Adjustment of exercise based on artificial intelligence, exercise plan, and user feedback

Abstract

A method for generating an exercise session for a user using an exercise machine is disclosed herein. The method includes receiving a plurality of inputs, wherein the plurality of inputs comprise an indication of a level of pain of the user and a range of motion of a body part of the user. The method also includes determining, based on the plurality of inputs, an exercise level of the user, generating, using a machine learning model, the exercise session for the user by selecting, based on the exercise level of the user, one or more exercises to be performed by the user using an exercise machine, and causing initiation of the exercise session on the exercise machine and a virtual coach executed by a computing device associated with the exercise machine to provide instructions pertaining to the exercise session.

What is claimed is: 
     
         1 . A method for generating an exercise session for a user using an exercise machine, the method comprising:
 receiving a plurality of inputs, wherein the plurality of inputs comprise an indication of a level of pain of the user and a range of motion of a body part of the user;   determining, based on the plurality of inputs, an exercise level of the user;   generating, using a machine learning model, the exercise session for the user by selecting, based on the exercise level of the user, one or more exercises to be performed by the user using an exercise machine; and   causing initiation of the exercise session on the exercise machine and a virtual coach executed by a computing device associated with the exercise machine to provide instructions pertaining to the exercise session.   
     
     
         2 . The method of  claim 1 , wherein the selecting, based on the exercise level of the user, the one or more exercises to be performed by the user using the exercise machine further comprises:
 tagging each exercise of a plurality of exercises with a respective user exercise level, wherein the plurality of exercises are specified in a data structure accessed by the machine learning model.   
     
     
         3 . The method of  claim 2 , further comprising filtering the plurality of exercises by:
 identifying, based on the tagging, a subset of exercises having the respective user exercise level that matches the exercise level of the user; and   selecting the subset of exercises as the one or more exercises.   
     
     
         4 . The method of  claim 3 , further comprising filtering the plurality of exercises by:
 identifying a first subset of exercises having a respective section of a plurality of sections, wherein the plurality of sections comprise warm-up, cycling, strength, flexibility, or some combination thereof,   identifying a second subset of exercises that result in a desired outcome specified by a medical professional, wherein the desired outcome pertains to increasing a range of motion, mobility, strength, flexibility, or some combination thereof,   identifying, using a historical performance of the user, a third subset of exercises that have been performed by the user less than a threshold number of times,   identifying, based on feedback from the user, a fourth subset of exercises that have been performed by the user and indicated as being too easy or too hard for the user, and   selecting at least one of the subset of exercises, the first subset of exercises, the second subset of exercises, the third subset of exercises, or the fourth subset of exercises as the one or more exercises.   
     
     
         5 . The method of  claim 1 , wherein the plurality of inputs further comprise a plurality of characteristics of the user, and the plurality of characteristics of the user comprise:
 an age of the user,   a height of the user,   a weight of the user,   a gender of the user,   a condition that caused the pain in the body part,   one or more procedures perform on the user,   a goal of the user,   whether the user is in a pre-procedure stage or a post-procedure stage,   or some combination thereof.   
     
     
         6 . The method of  claim 1 , further comprising:
 receiving, from the user while the user is performing an exercise of the one or more exercises, feedback pertaining to the exercise, wherein the feedback comprises an indication of a level of difficulty of the exercise;   determining whether the feedback has been received more than a threshold number of times for the exercise;   responsive to determining the feedback has been received more than the threshold number of times for the exercise, adjusting, in real-time or near real-time, the exercise session, wherein adjusting the exercise session comprises changing to another exercise, controlling the exercise machine to stop the exercise, removing the exercise from the exercise session, changing an intensity of the exercise, or some combination thereof; and   causing the virtual coach to provide an indication of the adjustment.   
     
     
         7 . The method of  claim 1 , further comprising:
 receiving, from the user while the user is performing an exercise of the one or more exercises, feedback pertaining to the exercise, wherein the feedback comprises an indication that the exercise is too easy;   responsive to receiving the feedback, causing an intensity of the exercise to increase; and   causing the virtual coach to provide an indication of the increase of the intensity of the exercise.   
     
     
         8 . The method of  claim 7 , further comprising:
 responsive to determining the feedback has been received more than a threshold number of times, controlling, in real-time or near real-time, the exercise machine to initiate a more advanced exercise than the exercise; and   causing the virtual coach to provide an indication that the more advanced exercise has been initiated.   
     
