Terminal AI Computing Power Reporting for Wireless Model Allocation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current wireless communication systems face challenges in accurately estimating the remaining AI computing power of User Equipment (UE), leading to inefficient utilization of AI resources and affecting communication system performance due to incorrect AI model assignments.

Innovation Solution

A method where a terminal reports first AI computing power information to a network-side device, enabling the device to estimate and manage AI model resources accurately, allowing for optimal AI model configuration and utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the network side device estimates AI computing power without terminal reporting, then the system can operate with simpler protocol, but the estimation accuracy deteriorates leading to inefficient AI resource utilization

Engineering Contradiction:

ImproveAI computing power estimation accuracyVSAvoidprotocol complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The terminal reports its AI computing power information to the network side device, establishing a feedback mechanism that enables accurate estimation of remaining AI computing power. This feedback loop allows the network to obtain real-time data about terminal capabilities and adjust AI model assignments accordingly, resolving the contradiction between measurement precision and protocol complexity.

Inventive Principle:

Principle #23Feedback

2Reliability

If the terminal reports real-time AI computing power information, then AI model allocation accuracy improves, but the frequency of reporting and processing increases system overhead

Engineering Contradiction:

ImproveAI model allocation reliabilityVSAvoidreporting overhead

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system dynamically adjusts the reporting mechanism based on actual needs. The terminal reports AI computing power information at appropriate intervals or when changes occur, rather than continuously. This dynamic approach maintains reliable AI model allocation while minimizing reporting overhead and system time consumption.

Inventive Principle:

Principle #15Dynamics

3Productivity

If the network assigns AI models without considering real-time terminal resources, then the assignment process is faster, but resource utilization efficiency deteriorates

Engineering Contradiction:

ImproveAI resource utilization efficiencyVSAvoidmodel assignment time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The terminal proactively reports its AI computing power information in advance, allowing the network side device to perform preliminary assessment and pre-configure appropriate AI models. This preliminary action enables the network to make informed assignment decisions without delaying the actual model deployment, thus improving resource utilization efficiency while maintaining fast assignment.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250310756A1Ai computing power reporting method, terminal, and network-side device

Publication Date: 2025.10.02 VIVO MOBILE COMM CO LTD

AI summary

Disclosed are an AI computing power reporting method, a terminal, and a network-side device, relating to the technical field of communications. A terminal obtains first AI computing power information. The terminal sends the first AI computing power information to a network-side device. The first AI computing power information is used for indicating at least one of the following: current remaining AI model computing resources of the terminal; current available AI model computing resources of the terminal; all AI model computing resources of the terminal; or all AI model computing resources of the terminal available for wireless communication.