ML Root Cause Analysis for Wireless Complaint Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wireless telecommunication carriers face challenges in identifying and resolving quality of service issues due to the lack of comprehensive end-to-end visibility and effective troubleshooting tools, leading to increased time and costs in resolving customer complaints, and potential revenue loss.
Innovation Solution
A data management platform combined with machine learning applications that aggregate and analyze user device and network performance data from multiple sources to identify root causes of quality of service issues, enabling automatic complaint resolution and resource-aware monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of customer complaints is performed by network engineers, then comprehensive troubleshooting can be conducted, but the resolution time increases significantly and operational costs increase
Solution Approach 1:
An automated analysis system acts as an intermediary between customer complaints and network engineers. The system collects data from multiple sources (network elements, customer premises equipment, handsets), processes it through analytical applications, and generates diagnostic reports that assist engineers in resolving complaints more efficiently while maintaining accuracy.
Solution Approach 2:
The patent replaces the manual mechanical process of engineer analysis with an automated electronic system. The analytical applications automatically collect, process, and analyze data from multiple sources, substituting the manual troubleshooting process with an automated computational approach that reduces resolution time while maintaining diagnostic accuracy.
2Ease of manufacture
If key performance indicators are aggregated at network cell level, then network performance can be monitored, but visibility into subscriber-specific and handset-specific problems is lost
Solution Approach 1:
The system segments the analysis into multiple levels: network element level, customer premises equipment level, and handset level. This segmentation allows the system to maintain the simplicity of network-level monitoring while simultaneously providing detailed subscriber-specific and device-specific insights through separate analytical layers.
Solution Approach 2:
The patent adds another dimension to network monitoring by incorporating customer premises equipment and handset data alongside traditional network element data. This multi-dimensional approach enables comprehensive end-to-end visibility without sacrificing the simplicity of traditional network-level KPI aggregation.
3Reliability
If comprehensive end-to-end data collection from multiple sources is implemented, then complete visibility of service experience is achieved, but system complexity and data processing requirements increase
Solution Approach 1:
The analytical applications are designed to be universal and multi-functional, capable of collecting and processing data from diverse sources (network elements, CPE, handsets) using a unified approach. This universality reduces system complexity by applying the same analytical framework across different data types and sources rather than requiring separate specialized systems for each.
Data Source
AI summary
An analytic application may automatically determine a root cause of an issue with a wireless carrier network and generate a solution for the root cause. Initially, a data management platform may receive performance data regarding user device and network components of a wireless carrier network from multiple data sources. Subsequently, the analytic application may receive an indication of an issue affecting one or more user devices that are using the wireless carrier network. The analytic application may analyze the performance data using a trained machine learning model to determine a root cause for the issue affecting the one or more user devices. The trained machine learning model may employ multiple types of machine learning algorithms to analyze the performance data. The analytic application may provide the root cause or the solution that resolves the root cause for presentation.