Class personalization within a connected fitness platform

Abstract

The systems and methods described herein receive a fitness goal or target (e.g., a user wants to be stronger, or run faster, or bike longer within a certain heart rate zone) as seed input into a guidance system, which generates a personalized plan of recommended classes/activities for the user based on their goal/target. At different points along the plan, the guidance system may modify or update its recommendations with different or enhanced classes/activities, in order to keep the user on their target or goal.

What is claimed is: 
     
         1 . A system, comprising:
 a sequence module that generates a baseline sequence of exercise classes associated with a fitness goal or target for a user of a connected fitness platform;   a modification module that modifies the baseline sequence based on class preferences associated with the user of the connected fitness platform; and   an output module that presents a class sequence based on the modified baseline sequence to the user of the connected fitness platform.   
     
     
         2 . The system of  claim 1 , wherein the sequence module:
 accesses a library of exercise classes available to the user of the connected fitness platform; and   generates the baseline sequence of exercise classes by applying a machine learning (ML) model to the accessed library of exercise classes to select distinguished exercise classes to include in the baseline sequence of exercise classes.   
     
     
         3 . The system of  claim 1 , wherein the sequence module:
 accesses a library of exercise classes available to the user of the connected fitness platform; and   generates the baseline sequence of exercise classes by applying a machine learning (ML) model to the accessed library of exercise classes to select one or more class types of exercise classes to include in the baseline sequence of exercise classes.   
     
     
         4 . The system of  claim 1 , wherein the sequence module:
 accesses a selection of exercise classes available to the user of the connected fitness platform that was performed by fitness experts associated with the connected fitness platform; and   generates the baseline sequence of exercise classes by applying a machine learning (ML) model to the accessed selection of exercise classes to select one or more class types of exercise classes to include in the baseline sequence of exercise classes.   
     
     
         5 . The system of  claim 1 , wherein the sequence module:
 generates the baseline sequence of exercise classes by applying a machine learning (ML) model to identify multiple types of exercise activities to include in the baseline sequence of exercise classes; and   selects, from a library of exercise classes available to the user of the connected fitness platform, multiple exercise classes that include the identified multiple types of exercise activities.   
     
     
         6 . The system of  claim 1 , wherein the modification module:
 determines music preferences, instructor preferences, or class length preferences for the user; and   modifies the baseline sequence to include exercise classes associated with the determined music preferences, instructor preferences, or class length preferences for the user.   
     
     
         7 . The system of  claim 1 , wherein the modification module:
 determines an exercise level for the user; and   modifies the baseline sequence to include exercise classes associated with the determined exercise level for the user.   
     
     
         8 . The system of  claim 1 , wherein the modification module:
 determines an exercise location associated with the user; and   modifies the baseline sequence to include exercise classes supported by the exercise location associated with the user.   
     
     
         9 . The system of  claim 1 , wherein the output module presents the class sequence to the user via a display of an exercise machine associated with the user. 
     
     
         10 . The system of  claim 1 , wherein the output module presents the class sequence to the user via a mobile device associated with the user. 
     
     
         11 . A non-transitory, computer-readable medium whose contents, when executed by a computing system, causes the computing system to perform a method, the method comprising:
 receiving, at a machine learning (ML) model, an input that identifies a fitness goal for a user of a connected fitness platform;   determining, via the ML model, a baseline sequence of virtual classes based on the fitness goal for the user;   obtaining preference information associated with the user; and   updating the baseline sequence of virtual classes based on the obtained preference information associated with the user.   
     
     
         12 . The non-transitory, computer-readable medium of  claim 11 , further comprising:
 performing an action to present the updated baseline sequence of virtual classes to the user of the connected fitness platform.   
     
     
         13 . The non-transitory, computer-readable medium of  claim 12 , wherein performing the action includes displaying a list of recommended virtual classes to the user via a display of an exercise machine associated with the user. 
     
     
         14 . The non-transitory, computer-readable medium of  claim 12 , wherein performing the action includes presenting a virtual class to the user via a mobile device associated with the user. 
     
     
         15 . The non-transitory, computer-readable medium of  claim 11 , wherein the preference information associated with the user includes class preference information that identifies characteristics of virtual classes previously taken by the user via the connected fitness platform. 
     
     
         16 . The non-transitory, computer-readable medium of  claim 11 , wherein the preference information associated with the user includes difficulty information for virtual classes previously taken by the user via the connected fitness platform. 
     
     
         17 . The non-transitory, computer-readable medium of  claim 11 , wherein the preference information associated with the user includes exercise machines available to the user. 
     
     
         18 . A method performed by a guidance system of a connected fitness platform, the method comprising:
 accessing a fitness goal associated with a user of the connected fitness platform and a sequence of multiple fitness activities generated for the user and based on the fitness goal associated with the user;   predicting the user is not on pace to achieve the fitness goal; and   modifying the sequence of multiple fitness activities based on the prediction.   
     
     
         19 . The method of  claim 18 , wherein predicting the user is not on pace to achieve the fitness goal includes:
 quantifying a fitness state of the user during performance of the sequence of multiple fitness activities;   determining the quantified fitness state is outside of a threshold fitness state.   
     
     
         20 . The method of  claim 18 , wherein modifying the sequence of multiple fitness activities based on the prediction includes:
 determining the user is performing at least one fitness activity of the multiple fitness activities at a certain location;   identifying exercise machines available to the user at the certain location; and   modifying the sequence of multiple fitness activities to include one or more fitness activities that incorporate the exercise machines available to the user at the certain location.