Communication Network AI Task Allocation by Terminal Capability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile network planning, configuration, and resource scheduling methods are inefficient, leading to high time consumption, high costs, and poor adaptability due to reliance on manual experience or simple algorithms, which are inadequate for supporting diverse service types.
Innovation Solution
A communication method and apparatus that determine a terminal capable of executing AI tasks by considering various terminal capabilities, such as computing power, memory, and signal quality, to enhance the accuracy and targeting of AI task execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual experience or simple algorithms are used for network planning, configuration, and resource scheduling, then the process is easier to implement, but time consumption increases and productivity decreases
Solution Approach 1:
The network device performs self-optimization by automatically determining terminal capabilities for AI task execution using multiple assessment dimensions (computing capability, memory capability, signal quality, etc.), eliminating the need for manual configuration and reducing time consumption while maintaining ease of deployment
Solution Approach 2:
The system changes from simple algorithmic approaches to a multi-parameter assessment model that evaluates computing capability, memory capability, signal quality, and other dimensions, enabling more accurate and efficient terminal selection for AI tasks without increasing operational complexity
2Ease of operation
If manual experience or simple algorithms are used for network planning, configuration, and resource scheduling, then the implementation is simpler, but costs increase due to inefficiency
Solution Approach 1:
The automated capability determination system performs self-optimization of resource allocation, reducing the need for expensive manual intervention and optimization processes while maintaining implementation simplicity through standardized assessment procedures
Solution Approach 2:
The system replaces manual optimization processes with automated electronic assessment and determination mechanisms, evaluating multiple terminal parameters programmatically to reduce labor costs and improve efficiency without increasing implementation complexity
3Ease of operation
If manual experience or simple algorithms are used for network planning, configuration, and resource scheduling, then the system is easier to manage, but adaptability decreases
Solution Approach 1:
The system transitions from static manual configuration to dynamic multi-parameter assessment, evaluating computing capability, memory capability, signal quality, and other variables to automatically adapt terminal selection to changing network conditions and service requirements
Solution Approach 2:
The capability determination process incorporates feedback mechanisms where the network device assesses terminal performance across multiple dimensions and uses this information to continuously optimize AI task allocation, improving adaptability while maintaining manageable complexity through structured evaluation frameworks
4Device complexity
If simple algorithms are used for resource scheduling, then the system is less complex, but scheduling algorithm adaptability decreases
Solution Approach 1:
The scheduling algorithm incorporates multiple assessment parameters (computing capability, memory capability, signal quality, current load) to dynamically adapt terminal selection for AI tasks, improving versatility while managing complexity through modular evaluation components
Solution Approach 2:
The capability determination process is segmented into distinct assessment dimensions (computing capability assessment, memory capability assessment, signal quality assessment, etc.), allowing the algorithm to handle complexity through structured, modular evaluation while maintaining overall system adaptability
Data Source
AI summary
A communication method and an apparatus, to determine a terminal that is to execute an artificial intelligence (artificial intelligence, AI) task, so that execution of the AI task is more targeted, and an execution result is more accurate. The method includes receiving first information from an AI apparatus, where the first information indicates information about a first terminal capable of executing a first AI task; receiving information from a second terminal; and determining, based on the first information and the information about the second terminal, whether the second terminal is configured to perform the first AI task.