Stress Level Estimation via Working Hour Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional stress level estimation methods lack accuracy as they do not differentiate between working and non-working hours, where body motion data can have opposite correlations with stress levels due to job-related and leisure activities.
Innovation Solution
A method that classifies measurement data into working and non-working hour data, generating separate feature quantities and training data to create estimation models for accurate stress level estimation, using a processor to differentiate between first and second measurement data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If body motion data is collected without differentiating between working and non-working hours, then data collection is simple and continuous, but stress level estimation accuracy deteriorates due to opposite correlations in different time periods
Solution Approach 1:
The patent segments the continuous body motion data into two distinct categories: first measurement data collected during working hours and second measurement data collected during non-working hours. This segmentation allows the system to apply different correlation interpretations to different time periods, thereby resolving the accuracy problem caused by opposite correlations while maintaining a relatively simple classification approach based on time stamps.
2Measurement precision
If separate training data is generated for working and non-working hours, then estimation accuracy improves, but data processing time and computational resources increase
Solution Approach 1:
The patent segments the training data generation process into two distinct workflows: one for working hours data and another for non-working hours data. This allows parallel processing of different data types and enables the system to generate specialized feature quantities and training models for each time period, improving accuracy while managing computational load through structured separation.
Solution Approach 2:
The patent performs preliminary classification of measurement data into working and non-working hours categories before proceeding with feature quantity calculation and model training. This preliminary action organizes the data in advance, reducing computational complexity during the actual training phase and enabling more efficient processing of large datasets.
Data Source
AI summary
In order to estimate a stress level with higher accuracy than conventional techniques, a stress level estimation method includes: classifying, by at least one processor, measurement data into first measurement data and second measurement data, the measurement data having been measured during a predetermined time period and pertaining to a stress level that indicates a degree of stress of a subject, the first measurement data having been measured during working hours of the subject, and the second measurement data having been measured outside the working hours; and estimating, by the at least one processor, a stress level of the subject using at least one of the first measurement data and the second measurement data.