Learning Model for Teaching Material Attribute Identification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional systems struggle to accurately define attributes such as subject name, unit name, and target grade for teaching materials when meta information is missing, requiring manual user input which is cumbersome.

Innovation Solution

An information processing device employs a machine-learned learning model to associate image data of teaching materials with attribute information, using a data set to automatically identify and store these attributes, and a learning device performs machine learning to enhance this association.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual user input is used to register attributes when meta information is not given, then attribute definition is possible, but operation complexity and time consumption increase significantly

Engineering Contradiction:

Improveease of attribute registrationVSAvoidtime for manual input

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-service by automatically extracting attributes from teaching material images using the learning model, eliminating the need for manual user input. The processing unit inputs image data to the learning model which outputs attribute information automatically, allowing the system to define attributes without human intervention.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual input process with an automated image recognition system. The learning model processes teaching material images and automatically extracts attributes such as subject name, unit name, and target grade, substituting the manual registration process with automated optical and computational methods.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If automated image recognition is used to identify attributes, then manual input is reduced, but system complexity increases due to machine learning model requirements

Engineering Contradiction:

Improveautomation of attribute identificationVSAvoidcomplexity of learning model system

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-training the learning model with a dataset of teaching material images and their corresponding attributes before actual use. This preliminary training phase prepares the model to automatically recognize and extract attributes from new images without requiring complex real-time processing or manual intervention during operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces a learning model as an intermediary between the input image data and the extracted attributes. This intermediary component processes the images and outputs structured attribute information, simplifying the overall system architecture by centralizing the complex recognition logic in a dedicated model rather than distributing it throughout the system.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12518535B2Information processing device, learning device, and method for controlling information processing device

Publication Date: 2026.01.06 SEIKO EPSON CORP

AI summary

An information processing server includes an information processing server storage unit that stores a machine-learned learning model based on a data set in which data of a teaching material content is associated with attribute information indicating an attribute of the teaching material content, a receiver that acquires the data of the teaching material content, and an input and output processing unit that inputs the data of the teaching material content acquired by the receiver to the learning model stored in the information processing server storage unit and causes the attribute information to be output from the learning model. The information processing server storage unit stores a related information record in which the data of the teaching material content acquired by the receiver is associated with the attribute information output from the learning model by the input and output processing unit.