Personalized Exercise Via Digital Twins and Electronic Exercise Equipment

Abstract

System and method for creating an exercise plan for a user based on a goal state of a digital twin of the user. A baseline state of the digital twin is created based on a first 3D model of the user and first physiological data of the user. Using a machine-learning model, an exercise plan for the user, comprising one or more motion profiles, is created that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin. Electronic exercise equipment is configured to physically manifest the one or more motion profiles during exercise activity of the user, and data is acquired by the electronic exercise equipment based on the exercise activity.

Claims

1. A method, comprising: creating a baseline state of a digital twin of a user based on a first 3D model of the user and first physiological data of the user; creating, using a machine learning model trained on exercise activity and outcomes of other users, an exercise plan for the user, comprising one or more motion profiles, that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin; configuring an electronic exercise machine to physically manifest the one or more motion profiles during exercise activity of the user; and acquiring, by the electronic exercise machine, exercise data based on the exercise activity.

2. The method of claim 1, further comprising: updating at least one of the goal state of the digital twin or the exercise plan based on the exercise data.

3. The method of claim 1, further comprising: updating the baseline state of the digital twin based on a second 3D model of the user and second physiological data of the user each acquired after acquiring the exercise data; and updating at least one of the goal state of the digital twin or the exercise plan based on the updated baseline state of the digital twin.

4. The method of claim 1, further comprising: determining a comparison between the baseline state of the digital twin and the goal state of the digital twin; and presenting, by a graphical display, at least one of: the baseline state of the digital twin and the goal state of the digital twin, or the comparison.

5. The method of claim 1, further comprising: determining a comparison between at least one of the baseline state of the digital twin or the goal state of the digital twin and a state of a different digital twin of a different individual; and presenting, by a graphical display, at least one of: at least one of the baseline state of the digital twin or the goal state of the digital twin and the state of the digital twin of the different individual, or the comparison.

6. The method of claim 1, wherein the one or more motion profiles comprise at least one of: one or more torques as a function of time; or one or more velocities as a function of time.

7. The method of claim 1, wherein the exercise plan further comprises: indications of one or more exercise sessions each comprising at least one of the one or more motion profiles.

8. The method of claim 1, further comprising: creating the baseline state of the digital twin based further on first physical-performance data of the user.

9. The method of claim 1, further comprising: creating the baseline state of the digital twin based further on genetic data of the user.

10. The method of claim 1, further comprising: obtaining an indication of the goal state of the digital twin from an individual.

11. The method of claim 1, further comprising: obtaining an indication of the goal state of the digital twin from the machine learning model.

12. The method of claim 1, wherein the electronic exercise machine comprises at least one of: an electronic resistance machine; a treadmill; a stair climber; a stationary bike; an elliptical trainer; a rowing machine; an incline trainer; a recumbent bike; a stepper machine; a cross trainer; an arc trainer; a spin bike; a climbing machine; a vibration platform; a ski machine; a cable machine; or a multi-gym machine.

13. The method of claim 1, wherein the first physiological data comprises at least one of: resting metabolic rate (RMR); resting heart rate; maximum heart rate during exercise; maximum oxygen uptake during exercise (VO2 max); blood pressure; blood glucose level; body mass index (BMI); body fat percentage; or respiratory exchange ratio (RER).

14. The method of claim 8, wherein the first physical-performance data comprises at least one of: joint flexibility; muscle strength; muscle speed; or muscle fatigue.

15. The method of claim 9, wherein the genetic data comprises at least one of: gene variants related to Alpha-Actinin-3 (ACTN3); gene variants related to Angiotensin-Converting Enzyme (ACE); gene variants related to Peroxisome Proliferator-Activated Receptor Gamma Coactivator 1-Alpha (PPARGC1A); gene variants related to Collagen Type I Alpha 1 Chain (COL1A1); gene variants related to Nuclear Factor Erythroid 2-Related Factor 2 (NRF2); gene variants related to Growth Differentiation Factor 5 (GDF5); gene variants related to Beta-2 Adrenergic Receptor (ADRB2); gene variants related to Hypoxia-Inducible Factor 1-Alpha (HIF1A); gene variants related to Fat Mass and Obesity-Associated Protein (FTO); gene variants related to Creatine Kinase, Muscle (CKM); gene variants related to Interleukin 6 (IL6); or gene variants related to Brain-Derived Neurotrophic Factor (BDNF).

16. The method of claim 1, wherein the digital twin comprises: an anatomically simulatable anatomical model of the user; and a physiologically simulatable physiological model of the user.

17. A system, comprising: one or more memories; and one or more processors configured to execute instructions stored in the one or more memories to: create a baseline state of a digital twin of a user based on a first 3D model of the user and first physiological data of the user; create, using a machine learning model trained on exercise activity and outcomes of other users, an exercise plan for the user, comprising one or more motion profiles, that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin; configure an electronic exercise machine to physically manifest the one or more motion profiles during exercise activity of the user; and acquire, by the electronic exercise machine, exercise data based on the exercise activity.