     
         9 . The method of  claim 1 , further comprising:
 monitoring progress of the user while the user uses the exercise machine to perform the one or more exercises, wherein the progress comprises an amount of time the user performs the one or more exercises, the range of motion of the user while the user performs the one or more exercises, the level of pain of the user while the user performs the one or more exercises, whether the user completes the one or more exercises, an indication of the user of a level of difficulty of the one or more exercises, or some combination; and   adjusting, by the machine learning model, a subsequent exercise session based on the progress of the user, wherein the adjusting is based on:
 advancing the exercise level of the user to a next exercise level, 
 achieving a desired goal as defined by the user, a medical professional, or both, or 
 some combination thereof. 
   
     
     
         10 . The method of  claim 1 , further comprising:
 monitoring progress of the user while the user uses the exercise machine to perform the one or more exercises; and   causing, based on the progress of the user, an incentive, reward, or both to be elicited by a computing device associated with the exercise machine, wherein the incentive, reward, or both comprise an animation, video, audio, haptic feedback, image, push notification, email, text, or some combination thereof; and   causing the virtual coach to perform an encouraging action.   
     
     
         11 . The method of  claim 10 , further comprising:
 determining when a number of incentives, rewards, or both elicited by the computing device satisfy a threshold value; and   responsive to determining that threshold value is satisfied, causing a certificate to be transmitted to the computing device and associated with an account of the user using the exercise machine.   
     
     
         12 . The method of  claim 1 , further comprising:
 selecting, for the virtual coach, a persona from a plurality of personas;   causing the virtual coach to provide instructions as the user performs the one or more exercises;   monitoring a parameter associated with the user while the user performs the one or more exercises, wherein the parameter pertains to a progress of the user, an indication of whether the user likes the persona of the virtual coach, or both; and   selecting, based on the parameter, a subsequent persona for the virtual coach.   
     
     
         13 . The method of  claim 1 , further comprising:
 selecting, for the virtual coach, a persona from a plurality of personas;   causing the virtual coach to provide instructions as the user performs the one or more exercises;   monitoring a parameter associated with the user while the user performs the one or more exercises, wherein the parameter pertains to a progress of the user, an indication of whether the user likes the persona of the virtual coach, or both; and   switching, in real-time or near real-time, based on the parameter, a different persona for the virtual coach while the user performs the one or more exercises.   
     
     
         14 . The method of  claim 1 , further comprising:
 determining, by the machine learning model, a plurality of audio segments for the virtual coach to say while the user performs the one or more exercises.   
     
     
         15 . The method of  claim 1 , further comprising:
 determining, by the machine learning model, a schedule of a plurality of exercise sessions to be performed by the user to achieve a desired goal specified by the user, a medical professional, or both.   
     
     
         16 . The method of  claim 1 , wherein the virtual coach is controlled, in real-time or near real-time, by the machine learning model. 
     
     
         17 . A tangible, non-transitory computer-readable medium storing instructions that, when executed, cause a processing device to:
 receive a plurality of inputs, wherein the plurality of inputs comprise an indication of a level of pain of the user and a range of motion of a body part of the user;   determine, based on the plurality of inputs, an exercise level of the user;   generate, using a machine learning model, an exercise session for the user by selecting, based on the exercise level of the user, one or more exercises to be performed by the user using an exercise machine; and   cause initiation of the exercise session on the exercise machine and a virtual coach executed by a computing device associated with the exercise machine to provide instructions pertaining to the exercise session.   
     
     
         18 . The computer-readable medium of  claim 17 , wherein to select, based on the exercise level of the user, the one or more exercises to be performed by the user using the exercise machine, the processing device is further to:
 tag each exercise of a plurality of exercises with a respective user exercise level, wherein the plurality of exercises are specified in a data structure accessed by the machine learning model.   
     
     
         19 . A system comprising:
 a memory device storing instructions;   a processing device communicatively coupled to the memory device, the processing device executes the instructions to:
 receive a plurality of inputs, wherein the plurality of inputs comprise an indication of a level of pain of the user and a range of motion of a body part of the user; 
 determine, based on the plurality of inputs, an exercise level of the user; 
 generate, using a machine learning model, an exercise session for the user by selecting, based on the exercise level of the user, one or more exercises to be performed by the user using an exercise machine; and 
 cause initiation of the exercise session on the exercise machine and a virtual coach executed by a computing device associated with the exercise machine to provide instructions pertaining to the exercise session. 
   
     
     
         20 . The system of  claim 19 , wherein to select, based on the exercise level of the user, the one or more exercises to be performed by the user using the exercise machine, the processing device is further to:
 tag each exercise of a plurality of exercises with a respective user exercise level, wherein the plurality of exercises are specified in a data structure accessed by the machine learning model.