Customer Experience Modeling for UE Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems fail to accurately measure and address individual customer experiences in telecommunications networks, leading to inefficiencies in reducing customer churn and improving network quality.
Innovation Solution
A neural network trained on network KPIs and customer satisfaction metrics identifies anomalies in individual customer experiences, generating impact zones and actionable tasks to mitigate performance degradation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional systems are used to measure customer experiences, then system simplicity is maintained, but measurement precision of individual customer experiences deteriorates
Solution Approach 1:
The patent replaces conventional mechanical measurement systems with machine learning models, specifically neural networks, to analyze customer experience data. The neural network processes multiple KPIs and historical data to detect anomalies and predict customer churn with high precision, substituting traditional measurement approaches with intelligent algorithms that can handle complex, multi-dimensional customer experience metrics.
2Reliability
If machine learning models are implemented to detect individual customer anomalies, then customer retention is improved, but computational complexity increases
Solution Approach 1:
The system performs preliminary training of neural network models using historical customer data and KPIs before deployment. This preliminary action creates a pre-configured anomaly detection system that can quickly process current customer data without requiring complex real-time computations during operation, thereby improving customer retention while managing computational complexity through offline model preparation.
Solution Approach 2:
The machine learning model operates autonomously to detect anomalies and predict churn risks without requiring manual intervention. The neural network self-adjusts by learning from historical data and automatically identifies patterns indicating customer dissatisfaction, enabling the system to serve itself in detecting and flagging at-risk customers for retention efforts.
3Measurement precision
If multiple KPIs are analyzed to determine customer impact zones, then detection precision is improved, but processing time increases
Solution Approach 1:
The system pre-processes and stores historical KPI data in structured formats during the training phase, organizing customer baseline metrics, network performance data, and service usage patterns into readily accessible formats. This preliminary organization enables the neural network to quickly retrieve and compare current KPIs against historical baselines without time-consuming data preparation during anomaly detection operations.
Data Source
AI summary
Anomalies are detected corresponding to user equipment (UE) performance degradation. A neural network is trained using historical network key performance indicators (KPIs), customer retention metrics, and network KPIs. As a result, the trained neural network is configured to output a plurality of customer impact zones, including a threshold for each of the plurality of customer impact zones. The trained neural network may further identify an anomaly that has caused the UE's performance degradation to exceed a threshold and identify an actionable field task that may be implemented by a field team and that may lower the UE's performance degradation below a threshold.