Knowledge Tracing Model for Personalized Content Recommendations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing content recommendation services fail to consider a user's knowledge level when recommending content, limiting their effectiveness, especially in environments where problem-solving methods are not applicable, such as with articles or videos.

Innovation Solution

A method and system that sense a user's reaction while consuming content, determine their understanding, and update their knowledge level using a knowledge tracing model, allowing for personalized content recommendations based on their knowledge level.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing content recommendation services only consider content type or user interest, then the recommendation system is simple to implement, but the recommendation accuracy and personalization are insufficient

Engineering Contradiction:

Improveknowledge level measurement accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by sensing user reactions and determining understanding levels before generating content recommendations. The knowledge tracing model is pre-trained with educational theories and cognitive models to enable accurate knowledge level assessment without requiring complex real-time analysis during recommendation generation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

A knowledge tracing model serves as an intermediary between user reaction sensing and content recommendation. This mediator processes raw user reactions, determines understanding levels, and translates them into knowledge level profiles that guide personalized content selection, simplifying the overall system architecture while improving recommendation accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If knowledge tracing technology is applied to content consumption environments without problem-solving interactions, then personalized recommendations can be achieved, but the technology adaptation from problem-solving to content consumption is challenging

Engineering Contradiction:

Improvetechnology adaptability to content consumptionVSAvoidtechnology implementation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The knowledge tracing model is designed with multi-functionality to handle both traditional problem-solving interactions and content consumption scenarios. By integrating educational theories and cognitive models, the system universally applies knowledge tracing across different interaction types, enabling personalized recommendations for articles, videos, and other content without requiring separate systems.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system adapts to different content consumption environments by changing parameters such as reaction types, understanding metrics, and knowledge level thresholds. This flexibility allows the knowledge tracing technology to effectively transition from problem-solving to content consumption contexts while maintaining personalization capabilities.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If user reactions are sensed and knowledge level is traced in real-time, then personalized content recommendations are achieved, but the processing time and computational resources increase

Engineering Contradiction:

Improvepersonalization accuracyVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The knowledge tracing model is pre-trained with educational theories and cognitive models before deployment. This preliminary preparation enables the system to quickly process user reactions and determine understanding levels during actual content consumption, reducing real-time processing time while maintaining high personalization accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system processes only the most relevant user reactions and updates knowledge levels selectively rather than analyzing every possible data point. This partial processing approach reduces computational overhead and processing time while still achieving reliable personalized recommendations.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20240323464A1Method of tracing knowledge level of user consuming content and recommending content based on knowledge level of user, and computing device executing the same

Publication Date: 2024.09.26 SAMSUNG ELECTRONICS CO LTD

AI summary

A method of tracing a knowledge level of a user, includes: sensing a reaction of the user consuming content; determining an understanding of the user with respect to the content based on the reaction of the user; inputting the understanding and information about the content into a knowledge tracing model; and updating the knowledge level of the user based on an output from the knowledge tracing model.