AI Task Offloading Across Hierarchical Network Elements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The integration of AI functions in communication networks results in high overhead due to their add-on application without a unified technical framework, leading to fragmented AI scenarios and inefficient resource allocation.
Innovation Solution
Introduce AI network elements with a parent-child relationship, refining them based on specific algorithms and task types, and implement a task offloading policy to determine processing parameters and allocate resources efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If AI functions are added as add-on applications to network processes, then AI service functionality is provided, but network overhead increases significantly
Solution Approach 1:
The patent segments AI network elements into parent-child relationships where parent elements manage multiple child elements. This segmentation allows distributed AI task execution across multiple elements while reducing centralized overhead, as each element handles specific AI functions independently under coordinated management.
Solution Approach 2:
The patent introduces a hierarchical dimension to AI network element organization by establishing parent-child relationships. This hierarchical structure adds a management layer that coordinates AI tasks across multiple elements, enabling efficient resource allocation and reducing overall network overhead through structured coordination.
2Adaptability or versatility
If multiple AI functions are integrated into the network, then AI service capabilities are enhanced, but resource allocation efficiency decreases
Solution Approach 1:
The patent implements dynamic task offloading policies where parent AI network elements dynamically determine which child elements should execute specific AI tasks based on current network conditions, resource availability, and task requirements. This dynamic allocation optimizes resource utilization across the network while supporting multiple AI functions.
Solution Approach 2:
The patent changes the parameter of resource allocation from static to dynamic by introducing processing parameters that are determined based on task characteristics and network state. Parent elements adjust task allocation decisions based on varying conditions, enabling efficient resource utilization across diverse AI workloads.
3Adaptability or versatility
If AI tasks are executed without unified technical framework, then AI scenario flexibility is maintained, but task execution efficiency is reduced
Solution Approach 1:
The patent creates a universal parent-child framework that can accommodate multiple types of AI tasks and scenarios. The framework provides standardized mechanisms for task management, resource allocation, and coordination that work across different AI applications, while allowing child elements to implement scenario-specific logic for maintaining flexibility.
Solution Approach 2:
The patent introduces parent AI network elements as intermediaries that coordinate between the network management system and child elements. These intermediaries implement unified task management policies while allowing child elements to execute specific AI scenarios, thus bridging the gap between standardized management and flexible execution.
Data Source
AI summary
An artificial intelligence (AI) task processing method is executed by a first AI network element. The method includes: receiving an AI service request message sent by an AMF network element, the AI service request message being used to indicate an AI service to be provided; determining at least one AI task according to the AI service request message; determining a first processing parameter of the first AI network element and a second processing parameter of a second AI network element; according to the at least one AI task, the first processing parameter and the second processing parameter, determining at least one of a first task executed by the first AI network element in the AI task or a second task executed by the second AI network element.