Exercise Recommendation Ranking With User-Selected Workout Variance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current workout systems fail to allow users to specify their preference for workout variety while accounting for their goals and capabilities, and they lack the ability to predict users' capabilities based on their previous exercises.
Innovation Solution
An exercise recommendation system that uses machine learning to rank exercises based on user profiles, including exercise history, available equipment, and goals, and adjusts rankings based on user-specified variance, while predicting user capabilities through a moving average of past performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If current workout systems are used, then workout plans can be generated, but users cannot specify their preference for workout variety while accounting for goals and capabilities
Solution Approach 1:
The system dynamically adjusts workout plans based on user-specified variance levels. The workout generator receives a variance parameter (e.g., low, medium, high) and adapts the exercise selection, order, and variations accordingly. This allows the same system to produce diverse workout plans while maintaining ease of use through simple variance input.
Solution Approach 2:
The system changes the parameter of workout plan generation by incorporating user-selected variance as an input parameter. The workout generator modifies its output based on this parameter, adjusting exercise variety, repetition ranges, and set structures to match user preferences while still considering goals and capabilities.
2Measurement precision
If current workout systems are used, then workout plans can be generated, but the system lacks the ability to predict users' capabilities based on previous exercises
Solution Approach 1:
The capability predictor uses feedback from previous exercise performance data to continuously improve capability predictions. The system analyzes historical exercise completion data, weights used, and performance metrics to update and refine capability estimates for each user, enabling more accurate future workout recommendations.
Solution Approach 2:
The system performs preliminary capability assessment by analyzing past exercise history before generating new workout plans. The capability predictor processes historical data in advance to establish baseline capabilities, which then inform subsequent workout plan generation and adjustment.
3Stability of the object's composition
If workout plans follow the same exercises every week, then consistency is maintained, but user engagement and fitness progression are limited
Solution Approach 1:
The system dynamically adjusts workout consistency based on user goals and variance preferences. For users seeking consistency, the system maintains core exercise patterns while introducing variations. For users seeking progression, the system systematically varies exercises, sets, and weights while maintaining structural consistency, enabling both stability and progression simultaneously.
Solution Approach 2:
The system implements periodic variation in workout plans based on user progress and preferences. Rather than static repetition or random variation, the system uses periodic adjustment cycles that introduce variety at appropriate intervals while maintaining overall workout structure and goals, optimizing both consistency and progression.
Data Source
AI summary
An exercise recommendation system determines workout plans for users. The exercise recommendation system receives a profile of a user and a level of variance selected by the user. The profile includes a history of exercises the user has performed, available gym equipment, and exercise goals. The exercise recommendation system inputs the profile to a machine learning model configured to rank a set of exercises for a user to perform. The exercise recommendation system modifies the ranking of exercises based on the level of variance selected by the user. Modification of the ranking is greater for a first level of variance than for a second level of variance less than the first level of variance. The exercise recommendation system generates a workout plan for display within a user interface to the user based on the modified ranking.