18. The system of claim 17, wherein the one or more processors are configured to execute the instructions to: update at least one of the goal state of the digital twin or the exercise plan based on the exercise data.

19. A non-transitory computer-readable medium storing instructions operable to cause one or more processors to perform operations comprising: creating a baseline state of a digital twin of a user based on a first 3D model of the user and first physiological data of the user; creating, using a machine learning model trained on exercise activity and outcomes of other users, an exercise plan for the user, comprising one or more motion profiles, that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin; configuring an electronic exercise machine to physically manifest the one or more motion profiles during exercise activity of the user; and acquiring, by the electronic exercise machine, exercise data based on the exercise activity.

20. The non-transitory computer-readable medium of claim 19, the operations further comprising: updating at least one of the goal state of the digital twin or the exercise plan based on the exercise data.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG. 1 is a block diagram of an example of a system for executing personalized exercise plans based on a digital twin and electronic exercise equipment.

[0011] FIG. 2 is a block diagram of an example internal configuration of a computing device 200 of a system for executing personalized exercise plans based on a digital twin and electronic exercise equipment.

[0012] FIG. 3 is a block diagram of an example process for creating one or more states of a digital twin by a system for executing personalized exercise plans based on a digital twin and electronic exercise equipment.

[0013] FIG. 4 is a representation of an example of a graphical user interface of a system for executing personalized exercise plans based on a digital twin and electronic exercise equipment.

[0014] FIG. 5 is a flowchart of an example of a technique for executing personalized exercise plans based on a digital twin and electronic exercise equipment.

DETAILED DESCRIPTION

[0015] FIG. 1 is a block diagram of an example of a system 100 for executing personalized exercise plans based on a digital twin and electronic exercise equipment 122. The system 100 receives inputs, such as one or more body scans 102, which may comprise anatomical and physiological data 103, one or more goal states 104, and supplementary user data 106. These inputs may be received via a graphical user interface such as the user interface 212 of FIG. 2, discussed later.

[0016] The one or more body scans 102, which may be referred to herein as a single or aggregate body scan 102, may be ascertained via one or more anatomical and/or physiological scan of a user's body, which may determine a general shape and/or form of the user and various physiological parameters of the user, such as the user's distribution of fat and lean body tissue, bone density, resting metabolic rate (RMR), resting heart rate, maximum heart rate during exercise, maximum oxygen uptake during exercise (VO2 max), blood pressure, blood glucose level, body mass index (BMI), body fat percentage, and respiratory exchange ratio (RER). The body scan 102 may be an input for creating a digital twin, as discussed later, where the digital twin may include one or more states, such as the baseline state 402 and the goal state 406 of the digital twin 418 represented in FIG. 4, discussed later.

[0017] Body scanners capable of ascertaining body scans 102 are known in the art, and can use various modalities to assess body composition, shape, and other physiological and anatomical metrics. Common modalities include: optical scanning, which uses light or lasers to create detailed 3D models of the body's surface, such as the ShapeScale 3D scanner; X-ray-based scanning, which offer more detailed internal assessments by measuring bone density and differentiating between fat and lean mass, such as a dual-energy X-ray absorptiometry (DEXA) scanner; ultrasound scanning, which uses sound waves to visualize body tissue layers and estimate body fat; and infrared scanning, which measures heat distribution to assess metabolic activity. Other advanced techniques include magnetic resonance imaging (MRI), which provides highly detailed cross-sectional images of body tissues. Some brands or types of body scanners include InBody for bioelectrical impedance, Fit3D for 3D optical body shape scanning, and BodPod, which measures body composition through air displacement plethysmography. These technologies offer varied approaches depending on the depth of analysis required. Other devices, such as fitness trackers, smartwatches, and general healthcare devices, may be suitable for ascertaining some of the anatomical and physiological data 103.

[0018] The one or more goal states 104, which may be referred to herein as singular or plural, is a desired state that may include physical, anatomical, and/or physiological parameters or metrics. For example, the goal state 104 may embody: physical appearance, such as a visual representation of the amount and distribution of fat and lean mass; physical strength, such as a capability to instantaneously apply a specified force over a specified duration, for example, regarding exercises like bench press, squat, bicep curl, and so on; physical speed, such as a running ability; endurance, such as a capability to repeatedly apply a specified force over a specified duration, for example, regarding exercises like bench press, squat, bicep curl, and so on; mobility, such as proper exercise form, sports biomechanics, joint flexibility; bone density; metabolic rate; and so on. The goal state 104 is a state of a digital twin of the user. FIG. 4 depicts an example of a goal state 406, discussed later. The goal state 104 may be user-defined or user-selected. A user-defined goal state 104 may be provided by the user, for example, via input of desired physical, anatomical, and/or physiological parameters or metrics to the user interface 212 of FIG. 2, discussed later. A user-selected goal state 104 may be selected by the user from a variety of user-selectable options, which may be created by the system 100, discussed later.

