Body Activity Evaluation Using Anonymous Motion Pattern Comparison

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for remotely measuring and tracking the autonomy of individuals, such as frail or isolated persons, face challenges including the need for subjective questionnaires, complex setups, privacy concerns, and inaccurate posture identification, leading to unreliable alerts and unsuitable long-term tracking.

Innovation Solution

A method using non-supervised classification techniques to analyze raw motion data from inertial sensors, grouping similar postures into anonymized data classes, and comparing these over time to detect variations in body activity, providing an objective autonomy index.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If supervised methods with motion detection sensors are used to identify postures, then motion detection capability is improved, but measurement precision deteriorates due to confusion between similar postures

Engineering Contradiction:

Improvemotion detection capabilityVSAvoidposture identification accuracy

Core Design Contradiction:

Difficulty of detecting and measuringVSMeasurement precision

Solution Approach 1:

The patent segments the complex posture identification task into multiple sequential steps: raw acceleration data is first divided into time windows, then each window is processed through feature extraction to identify specific motion patterns. This segmentation allows the system to analyze different aspects of motion separately, improving the precision of posture identification by breaking down the confusing holistic pattern into distinguishable components.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transitions from analyzing raw acceleration data in three spatial dimensions to extracting features in an expanded feature space that includes temporal characteristics, magnitude, and pattern recognition dimensions. By mapping the data into this higher-dimensional feature space, the system can distinguish between postures that appear similar in physical space but have different temporal or dynamic characteristics.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Measurement precision

If multiple inertial sensors and cameras are deployed to refine motion identification, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improvemotion identification accuracyVSAvoidsensor setup complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential features needed for posture identification from the raw sensor data, discarding redundant information. By taking out only the relevant characteristics (such as acceleration patterns, velocity changes, and temporal sequences) and ignoring unnecessary data, the system achieves high measurement precision with a single inertial sensor rather than requiring multiple sensors and cameras.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the mechanical system of multiple physical sensors (inertial sensors on body parts and cameras in living spaces) with a computational approach that uses signal processing and pattern recognition algorithms. This substitution reduces device complexity by eliminating the need for multiple hardware components while maintaining or improving measurement precision through advanced data analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If detailed posture characterization is performed to improve motion analysis, then measurement precision is improved, but loss of information increases due to privacy concerns

Engineering Contradiction:

Improveposture analysis accuracyVSAvoidprivacy protection

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different processing levels to different aspects of the data: detailed analysis is applied only to the necessary motion features for posture identification, while personal identifying information and sensitive details are deliberately obscured or aggregated. This local quality approach allows precise posture analysis while protecting privacy by applying coarser processing to sensitive data elements.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12573492B2Method for evaluating the body activity of a user

Publication Date: 2026.03.10 ORANGE SA

AI summary

A method of evaluating the body activity of a user includes: at a given date and for a given duration, acquiring movement data from the user, distributing the acquired movement data corresponding to different types of movement, calculating a data structure representative of the body activity of the user performed at the given date and for the given duration, comparing the data structure with at least one other structure representative of the body activity performed at a date prior to the given date and for the given duration, duplicating the comparisons for different durations and determining an objective measurement of the user's autonomy.