Machine Learning Print Setting Conflict Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Printers face conflicts due to incompatible print settings, leading to printing failures, as they often lack the ability to detect and resolve these conflicts efficiently without user intervention, especially in cloud printing scenarios where device-specific drivers may not be available.

Innovation Solution

Implementing a system that uses machine-learning models to detect print-setting conflicts and generate resolutions, allowing for automatic adjustment of print settings or user input to resolve conflicts, without the need for device-specific drivers, by employing conflict-detection and conflict-resolution models that communicate with user devices and image-forming devices via networks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional print setting conflict detection methods are used, then device-specific drivers are required, but this reduces adaptability in cloud printing environments

Engineering Contradiction:

Improveadaptability in cloud printing environmentsVSAvoiddevice-specific drivers

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal conflict detection and resolution system that works across multiple printer types and cloud printing environments without requiring device-specific drivers. The machine learning models are trained on diverse print setting data to recognize conflicts universally, enabling the system to adapt to different printers and cloud services through a single standardized interface.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent replaces the traditional mechanical approach of device-specific drivers with an intelligent system using machine learning models. Instead of relying on pre-programmed driver software for each device, the system uses trained models to detect and resolve print setting conflicts, substituting automated intelligence for conventional driver-based mechanisms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If automatic conflict detection and resolution is implemented, then user intervention is reduced, but system complexity increases

Engineering Contradiction:

Improveuser intervention requirementVSAvoidmachine-learning models

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by training machine learning models in advance on extensive datasets of print settings and conflicts. This pre-training enables the models to automatically detect and resolve conflicts without requiring user intervention during actual printing operations. The complex learning process is performed beforehand, simplifying the operational phase.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-service by enabling printers and printing systems to automatically detect and resolve their own print setting conflicts using the machine learning models. The system serves itself by identifying conflicts and applying resolutions without external user input, making the complex automated process transparent to the end user.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If machine-learning models are used for conflict detection, then detection accuracy is improved, but computational resources increase

Engineering Contradiction:

Improveconflict detection accuracyVSAvoidcomputational resources

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by implementing a two-stage process: first, a lightweight conflict detection model identifies potential conflicts, and only then is a more comprehensive resolution model applied to specific conflicts. This selective approach uses computational resources proportionally to the actual need, avoiding full-model execution for every print job while maintaining high detection accuracy.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11429328B2Devices, systems, and methods for resolving conflicting print settings

Publication Date: 2022.08.30 CANON KK

AI summary

Devices, systems, and methods obtain a print job, wherein the print job includes printing content, a plurality of respective selected print-settings options for a plurality of print settings, and print-job metadata; determine if the print job includes one or more print-setting conflicts based on the plurality of selected print-settings options and on a first machine-learning model, wherein the first machine-learning model accepts the selected print-settings options as inputs and outputs an indicator that indicates whether the print job includes one or more print-setting conflicts; and generate respective resolutions that include a respective resolution for each of the one or more print-setting conflicts based on a second machine-learning model, wherein the second machine-learning model accepts the plurality of selected print-settings options as inputs, and wherein the second machine-learning model outputs the respective resolutions.