[0019] The supplementary user data 106 may include, for example: data concerning nutritional intake of the user, such as macronutrient intake, eating schedules, portion sizes, and so on; data concerning sleep schedules or sleep habits of the user, such as average nightly duration of sleep, typical or perceived sleep quality, time of day for sleeping, and so on; and data concerning genetic attributes or markers of the user, such as gene variants related to Alpha-Actinin-3 (ACTN3); gene variants related to Angiotensin-Converting Enzyme (ACE); gene variants related to Peroxisome Proliferator-Activated Receptor Gamma Coactivator 1-Alpha (PPARGC1A); gene variants related to Collagen Type I Alpha 1 Chain (COL1A1); gene variants related to Nuclear Factor Erythroid 2-Related Factor 2 (NRF2); gene variants related to Growth Differentiation Factor 5 (GDF5); gene variants related to Beta-2 Adrenergic Receptor (ADRB2); gene variants related to Hypoxia-Inducible Factor 1-Alpha (HIF1A); gene variants related to Fat Mass and Obesity-Associated Protein (FTO); gene variants related to Creatine Kinase, Muscle (CKM); gene variants related to Interleukin 6 (IL6); and gene variants related to Brain-Derived Neurotrophic Factor (BDNF). The supplementary data 106 may be an input for creating the digital twin, discussed later.

[0020] The system 100 includes a database 108, configured to store input information such as the body scan 102, the goal state 104, and the supplementary user data 106, and also exercise data 124 that may be acquired from electronic exercise equipment 122, discussed later. The database 108 is also configured to store output data, such as an exercise plan 114 and lifestyle/nutrition recommendations 120.

[0021] The system 100 may provide one or more outputs, including a visual representation of the digital twin 112, one or more exercise plans 114, a visual representation of exercise data 118, and the lifestyle/nutrition recommendations 120. The outputs may be provided via a user interface, such as the user interface 212 of FIG. 2, discussed later.

[0022] The visual representation of the digital twin 112 may include one or more 2-dimensional (2D) or 3-dimensional (3D) avatars or models of the user, such as renderings that depict overall body appearance and/or composition, musculature, vasculature, skeletal structure, and so on. The visual representation of the digital twin 112 may also include text, tables, graphs, charts, and other forms of representing information, for example, a chart depicting resting heart rate (RHR) and blood pressure. An example of a visual representation of the digital twin 112 is the digital twin 418 depicted in FIG. 4. The digital twin 418 comprises one or more states, such as a baseline state 402 and a goal state 406. The baseline state 402 is a digital representation of the user at a current or previous point in time. For example, the baseline state 402 may depict or describe baseline abilities or metrics of the user, such as how much weight the user can currently bench press or the user's current metabolic rate. The goal state 406 may be, for example, an embodiment of the goal state 104 of FIG. 1. For example, the goal state 406 may depict or describe desired abilities or metrics of the user, such as how much weight the user wants to bench press or a metabolic rate that the system 100 determines is ideal for the user based on, for example, the user's age, height, weight, BMI, and so on.

[0023] The visual representation of exercise data 118 may depict exercise data that is manually input by the user, and it may depict exercise data 124 that is automatically ascertained by the electronic exercise equipment 122. The visual representation of exercise data 118 may include text, tables, graphs, charts, and other forms of information representation, for example, a graph showing the user's maximum vertical leap as a function of time.

[0024] The lifestyle/nutrition recommendations 120 may include recommendations to help the user achieve the goal state 104. Lifestyle recommendations may include, for example, recommendations concerning sleep schedules, drug use, and alcohol consumption. Nutritional recommendations may include, for example, recommendations concerning macronutrient intake, eating schedules, and vitamin supplementation.

[0025] The exercise plan 114 is an overall plan for the user to achieve the goal state 104. The exercise plan may be created according to a machine-learning (ML) model trained on data from a pool, group, or population of individuals comprising at least their exercise regimens and exercise outcomes, such as particular exercises, frequency of exercise, intensity of exercise, rest periods, sets, repetitions per set, muscular loading profiles, muscle mass gains, strength gains, endurance gains, and so on. The data may further include anatomical and physiological data of the individuals in the pool, group, or population, such as height, weight, body type, biomechanical kinematics, and so on. The data may further include nutritional data of the individuals in the pool, group, or population, such as daily calorie intake and macronutrient intake. The data may include other relevant data of the individuals in the pool, group, or population, such as age and genetics (such as particular genetic markers).

