Wireless AI/ML Model Signaling Through Layered MIB-SIBs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in efficiently sharing and updating AI/ML models between base stations and terminals, particularly in managing model groups and their associated information, which is crucial for enhancing communication reliability and capacity.
Innovation Solution
A method and device for sharing AI/ML model information and updates by configuring a layered structure in wireless communication systems, utilizing master and system information blocks to transmit AI/ML model group information and messages, allowing terminals to manage valid areas and resource scheduling for efficient model usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI/ML model information is shared between base station and terminal, then communication reliability and capacity are improved, but device complexity and information management overhead increase
Solution Approach 1:
The patent segments AI/ML model information into multiple system information blocks (SIBs) with hierarchical structure. The MIB contains basic AI/ML model group information, while subsequent SIBs contain detailed model information and update information. This segmentation allows the terminal to receive information in manageable portions rather than as a single large data structure, reducing processing complexity while maintaining reliability.
Solution Approach 2:
The patent introduces a new dimension of organization by grouping AI/ML models into model groups and using layered SIB structures. Instead of treating all AI/ML information as a single entity, the system adds hierarchical dimensions (MIB → SIB1 → SIB2) and grouping dimensions (model groups), enabling more efficient information management and reducing terminal processing burden.
2Loss of information
If AI/ML model information is transmitted through multiple system information blocks, then information completeness is improved, but transmission overhead and processing time increase
Solution Approach 1:
The patent applies preliminary action by providing AI/ML model group information in the MIB before the terminal needs to process detailed model information. The terminal can use this advance information to prepare for receiving and processing subsequent SIBs more efficiently, reducing overall processing time while ensuring complete information delivery.
Solution Approach 2:
The patent implements periodic action through the structured transmission of system information blocks at different stages. The MIB is transmitted first, followed by SIB1 and SIB2 in sequence, allowing the terminal to process information in periodic batches rather than receiving all information simultaneously, thus reducing processing time while maintaining completeness.
Data Source
AI summary
In the present disclosure, a method for operating a terminal in a wireless communication system may receiving, by the terminal, an MIB from a base station, obtaining a first system information block based on the received MIB, obtaining a second system information block based on the first system information block, and performing communication with the base station based on the second system information block. Herein, the second system information block may include AI/ML model group information and message information associated with an AI/ML model group.