Fitness Tracking Movement Variable Estimation via Remote Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fitness tracking systems face challenges in accurately determining movement variables such as speed and distance due to limitations in data processing and integration methods, leading to inconsistent and unreliable user metrics.
Innovation Solution
A fitness tracking system that utilizes a remote processing server with a machine learning model to process feature data, raw speed data, and raw distance data from a personal electronic device, enabling the determination of accurate movement variables like estimated speed, distance, and stride length, which are then transmitted back to the device for display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional data processing and integration methods are used in fitness tracking systems, then the system structure remains simple, but the accuracy of movement variable calculations deteriorates with errors up to ±10%
Solution Approach 1:
The patent transitions from local processing on personal devices to remote processing on servers, adding a spatial dimension to the data processing architecture. This allows complex machine learning models to run on powerful remote infrastructure while keeping personal devices simple, resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The patent introduces a remote server as an intermediary between the personal electronic device and the data processing functions. The server acts as a mediator that performs complex calculations using machine learning models, while the personal device simply collects and transmits data, thereby improving accuracy without increasing device complexity
2Measurement precision
If complex processing is performed on personal electronic devices to improve accuracy, then measurement precision improves, but the processing demands and energy consumption on personal devices increase
Solution Approach 1:
The patent extracts the complex processing functions from personal electronic devices and relocates them to remote servers. The personal device is stripped of heavy computational tasks, retaining only data collection and transmission functions, while the server handles complex machine learning-based calculations, thereby improving accuracy without increasing energy consumption on personal devices
Solution Approach 2:
The remote server serves as an intermediary that absorbs the computational burden. Instead of personal devices performing energy-intensive processing, the server mediates the processing tasks using its superior computational resources, allowing personal devices to maintain low energy consumption while achieving high measurement precision
Data Source
AI summary
A fitness tracking system for generating movement variables corresponding to movement of a user includes a monitoring device, a personal electronic device, and a remote processing server. The monitoring device is configured to be worn or carried by the user and includes a movement sensor configured to collect movement data. The personal electronic device is operably connected to the monitoring device. At least one of the personal electronic device and the monitoring device is configured to calculate feature data by applying a set of rules to the movement data, to calculate raw speed data corresponding to a speed of the user from the subset of the movement data, and to calculate raw distance data corresponding to a distance moved by the user from the subset of the movement data. The remote processing server includes a machine learning model for processing at least the feature data.