[0026] One or more types of ML models may be utilized to create the exercise plan 114. For example, supervised learning models, such as linear regression or support vector machines (SVMs), may predict user performance or outcomes based on labeled datasets of past exercise routines and physiological data; unsupervised learning models, like k-means clustering, may identify patterns in user behavior or group similar users together to tailor exercise plans based on shared characteristics; reinforcement learning models may dynamically adjust exercise plans in response to real-time feedback on user performance; deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), may process complex data, including images, body scans, or time-series physiological data, to personalize exercise plans by predicting how different motion profiles will impact user fitness over time.

[0027] The exercise plan 114 is a long-term plan (e.g., days, weeks, or months) that may include one or more exercise sessions and one or more motion profiles 116. An exercise session is a discrete portion of an exercise plan 114, such as a group of exercises to be performed on a given day. A motion profile 116 comprises information concerning individual exercises or components of exercises, such as an amount of weight a user is to lift for a bicep curl, or a speed at which the user is to lift the weight. Regarding electronic exercise equipment 122, which may comprise electronic controlled motors for effectuating a given amount of resistance or a given velocity of a user-moveable component of the equipment, the motion profiles 116 may comprise one or more torques as a function of time and/or one or more velocities as a function of time.

[0028] The exercise plan 114, or portions thereof, such as the motion profiles 116, may be output, sent, or transmitted to the electronic exercise equipment 122 to physically manifest the one or more motion profiles 116 during exercise activity of the user. Physical manifestation of the one or more motion profiles 116 may comprise, for example, causing the electronic exercise equipment 122 to be programmed or configured with appropriate control instructions or parameters. The electronic exercise equipment 122 may include, for example, an electronic resistance machine, a treadmill, a stair climber, a stationary bike, an elliptical trainer, a rowing machine, an incline trainer, a recumbent bike, a stepper machine, a cross trainer, an arc trainer, a spin bike, a climbing machine, a vibration platform, a ski machine, a cable machine, or a multi-gym machine. The outputting, sending or transmitting of the motion profiles 116 may be implemented via a network interface connected to a network, such as the network interface 214, discussed later.

[0029] The system 100 includes one or more processing devices 110 for processing data stored in the database 108. The one or more processing devices 110, which may be referred to herein as a single processing device 110, may execute part or all of the ML model for creation of the exercise plan 114. For large or complex ML models (or data sets), the processing device 110 may communicate with a remote server that executes the ML model. The processing device 110 may also execute instructions for creating the visual representation of the digital twin 112, for creating the visual representation of the exercise data 118, and for creating the lifestyle/nutrition recommendations 120.

[0030] FIG. 2 is a block diagram of an example internal configuration of a computing device 200 of a system for executing personalized exercise plans based on a digital twin and electronic exercise equipment. The computing device 200, may implement the processing device 110 or the database 108 of FIG. 1; the system for executing personalized exercise plans based on a digital twin and electronic exercise equipment may be the system 100 of FIG. 1; and the exercise plans may be the one or more exercise plans 114 of FIG. 1.

[0031] The computing device 200 includes components or units, such as a processor 202, a memory 204, a bus 206, a power source 208, peripherals 210, a user interface 212, a network interface 214, other suitable components, or a combination thereof. One or more of the memory 204, the power source 208, the peripherals 210, the user interface 212, or the network interface 214 can communicate with the processor 202 via the bus 206.

[0032] The processor 202 is a central processing unit, such as a microprocessor, and can include single or multiple processors having single or multiple processing cores. Alternatively, the processor 202 can include another type of device, or multiple devices, configured for manipulating or processing information. For example, the processor 202 can include multiple processors interconnected in one or more manners, including hardwired or networked. The operations of the processor 202 can be distributed across multiple devices or units that can be coupled directly or across a local area or other suitable type of network. The processor 202 can include a cache, or cache memory, for local storage of operating data or instructions.

[0033] The memory 204 includes one or more memory components, which may each be volatile memory or non-volatile memory. For example, the volatile memory can be RAM (e.g., a DRAM module, such as DDR SDRAM). In another example, the non-volatile memory of the memory 204 can be a disk drive, a solid-state drive, flash memory, or phase-change memory. In some implementations, the memory 204 can be distributed across multiple devices. For example, the memory 204 can include network-based memory or memory in multiple clients or servers performing the operations of those multiple devices.

[0034] The memory 204 can include data for immediate access by the processor 202. For example, the memory 204 can include executable instructions 216, application data 218, and an operating system 220. The executable instructions 216 can include one or more application programs, which can be loaded or copied, in whole or in part, from non-volatile memory to volatile memory to be executed by the processor 202. For example, the executable instructions 216 can include instructions for performing some or all of the techniques of this disclosure. The application data 218 can include user data, database data (e.g., database catalogs or dictionaries), or the like. In some implementations, the application data 218 can include functional programs, such as a web browser, a web server, a database server, another program, or a combination thereof. The operating system 220 can be, for example, Microsoft Windows, Mac OS X, or Linux; an operating system for a mobile device, such as a smartphone or tablet device; or an operating system for a non-mobile device, such as a mainframe computer.

