Grade Adjusted Pace Model Using Aggregate Activity Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Grade Adjusted Pace (GAP) models derived from lab settings are inaccurate for downhill race performance and based on limited running activities, failing to account for the relative difficulty of running on varying elevations effectively.
Innovation Solution
A system that generates a GAP model using aggregated activity data from recorded runs, including heart rate information, to adjust pace based on elevation gradients, providing a dimensionless grade pace adjustment coefficient that reflects the relative difficulty of running on different elevations compared to a flat surface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GAP models are derived from lab settings with limited running activities, then the model development is simple and controlled, but the accuracy for downhill race performance and varying elevations is poor
Solution Approach 1:
The patent merges data from multiple sources including GPS tracking, elevation data, heart rate monitors, and power meters into a unified dataset. By combining these diverse data streams from numerous athletes across different terrains and conditions, the system creates a comprehensive dataset that improves GAP model accuracy for varying elevations and downhill performance while distributing the complexity across multiple integrated components
Solution Approach 2:
The system creates a universal GAP model that functions across multiple conditions and terrains through aggregate data from diverse sources. The model is designed to be universally applicable to different athletes, elevations, and running conditions, transforming the complexity of varied inputs into a single multi-functional solution that accurately predicts performance across all scenarios
2Measurement precision
If aggregate activity data from multiple athletes is used to generate GAP model, then the model accuracy for varying elevations is improved, but the data processing complexity increases
Solution Approach 1:
The patent segments the aggregate data processing into distinct components: individual athlete performance data is processed separately first, then combined with elevation data and heart rate information in staged processing steps. This segmentation allows the system to handle complex multi-athlete aggregate data by breaking it into manageable segments that can be processed independently before integration, improving pace adjustment accuracy while managing processing complexity
Solution Approach 2:
The system introduces intermediate processing layers including data normalization, filtering, and aggregation stages that mediate between raw multi-athlete activity data and the final GAP model. These intermediary processes transform complex aggregate data into standardized formats, enabling accurate pace adjustment calculations while reducing the computational complexity of directly processing raw data from multiple sources
Data Source
AI summary
Using aggregate activity data to generate a grade adjusted pace model is disclosed, including: receiving a plurality of activities; selecting a portion of the plurality of activities based at least in part on recorded heart rate information associated with the plurality of activities; and generating a Grade Adjusted Pace (GAP) model based at least in part on the selected portion of the plurality of activities.