Geometric Movement Path Evaluation for Activity Classification

Solution Overview

Problem

Existing activity monitoring systems face challenges in providing accurate contextual intelligence for user activities, often relying on computationally intensive methods that are inefficient and lack sufficient contextual information, making it difficult to distinguish between utilitarian and health-related activities.

Innovation Solution

A geometric evaluation system that classifies movement based on a score characterizing geometrical properties of the path, using sensors to determine parameters such as path length and area, allowing for less computationally intensive and more accurate contextual intelligence provision, without requiring external services or extensive data processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing activity monitoring systems use computationally intensive methods to provide contextual intelligence, then measurement precision of activity classification is improved, but use of energy and device complexity increase

Engineering Contradiction:

Improveactivity classification accuracyVSAvoidcomputational energy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts only the essential geometric parameters (path length, area, orientation) needed for activity classification from the full sensor data stream. By taking out only these critical geometric features rather than processing all raw sensor data, the system achieves accurate activity differentiation with significantly reduced computational energy consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary geometric evaluation of movement paths by calculating path length, area, and orientation parameters before detailed activity classification. This preliminary geometric assessment filters and structures the data in advance, enabling more efficient subsequent classification with lower energy requirements.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If existing systems process extensive data points to infer activity context, then contextual intelligence accuracy is improved, but productivity and processing efficiency decrease

Engineering Contradiction:

Improvecontextual intelligence accuracyVSAvoidprocessing efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent extracts only the essential geometric parameters (path length, area, orientation) needed for activity classification from the full sensor data stream. By taking out only these critical geometric features rather than processing all raw sensor data, the system achieves accurate activity differentiation with significantly reduced computational energy consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary geometric evaluation of movement paths by calculating path length, area, and orientation parameters before detailed activity classification. This preliminary geometric assessment filters and structures the data in advance, enabling more efficient subsequent classification with lower energy requirements.

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If activity monitoring lacks comprehensive semantic context, then device complexity is reduced, but measurement precision of activity classification deteriorates

Engineering Contradiction:

Improvesystem simplicityVSAvoidactivity classification accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies geometric evaluation principles that are universally applicable across different activity types (walking, running, cycling, swimming). The same geometric parameters (path length, area, orientation) and classification methodology work across multiple activities and devices, providing comprehensive contextual intelligence without increasing device complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11355226B2Ambulatory path geometric evaluation

Publication Date: 2022.06.07 KONINKLIJKE PHILIPS NV

AI summary

In an embodiment, an apparatus (16) is presented that classifies device-sensed movement along a path based on a score that characterizes a geometrical property of the movement.