ML Rehabilitation Device Control for Personalized Exercise Plans

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional rehabilitation and exercise devices lack effective monitoring of progress and control over electromechanical devices, failing to provide optimal treatment plans and real-time feedback, leading to potential over-exertion, improper form, and delayed rehabilitation.

Innovation Solution

A control system using machine learning to generate personalized health improvement plans, adjust device configurations, and monitor user progress in real-time, enabling operation in various modes and providing granular control over electromechanical devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional rehabilitation devices are used without machine learning control, then device simplicity is maintained, but treatment effectiveness and real-time monitoring capability deteriorate

Engineering Contradiction:

Improvetreatment effectivenessVSAvoidcontrol system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The machine learning model enables the rehabilitation device to automatically generate personalized treatment plans and adjust parameters based on user data and real-time feedback, eliminating the need for constant manual intervention by therapists while improving treatment effectiveness

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system continuously collects user performance data and physiological signals during exercise sessions, processes this information through the machine learning model, and automatically adjusts device parameters in real-time to optimize treatment outcomes and prevent over-exertion

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If machine learning models are used to generate personalized treatment plans, then treatment customization is improved, but data processing requirements and system complexity increase

Engineering Contradiction:

Improvetreatment personalizationVSAvoidsystem architecture complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The machine learning model is pre-trained with extensive user data, medical records, and exercise outcomes before deployment, enabling it to generate personalized treatment plans quickly without requiring complex real-time computations during actual exercise sessions

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

A cloud-based processing system serves as an intermediary between the user device and the machine learning model, handling complex data processing and model training remotely while the local device only needs to communicate basic parameters and receive adjusted treatment plans

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If real-time monitoring and adaptive control are implemented, then user safety is improved, but computational load and energy consumption increase

Engineering Contradiction:

Improveuser safetyVSAvoidcomputational energy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs comprehensive safety checks and data processing at critical transition points between exercise phases rather than continuously during entire sessions, reducing computational load while maintaining user safety through periodic monitoring at key moments

Inventive Principle:

Principle #21Skipping (Rushing through)

Solution Approach 2:

The machine learning model focuses computational resources on monitoring only the most critical safety parameters and high-risk exercise movements, applying full monitoring intensity selectively when needed rather than uniformly across all exercise conditions

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12515104B2Systems and methods for using machine learning to control a rehabilitation and exercise electromechanical device

Publication Date: 2026.01.06 ROM TECH INC

AI summary

A method includes receiving user data for a user capable of operating an electromechanical device. The user data comprises health history data related to one or more health indicators of the user. The method further includes generating a health improvement plan by using a machine learning model to process the user data. The health improvement plan includes an exercise session to be performed on the electromechanical device. The method further includes providing the health improvement plan to one or more user portals. The method further includes selecting, for the electromechanical device, a device configuration that corresponds to the health improvement plan. The device configuration includes mode data related to one or more modes the electromechanical device is capable of operating during the exercise session. The method further includes providing the device configuration to the electromechanical device such that the device configuration may be implemented on the electromechanical device.