ML-Based Maintenance Response Time Proposal for Network Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for allocating human resources for preventive maintenance in network devices require manual estimation of resource usage, making it impossible to fully automate the execution plan for device malfunctions.
Innovation Solution
A maintenance response time suggestion device that uses a machine learning engine to estimate and calculate the usage amount of human and physical resources, determining an optimal time and method for countermeasures based on detected malfunction signs and resource utilization plans, allowing for automated planning without human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If manual estimation of resource usage is used for preventive maintenance planning, then flexibility and adaptability are maintained, but automation cannot be fully achieved and productivity is reduced
Solution Approach 1:
The system enables self-service by allowing the preventive maintenance planning system to automatically estimate resource usage itself through the resource usage amount estimation unit, eliminating the need for manual estimation while achieving full automation of execution plan formulation
Solution Approach 2:
The patent replaces manual mechanical estimation processes with an automated machine learning-based estimation system that uses historical data and algorithms to predict resource usage amounts, thereby achieving automation without sacrificing productivity
2Productivity
If preventive maintenance is executed at convenient times with available resources, then resource utilization efficiency is improved, but response time to malfunction signs increases
Solution Approach 1:
The system performs preliminary action by proactively estimating resource usage amounts for future maintenance activities using machine learning models, allowing planners to schedule maintenance at optimal times before malfunctions occur while ensuring resources will be available, thus improving efficiency without excessive delay
Solution Approach 2:
The system uses feedback from historical resource usage data and maintenance outcomes to continuously refine its predictions, enabling it to balance between scheduling maintenance at convenient times and responding quickly to malfunction signs by learning from past patterns
Data Source
AI summary
A maintenance response time suggestion device 1 suggests a response time for preventive maintenance against malfunction of a device. The device 1 includes: a sign receiving unit 11 that receives sign detection information in which a sign of malfunction of the device is detected; a resource receiving unit 14 that receives resource utilization plan information that indicates a plan for a usage and a utilization time of human and physical resources related to a predicted occurrence period of the malfunction of the device; a resource estimation unit 15 that estimates and calculates transition data of a usage amount of the human and physical resources related to the predicted occurrence period of the malfunction of the device by inputting the usage and the utilization time of the human and physical resources included in the resource utilization plan information to a machine learning engine that generates transition data of a usage amount of human and physical resources based on a usage and a utilization period of human and physical resources and performing machine learning; and a countermeasure determination unit 17 that determines a time and a method for taking countermeasures against the malfunction of the device based on the sign detection information and the transition data of the usage amount of the human and physical resources.