Print Order Workload Prediction Using Neural Network Estimation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to accurately predict the workload involved in the creation process of printed materials due to frequent changes in specifications or design, leading to operational challenges in large factories with complex manufacturing flows.

Innovation Solution

An information processing system that utilizes a neural network model to estimate the workload of a creation process by analyzing order information, including text, voice inputs, and images, to determine the specifications or design of printed materials.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a manufacturing plan is made for large factory with numerous manufacturing patterns, then the factory can handle complex printed material production, but it becomes difficult to estimate workload and operators face heavy load

Engineering Contradiction:

Improvemanufacturing pattern flexibilityVSAvoidworkload estimation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent replaces manual workload estimation with an automated machine learning model. The model takes order information as input and automatically predicts workload metrics, substituting the manual analytical process with an automated computational system that handles the complexity of numerous manufacturing patterns.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces a machine learning model as an intermediary between order information and workload assessment. This intermediary process automatically translates diverse order details into standardized workload metrics, bridging the gap between complex manufacturing patterns and actionable planning data.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If change requests from clients in specifications or design are frequently accommodated, then client satisfaction is improved, but manufacturing plan changes occur each time increasing operational burden

Engineering Contradiction:

Improvespecification change responsivenessVSAvoidmanufacturing plan revision time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent performs preliminary workload estimation by analyzing order information before finalizing the manufacturing plan. By predicting workload metrics in advance, the system prepares for potential changes more efficiently, reducing the time required when specification changes occur.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism where the machine learning model continuously learns from actual manufacturing data and change patterns. This feedback loop improves the accuracy of workload predictions over time, enabling better preparation for anticipated changes and reducing revision time.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260024367A1Information 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 workload of a creation process corresponding to new order information by inputting to a model the new order information on a printed material, the model being pre-learned such that, when order information on a printed material is input, information on the workload involved in the creation process that determines specifications or design of the printed material is output.