Training Status Determination Using Sequential Selection Rules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems fail to accurately determine training status from multiple exercises due to limited CPU and memory resources in embedded devices, such as heart rate monitors and mobile phones, making it challenging to analyze physiological data effectively.
Innovation Solution
A method and apparatus that utilize the ETE and THA libraries for real-time heart rate analysis and training history analysis, minimizing resource demand by storing exercise characteristics in memory and calculating training status based on VO2max, HRV, and training load, allowing for determination of short-term and long-term training effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If training status is determined from multiple exercises using comprehensive physiological analysis, then measurement precision and reliability of training status determination is improved, but CPU and memory resource consumption increases beyond embedded device capabilities
Solution Approach 1:
The patent segments the training status determination process into distinct functional modules: exercise monitoring module that collects physiological data, training load calculation module that computes acute and chronic loads, fitness level assessment module that evaluates VO2max trends, and training status determination module that integrates these inputs. This segmentation allows each module to operate with minimal resource requirements while collectively achieving comprehensive analysis across multiple exercises.
Solution Approach 2:
The patent extracts and stores only the most critical physiological parameters and exercise characteristics in memory during exercise execution, rather than storing complete raw data streams. Key extracted variables include heart rate, power output, exercise duration, and exercise type. This extraction approach maintains measurement precision for training status determination while dramatically reducing memory requirements in embedded devices.
2Loss of time
If real-time physiological data is continuously analyzed during exercise, then training status feedback timeliness is improved, but energy consumption and CPU usage increase
Solution Approach 1:
The patent implements periodic analysis cycles where physiological data is continuously collected during exercise but processed in discrete time intervals rather than continuously analyzed. The system accumulates exercise characteristics and physiological measurements, then performs training load and status calculations at predetermined intervals or upon exercise completion. This periodic processing maintains timely feedback while significantly reducing CPU usage and energy consumption compared to continuous real-time analysis.
3Measurement precision
If comprehensive training history is stored for multiple exercises, then training status calculation accuracy is improved, but memory resource requirements exceed embedded device capacity
Solution Approach 1:
The patent extracts and stores only essential exercise characteristics and aggregated training metrics in device memory, such as exercise type, duration, intensity, and calculated training load values. Complete raw physiological data streams and detailed exercise metadata are excluded from long-term storage. This extraction strategy enables comprehensive training history analysis across multiple exercises while maintaining memory usage within embedded device constraints.
Solution Approach 2:
The patent transforms raw physiological measurements into condensed training status parameters that capture the essential information needed for accurate training status determination. Instead of storing comprehensive raw data, the system calculates and stores derived parameters such as acute training load, chronic training load, their ratio, and VO2max trends. This parameter transformation maintains calculation accuracy while dramatically reducing storage requirements.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
The invention relates to a method and system for determining training status of a user from plurality of exercises using a device (80) with a heart rate sensor (72), a processor (62), memory (61A, 62B), an output device (14) and software. The training status is selected from a fixed group of alternatives (105, 140). Each exercise is monitored using the heart rate sensor (72). Chosen exercise characteristics of each executed exercise are determined using obtained heart rate data and the determined characteristics of each executed exercise are stored in a memory (62B). The chosen exercise characteristics include values of at least following variables: - a date of the exercise , - a value depicting physical readiness level for exercise during the exercise - a value depicting a training load of the exercise. When the plurality of exercises has been executed, values of selection variables are calculated using the stored exercise characteristics in the memory (62B). The training status is determined using sequential pre-determined selection rules (103, 104), each rule being connected to one unique variable of said selection variables, wherein each selection rule uses a calculated value of its selection variable to limit a number of remaining alternatives and after all selection rules have been sequentially used, only one alternative is selected.