Communication Model Quantization for Low-Overhead Terminal AI

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing AI models in communication systems face challenges in being small enough for terminal scenarios while maintaining high throughput, due to high memory footprints and computational demands, which are not adequately addressed by current quantization methods.

Innovation Solution

Implementing model quantization configuration information exchange between communication devices to reduce AI model size and improve inference efficiency by converting high-precision models to lower precision formats like INT8, using quantization aware training or post-training quantization, and optimizing parameter precision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If AI models are used in terminal scenarios, then high throughput and intelligence are achieved, but model size and memory footprint become too large for terminal devices

Engineering Contradiction:
ImprovethroughputVSAvoidmodel size
Core Design Contradiction:
ProductivityVSWeight of stationary object

Solution Approach 1:

The patent applies parameter changes by converting model parameters from high-precision floating-point format to low-precision integer format (quantization). This changes the numerical representation parameters of the model, reducing the bit width required to store each parameter while maintaining acceptable inference accuracy, thus resolving the contradiction between model size and throughput

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If high-precision AI models are deployed, then inference accuracy is maintained, but memory consumption and power usage increase

Engineering Contradiction:
Improveinference accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent changes the precision parameter of model weights and activations from high-precision floating-point to low-precision integer formats. This parameter transformation reduces memory bandwidth requirements and computational energy consumption while maintaining inference accuracy within acceptable ranges through quantization-aware training or post-training quantization techniques

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If full-precision model parameters are transmitted over the air interface, then model accuracy is preserved, but transmission overhead increases

Engineering Contradiction:
Improvemodel precisionVSAvoidtransmission overhead
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent changes the representation parameter of model parameters from full-precision floating-point to compressed low-precision integer formats before transmission. This parameter transformation significantly reduces the number of bits required to represent each parameter, thereby reducing air interface transmission overhead while maintaining sufficient model precision for terminal inference tasks

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4716276A1Communication method and device
Publication Date: 2026.03.25 GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD
  • EP4716276A1 patent drawingFigure 1~2
  • EP4716276A1 patent drawingFigure 3~4B
  • EP4716276A1 patent drawingFigure 5~6

AI summary

The present application relates to a communication method and device. The method comprises: 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. In embodiments of the present application, the model quantization configuration information can indicate a model quantization related operation, and model quantization is realized.