ML Recommendation Engine for Telecom Event Misrouting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ITSM systems face inefficiencies due to noise in workflows, misclassifications, and misrouting of events, leading to increased manual effort and delayed resolutions in network operations centers (NOCs).
Innovation Solution
A recommendation engine utilizing machine learning (ML) algorithms processes historical event data to train a classification framework, providing recommendations that guide reviewers through workflows, reducing noise and improving operational efficiencies by automating event management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual classification and routing of events is performed in ITSM systems, then flexibility and adaptability are maintained, but productivity and resolution speed decrease due to increased manual effort and time
Solution Approach 1:
The system enables self-service through automated event classification and routing using machine learning models. The classification engine automatically analyzes event data, determines event types, and routes events to appropriate handlers without requiring manual intervention, allowing the system to serve itself in the classification and routing tasks
Solution Approach 2:
The patent replaces the mechanical manual classification process with an automated machine learning-based classification engine. The ML model processes event data, extracts features, and automatically classifies events, substituting the manual mechanical process with an automated intelligent system that operates without human physical intervention
2Measurement precision
If comprehensive event data is processed to improve classification accuracy, then measurement precision improves, but loss of time increases due to the complexity of analyzing multiple event attributes
Solution Approach 1:
The classification process is segmented into distinct stages: data collection from multiple sources, feature extraction to identify relevant attributes, ML model processing for classification, and routing decisions. This segmentation allows the system to process comprehensive event data systematically without overwhelming the processing pipeline, improving both accuracy and efficiency
Solution Approach 2:
The system performs preliminary feature extraction and data preprocessing before the main classification task. By pre-processing event data to extract relevant features and organize information in advance, the ML model receives refined input that accelerates the classification process while maintaining high accuracy
3Reliability
If multiple event attributes are analyzed to reduce misclassifications, then reliability of classification improves, but device complexity increases due to the need for advanced ML models and data processing infrastructure
Solution Approach 1:
The classification engine is designed as a universal multi-functional system that handles multiple event types (alarms, incidents, service requests, problems, changes) through a single ML model framework. The system can classify and route different categories of events using the same underlying technology, reducing the need for separate specialized systems for each event type
Data Source
AI summary
A system can obtain a service request message indicating an event that affects a user device of a telecommunications network. The system can store an indication of the event at a memory device that stores historical information of events and can process the event with a machine learning (ML) model that is trained based on the historical information to simulate the effect of the event on the telecommunications network. The system generates an output for display on a computing device. The output includes a recommendation and identifies an attribute of the event and a predicted value configured to reduce a workload or increase operational efficiency. The recommendation is configured to make the event actionable. The system receives feedback that a reviewer has acted on the recommendation. In response to the feedback, the system can re-train the ML model and configure the process for handling the service request.