Print Job Involved-Time Prediction for Accurate Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurate calculation of involved time for print jobs is difficult due to dependence on equipment performance and worker skill levels, leading to inefficient equipment scheduling in the printing industry.
Innovation Solution
An information processing system utilizing a neural network model to predict involved time based on input information about the job, worker, and equipment, enabling more precise scheduling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If involved time is predicted based on experience and time to spare, then scheduling can be formed, but the prediction accuracy is insufficient
Solution Approach 1:
The system collects actual involved time data from completed print jobs and uses this feedback to train and improve the prediction model continuously. The model learns from historical data including job characteristics, equipment performance, and worker skill levels to progressively enhance prediction accuracy.
Solution Approach 2:
The patent replaces the manual experience-based prediction method with an automated machine learning model. The neural network or regression model automatically processes input features (job details, equipment, worker information) to generate predictions, substituting human intuition with computational algorithms that can be continuously refined.
2Measurement precision
If accurate calculation of involved time is attempted considering equipment performance and worker skill, then scheduling accuracy improves, but calculation complexity increases
Solution Approach 1:
The system transforms the complex calculation problem into a parameter-based prediction model. Instead of manually calculating involved time by considering multiple factors, the model takes these factors as input parameters (job characteristics, equipment performance metrics, worker skill levels) and directly outputs the predicted involved time through learned relationships.
Solution Approach 2:
The prediction model serves multiple functions: it estimates involved time for scheduling, identifies bottlenecks in production, optimizes resource allocation, and provides insights for process improvement. This single multi-functional system replaces what would otherwise require multiple separate analysis tools and manual processes.
3Measurement precision
If more factors are considered in involved time prediction (equipment performance, worker skill, job characteristics), then prediction accuracy improves, but data processing complexity increases
Solution Approach 1:
The system merges multiple data sources and factors into a unified prediction model. Job characteristics, equipment performance data, and worker skill information are combined into a single integrated model that processes all inputs simultaneously to generate the involved time estimate, rather than handling each factor separately.
Solution Approach 2:
The model creates a virtual representation or copy of the complex real-world system involving equipment, workers, and jobs. This digital twin or simulation model allows the system to predict involved time by processing simplified input data through learned relationships, avoiding the need for complex real-time analysis of all underlying factors.
Data Source
AI summary
An information processing system includes: a processor configured to: when new input information including information on a new job and information on a worker performing work on the new job is input to a model, output involved time in response to the new input information wherein the model has been learned such that involved time for a job is output when input information including information on the job on print paper and information on the worker is input to the model.