Adaptive Learning Problem Generation via Changeable Area Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for creating learning problems struggle to adapt to specific situations or learners, as they rely on random changes to formulas or texts, failing to reflect the context and resulting in a lack of variety and suitability in learning materials.

Innovation Solution

A method and system that determine changeable areas in reference learning problems, adjust data within specified ranges, and create new problems based on changed data, allowing for adaptive modification of visual elements and difficulty levels to generate diverse and tailored learning materials.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If learning problems are created by randomly determining numbers or characters, then a large number of learning problems can be generated, but it is difficult to reflect the context of a learning situation or a learner, making it difficult to create learning problems suitable for a specific situation or a specific learner

Engineering Contradiction:
Improvenumber of learning problems generatedVSAvoidsuitability for specific situation or learner
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent applies local quality by identifying and modifying specific changeable areas (such as numerical values, problem conditions, or answer options) within the learning problem template, rather than randomly changing entire problems. This allows targeted adaptation to learner needs while maintaining the overall problem structure and context.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system changes specific parameters (numerical values, difficulty levels, problem conditions) within defined ranges to generate varied learning problems. This enables systematic adaptation to different learner levels and situations while ensuring problems remain valid and educationally sound.

Inventive Principle:
Principle #35Parameter changes

2Ease of manufacture

If new learning problems are created by making limited changes only to the formulas or texts included in existing learning problems, then the creation process is simple, but it is difficult to create a variety of learning problems

Engineering Contradiction:
Improvesimplicity of problem creation processVSAvoidvariety of learning problems
Core Design Contradiction:
Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent segments the learning problem into multiple changeable areas (formulas, texts, numerical values, problem conditions, answer options). By allowing independent modification of each segment within its defined range, the system achieves both simplicity in the creation process and high variety in the generated problems.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts which areas are changed and by how much, based on learner characteristics and learning situations. This dynamic approach enables the same base problem to generate diverse variations suitable for different learners while maintaining a simple automated creation process.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS20240412655A1Method, system and non-transitory computer-readable recoding medium for creating learning problems
Publication Date: 2024.12.12 MATA EDU INC
  • US20240412655A1 patent drawing
  • US20240412655A1 patent drawing
  • US20240412655A1 patent drawing

AI summary

A method for creating learning problems is provided. The method includes the steps of: with reference to setting information on a reference learning problem, determining changeable areas in the reference learning problem, and determining ranges of data change in the changeable areas; changing data included in at least one of the determined changeable areas, within the range of data change in the at least one changeable area; and creating a new learning problem from the reference learning problem on the basis of the changed data.