AI/ML Event Management for Per-UE Cellular Troubleshooting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cellular network troubleshooting methods struggle to efficiently identify and resolve customer-specific service issues at the per-user equipment level, requiring costly and time-consuming manual analysis due to complex spatial and temporal correlations, limited ground truth data, and diverse user experiences.
Innovation Solution
An AI/ML-based system that utilizes machine learning models to analyze cell-level and UE-level data, incorporating graph convolutional neural networks to predict service issues and categorize their root causes, enabling automated troubleshooting and resource dispatch for rapid issue resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis methods are used to troubleshoot cellular service issues at per-UE level, then diagnostic accuracy can be achieved through expert analysis, but the process becomes costly and time-consuming
Solution Approach 1:
The patent replaces manual mechanical analysis processes with an automated machine learning system that uses graph convolutional neural networks to analyze network data. The ML model automatically processes cell-level and UE-level data to identify service issues, substituting human expert analysis with computational algorithms that achieve comparable or superior diagnostic accuracy while significantly reducing time and cost.
Solution Approach 2:
The system enables self-service troubleshooting by automatically analyzing network data and identifying issues without requiring human expert intervention. The ML model independently processes data from multiple sources, performs root cause analysis, and generates diagnostic results, allowing the system to serve itself in the troubleshooting process.
2Productivity
If automated systems are implemented to reduce manual investigation time, then troubleshooting efficiency improves, but system complexity increases
Solution Approach 1:
The patent segments the troubleshooting system into distinct modular components: data collection modules that gather cell-level and UE-level data, a graph construction module that builds network topology representations, a graph convolutional neural network module that performs feature extraction and analysis, and a result interpretation module that generates diagnostic outputs. This segmentation allows each component to be developed, tested, and maintained independently, managing overall system complexity while enabling high productivity.
Solution Approach 2:
The graph convolutional neural network serves multiple functions within the system: it processes spatial relationships between network elements, temporal patterns in service degradation, feature extraction from heterogeneous data sources, and root cause identification. This multi-functionality reduces the need for separate specialized systems, managing complexity while maintaining high troubleshooting efficiency.
Data Source
AI summary
Aspects of the subject disclosure may include, for example, receiving, from a machine learning model, information about an event causing a service degradation in a cellular network, wherein the event is external to the cellular network, determining one or more event categories associated with the event causing the service degradation, determining, based on the one or more event categories, likely affected customers, the likely affected customers being likely to experience the service degradation, determining, by the machine learning model, proper resources for resolution of the service degradation, wherein the determining proper resources is based on the one or more event categories, and dispatching the proper resources for resolution of the service degradation. Other embodiments are disclosed.