Adaptive Training Plan System Using Dynamic Load Adjustment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing training systems fail to dynamically adapt and update training plans based on real-time user data, leading to suboptimal fitness progression and potential overtraining or undertraining, as they rely on fixed schedules and do not account for changing user conditions or preferences.

Innovation Solution

A system that automatically adjusts training plans daily, using parameters like EPOC, heart rate variability, and user input to ensure the training load remains within optimal limits, incorporating user-defined goals and preferences, and dynamically updates the training schedule to maintain a balanced fitness rhythm.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a fixed training schedule is used, then the training plan is simple to implement, but it cannot adapt to changing user conditions or preferences

Engineering Contradiction:
Improveadaptability to changing user conditionsVSAvoidtraining plan complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The training plan transitions from a static fixed schedule to a dynamic adaptive schedule that automatically adjusts based on real-time user data including EPOC values, heart rate variability, and user input. The system continuously modifies training parameters such as intensity, duration, and frequency to maintain optimal training load within calculated limits while responding to changing user conditions and preferences.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements continuous feedback loops where user data from wearables (EPOC, heart rate variability) and manual input are processed to automatically adjust the training plan. The control algorithm receives real-time feedback on training load, fitness level, and user preferences, then dynamically modifies subsequent training sessions to maintain optimality and prevent overtraining or undertraining.

Inventive Principle:
Principle #23Feedback

2Ease of operation

If manual training planning is used, then the user has control over their training, but it requires user expertise in training planning

Engineering Contradiction:
Improveease of training plan creationVSAvoidtraining optimization reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs self-service by automatically generating and adjusting training plans without requiring user expertise. The control algorithm independently processes user data, calculates optimal training parameters, and modifies the training schedule based on real-time feedback, eliminating the need for manual planning while maintaining high reliability through automated optimization algorithms.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system automatically modifies training parameters including intensity, duration, frequency, and rest periods based on calculated EPOC values, heart rate variability, and user input. The control algorithm dynamically adjusts these parameters to maintain training load within optimal limits, ensuring reliable training optimization without manual intervention.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If training load is increased to improve fitness progression, then fitness improvement is accelerated, but overtraining or undertraining may occur

Engineering Contradiction:
Improvefitness progression speedVSAvoidtraining safety
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system continuously monitors training load through EPOC values, heart rate variability, and user input, then provides feedback to the control algorithm. This feedback loop allows the system to automatically adjust training intensity and duration to maintain optimal load within calculated limits, accelerating fitness progression while preventing overtraining or undertraining through real-time safety monitoring.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system dynamically modifies training parameters based on real-time EPOC measurements and heart rate variability data. The control algorithm adjusts intensity, duration, and frequency parameters to maintain training load within optimal ranges, enabling accelerated fitness progression while automatically preventing overtraining or undertraining through continuous parameter optimization.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP1993681B1Method and system for controlling training
Publication Date: 2018.04.11 FIRSTBEAT TECHNOLOGIES OY
  • EP1993681B1 patent drawingFigure 1
  • EP1993681B1 patent drawingFigure 2
  • EP1993681B1 patent drawingFigure 3a~3b

AI summary

The invention relates to method and system for controlling a training plan for a user having a chosen aim for training, where - at least one parameter describing physical characteristics of the user is determined, and - a training plan consists of plurality of days, each day having one or more training sessions or rest, and - each performed and coming session having a training load described by one or more parameters - a training template is determined according to the aim and the said one or more parameters describing physical characteristics, each training template having a cumulative training load target according to the said parameter and the chosen aim and consisting of one or more training sessions or rest in each day, each training session of the template having a pre-selected training load, and - an adapting window is determined, the adapting window consisting of a plurality of days, which include one or more previous sessions and one ore more coming sessions according to the training template, and - training loads of each session in the adapting window are combined into a cumulative training load, which is compared relatively to the cumulative training load target in the template, and - depending on the comparison one or more coming sessions in the adapting window are adapted by changing one or more training loads of these so that the performed training load and the training load of the coming sessions as a combination meets the cumulative training load target.