NWDAF Evaluation Criteria Exchange for Accurate Service Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for selecting a Network Data Analytics Function (NWDAF) do not account for the generation standard of accuracy information, leading to inappropriate service selection by consumers due to varying evaluation criteria, as consumers lack knowledge of the generation standard and cannot choose an appropriate NWDAF based on their specific criteria.
Innovation Solution
A method and system that utilize a preset parameter, such as a classification error cost matrix or class weight, to generate evaluation information, allowing network elements to determine and return appropriate NWDAF selection based on the consumer's specific criteria, including accuracy, precision, and recall rates, using a formula or calculation method to evaluate the NWDAF's performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If accuracy information is provided without generation standard, then service consumers can check accuracy levels, but consumers cannot select appropriate NWDAF based on their specific evaluation criteria
Solution Approach 1:
The patent segments the accuracy information into two distinct parts: the accuracy level itself (Low, Medium, High, Highest) and the generation standard (preset parameters such as classification error cost matrix or class weight). This segmentation allows consumers to receive both pieces of information separately, enabling them to evaluate whether the generation standard matches their requirements while still accessing the accuracy level information.
Solution Approach 2:
The patent implements a feedback mechanism where the service consumer first sends a request indicating their evaluation criteria (preset parameters), receives evaluation information generated based on those criteria, and then can make an informed selection. This feedback loop ensures that the provided accuracy information aligns with the consumer's specific needs.
2Adaptability or versatility
If different consumers use different evaluation criteria, then each consumer has specific requirements, but uniform accuracy information cannot satisfy all consumers' selection needs
Solution Approach 1:
The patent applies preliminary action by having the service consumer specify their evaluation criteria (preset parameters) in advance, before receiving the accuracy information. The NWDAF then uses these pre-specified parameters to generate the evaluation information, ensuring it matches the consumer's needs without requiring complex post-processing or multiple information generation pathways.
Solution Approach 2:
The patent enables parameter changes by allowing the generation of accuracy information to be based on different preset parameters (such as classification error cost matrix or class weight) depending on the consumer's requirements. This flexibility in parameters allows the same NWDAF to provide customized evaluation information to different consumers without increasing system complexity.
3Reliability
If evaluation information is generated based on consumer-specific preset parameters, then consumers can select appropriate NWDAF, but the system requires additional information exchange and processing
Solution Approach 1:
The patent applies universality by designing a multi-functional information exchange mechanism that serves multiple purposes: it conveys the consumer's evaluation criteria, enables customized accuracy information generation, and provides the evaluation results all through a standardized interface. This universal approach reduces the need for multiple specialized communication channels despite the increased information requirements.
Data Source
Figure 1(a)~2
Figure 3
Figure 4
AI summary
Embodiments of this application provide an evaluation information determining method, a related system, and a storage medium. The method includes: receiving a first request sent by a second network element, where the first request includes first information, the first information includes a preset parameter, and the preset parameter is used to generate evaluation information; obtaining evaluation information based on the first information, where the evaluation information is used to evaluate a service or a model; and returning the evaluation information to the second network element. In this manner, the preset parameter in the first information sent by the second network element is used to generate evaluation information. In this way, the second network element knows a generation standard of the evaluation information. This can help the second network element select an appropriate first network element.