Markov Model for Unusual Event Detection in Telecommunications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In telecommunications networks, large trail groups containing hundreds of communication session events make it difficult for service providers and support engineers to identify unusual or error-causing events, especially for inexperienced personnel.
Innovation Solution
A method and apparatus that maintain a Markov model to assign a probability of occurrence metric to event sequences, triggering an alert when a sequence exceeds a predetermined threshold, and highlighting unusual events through a user interface, allowing for efficient detection of unusual communication session events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If service monitoring network nodes store and display all communication session events in trail groups, then complete troubleshooting information is available, but it becomes difficult to identify unusual or error-causing events among hundreds of events
Solution Approach 1:
The patent applies visual highlighting (color changes) to unusual events in the user interface. Events are displayed with different visual characteristics based on their calculated unusualness metric, allowing operators to quickly identify problematic events without manually reviewing hundreds of events. This directly addresses the difficulty of detecting unusual events among large volumes of data.
Solution Approach 2:
The patent replaces manual analysis of event sequences with an automated computational system. A Markov model automatically calculates the probability of event sequences and identifies unusual events through algorithmic analysis, substituting the mechanical process of human review with an automated information processing system. This resolves the contradiction by maintaining complete event storage while enabling efficient automatic detection.
2Measurement precision
If support engineers manually review large trail groups to identify errors, then thorough analysis is possible, but it consumes excessive time and is particularly difficult for inexperienced personnel
Solution Approach 1:
The system performs self-service by automatically analyzing event sequences and identifying unusual events without requiring extensive human intervention. The Markov model autonomously calculates probabilities and highlights anomalies, enabling the system to serve its own troubleshooting function. This reduces both time loss and the skill level required from operators while maintaining detection accuracy.
Solution Approach 2:
The patent introduces an intermediary computational layer between raw event data and operator analysis. The system calculates unusualness metrics and generates highlighted displays that mediate between the complete event trail and the operator's decision-making process. This intermediary processing reduces troubleshooting time while preserving detection accuracy by pre-processing and organizing information.
3Loss of information
If the system displays all events in trail groups through web interface, then complete information is provided, but unusual events are hard to distinguish without expert knowledge
Solution Approach 1:
The patent uses visual highlighting to differentiate unusual events in the user interface. Events are displayed with distinct visual characteristics based on their calculated unusualness, making them easily distinguishable without requiring expert knowledge. This maintains complete information display while dramatically improving ease of operation for users of all skill levels.
Solution Approach 2:
The patent segments the display of events by highlighting unusual ones differently from normal events. Instead of presenting a uniform list, the system divides events into visually distinct categories based on their unusualness metric, allowing users to quickly identify problematic segments without losing access to complete information. This segmentation improves usability while preserving information completeness.
Data Source
AI summary
Measures for detecting unusual communication session events in a telecommunications network. A Markov model for events occurring in communication sessions conducted in the network is maintained. The maintaining includes assigning a probability of occurrence metric to a plurality of event sequences in the conducted communication sessions. In response to a given sequence of communication session events being assigned a probability of occurrence metric which exceeds a predetermined threshold, an unusual communication session event alert in association with the given sequence is triggered.