Print Job Scheduling Using Cycledown Prediction Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing printing systems struggle with predicting and minimizing cycledowns, which reduce productivity, due to complex and unpredictable conditions, making it difficult to schedule print jobs effectively.

Innovation Solution

An information processing system that utilizes a neural network model to predict cycledowns between consecutive print jobs by learning from historical data, including information on print jobs, print settings, environmental conditions, and printer status, allowing for optimized job scheduling to minimize cycledowns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional printing systems process print jobs consecutively without prediction, then simple scheduling is maintained, but cycledowns occur frequently reducing productivity

Engineering Contradiction:

Improveprinting productivityVSAvoidcycledown time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary prediction of cycledown occurrence and timing before print jobs are executed by using a machine learning model to analyze job characteristics and estimate when cycledowns will occur, allowing advance scheduling adjustments to be made

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from actual cycledown occurrences and job processing results to continuously improve the prediction model, comparing predicted cycledown timing with actual timing to refine future predictions and scheduling decisions

Inventive Principle:

Principle #23Feedback

2Productivity

If cycledown prediction is attempted using complex analysis, then productivity improvement may be achieved, but system complexity increases making scheduling difficult

Engineering Contradiction:

Improveprinting productivityVSAvoidscheduling system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system introduces a machine learning model as an intermediary component that handles the complex analysis of job characteristics and cycledown prediction, separating the complexity from the scheduling decision-making process and providing clear prediction outputs for scheduling adjustments

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system changes the approach from attempting to analyze complex cycledown conditions directly to using a data-driven parameter-based prediction model that processes job characteristics and environmental factors to estimate cycledown timing probabilistically

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260023517A1Information processing system, non-transitory computer readable medium and information processing method

Publication Date: 2026.01.22 FUJIFILM BUSINESS INNOVATION CORP

AI summary

An information processing system includes: a processor configured to: output information on a cycledown that occurs between multiple new print jobs that are to be consecutively processed, by inputting, to a model, new input information including information on each of the new print jobs to be consecutively processed and information on print information to be printed in each of the new print jobs, the model being pre-learned to output information on a cycledown occurring between multiple print jobs when input information, including information on each of the print jobs to be consecutively processed and information on print information to be printed in each of the print jobs, is input.