Automated Skill Tagging via Text Analysis and Knowledge Graphs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The current manual process of skill tagging and knowledge graph creation for algorithm-based questions is time-intensive and costly, requiring Subject Matter Experts (SMEs) to manually review and analyze vast amounts of material to identify skills and learning objectives, making it inefficient and labor-intensive.

Innovation Solution

An automated system that analyzes electronic textbook data to identify problems and determine associated skills, generating tags and knowledge graphs, which defines relationships between concepts, skills, and problems, allowing for the automatic generation of assessments and customized exercises based on user performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual skill tagging and knowledge graph creation is performed by Subject Matter Experts, then accuracy and quality of skill identification is improved, but time consumption and cost increase significantly

Engineering Contradiction:

Improveskill identification accuracyVSAvoidtime for skill tagging

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an automated text analysis system as an intermediary between the problem statements and skill tags. This system uses natural language processing to extract skills from guided solutions and match them with glossary entries, serving as a mediator that reduces the direct manual effort required while maintaining reasonable accuracy through automated keyword matching and tag generation

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates automated copies of skill tagging by generating tags through text analysis algorithms that replicate the manual tagging process. The automated system copies the essential function of skill identification by analyzing problem text, extracting keywords, and generating appropriate tags without requiring direct human intervention for each problem

Inventive Principle:

Principle #26Copying

2Adaptability or versatility

If manual skill tagging is performed for all problems, then comprehensive skill coverage is improved, but labor intensity and cost increase

Engineering Contradiction:

Improveskill coverage completenessVSAvoidtagging efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system enables self-service skill tagging where the automated analysis system performs the tagging function independently. The text analysis system automatically processes problem statements, extracts relevant skills, and generates tags without requiring manual review for each problem, thereby maintaining comprehensive skill coverage while dramatically improving productivity

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes the parameter of skill identification from manual human analysis to automated computational analysis. By transforming the tagging process into an automated text processing task with configurable parameters such as keyword matching thresholds and tag generation rules, the system achieves both comprehensive coverage and high efficiency

Inventive Principle:

Principle #35Parameter changes

3Productivity

If automated text analysis is used for skill tagging, then time and cost are reduced, but complexity of the tagging system increases

Engineering Contradiction:

Improvetagging speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the skill tagging system into distinct functional modules: text analysis component, keyword extraction module, glossary matching engine, and tag generation system. This segmentation allows each component to perform its specific function independently, managing overall system complexity while enabling automated high-speed tagging through modular processing

Inventive Principle:

Principle #1Segmentation

4Adaptability or versatility

If automated generation of assessments and exercises is implemented, then adaptability to user needs is improved, but system complexity increases

Engineering Contradiction:

Improvepersonalization capabilityVSAvoidassessment generation system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements dynamic assessment generation that adapts to individual user needs based on performance data. The assessment generator dynamically selects and configures problems, tags, and exercise content based on real-time user responses and skill mastery levels, enabling personalization while managing complexity through adaptive algorithms rather than static pre-configured assessments

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11501655B2Automated skill tagging, knowledge graph, and customized assessment and exercise generation

Publication Date: 2022.11.15 PEARSON EDUCATION INC

AI summary

Systems and methods of the present invention provide for storing textbook data, a glossary, and problems within a database; identifying a problem's guided solution, and a keyword within the solution matching an entry within the glossary, from which a skill tag is associated. The disclosed system then automatically generates an assessment including an assessment problem associated with the skill. If an incorrect response is received for the assessment problem, the database is updated to associate a user that input the response with the assessment problem and a skill. The system then automatically generates a customized exercise assignment associated in the database with the skill.