Distributed Service Inference for Private MOS Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The collection of service-related data by the NWDAF network element in a 5G network raises privacy and security concerns due to the inclusion of both reportable and non-reportable private data, necessitating a method to determine a mean service score (MOS) while ensuring data privacy and security.
Innovation Solution
A data processing method involving a first device and second devices to generate inference values using respective models, ensuring private data is not shared, and allowing simultaneous determination of comprehensive inference values, thereby reducing computational overheads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the NWDAF network element collects service-related data from devices, then it can analyze the data to obtain MOS and adjust QoS parameters, but it may collect private data that devices are not allowed to report, causing privacy and security problems
Solution Approach 1:
The patent segments the data collection process into two distinct paths: one for reportable data that can be shared with NWDAF, and another for non-reportable private data that remains localized at the device. This segmentation allows MOS determination using only the permissible data subset, eliminating privacy violations while maintaining analytical capability.
Solution Approach 2:
The patent extracts and removes the private data component from the data collection process. By identifying and excluding non-reportable data elements, the system processes only the permissible reportable data, thereby determining MOS without accessing or transmitting private information that would cause security problems.
2Productivity
If the first device determines the first model for each of the M1 second devices, then computational overheads of the second devices are reduced, but the first device's computational burden increases
Solution Approach 1:
The patent introduces a third device as an intermediary that assumes the computational burden of determining the first model. This mediator (third device) performs the intensive model determination task, relieving both the first device of excessive computational load and enabling the second devices to benefit from optimized models without bearing the computational cost.
Data Source
AI summary
A data processing method and an apparatus are provided. In the method, a first device obtains a first inference value of each of M1 second devices in M second devices related to a first service, and receives a second inference value from each of M2 second devices in the M second devices; and the first device may determine a comprehensive inference value of the first service based on the first inference value of each of the M1 second devices and the second inference value of each of the M2 second devices. The first inference value is corresponding to the first inference value by using first data and a first model, and the first model is determined by the first device; and the second inference value is generated on the second device corresponding to the second inference value by using second data and a second model.