Event Notice Prioritization via Past-Preference Pairings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
IT service providers face challenges in accurately and efficiently prioritizing incoming event notices in complex virtualized and cloud environments, as manual prioritization is costly and time-consuming, and automated approaches often require exhaustive modeling and user labeling, which is not scalable.
Innovation Solution
An automated system and method that utilizes past-preference pairings of event notices and configuration items to create a prioritized ordering, eliminating the need for explicit user labeling and exhaustive modeling, allowing for efficient and reliable prioritization of incoming event notices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual prioritization is used to accurately review and prioritize event notices, then prioritization accuracy is improved, but time consumption and cost increase
Solution Approach 1:
The system uses historical operator preference data to automatically generate prioritization rankings without requiring continuous manual intervention. The automated prioritization service learns from past operator decisions and applies this knowledge to new event notices, enabling the system to serve itself rather than requiring constant human oversight
Solution Approach 2:
The system pre-processes historical event notice data to extract operator preferences and creates a prioritization model in advance. This preliminary analysis of past data enables the system to quickly prioritize new events without requiring real-time manual review, thus reducing time consumption while maintaining accuracy
2Productivity
If automated prioritization approaches are implemented, then time consumption is reduced, but system complexity and requirement for exhaustive modeling increase
Solution Approach 1:
The system extracts only the essential preference information from historical data that is needed for prioritization, rather than requiring comprehensive modeling of all possible event scenarios. By focusing on extracting operator preferences from past decisions, the system achieves automation without exhaustive modeling
Solution Approach 2:
The system changes the approach from modeling event characteristics to modeling operator preference parameters. Instead of creating complex models of IT events and their relationships, the system transforms the problem into analyzing operator decision patterns, which simplifies the overall system complexity while maintaining productivity
3Measurement precision
If explicit user labeling and exhaustive modeling are required for automated prioritization, then prioritization accuracy is improved, but ease of implementation and scalability worsen
Solution Approach 1:
The system automatically learns prioritization patterns from historical data without requiring explicit user labeling of events. The automated prioritization service extracts preferences from past operator decisions and uses this knowledge to prioritize new events, eliminating the need for manual labeling while maintaining accuracy
Solution Approach 2:
The system performs preliminary analysis of historical operator behavior to build preference models in advance. This pre-processing of historical data creates a knowledge base that can be directly applied to new events, improving ease of implementation by eliminating the need for ongoing explicit user labeling
Data Source
AI summary
In one example of the disclosure, event notices are received, with each notice indicative of degradation of a configuration item. Configuration item past-preference pairings are accessed. Each pairing includes a count of operator-exhibited preferences for event notices associated with a first configuration item relative to event notices associated with a second configuration item. A prioritized ordering of the received event notices is created utilizing the past-preference pairings.