5G User Plane Data Analytics via Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In 5G communications networks, there is a lack of specific methods for data analysis using network data analytics (NWDA) network elements, which hinders effective data processing and service type or execution rule determination for user plane data.
Innovation Solution
A data analytics method and apparatus that involves a user plane data processing network element obtaining feature parameters from a data analytics network element, processing user plane data based on received service types or execution rules, and sending responses back to the data analytics network element for further analysis, enabling efficient data analysis and processing within the communications network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep packet inspection is used to determine service types or execution rules, then measurement precision is improved, but device complexity and network congestion increase
Solution Approach 1:
The patent extracts only the necessary feature parameters from user plane data that are sufficient for service type determination, rather than performing comprehensive deep packet inspection. The NWDA network element receives specific feature parameters and uses trained models to determine service types, eliminating the need for complex deep packet inspection while maintaining determination accuracy.
Solution Approach 2:
The patent introduces an intermediary processing layer where the NWDA network element acts as a mediator between user plane data and service type determination. The NWDA receives feature parameters, applies trained models, and returns determination results, thereby reducing the complexity burden on individual network elements while maintaining overall system precision.
2Measurement precision
If deep packet inspection is used to analyze user plane data, then measurement precision is improved, but network congestion worsens
Solution Approach 1:
The patent extracts only essential feature parameters from user plane data for analysis by the NWDA network element, rather than performing complete deep packet inspection on all data packets. This selective extraction approach maintains data analysis accuracy while significantly reducing the volume of data that needs to be processed, thereby preventing network congestion and maintaining high network throughput.
3Productivity
If feature parameters are extracted and analyzed by NWDA network element, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent segments the data processing function into distinct components: feature parameter extraction performed by user plane data processing network elements and model-based analysis performed by the NWDA network element. This segmentation allows each component to focus on specific tasks, improving overall data processing efficiency while distributing complexity across multiple specialized elements rather than concentrating it in a single complex system.
Data Source
AI summary
Embodiments of this application provide example data analytics methods and example data analytics apparatuses. An example method carried out by a user plane data processing network element includes: obtaining information about at least one feature set from a data analytics network element, where information about each feature set in the information about the at least one feature set corresponds to at least one service type or at least one execution rule; obtaining a feature parameter of user plane data based on the information about the at least one feature set; sending the feature parameter to the data analytics network element; obtaining a response result of the feature parameter from the data analytics network element; obtaining, based on the response result, a service type associated with the user plane data or an execution rule associated with the user plane data.