Virtual Care System Anomaly Detection via Computer Vision

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual comparison of user movement and speech with historical data or statistical norms is inefficient and prone to inconsistent results due to the large size and variability of the data, making it difficult to achieve accurate medical diagnoses in remote healthcare settings.

Innovation Solution

An interactive virtual care system utilizing computer-vision technology and multi-modal data acquisition, including depth cameras and microphone arrays, to capture and analyze user movements and speech, generating a computer-generated version that highlights anomalies for objective comparison with historical data or statistical norms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual comparison of user movement and speech with historical data is performed, then diagnostic analysis can be conducted, but the process becomes inefficient and prone to inconsistent results due to large data size and variability

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidevaluation efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual visual inspection and subjective interpretation with computer-vision technology and automated analysis systems. Depth cameras capture movement data, microphone arrays record speech, and algorithms objectively compare these against historical data, eliminating human subjectivity and significantly improving both diagnostic accuracy and evaluation efficiency

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

Solution Approach 2:

The system creates computer-generated versions of user movements and speech patterns that can be precisely replicated and compared against historical data. This digital copying enables consistent, repeatable analysis without the variability inherent in manual observation

Inventive Principle:
Principle #26Copying

2Ease of operation

If visual inspection of individual movements is performed by health care providers, then diagnostic evaluation can be conducted, but the results become subjective based on provider interpretation

Engineering Contradiction:
Improveevaluation simplicityVSAvoiddiagnostic consistency
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent substitutes human visual inspection with automated computer-vision systems that objectively capture and analyze movement data. Depth cameras and sensors replace the health care provider's eyes and interpretation, eliminating subjectivity while maintaining ease of operation through automated processing

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

Solution Approach 2:

The system enables objective self-evaluation by capturing user movements and speech, automatically comparing them against historical data and statistical norms. The computer-generated analysis provides reliable, consistent results without requiring subjective human interpretation

Inventive Principle:
Principle #25Self-service

3Measurement precision

If computer-vision technology and multi-modal data acquisition are used to capture and analyze user movements and speech, then objective anomaly identification is achieved, but system complexity increases

Engineering Contradiction:
Improveanomaly detection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the complex analysis task into separate modular components: depth cameras for movement capture, microphone arrays for speech recording, and distinct algorithms for processing each data type. This segmentation manages system complexity by organizing functions into independent, manageable modules while maintaining high detection accuracy

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP2560141B1Interactive virtual care
Publication Date: 2018.03.14 ACCENTURE GLOBAL SERVICES LTD
  • EP2560141B1 patent drawingFigure 1
  • EP2560141B1 patent drawingFigure 2
  • EP2560141B1 patent drawingFigure 3

AI summary

An interactive virtual care system may include a user sensory module to acquire multi-modal user data related to user movement. A data analysis module may compare the multi-modal user data to predetermined historical user data and/or statistical norm data for users to identify an anomaly in the user movement.