Neural Network Signal Encoding for Reliable Wireless Uplink

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing wireless communication systems face challenges in handling large communication capacities and ensuring reliability and low latency for diverse services, particularly in environments requiring enhanced mobile broadband and massive machine type communications.

Innovation Solution

Implementing neural networks, specifically real and complex neural networks, for encoding and decoding data in user equipment (UE) and base stations to enhance communication efficiency and reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional encoding methods are used in wireless communication systems, then device complexity is low and ease of manufacture is high, but communication capacity and reliability are insufficient for enhanced mobile broadband and massive machine type communications

Engineering Contradiction:

Improvecommunication reliabilityVSAvoidencoding device complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical/mathematical encoding systems with a neural network-based encoding system. The neural network learns optimal encoding strategies through training, substituting conventional algorithmic approaches with data-driven intelligent processing, thereby achieving higher communication reliability and capacity while adapting to diverse service requirements

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the fundamental parameters of the encoding system by transitioning from fixed algorithmic parameters to adaptive neural network parameters. The neural network's weights and biases are dynamically adjusted during training to optimize encoding performance for different communication scenarios, enabling the system to handle enhanced mobile broadband and massive machine type communications effectively

Inventive Principle:

Principle #35Parameter changes

2Productivity

If neural networks are implemented for encoding and decoding, then communication capacity and reliability are improved, but device complexity and computational requirements increase

Engineering Contradiction:

Improvecommunication capacityVSAvoidneural network implementation complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by training the neural network encoding and decoding models in advance using extensive datasets. This pre-training phase allows the neural networks to learn optimal encoding strategies and patterns before actual communication operations, reducing real-time computational complexity while maintaining high communication capacity and reliability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by implementing separate neural network models for encoding and decoding that are trained independently but work together. This allows the system to optimize each function separately while achieving synergistic effects in the overall communication process, managing complexity through functional decomposition

Inventive Principle:

Principle #26Copying

Data Source

PatentUS12432009B2Method and apparatus for transmitting and receiving signals of user equipment and base station in wireless communication system

Publication Date: 2025.09.30 LG ELECTRONICS INC

AI summary

A method of operating a user equipment (UE) and a base station in a wireless communication system and an apparatus supporting this are disclosed. The method of operating the UE may comprise encoding input data based on a neural network and transmitting the encoded input data to a base station. In this case, the neural network may be determined to be at least one of a real neural network or a complex neural network.