Dynamic Tagging Knowledge Graph Resume Parsing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The complex and non-deterministic relationships between job titles and job responsibilities make it challenging to automatically parse and map job titles to actual experience, leading to inconsistencies and inaccuracies in resume analysis and job matching.

Innovation Solution

A computer-implemented method that extracts keywords from resume content, identifies existing job titles, and uses a knowledge graph to find associated job titles, linking content phrases with additional job titles based on determined associations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional resume parsing methods are used, then processing speed is maintained, but mapping accuracy between job titles and experiences deteriorates due to complex and non-deterministic relationships

Engineering Contradiction:
Improvemapping accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces a knowledge graph as an intermediary data structure that stores pre-established relationships between job titles and job responsibilities. This knowledge graph acts as a mediator between the resume text and the parsing system, enabling accurate mapping by looking up pre-defined relationships rather than attempting to infer complex relationships in real-time. The knowledge graph contains structured data about job title hierarchies, typical responsibilities, and skill associations, which resolves the non-deterministic nature of job title mappings.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary action by pre-processing and storing job title relationships in a knowledge graph before actual resume parsing occurs. During resume analysis, the system queries this pre-built knowledge structure rather than performing complex real-time reasoning about job title meanings and relationships. This preliminary structuring of data enables fast and accurate mapping during the actual parsing operation.

Inventive Principle:
Principle #10Preliminary action

2Loss of information

If comprehensive job title mapping is performed, then mapping completeness improves, but processing time increases due to the need to analyze complex relationships

Engineering Contradiction:
Improvemapping completenessVSAvoidprocessing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The knowledge graph is built in advance with comprehensive job title relationships, allowing the parsing system to query pre-computed mappings rather than performing exhaustive analysis during resume processing. This preliminary structuring captures comprehensive job title-responsibility-skill relationships offline, enabling fast online queries that maintain completeness without sacrificing processing speed.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a simplified copy of job title relationship structures in the knowledge graph that can be quickly queried. Instead of performing complex relationship reasoning during resume parsing, the system copies relevant mapping relationships from the comprehensive knowledge base into the parsing process, enabling fast lookup of job title associations while maintaining completeness of the mapping information.

Inventive Principle:
Principle #26Copying

3Measurement precision

If manual job title analysis is used, then mapping accuracy improves, but productivity deteriorates due to the time-consuming nature of manual parsing

Engineering Contradiction:
Improveparsing accuracyVSAvoidprocessing throughput
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system enables self-service by automatically querying the knowledge graph for job title relationships without requiring manual intervention. The parsing system independently retrieves relevant job title mappings, responsibilities, and skill associations from the pre-built knowledge graph, eliminating the need for manual analysis while maintaining the accuracy that would otherwise require human expertise. This automation achieves both high accuracy and high throughput.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual job title analysis with an automated computational system that queries the knowledge graph. Instead of human experts manually interpreting job titles and inferring relationships, the system uses structured queries against the pre-built knowledge base to automatically determine job title mappings, responsibilities, and skill associations, achieving both accuracy and scalability.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4546236A1Dynamic tagging
Publication Date: 2025.04.30 LIVECAREER
  • EP4546236A1 patent drawingFigure 1
  • EP4546236A1 patent drawingFigure 2
  • EP4546236A1 patent drawingFigure 3

AI summary

Certain aspects of the disclosure provide systems and methods for extracting and exploiting keyword and job title relations. Systems and methods provide for generating a knowledge graph embedding keywords, job titles, and additional resume data. Further, systems and methods provide for utilizing the knowledge graph to identify and link additional job titles with the embedded keywords.