Wireless Terminal AI/ML Resource Reporting via Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems face challenges in effectively coordinating between wireless terminals and telecommunications networks to report and manage Artificial Intelligence/Machine Learning (AI/ML) model capabilities, leading to potential overconfiguration or underutilization of AI/ML models and functionalities due to limitations in device and network resource awareness.
Innovation Solution
The implementation of a message-based system where the network requests and receives AI/ML-related information from wireless terminals, allowing for periodic or triggered reporting of run-time capabilities and resource restrictions, enabling dynamic adaptation and optimization of AI/ML model support to meet performance Key Performance Indicators (KPIs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the network configures AI/ML models in wireless terminals without accurate resource awareness, then AI/ML model functionality is provided, but device complexity and resource overconfiguration increase
Solution Approach 1:
The patent implements feedback mechanisms where wireless terminals report their AI/ML resource capabilities (processing power, memory, energy) to the network, and the network adjusts AI/ML model configurations based on received capability information. This closed-loop feedback ensures models are appropriately configured to terminal capabilities, preventing both overconfiguration and underutilization.
Solution Approach 2:
The patent enables dynamic adaptation of AI/ML model configurations based on real-time terminal resource status. Terminals can switch between different AI/ML models or adjust model parameters according to their current resource availability, allowing the system to adapt to changing conditions rather than using static configurations.
2Productivity
If the network requests detailed AI/ML capability information from wireless terminals, then resource optimization is achieved, but signaling overhead and communication complexity increase
Solution Approach 1:
The patent extracts only the essential AI/ML capability parameters needed for optimization (processing capability, memory capacity, energy constraints) and transmits them to the network. By selecting and transmitting only the most critical capability indicators rather than complete detailed information, the system achieves resource optimization while minimizing signaling overhead.
3Speed
If wireless terminals autonomously manage AI/ML models without network coordination, then response time is reduced, but system reliability and performance consistency deteriorate
Solution Approach 1:
The patent implements preliminary action by having the network pre-configure multiple AI/ML models in wireless terminals based on predicted resource needs and historical performance data. When resource conditions change, terminals can quickly switch between pre-configured models without lengthy negotiation, achieving fast response while maintaining reliable performance through network-planned model selections.
Data Source
AI summary
A wireless terminal comprising receiver circuitry, processor circuitry, and transmitter circuitry. The receiver circuitry is configured to receive from a radio access network at least one message which requests the wireless terminal to report Artificial Intelligence/Machine Learning Model (AI/ML) related information to the network. The processor circuitry is configured to generate at least one resource restriction response message from the wireless terminal. The resource restriction response message comprises an indication that the wireless terminal guards AI/ML model and/or AI/ML functions of the wireless terminal. The transmitter circuitry is configured to transmit the at least one resource restriction response message to the network.