Psychosomatic State Estimation Using Dynamic Acoustic Thresholds

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for estimating emotional and psychosomatic states from sound data are subjective, time-consuming, and vulnerable to noise and sound quality deterioration, requiring extensive sample data and subjective human determination.

Innovation Solution

A method and system that calculates feature amounts such as pitch frequency and intensity changes from sound data using a computational device, estimating psychosomatic states objectively without pre-defined correspondence relations, using a portable communication terminal to acquire and process sound data, and outputting estimated states on a display.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If correspondence relation between emotional state and parameters is generated by having multiple persons determine emotional states for each sample data, then estimation accuracy is improved, but time consumption and complexity increase significantly

Engineering Contradiction:
Improveestimation accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system uses the subject's own voice data to automatically determine emotional state through computational analysis of pitch frequency and intensity, eliminating the need for multiple human raters to manually assess each sample. The computational device performs the determination function that previously required human judgment, achieving both automation and objectivity.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of human emotional state determination with an automated computational system that analyzes acoustic parameters. The computational device calculates pitch frequency and intensity changes, then automatically determines emotional state based on these calculations, substituting human subjective judgment with objective computational analysis.

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

2Loss of information

If correspondence relation between emotional state and parameters is generated by having multiple persons determine emotional states, then more comprehensive data is obtained, but device complexity and operational difficulty increase

Engineering Contradiction:
Improvecomprehensive dataVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system performs self-determination of emotional state through computational analysis, eliminating the complex coordination required for multiple human raters. The computational device independently analyzes the voice data and determines emotional state without requiring human involvement in the determination process.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the complex human-based determination system with a computational system that automatically analyzes acoustic parameters. The computational device performs calculations of pitch frequency and intensity, then determines emotional state based on these calculations, simplifying the overall system while maintaining comprehensive data analysis.

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

3Ease of operation

If threshold values are set for estimating emotional state from parameters, then estimation can be performed, but the estimates become vulnerable to noise and sound quality deterioration

Engineering Contradiction:
Improveestimation capabilityVSAvoidrobustness to noise
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent employs dynamic threshold adjustment based on the statistical distribution of the parameter. Instead of using fixed thresholds, the system determines thresholds dynamically from the data itself, allowing the estimation to adapt to varying sound conditions and maintain reliability even when noise or quality deterioration occurs.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the approach from using fixed threshold values to using dynamically determined thresholds based on the parameter's distribution characteristics. This parameter change allows the system to adapt to different sound conditions and maintains robustness against noise and quality variations.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3417780B1Estimation method, estimation program, estimation device, and estimation system
Publication Date: 2024.03.13 PST INC (NEWCO)
  • EP3417780B1 patent drawingFigure 1
  • EP3417780B1 patent drawingFigure 2
  • EP3417780B1 patent drawingFigure 3~3(b)

AI summary

At least one feature amount is calculated with sound data uttered by a subject, a degree of a psychosomatic state of the subject is calculated based on the calculated feature amount, and the psychosomatic state of the subject are estimated based on the calculated degree.