User-Plane ML Model Transmission Between Terminals and Network Elements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication technologies face challenges in efficiently utilizing machine learning (ML) models for enhancing communication performance, particularly in terms of model transmission and inference between terminals and network elements.
Innovation Solution
Implementing user-plane model transmission methods and apparatuses that enable terminals and network elements to exchange ML models via user plane sessions or tunnels, allowing for efficient model transfer and inference, including receiving and sending information of ML models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If machine learning models are transmitted between terminals and network elements, then communication performance can be improved, but transmission efficiency and model exchange speed may be insufficient
Solution Approach 1:
The patent introduces a user plane function element as an intermediary to facilitate model transmission between the terminal and network elements. This mediator manages the model transmission process, coordinates with the terminal to obtain model information, and handles the actual data exchange, thereby improving transmission efficiency while maintaining communication performance
Solution Approach 2:
The patent divides the model transmission process into distinct functional segments: terminal-side model preparation, user plane function coordination, and network element reception. This segmentation allows each component to be optimized independently, with the user plane function specifically handling the transmission coordination to improve overall efficiency
2Reliability
If ML model information is exchanged between terminal and network elements, then model transmission performance improves, but transmission speed may be limited
Solution Approach 1:
The user plane function acts as a mediator that optimizes the transmission path for ML model information. It establishes direct communication channels between the terminal and network elements, bypassing traditional slower routing paths, thereby improving both transmission performance and exchange speed
Solution Approach 2:
The terminal performs preliminary actions by preparing and formatting ML model information before transmission. The user plane function pre-coordinates the transmission parameters and establishes communication channels in advance, reducing delays during actual model exchange and improving overall speed
Data Source
AI summary
Provided are an information transmission method and apparatus, a terminal, and a network-side device. The information transmission method includes: obtaining, by a terminal, information of a target network element corresponding to a machine learning ML model, where the target network element supports the function of user-plane model transmission; and performing, by the terminal, model transmission with the target network element via a user plane session or tunnel, where the tunnel is a tunnel established between the terminal and the target network element based on the user plane session, and the model transmission includes at least one of the following: receiving information of the ML model from the target network element; and sending the information of the ML model to the target network element.