Cognitive Bias Determination and Modeling for User Learning Styles

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current computing systems fail to effectively adapt to individual user learning styles, leading to suboptimal interaction and information consumption experiences.

Innovation Solution

A method and system that analyze user interactions and clipboard data to determine preferred learning styles, creating user models that dynamically adjust information presentation to suit individual needs, and group users for personalized content delivery.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If computing systems provide generic information presentation to all users, then system complexity is reduced and ease of operation is improved, but user learning effectiveness and information consumption efficiency deteriorate

Engineering Contradiction:

Improvesystem operation simplicityVSAvoidlearning effectiveness

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system dynamically adapts information presentation based on detected user learning styles. User models are continuously updated as the system observes user interactions with information, allowing the presentation format to evolve from generic to personalized over time, thereby improving learning effectiveness without requiring users to manually configure settings

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system automatically detects user learning styles by analyzing interaction patterns with information, eliminating the need for users to manually self-report or configure their preferences. The user model is built and updated autonomously through observation of actual behavior, reducing operational complexity while enabling personalized delivery

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If computing systems collect and analyze detailed user interaction data to determine learning styles, then user personalization and learning effectiveness are improved, but data processing complexity and measurement difficulty increase

Engineering Contradiction:

Improveuser personalization capabilityVSAvoidlearning style detection complexity

Core Design Contradiction:

Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system implements continuous feedback loops where user interactions with information are monitored, analyzed, and used to update user models. This feedback mechanism automatically refines the detection of learning styles over time, transforming the complex measurement problem into an iterative optimization process that improves personalization accuracy without requiring manual intervention

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system begins collecting and analyzing user interaction data from the outset of user engagement, building user models proactively before explicit personalization is needed. This preliminary data collection and analysis establishes the foundation for future personalized information delivery, reducing the complexity of real-time detection

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10109214B2Cognitive bias determination and modeling

Publication Date: 2018.10.23 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

In an approach for determining a preferred learning style of the user, a computer receives user information of a user. The computer collects data for user model development, wherein data includes actions performed by the user. The computer creates one or more associations between actions in the collected data for user model development and received user information. The computer determines a preferred learning style of the user based on the created one or more associations.