Maintenance Alert Fair Queueing for Multi-Criteria Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current alert ranking systems for medical imaging devices primarily rely on priority, which fails to consider other critical factors such as deadline, hospital impact, and service contract type, leading to missed alerts and suboptimal scheduling, especially in scenarios where hospitals have multiple or single systems of a modality.
Innovation Solution
Adaptation of fair queuing methods, specifically credit-based and multi-criterion fair queuing, to rank alerts based on normalized shares of criteria such as predictive model priority, deadline, service contract, and modality, ensuring that all relevant factors are accounted for in the ranking process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If alerts are ranked solely by priority, then high-priority alerts are reviewed first, but alerts with lower priority may never be observed and critical factors such as deadline and hospital impact are ignored
Solution Approach 1:
The patent transforms the alert ranking system from using a single parameter (priority) to using multiple parameters including priority, deadline, and hospital impact. This multi-parameter approach ensures that alerts are comprehensively evaluated based on various critical factors rather than being filtered out by low priority alone.
Solution Approach 2:
The patent adds new dimensions to the alert ranking problem by introducing deadline and hospital impact as additional ranking criteria beyond priority. This dimensional expansion creates a more nuanced ranking system that captures the complexity of real-world alert evaluation scenarios.
2Loss of time
If alerts are ranked using earliest-deadline-first algorithm, then deadline is emphasized, but priority is not considered
Solution Approach 1:
The patent merges multiple ranking criteria (priority, deadline, hospital impact) into a unified multi-criteria ranking system. Rather than using separate algorithms for each criterion, the system integrates them into a single comprehensive ranking mechanism that considers all factors simultaneously.
3Reliability
If multiple criteria are used for ranking, then comprehensive evaluation is achieved, but the ranking system becomes more complex
Solution Approach 1:
The patent introduces a service contract type criterion that acts as an intermediary factor in the ranking system. This criterion captures hospital-specific requirements and constraints, serving as a mediator between the alert's technical characteristics and the hospital's operational needs, thereby simplifying the overall evaluation process.
Data Source
Figure 1
Figure 2
AI summary
A method (100) of generating a ranked list (42) of alerts (30) from files (32) of electronic devices (12) includes: applying predictive models (34) to data of the files to generate maintenance alerts for the electronic devices; assigning discrete values for a set of criteria (36) to each maintenance alert whereby the maintenance alert has a share computed as a product of the assigned discrete values; performing a credit-based queuing process (38) to assign the maintenance alerts to slots of a ranked list, wherein in the credit-based queuing process the maintenance alerts accumulate credits in accord with the shares computed for the respective maintenance alerts; and displaying, on a display device (24) operatively connected with the at least one electronic processor, the maintenance alerts as the ranked list in accordance with the assignments of the maintenance alerts to the slots of the ranked list.