Motion-Based Skill Evaluation Using Model Worker Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies fail to accurately evaluate the work skills of an examinee by comparing motions that are not important evaluation items, leading to degraded skill evaluation accuracy.
Innovation Solution
A skill evaluation device that identifies and evaluates skills based on motion data from a sensor, extracting common feature amounts with less variation from multiple model workers to focus on important evaluation items, reducing the impact of non-essential motion comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the level calculating unit compares the motion of the examinee with the motion of the model worker for all motions including non-important evaluation items, then the comparison process is comprehensive, but the accuracy of skill level calculation is degraded
Solution Approach 1:
The patent segments the motion comparison process by dividing evaluation items into important and non-important categories. The motion data is processed differently for each category: important evaluation items undergo detailed comparison for accurate skill assessment, while non-important items are either excluded or given minimal weight. This segmentation allows the system to maintain high measurement precision for critical skills without the computational burden of equally detailed analysis of all motions.
Solution Approach 2:
The patent applies local quality by assigning different levels of analysis depth to different parts of the motion data. Important evaluation items receive thorough, precise comparison with the model worker's motion, while non-important items receive simplified or aggregated processing. This differential processing quality optimizes the overall skill evaluation accuracy by concentrating computational resources where they most impact the evaluation outcome.
2Reliability
If the system compares all motion data between examinee and model worker, then the evaluation is thorough, but the degree of freedom in non-essential motions causes inaccurate skill assessment
Solution Approach 1:
The patent segments motion data into important evaluation items and other motions. By isolating important evaluation items, the system ensures that skill evaluation reliability is based on critical performance metrics rather than being diluted by variations in non-essential motions. This segmentation allows the system to maintain reliable assessment of core skills while accommodating natural variations in peripheral movements.
Solution Approach 2:
The patent changes the weighting parameters in the skill level calculation by assigning significant weights only to important evaluation items and minimal or zero weights to non-important items. This parameter adjustment transforms the evaluation system from one that equally considers all motions to one that selectively emphasizes critical skills, thereby improving reliability while tolerating motion variations in non-essential areas.
3Measurement precision
If the level calculating unit uses all motion data for comparison, then no evaluation criteria are missed, but the skill evaluation accuracy is degraded due to non-important motions
Solution Approach 1:
The patent extracts and isolates important evaluation items from the complete motion data set. By taking out only the critical evaluation parameters needed for accurate skill assessment, the system eliminates the degrading influence of non-important motions while preserving all necessary evaluation information. This extraction process ensures that the skill level measurement is based solely on relevant criteria.
Solution Approach 2:
The patent applies different processing qualities to different portions of the motion data. Important evaluation items undergo precise, detailed analysis to maintain measurement accuracy, while non-important items are either excluded or processed with lower fidelity. This local differentiation of processing quality ensures that the skill evaluation maintains high precision without being contaminated by irrelevant motion variations.
Data Source
AI summary
A skill evaluation device includes: a motion data acquiring unit that acquires motion data indicating a motion of a work, from a sensor that detects the motion of the work being performed by an examinee in work skill evaluation; and a model work analyzing unit that identifies an evaluation item important in evaluating the work of the examinee, on the basis of model-worker motion data indicating a motion of a model worker. Also, the skill evaluation device includes a skill evaluating unit that evaluates the skills of the examinee, on the basis of the motion data acquired by the motion data acquiring unit and the evaluation item identified by the model work analyzing unit.