantization based on the model quantization configuration information.

### Claim 9 (depends on 8)

The first communication device of claim 8, wherein
the model quantization configuration information comprises target precision information;
the target precision information comprises one or more of: a target quantization precision of an activation parameter, a target quantization precision of a bias parameter, or a target quantization precision of a weight parameter.

### Claim 10 (depends on 9)

The first communication device of claim 9, wherein the processor is further configured to:
when the first communication device comprises a first model corresponding to the target precision information, control the transceiver to transmit the first model and/or a parameter of the first model to the second communication device;
when the first communication device comprises no first model corresponding to the target precision information, convert a second model to the first model based on the target precision information, and control the transceiver to transmit the first model and/or a parameter of the first model to the second communication device.

### Claim 11 (depends on 8)

The first communication device of claim 8, wherein the processor is further configured to control the transceiver to:
transmit a model quantization configuration request to the second communication device.

### Claim 12 (depends on 8)

The first communication device of claim 8, wherein a model quantization precision supported by the first communication device comprises one or more of: a quantization precision of an activation parameter, a quantization precision of a bias parameter, or a quantization precision of a weight parameter.

### Claim 13 (depends on 10)

The first communication device of claim 10, wherein
the first model is obtained based on a model trained by the first communication device or a sub-model of the model trained by the first communication device; and/or
the first communication device is a terminal device, and the second communication device is a network device, the first model is a decoder model of a CSI model, and the CSI model is trained on the terminal device and is deployed on the network device and/or the terminal device.

### Claim 14 (depends on 8)

The first communication device of claim 8, wherein the first communication device is a first terminal device, and the second communication device is a second terminal device.

### Claim 15

A second communication device, comprising:
a processor;
a memory for storing a computer program executable on the processor; and
a transceiver;
wherein the processor is configured to execute the computer program to:
control the transceiver to transmit model quantization configuration information to a first communication device, the model quantization configuration information indicating the first communication device to perform an operation related to model quantization.

### Claim 16 (depends on 15)

The second communication device of claim 15, wherein the model quantization configuration information comprises target precision information.

### Claim 17 (depends on 16)

The second communication device of claim 16, wherein the target precision information comprises one or more of: a target quantization precision of an activation parameter, a target quantization precision of a bias parameter, or a target quantization precision of a weight parameter.

### Claim 18 (depends on 16)

The second communication device of claim 16, wherein the processor is further configured to control the transceiver to:
receive a first model corresponding to the target precision information from the first communication device, wherein the first model is obtained based on a model trained by the first communication device or a sub-model of the model trained by the first communication device.

### Claim 19 (depends on 15)

The second communication device of claim 15, wherein the processor is further configured to control the transceiver to:
receive a model quantization configuration request from the first communication device.

### Claim 20 (depends on 15)

The second communication device of claim 15, wherein a model quantization precision supported by the first communication device comprises one or more of: a quantization precision of an activation parameter, a quantization precision of a bias parameter, or a quantization precision of a weight parameter.