[0035] The power source 208 provides power to the computing device 200. For example, the power source 208 can be an interface to an external power distribution system. In another example, the power source 208 can be a battery, such as where the computing device 200 is a mobile device or is otherwise configured to operate independently of an external power distribution system. In some implementations, the computing device 200 may include or otherwise use multiple power sources. In some such implementations, the power source 208 can be a backup battery.

[0036] The peripherals 210 includes one or more sensors, detectors, or other devices configured for monitoring the computing device 200 or the environment around the computing device 200. For example, the peripherals 210 can include a geolocation component, such as a global positioning system location unit. In another example, the peripherals can include a temperature sensor for measuring temperatures of components of the computing device 200, such as the processor 202. In some implementations, the computing device 200 can omit the peripherals 210.

[0037] The user interface 212 includes one or more input interfaces and/or output interfaces. An input interface may, for example, be a positional input device, such as a mouse, touchpad, touchscreen, or the like; a keyboard; or another suitable human or machine interface device. An output interface may, for example, be a display, such as a liquid crystal display, a cathode-ray tube, a light emitting diode display, or other suitable display.

[0038] The network interface 214 provides a connection or link to a network. The network interface 214 can be a wired network interface or a wireless network interface. The computing device 200 can communicate with other devices via a network interface 214 using one or more network protocols, such as using Ethernet, transmission control protocol (TCP), internet protocol (IP), power line communication, an IEEE 802.X protocol (e.g., Wi-Fi, Bluetooth, or ZigBee), infrared, visible light, general packet radio service (GPRS), global system for mobile communications (GSM), code-division multiple access (CDMA), Z-Wave, another protocol, or a combination thereof.

[0039] FIG. 3 is a block diagram of an example process 300 for creating one or more states of a digital twin by a system for executing personalized exercise plans based on a digital twin and electronic exercise equipment. The system may be the system 100 of FIG. 1 and the exercise plans may be the one or more exercise plans 114 of FIG. 1.

[0040] The process 300 may receive as input 302 body scan data and physical assessment data, such as strength, speed, mobility, flexibility, cardio, reaction times, and so on. The input 302 may be stored in a database 304, which may be the database 108 of FIG. 1, and processed by a processing device 306, which may be the processing device 110 of FIG. 1. The processing device 110 may create a current state of a digital twin and output a visual representation of the current state in block 308. A first or initial current state of the digital twin may be considered a baseline state of the digital twin.

[0041] In block 310, the user may provide user-defined or user-selectable parameters, based on the current state of the digital twin, to determine a goal state. For example, the user may provide parameters such as a desired strength or size of a given muscle group or a desired time for running a mile. As another example, the user may select parameters from a recommendation list that is generated by the processing device 306.

[0042] Based on the current state of the digital twin and the user's input, the processing device 306 determines a goal state of the digital twin and an exercise plan to achieve the goal state. The goal state may be visually presented to the user in block 316. The goal state may be associated with a time duration that indicates, based on an exercise plan, how long it will take for the user to achieve the goal state. Further, the processing device 306 may determine one or more intermediate states of the digital twin, and intermediate points in time between the current time of the current state and the future time of the goal state, and the processing device may cause those intermediate states to be presented to the user, such as in blocks 312 and 314.

[0043] The intermediate states of the digital twin may be determined by simulating the current state of the digital twin according to the exercise plan, and optionally, according to lifestyle and nutrition recommendations, such as the lifestyle/nutrition recommendations 120 of FIG. 1. The digital twin comprises an anatomically simulatable anatomical model of the user, for example, simulatable kinematics according to the user's skeletal structure and muscular structure, and the digital twin comprises a physiologically simulatable physiological model of the user, for example, simulatable endurance according to the user's lung capacity, VO2 max, or muscle fiber composition.

[0044] The several states of the digital twin enable the user to visualize his expected progress from the current state to the goal state. Visualizations of the various states may comprise static or dynamic 2D or 3D models, graphs, charts, and other relevant representations of information. For example, assume the current state of the digital twin comprises a vertical leap capability of 12 inches, and the goal state of the digital twin comprises a vertical leap capability of 24 inches. Vertical leap progress may be visually represented as a graph of vertical leap on an x-axis showing 12 inches at the current time, 15 inches at the time associated with the first intermediate state, 20 inches at the time associated with the second intermediate state, and 24 inches at the time associated with the goal state. Alternatively, vertical leap progress could be represented by a graphical line drawn next to or superimposed on top of respective 3D models of the various states. Alternatively, vertical leap progress could be represented by respective animations of each of the various states of the digital twin vertically leaping to the height determined for that intermediate state of the digital twin. In some implementations, the kinematics of the animations are based on the anatomical and physiological data of the user.

