Workout modification based on muscle strength measurement trends
An exercise recommendation system determines workout plans for users. The exercise recommendation system trains a machine-learned model configured to rank a set of exercises, and the ranking of exercises can be modified based on feedback from a user, for instance requesting that an exercise be recommended more frequently, less frequently, or never. The exercise recommendation system can also implement a machine-learned model configured to predict a measure of strength for the user, and can, in response to determining that the measure of strength of the user has decreased or plateaued over time, modify a workout for a user based on a muscle or muscle group associated with the measure of strength. Likewise, the exercise recommendation system can modify a workout in response to a predicted measure of strength being less than an actual measure of strength, for instance to include exercises targeting muscles associated with the measure of strength.
1 . A method for modifying a workout plan, the method comprising:
accessing training data comprising information describing characteristics of a population of users and historical performance data representative of a performance of exercises by the population of users;
training a machine-learned model using the accessed training data, the machine-learned model configured to predict a measure of strength of a target user based on characteristics of the target user and data describing a performance of one or more exercises by the target user;
identifying, based on an output of the machine-learned model, that the predicted measure of strength for the target user has plateaued or decreased over time; and
modifying a workout for the target user based on a muscle or muscle group associated with the predicted measure of strength.
2 . The method of claim 1 , wherein the historical performance data includes a measure of strength for the historical users when performing the exercises.
3 . The method of claim 2 , wherein the measure of strength for the historical users is calculated based on at least one of: repetitions and weights associated with the exercises performed by the historical users.
4 . The method of claim 1 , wherein the predicted measure of strength for the target user is determined by applying the machine-learned model to performance data associated with one or more exercises performed by the target user and characteristics of the target user.
5 . The method of claim 1 , wherein a plateaued measure of strength for the target user is identified by the predicted strength of the target user increasing by less than a threshold amount over a set interval of time.
6 . The method of claim 1 , wherein a decreased measure of strength for the target user is identified by the predicted strength of the target user decreasing by more than a threshold amount over a set interval of time.
7 . The method of claim 1 , wherein modifying the workout for the target user comprises:
adding one or more exercises associated with the muscle or muscle group to the workout.
8 . A system for modifying a workout plan, the system comprising:
at least one processor; and
at least one memory comprising stored instructions, the instructions when executed by the at least one processor configured to cause the at least one processor to:
access training data comprising information describing characteristics of a population of users and historical performance data representative of a performance of exercises by the population of users;
train a machine-learned model using the accessed training data, the machine-learned model configured to predict a measure of strength of a target user based on characteristics of the target user and data describing a performance of one or more exercises by the target user;
identify, based on an output of the machine-learned model, that the predicted measure of strength for the target user has plateaued or decreased over time; and
modify a workout for the target user based on a muscle or muscle group associated with the predicted measure of strength.
9 . The system of claim 8 , wherein the historical performance data includes a measure of strength for the historical users when performing the exercises.
10 . The system of claim 8 , wherein the measure of strength for the historical users is calculated based on at least one of: repetitions and weights associated with the exercises performed by the historical users.
11 . The system of claim 8 , wherein the predicted measure of strength for the target user is determined by applying the machine-learned model to performance data associated with one or more exercises performed by the target user and characteristics of the target user.
12 . The system of claim 8 , wherein a plateaued measure of strength for the target user is identified by the predicted strength of the target user increasing by less than a threshold amount over a set interval of time.
13 . The system of claim 8 , wherein a decreased measure of strength for the target user is identified by the predicted strength of the target user decreasing by more than a threshold amount over a set interval of time.
14 . The system of claim 8 , wherein modifying the workout for the target user comprises:
adding one or more exercises associated with the muscle or muscle group to the workout.
15 . A non-transitory computer readable medium having instructions for modifying a workout plan encoded thereon that, when executed by a processor, cause the processor to:
access training data comprising information describing characteristics of a population of users and historical performance data representative of a performance of exercises by the population of users;
train a machine-learned model using the accessed training data, the machine-learned model configured to predict a measure of strength of a target user based on characteristics of the target user and data describing a performance of one or more exercises by the target user;
identify, based on an output of the machine-learned model, that the predicted measure of strength for the target user has plateaued or decreased over time; and
modify a workout for the target user based on a muscle or muscle group associated with the predicted measure of strength.
16 . The non-transitory computer readable medium of claim 15 , wherein the historical performance data includes a measure of strength for the historical users when performing the exercises.
17 . The non-transitory computer readable medium of claim 15 , wherein the measure of strength for the historical users is calculated based on at least one of: repetitions and weights associated with the exercises performed by the historical users.
18 . The non-transitory computer readable medium of claim 15 , wherein the predicted measure of strength for the target user is determined by applying the machine-learned model to performance data associated with one or more exercises performed by the target user and characteristics of the target user.
19 . The non-transitory computer readable medium of claim 15 , wherein a plateaued measure of strength for the target user is identified by the predicted strength of the target user increasing by less than a threshold amount over a set interval of time.
20 . The non-transitory computer readable medium of claim 15 , wherein a decreased measure of strength for the target user is identified by the predicted strength of the target user decreasing by more than a threshold amount over a set interval of time.