Exercise Motion Analysis Using Grouped Representative Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing exercise analysis technologies fail to provide comprehensive analysis of exercise motions, potentially leading to inaccurate results due to the exclusion of abnormal data, which can worsen user performance.
Innovation Solution
An exercise analysis device that classifies activity data into multiple groups based on reference data, generates representative data for each group, and analyzes the tendency of these representative data to provide a comprehensive analysis of exercise motions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If only measurement data matching extraction conditions are transferred to the server for exercise analysis, then data transfer volume is reduced and processing is sped up, but the analysis results may not be reasonable for the entire exercise and may worsen user performance due to abnormal extracted data
Solution Approach 1:
The patent segments the exercise data processing into two distinct parts: (1) extraction of measurement data matching specific conditions from the entire exercise dataset, and (2) analysis of both the extracted data and the remaining data separately. This segmentation allows efficient processing of extracted data while preserving the ability to analyze the complete dataset for overall tendency assessment, thereby resolving the contradiction between processing speed and result accuracy.
Solution Approach 2:
The patent introduces an intermediary mechanism that manages multiple datasets: the extracted measurement data matching conditions, and the remaining data not matching conditions. By maintaining and analyzing both datasets separately and then integrating their results, the system ensures that neither the efficiency benefits of extracted data analysis nor the accuracy benefits of complete data analysis are lost.
2Productivity
If extracted measurement data is used for exercise analysis, then processing efficiency is improved, but the results may be contrary to the tendency of the entire exercise
Solution Approach 1:
The patent divides the data analysis into segmented components: extracted data analysis and remaining data analysis. Each segment is processed independently to preserve its unique characteristics, and the results are then integrated. This ensures that information from both the extracted subset and the complete dataset is retained, preventing loss of overall exercise tendency information while maintaining processing efficiency.
Solution Approach 2:
The patent merges the analysis results from extracted measurement data with the analysis results from the remaining data. By combining these two analytical perspectives, the system achieves a comprehensive understanding that captures both the specific patterns in extracted data and the overall tendencies in the complete dataset, thereby preventing information loss.
3Reliability
If all measurement data during exercise is transferred to the server for analysis, then comprehensive analysis is achieved, but data transfer volume increases and processing time extends
Solution Approach 1:
The patent extracts only the measurement data that matches predetermined conditions from the entire exercise dataset for separate analysis. This extraction approach allows the system to focus computational resources on specific data subsets that are most relevant to particular analysis objectives, reducing overall processing time and data transfer requirements while maintaining comprehensive analysis capabilities through separate processing of the remaining data.
Solution Approach 2:
The patent performs preliminary extraction and filtering of measurement data before the main analysis process. By pre-identifying and separating data that matches extraction conditions, the system prepares the data in advance for more efficient processing, reducing the computational burden during the actual analysis phase and thereby reducing overall processing time.
Data Source
AI summary
An exercise analysis device includes: a group classification unit that classifies activity data, as which measurement data associated with an exercise motion is recorded together with certain reference data that changes during exercise, into multiple groups based on the reference data; a representative data generating unit that generates representative data for the activity data in each of the multiple groups; and a tendency analysis unit that analyzes a tendency of the representative data with respect to the reference data in the multiple groups. With the exercise analysis device, exercise motions can be analyzed appropriately in consideration of the tendency of the entire exercise.