[0045] FIG. 4 is a representation of an example of a graphical user interface 400 of a system for executing personalized exercise plans based on a digital twin and electronic exercise equipment. The system may be the system 100 of FIG. 1 and the exercise plans may be the one or more exercise plans 114 of FIG. 1. The graphical user interface 400 may be displayed via the user interface 212 of FIG. 2. The digital twin 418 is graphically represented by two states, a baseline state 402 and a goal state 406. In some implementations, a current state of the digital twin may be shown in addition to or in place of the baseline state of the digital twin. The right of the graphical user interface 400 includes several control and information areas, such as an area 410 for the user to input time commitments and exercise intensity; an area 412 for the user to adjust sizes and/or shapes of body areas; an area 414 for the user to establish goals regarding muscle mass, body fat percentage, running speed, endurance, vertical leap height, bicep curl strength, and so on; and an area 416 for displaying estimations of timelines for achieving various states of the digital twin, exercise plans, nutritional guidelines, and so on.

[0046] When the user provides input to the area 410, for example, a weekly time commitment for exercise, the system 100 may adjust the goal state, according to the ML model, to represent a most realistic goal state based on the time commitment. For example, the system may determine that a given goal state may not be achievable based on a time commitment of 1 hour of exercise per week, and the system may modify the goal state accordingly. Alternatively or additionally, the system may adjust the exercise plan based on the time commitment.

[0047] The graphical user interface 400 allows the user to adjust the size and/or shape of certain body areas, either via the area 412 or by direct manipulation of the digital twin. For example, a user that desires a larger bicep may directly select and manipulate, via a cursor or other suitable pointing device, a bicep 408 of the goal state. The system may highlight the bicep 404 in the current state and the bicep 408 in the goal state to emphasize differences therebetween.

[0048] To further describe some implementations in greater detail, reference is next made to an example of a technique 500 that may be performed by or using one or more computing devices for creating various states of a digital twin and one or more exercise plans. FIG. 5 is a flowchart of an example of a technique for executing personalized exercise plans based on a digital twin and electronic exercise equipment.

[0049] The technique 500 can be executed using computing devices, such as the systems, hardware, and software described or referenced with respect to FIGS. 1-4. The technique 500 can be performed, for example, by executing a machine-readable program or other computer-executable instructions, such as routines, instructions, programs, or other code. The steps, or operations, of the technique 500, or another technique, method, process, or algorithm described in connection with the implementations disclosed herein can be implemented directly in hardware, firmware, software executed by hardware, circuitry, or a combination thereof.

[0050] For simplicity of explanation, the technique 500 is depicted and described herein as a series of steps or operations. However, the steps or operations of the technique 500 in accordance with this disclosure can occur in various orders and/or concurrently. Additionally, other steps or operations not presented and described herein may be used. Furthermore, not all illustrated steps or operations may be required to implement a technique in accordance with the disclosed subject matter. The technique 500 may be performed by one or more components of a distributed computing system, such as one or more computing devices, such as the database 108 and/or the processing device 110 of FIG. 1.

[0051] The step 502 comprises creating a baseline state of a digital twin of a user based on a first 3D model of the user and first physiological data of the user. The baseline state may be the baseline state 402 of FIG. 4; the first 3D model of the user may comprise the physiological and anatomical data 103 of FIG. 1. The baseline state may be created utilizing the processing device 110 of FIG. 1. In some implementations, the digital twin comprises an anatomically simulatable anatomical model of the user and a physiologically simulatable physiological model of the user.

[0052] In some implementations, the baseline state is further on first physical-performance data of the user, for example, measurements or assessments of joint flexibility, muscle strength, muscle speed, or muscle fatigue. In some implementations, the baseline state is further based on genetic data of the user, for example, genetic markers or gene variants related to Alpha-Actinin-3 (ACTN3), Angiotensin-Converting Enzyme (ACE), Peroxisome Proliferator-Activated Receptor Gamma Coactivator 1-Alpha (PPARGC1A), Collagen Type I Alpha 1 Chain (COL1A1), Nuclear Factor Erythroid 2-Related Factor 2 (NRF2), Growth Differentiation Factor 5 (GDF5), Beta-2 Adrenergic Receptor (ADRB2), Hypoxia-Inducible Factor 1-Alpha (HIF1A), Fat Mass and Obesity-Associated Protein (FTO), Creatine Kinase, Muscle (CKM), Interleukin 6 (IL6), or Brain-Derived Neurotrophic Factor (BDNF).

