Telecom Network Region Trees for Anomaly Equipment Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in efficiently identifying and localizing faulty equipment in telecom networks, particularly in determining the root cause of network anomalies.
Innovation Solution
A computer-implemented method using a classification tree-based machine learning model to analyze network session reports, training the model to classify telecom network regions and identify anomaly-associated equipment by traversing decision paths in the tree.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to identify faulty equipment in telecom networks, then the system complexity remains manageable, but the accuracy and speed of anomaly localization deteriorates
Solution Approach 1:
The patent replaces traditional mechanical/network-based anomaly detection methods with a machine learning-based classification tree system. The classification tree model processes network session reports and automatically classifies anomalies into specific network regions, achieving high localization accuracy without requiring complex manual analysis procedures.
Solution Approach 2:
The patent introduces a classification tree model as an intermediary between raw network session reports and anomaly localization decisions. This intermediary system processes the reports through trained decision paths, translating complex network data into actionable anomaly location information without requiring direct complex analysis of the original data.
2Productivity
If manual troubleshooting methods are used, then the operational simplicity is maintained, but the troubleshooting time and productivity deteriorate
Solution Approach 1:
The system performs self-service by automatically analyzing network session reports and localizing anomalies without requiring manual intervention. The classification tree model autonomously processes data, traverses decision paths, and identifies affected network regions, eliminating the need for manual troubleshooting procedures and significantly reducing time loss.
Solution Approach 2:
The classification tree model is pre-trained using historical network data and anomaly patterns. This preliminary training enables the system to quickly and accurately localize new anomalies without requiring manual analysis, as the decision paths are already established through prior learning from network session reports.
3Measurement precision
If detailed network monitoring is implemented, then the measurement precision of network status improves, but the amount of data processing and information overload increases
Solution Approach 1:
The patent extracts only the essential information needed for anomaly localization from the detailed network session reports. The classification tree model processes and filters the data to identify only the critical features necessary for determining anomaly location, discarding redundant information and reducing the processing burden while maintaining high detection accuracy.
Solution Approach 2:
The patent segments the network into hierarchical regions (such as network regions, access points, and specific locations) that can be independently analyzed. This segmentation allows the system to process detailed monitoring data in manageable portions, traversing decision paths through hierarchical levels rather than processing the entire data set at once, thereby reducing information processing burden.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There is provided a processing circuitry-based method of localizing anomaly-associated equipment in a telecom network, comprising: a) receiving, from network monitors within the telecom network, network connectivity reports, wherein each report comprises: a respective telecom network region associated with a respective telecom network region hierarchy (TNRH), and a respective session anomaly status, b) training a classification tree-based machine learning model to classify a sequence telecom network region identifiers to an anomaly status, utilizing, a plurality of training tuples where each training tuple is based on a respective received network connectivity report; and c) identifying a telecom network region as including anomaly-associated equipment, based on identifying a decision path in the classification tree-based machine learning model, wherein a leaf of the identified decision path is associated with a given anomaly status.