UE AI Capability Reporting for Cloud-Terminal Service Allocation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current wireless communication systems lack effective synergy between terminal-side AI and cloud-side AI, leading to inefficient AI service allocation and resource utilization, as terminal-side AI and cloud-side AI typically process tasks independently without coordination.

Innovation Solution

An information transmission method where user equipment (UE) reports its AI capability information to a base station, allowing the base station to allocate AI services based on the reported capabilities, optimizing resource utilization and improving AI service synergy by coordinating tasks between terminal-side and cloud-side AI.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If terminal-side AI and cloud-side AI process tasks independently without coordination, then each can operate autonomously, but AI service allocation efficiency and resource utilization are poor

Engineering Contradiction:

ImproveAI service allocation efficiencyVSAvoidUE capability information transparency

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The UE reports its AI capability information (such as AI chip type, neural network processing capability, memory capacity) to the base station. This feedback mechanism enables the base station to understand the UE's AI capabilities and allocate AI services accordingly, improving allocation efficiency while maintaining information transparency.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The base station acts as an intermediary between the UE and the cloud-side AI system. It receives AI capability information from the UE, processes this information, and uses it to coordinate task allocation between terminal-side and cloud-side AI, thereby improving overall AI service allocation efficiency.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If AI capability information is reported from UE to base station, then AI service allocation can be optimized, but network resource consumption increases

Engineering Contradiction:

ImproveAI service allocation optimizationVSAvoidnetwork resource consumption

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The patent extracts only the essential AI capability information (AI chip type, neural network processing capability, memory capacity) that is necessary for service allocation, rather than transmitting all possible UE parameters. This selective extraction optimizes allocation while minimizing network resource consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system implements partial action by reporting AI capability information only when necessary for AI service allocation decisions, rather than continuously transmitting all capability data. This reduces network resource consumption while maintaining optimization capability.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20230232213A1Information transmission methods and apparatuses, and communication devices and storage medium

Publication Date: 2023.07.20 BEIJING XIAOMI MOBILE SOFTWARE CO LTD

AI summary

Information transmission methods, apparatuses, communication devices and non-transitory computer readable storage medium that enable a user equipment (UE) to report artificial intelligence (AI) capability information indicating an AI capability of the UE to a base station.