[0053] The step 504 comprises creating, using a machine learning model trained on exercise activity and outcomes of other users, an exercise plan for the user, comprising one or more motion profiles, that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin. The exercise plan may be the exercise plan 114 of FIG. 1; the one or more motion profiles may comprise the motion profile 116 of FIG. 1; and the goal state of the digital twin may be the goal state 406 of FIG. 4.

[0054] In some implementations, an indication of the goal state of the digital twin may be obtained from an individual, such as the user or a fitness trainer. The indication of the goal state may correspond to the user-defined goal state comprised in user-defined or user-selected goal state 104 of FIG. 1. In some implementations, an indication of the goal state of the digital twin may be obtained from the machine-learning model. The indication of the goal state may correspond to the user-selected goal state comprised in user-defined or user-selected goal state 104 of FIG. 1. For example, the system may create several goal state options for the user and allow the user to select a desired goal state.

[0055] In some implementations, the method further comprises the steps of determining a comparison between the baseline state of the digital twin and the goal state of the digital twin; and presenting, by a graphical display, at least one of: the baseline state of the digital twin and the goal state of the digital twin, or the comparison. The comparison may be performed by a suitable processing device, such as the processing device 110 of FIG. 1. Presenting the baseline state of the digital twin and the goal state of the digital twin, or the comparison, may correspond to the visual representation of the digital twin 112 of FIG. 1. The graphical display may be implemented by the user interface 212 of FIG. 2. The comparison may comprise similarities and differences between one or more respective parameters or metrics of the baseline state and the goal state.

[0056] In some situations, a user may wish to compare his digital twin to the digital twin of another user, such as a friend or colleague, for example, for exercise gamification or competitive purposes. Accordingly, in some implementations, the method further comprises the steps of determining a comparison between at least one of the baseline state of the digital twin or the goal state of the digital twin and a state of a different digital twin of a different individual; and presenting, by a graphical display, at least one of: at least one of the baseline state of the digital twin or the goal state of the digital twin and the state of the digital twin of the different individual, or the comparison. The comparison may be performed by a suitable processing device, such as the processing device 110 of FIG. 1. Presenting the baseline state of the digital twin or the goal state of the digital twin and the state of the digital twin of the different individual, or the comparison, may correspond to the visual representation of the digital twin 112 of FIG. 1. The graphical display may be implemented by the user interface 212 of FIG. 2. The comparison may comprise similarities and differences between one or more respective parameters or metrics of the baseline state or the goal state of the user and the state of the digital twin of the different individual.

[0057] The step 506 comprises configuring an electronic exercise machine to physically manifest the one or more motion profiles during exercise activity of the user. The electronic exercise equipment may be the electronic exercise equipment 122 of FIG. 1.

[0058] The step 508 comprises acquiring, by the electronic exercise machine, exercise data based on the exercise activity. The exercise data may be the exercise data 124 of FIG. 1.

[0059] In some implementations, at least one of the goal state of the digital twin or the exercise plan may be updated based on exercise data. For example, if the exercise data indicates that the user is not gaining bicep strength at a rate predicted by simulations of the digital twin, for example, as depicted by the one or more intermediate states of the digital twin, the system, via the processing device 110, may modify the exercise plan to increase an intensity or frequency of bicep exercises. As another example, if the exercise data indicates that the user is gaining bicep strength faster than predicted by simulations of the digital twin, then the system, via the processing device 110, may modify the goal state to increase the goal size or strength of the bicep muscles or decrease the expected time to achieve the goal state.

[0060] In some implementations, the baseline state of the digital twin may be updated based on a second 3D model of the user and second physiological data of the user each acquired after acquiring the exercise data; and at least one of the goal state of the digital twin or the exercise plan may be updated based on the updated baseline state of the digital twin. This process may be referred to as re-baselining, which can help to realign the predicted exercise outcomes determined by the ML model, e.g., the intermediate and goal states of the digital twin, with real-world exercise outcomes of the user.

[0061] Some implementations of executing personalized exercise plans based on a digital twin and electronic exercise equipment disclosed herein include a method, comprising: creating a baseline state of a digital twin of a user based on a first 3D model of the user and first physiological data of the user; creating, using a machine learning model trained on exercise activity and outcomes of other users, an exercise plan for the user, comprising one or more motion profiles, that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin; configuring an electronic exercise machine to physically manifest the one or more motion profiles during exercise activity of the user; and acquiring, by the electronic exercise machine, exercise data based on the exercise activity.

[0062] In some implementations, the method further comprises: updating at least one of the goal state of the digital twin or the exercise plan based on exercise data.

[0063] In some implementations, the method further comprises: updating the baseline state of the digital twin based on a second 3D model of the user and second physiological data of the user each acquired after acquiring the exercise data; and updating at least one of the goal state of the digital twin or the exercise plan based on the updated baseline state of the digital twin.

