UE AI/ML Capability Signaling for Compatible Model Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communications systems face challenges in coordinating between network entities and user equipment to select appropriate AI/ML models for efficient AI/ML functionality, leading to inefficient performance due to lack of coordination on supported functionalities and configurations.
Innovation Solution
Implement signaling procedures for exchanging AI/ML information between network entities and user equipment to facilitate appropriate model selection, including UE capability reporting and network confirmation of applicable AI/ML functionalities and configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI/ML models are selected without coordination between network entities and user equipment, then device complexity is reduced, but AI/ML functionality performance deteriorates due to lack of compatibility assurance
Solution Approach 1:
The patent implements capability reporting procedures where user equipment reports its AI/ML capabilities to the network entity in advance. This preliminary action allows the network entity to have prior knowledge of supported functionalities and configurations, enabling informed model selection without real-time coordination complexity during actual AI/ML operations.
Solution Approach 2:
The patent establishes a feedback mechanism where user equipment provides capability information back to the network entity. This feedback loop ensures the network entity receives accurate information about supported AI/ML functionalities, configurations, and conditions, enabling reliable model selection while maintaining manageable coordination through standardized reporting protocols.
2Measurement precision
If comprehensive capability reporting is implemented, then AI/ML model selection accuracy is improved, but signaling overhead increases
Solution Approach 1:
The patent segments capability reporting into distinct components: supported AI/ML functionalities, configurations for each functionality, and conditions for applicability. This segmentation allows the network entity to request only the specific capability information needed for particular AI/ML model selection scenarios, reducing unnecessary signaling overhead while maintaining accurate capability knowledge.
Solution Approach 2:
The patent implements partial capability reporting where user equipment reports capability information selectively based on network entity requests or specific operational needs. Instead of continuously reporting all possible capabilities, the system performs partial reporting only when relevant for current AI/ML operations, reducing signaling overhead while ensuring accuracy when needed.
Data Source
AI summary
Various aspects of the present disclosure relate to an apparatus and method for communicating artificial intelligence (AI)/machine learning (ML) information. A request message for information associated with AI can be received from a network entity. A response message including applicability-related information associated with at least one AI functionality supported by a UE can be transmitted to the network entity based at least in part on the received request message.