UE Machine Learning Module Selection via Decision Module

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

User equipment in wireless communication systems face challenges in selecting the appropriate machine learning modules and updating their configurations to handle varying scenarios and environments, as existing systems lack a mechanism for dynamic selection and adaptation of machine learning modules.

Innovation Solution

The network configures a decision-making module at the user equipment to control the selection and adaptation of machine learning modules, transmitting algorithms or parameters based on reference signals and environmental feedback, allowing the user equipment to locally execute the decision-making module and report back to the network for updates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If machine learning modules are used in wireless communication systems, then communication efficiency and accuracy are improved, but the complexity of selecting and configuring appropriate modules increases

Engineering Contradiction:

Improvecommunication efficiencyVSAvoidmodule selection complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The user equipment autonomously executes the decision-making module to self-determine the configuration and selection parameters of machine learning modules based on environmental feedback and reference signals, without requiring manual configuration or complex network-controlled selection processes

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements a feedback mechanism where the user equipment reports decisions and performance data back to the network, which then provides updated configurations and algorithms, creating a closed-loop system that adapts to changing conditions while maintaining simplicity at the user equipment side

Inventive Principle:

Principle #23Feedback

2Reliability

If machine learning modules are dynamically adapted to varying scenarios, then reliability is improved, but the difficulty of detecting and measuring appropriate configurations increases

Engineering Contradiction:

Improveadaptation reliabilityVSAvoidconfiguration detection difficulty

Core Design Contradiction:

ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The decision-making module acts as an intermediary that receives environmental feedback and reference signals from the network, processes this information through neural network algorithms, and automatically determines the appropriate machine learning module configurations without requiring direct human intervention or complex measurement procedures

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The network pre-configures multiple machine learning module options and algorithms before the user equipment needs to make selections, allowing the decision-making module to simply choose from pre-evaluated configurations rather than searching through vast configuration spaces in real-time

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12120604B2Cross-node deep learning methods of selecting machine learning modules in wireless communication systems

Publication Date: 2024.10.15 QUALCOMM INC

AI summary

A method of wireless communication is performed by a user equipment (UE). The method receives, from a network, a configuration for a decision making module. The method also executes the decision making module to determine a selection parameter for a configuration of at least one machine learning module. The method selects the configuration of the at least one machine learning module based on the selection parameter. Further, the method reports, to the network, a decision resulting from executing the decision making module.