[0064] In some implementations, the method further comprises: determining a comparison between the baseline state of the digital twin and the goal state of the digital twin; and presenting, by a graphical display, at least one of: the baseline state of the digital twin and the goal state of the digital twin, or the comparison.

[0065] In some implementations, the method further comprises: determining a comparison between at least one of the baseline state of the digital twin or the goal state of the digital twin and a state of a different digital twin of a different individual; and presenting, by a graphical display, at least one of: at least one of the baseline state of the digital twin or the goal state of the digital twin and the state of the digital twin of the different individual, or the comparison.

[0066] In some implementations, the one or more motion profiles comprise at least one of: one or more torques as a function of time; or one or more velocities as a function of time.

[0067] In some implementations, the exercise plan further comprises: indications of one or more exercise sessions each comprising at least one of the one or more motion profiles.

[0068] In some implementations, the method further comprises: creating the baseline state of the digital twin based further on first physical-performance data of the user.

[0069] In some implementations, the method further comprises: creating the baseline state of the digital twin based further on genetic data of the user.

[0070] In some implementations, the method further comprises: obtaining an indication of the goal state of the digital twin from an individual.

[0071] In some implementations, the method further comprises: obtaining an indication of the goal state of the digital twin from the machine learning model.

[0072] In some implementations, the electronic exercise machine comprises at least one of: an electronic resistance machine; a treadmill; a stair climber; a stationary bike; an elliptical trainer; a rowing machine; an incline trainer; a recumbent bike; a stepper machine; a cross trainer; an arc trainer; a spin bike; a climbing machine; a vibration platform; a ski machine; a cable machine; or a multi-gym machine

[0073] In some implementations, the first physiological data comprises at least one of: resting metabolic rate (RMR); resting heart rate; maximum heart rate during exercise; maximum oxygen uptake during exercise (VO2 max); blood pressure; blood glucose level; body mass index (BMI); body fat percentage; or respiratory exchange ratio (RER)

[0074] In some implementations, the first physical-performance data comprises at least one of: joint flexibility; muscle strength; muscle speed; or muscle fatigue.

[0075] In some implementations, the genetic data comprises at least one of: gene variants related to Alpha-Actinin-3 (ACTN3); gene variants related to Angiotensin-Converting Enzyme (ACE); gene variants related to Peroxisome Proliferator-Activated Receptor Gamma Coactivator 1-Alpha (PPARGC1A); gene variants related to Collagen Type I Alpha 1 Chain (COL1A1); gene variants related to Nuclear Factor Erythroid 2-Related Factor 2 (NRF2); gene variants related to Growth Differentiation Factor 5 (GDF5); gene variants related to Beta-2 Adrenergic Receptor (ADRB2); gene variants related to Hypoxia-Inducible Factor 1-Alpha (HIF1A); gene variants related to Fat Mass and Obesity-Associated Protein (FTO); gene variants related to Creatine Kinase, Muscle (CKM); gene variants related to Interleukin 6 (IL6); or gene variants related to Brain-Derived Neurotrophic Factor (BDNF).

[0076] In some implementations, the digital twin comprises: an anatomically simulatable anatomical model of the user; and a physiologically simulatable physiological model of the user

[0077] Some implementations of executing personalized exercise plans based on a digital twin and electronic exercise equipment disclosed herein include a system, comprising: one or more memories; and one or more processors configured to execute instructions stored in the one or more memories to: create a baseline state of a digital twin of a user based on a first 3D model of the user and first physiological data of the user; create, using a machine learning model trained on exercise activity and outcomes of other users, an exercise plan for the user, comprising one or more motion profiles, that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin; configure an electronic exercise machine to physically manifest the one or more motion profiles during exercise activity of the user; and acquire, by the electronic exercise machine, exercise data based on the exercise activity.

[0078] In some implementations, the one or more processors are configured to execute the instructions to: update at least one of the goal state of the digital twin or the exercise plan based on exercise data.

[0079] Some implementations of executing personalized exercise plans based on a digital twin and electronic exercise equipment disclosed herein include a non-transitory computer-readable medium storing instructions operable to cause one or more processors to perform operations comprising: creating a baseline state of a digital twin of a user based on a first 3D model of the user and first physiological data of the user; creating, using a machine learning model trained on exercise activity and outcomes of other users, an exercise plan for the user, comprising one or more motion profiles, that most likely effectuates a goal state of the digital twin from the baseline state of the digital twin; configuring an electronic exercise machine to physically manifest the one or more motion profiles during exercise activity of the user; and acquiring, by the electronic exercise machine, exercise data based on the exercise activity.

[0080] In some implementations, the operations further comprise: updating at least one of the goal state of the digital twin or the exercise plan based on exercise data

[0081] While the disclosure has been described in connection with certain implementations, it is to be understood that the disclosure is not to be limited to the disclosed implementations but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims, which scope is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures as is permitted under the law.