Cognitive Function Estimation With State-Segmented Facial Variations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional cognitive function estimation systems using facial expressions for dementia detection face challenges due to individual differences and variability in emotional expressions, making them inaccurate for assessing cognitive decline.

Innovation Solution

A cognitive function estimation device that analyzes specific body parts, particularly facial features, to classify video segments into distinct states and calculate variation amounts, using comparison features to estimate cognitive function accurately.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If a CNN model is used to estimate cognitive function from facial expressions, then the system can automatically detect emotions, but the accuracy is reduced due to individual differences and variability in emotional expressions

Engineering Contradiction:

Improveautomatic emotion detectionVSAvoidcognitive function estimation accuracy

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The patent segments the video into multiple sections based on detected states (e.g., task performance states vs. rest states), and calculates variation amounts for each segment separately. This segmentation allows the system to focus on state-specific behavioral patterns rather than analyzing the entire video as a single emotional expression sequence, thereby improving measurement precision while maintaining automation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent changes the analysis parameter from emotional expression intensity (subjective and variable) to variation amount of specific body parts (objective and measurable). By tracking positional changes, movement ranges, and temporal patterns of body parts across different states, the system achieves more precise cognitive function estimation that is less affected by individual differences in emotional expression.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If emotional expression analysis is used for cognitive function detection, then the system can identify cognitive decline, but the results vary depending on conversation topic, mood, and compatibility with conversation partner

Engineering Contradiction:

Improvedementia detection capabilityVSAvoidconsistency of measurement results

Core Design Contradiction:

ReliabilityVSStability of the object's composition

Solution Approach 1:

The patent performs preliminary state detection and video segmentation before calculating variation amounts. By identifying and isolating specific states (such as task performance states) beforehand, the system ensures that the subsequent measurements are taken under consistent and controlled conditions, reducing the influence of external factors like conversation topic or mood on the final results.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces variation amount calculations as an intermediary metric between raw body part positions and cognitive function assessment. This intermediary measurement focuses on quantitative changes in body part positions and movements, serving as a stable mediator that translates physical movements into cognitive function indicators while filtering out the noise from emotional variability and contextual influences.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of operation

If conventional facial expression analysis is used, then the system can estimate cognitive function, but it lacks accuracy because expressions of emotion are difficult to control and may not occur during conversation

Engineering Contradiction:

Improvenon-intrusive assessmentVSAvoidcognitive function measurement accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent enables the system to automatically perform state detection, video segmentation, and variation amount calculation without requiring manual annotation or control of emotional expressions. The system self-servingly identifies relevant video sections and computes the necessary metrics, maintaining ease of operation while improving precision through automated, objective measurement of body part variations.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent substitutes the emotional expression analysis mechanism with a body part variation analysis mechanism. Instead of relying on the complex and variable mechanism of emotional facial expressions, the system uses the more stable and measurable mechanical movements of body parts, which can be objectively tracked and quantified through video analysis, thereby improving measurement precision while keeping the system non-intrusive.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250302354A1Cognitive function estimation device, cognitive function estimation method, and recording medium

Publication Date: 2025.10.02 NEC CORP

AI summary

A cognitive function estimation device cognitive function estimation device acquires a video of a target person. The cognitive function estimation device detects a specific body part forming a body of the target person from the video, and acquire detection information concerning the body part. The cognitive function estimation device classifies each section of the video for each state by determining the state of the target person based on the detection information. The cognitive function estimation device calculates, for each state, a variation amount of a specific body part in each section of the video which is classified, and calculate features associated to the variation amount for each state. The cognitive function estimation device calculates comparison features, which are features related to comparison between states, by comparing features of respective states.