Wireless AI/ML Model Transmission by Control or Data Channel

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The integration of AI/ML models into communication systems lacks a standardized method for managing their transmission due to capability limitations of terminal devices.

Innovation Solution

A wireless communication method that utilizes control messages and data channels to transmit AI/ML models from network devices to terminal devices, allowing flexible deployment of models while respecting device capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If AI/ML models are introduced into communication systems to adapt to complexity and diversity of scenarios, then system adaptability is improved, but device complexity increases due to lack of standardized transmission management methods

Engineering Contradiction:
Improvesystem adaptabilityVSAvoidtransmission management complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies universality by establishing a standardized transmission management method that can handle multiple types of AI/ML models through unified control messages and data channels. The network device uses a general framework that works for different model types, avoiding the need for separate management mechanisms for each model, thus improving system adaptability while controlling complexity

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent utilizes parameter changes by dynamically adjusting transmission parameters such as model version, capability information, and transmission mode (control plane vs. user plane) based on terminal device capabilities and network conditions. This allows the system to adapt to different scenarios and device capabilities through parameter configuration rather than complex structural changes

Inventive Principle:
Principle #35Parameter changes

2Reliability

If AI/ML models are transmitted through control messages to ensure reliable delivery, then transmission reliability is improved, but transmission efficiency decreases due to control plane overhead

Engineering Contradiction:
Improvetransmission reliabilityVSAvoidtransmission efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent applies segmentation by dividing the model transmission process into two distinct paths: control plane transmission for reliable delivery of critical model information, and user plane transmission for efficient transfer of large model data. This segmentation allows each path to be optimized for its specific function, achieving both reliability and efficiency simultaneously

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent uses an intermediary approach by introducing capability information as a mediator between the network device and terminal device. The capability information determines which transmission mode(s) are available, allowing the system to flexibly select between control plane and user plane based on reliability and efficiency requirements

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If AI/ML models are transmitted through data channels to improve transmission efficiency, then productivity is improved, but security risks increase due to user plane transmission

Engineering Contradiction:
Improvetransmission efficiencyVSAvoidsecurity risks
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent applies dynamics by making the transmission mode flexible and adaptable rather than fixed. The system can dynamically switch between control plane and user plane transmission modes based on the specific model characteristics, network conditions, and security requirements. This dynamic approach allows optimization of both efficiency and security for different transmission scenarios

Inventive Principle:
Principle #15Dynamics

4Reliability

If network devices perform comprehensive model management to ensure proper deployment, then system reliability is improved, but computational burden on network devices increases

Engineering Contradiction:
Improvedeployment reliabilityVSAvoidcomputational burden
Core Design Contradiction:
ReliabilityVSPower

Solution Approach 1:

The patent applies self-service by enabling terminal devices to autonomously manage AI/ML model deployment based on their own capabilities. The terminal device independently determines which models it can support and manages the transmission process, reducing the computational burden on network devices while maintaining deployment reliability through standardized capability negotiation

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20250261195A1Wireless communication method, device, and storage medium
Publication Date: 2025.08.14 GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD
  • US20250261195A1 patent drawing
  • US20250261195A1 patent drawing
  • US20250261195A1 patent drawing

AI summary

Embodiments of the present application provide a wireless communication method, a device, and a storage medium. The method includes that: a core network device or an access network device sends first information to a terminal device, the first information including information associated with a first model, and a sending mode of the first information including: sending the first information by means of a control message and/or sending the first information by means of a data channel.