Musculoskeletal burden

Abstract

Physiological monitors use movement patterns during strength training activities, such as movement patterns detected by wearable monitors, to assess the degree of muscular, musculoskeletal, and / or biomechanical burden experienced by a user while performing strength training. The resulting burden can advantageously be quantified and used to provide coaching recommendations, update daily burden metrics, and take other responsive actions.

Description

[0001] Cross Reference to Related Applications

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 395,244, filed August 4, 2022, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present disclosure relates to physiological monitoring systems, and more specifically, to techniques for quantifying tracking musculoskeletal burden. BACKGROUND

[0004] Wearable physiological monitors can provide a wealth of physiological data from a wearer. However, the muscle burden generated during strength training can be difficult to characterize using conventional health metrics, such as heart rate or heart rate variability. There remains a need for improved methods and systems to monitor musculoskeletal burden and use quantified measures of burden to provide coaching recommendations, among other things. SUMMARY

[0005] A physiological monitor uses motion patterns during a strength training activity, e.g., motion patterns detected by a wearable monitor, to assess the degree of muscle, musculoskeletal, and / or biomechanical burden experienced by a user while performing strength training. The resulting burden can advantageously be quantified and used to provide coaching recommendations, update daily burden metrics, and take other responsive actions.

[0006] In one aspect, a computer program product disclosed herein can include computer executable code embodied in a non-transitory computer readable medium that, when executing on one or more computing devices, causes the one or more computing devices to perform the steps of: receiving raw motion data from one or more motion sensors of a wearable health monitor worn by a user during a set of one or more repetitions of a strength training activity, the raw motion data including angular rotation data from a plurality of gyroscopes and linear acceleration data from a plurality of accelerometers; fusing the raw motion data from the one or more motion sensors to mitigate gravity artifacts, thereby providing motion data including tri-axial acceleration data; identifying a type of the strength training activity; determining a number of the repetitions in the set based on a change in magnitude of the tri-axial acceleration data; for each of the repetitions, calculating a raw intensity score indicative of musculoskeletal movement based on a change in the tri-axial acceleration data; for each of the repetitions, determining a maximum intensity at which the user performed the strength training activity, the maximum intensity being indicative of an ability of the user to perform the strength training activity based on an exercise history of the user; estimating a maximum volume of the user and the strength training activity based on a history of user performance of the strength training activity, wherein the maximum volume is indicative of an upper threshold of the user to repeat the strength training activity without injury; calculating an effective load of the user during the strength training activity based on one or more load parameters, the effective load being indicative of a relative portion of the maximum volume exerted by the user during the strength training activity, the one or more load parameters including at least a body weight of the user and an added weight of the strength training activity; calculating a per-repetition musculoskeletal stress of each of the repetitions as a product of a first ratio of the effective load to the maximum volume and a second ratio of the raw intensity score to the maximum intensity; summing the per-repetition musculoskeletal stress of all repetitions in the set to provide a musculoskeletal stress score of the strength training activity; and displaying the musculoskeletal stress score of the strength training activity to the user. Other embodiments of this aspect can also or alternatively include a method that performs one or more of the above described steps. Other embodiments of this aspect can also or alternatively include a system having a wearable health monitor including one or more motion sensors and one or more processors configured to calculate a user-specific musculoskeletal stress score for a user of the wearable health monitor by performing one or more of the above described steps.

[0007] Implementations can include one or more of the following features. The computer program product can include code for causing the one or more computing devices to perform the step of generating a coaching suggestion to the user based on the musculoskeletal burden score. The coaching suggestion can be based at least in part on a health goal of the user. Calculating the raw intensity score for one of the repetitions can include calculating an average of a plurality of instantaneous intensity measurements for one of the repetitions. One or more of the plurality of instantaneous intensity measurements can be calculated based on an average of a ratio of a current acceleration change to the current acceleration. One or more of the plurality of instantaneous intensity measurements can be calculated based on a ratio of a first average of current acceleration changes to a second average of current accelerations. The computer program product can include code for causing the one or more computing devices to perform the step of creating a load repetition profile for the user based on a history of the strength training activity of the user, the load repetition profile indicating a repetition capacity of the user at one or more loads during the strength training activity. The computer program product can include code for causing the one or more computing devices to perform the step of adding a row to the load repetition profile when the user performs the strength training activity at a new load not included in the one or more loads in the load repetition profile. The computer program product can include code for causing the one or more computing devices to perform the step of updating the load repetition profile when the user exceeds a number of repetitions for one of the loads in the load repetition profile. The computer program product can include code to receive user input specifying the type of the strength training activity. The computer program product can include code for causing the one or more computing devices to perform the step of identifying the type of the strength training activity based on the raw motion data. Implementations of the technology can include hardware, a method or process, computer software on a computer-accessible medium, and a system.

[0008] In an aspect, the methods disclosed herein can include receiving movement data from one or more movement sensors of a wearable monitor worn by a user during a set of one or more repetitions of a strength training activity; identifying a type of the strength training activity; determining a number of the repetitions in the set; for each of the repetitions, computing a raw intensity score indicative of musculoskeletal movement based on a feature of the movement data, and scaling the raw intensity score relative to a maximum intensity of the user performing the strength training activity, the maximum intensity indicating an ability of the user to perform the strength training activity based on an exercise history of the user; for each of the repetitions, computing an individualized scale based on a ratio of an effective load of the user during the strength training activity to a predetermined load threshold of the user performing the strength training activity; computing a per-repetition musculoskeletal stress for each of the repetitions as a product of the per-repetition user intensity score and the individualized scale; computing a musculoskeletal stress score for the strength training activity by summing the per-repetition musculoskeletal stresses for all of the repetitions in the set; and taking an action based on the musculoskeletal stress score. Other embodiments of this aspect can also or alternatively include a computer program product including computer executable code embodied in a non-transitory computer readable medium that, when executing on one or more computing devices, causes the one or more computing devices to perform one or more of the above steps. Other embodiments of this aspect can also or alternatively include a system having a wearable health monitor including one or more movement sensors and one or more processors configured to compute a user-specific musculoskeletal stress score for a user of the wearable health monitor by performing one or more of the above steps.

[0009] Implementations can include one or more of the following features. Determining the number of repetitions in the set can include determining the number based on motion data. Determining the number of repetitions in the set can include determining the number based on user input. The action can include refining a daily load calculation for the user based on the musculoskeletal burden score. The action can include generating a coaching recommendation for the user. The method can include displaying the coaching recommendation to the user. The coaching recommendation can be a real-time coaching recommendation. The coaching recommendation can be related to a subsequent exercise activity of the user. The method can include automatically identifying the type of the strength training activity based on the motion data. The method can include calculating a plurality of musculoskeletal burden scores for each of a plurality of types of strength training activities in a workout program. The method can include calculating the effective load based on user input of a body weight of the user. The method can include calculating the effective load based on user input of an increased weight of the strength training activity. The motion data can include raw motion data from a three-axis gyroscope and a three-axis accelerometer that is fused to provide three-axis acceleration data of the repetitions while mitigating effects of acceleration due to gravity. The wearable monitor can include a wrist-worn photoplethysmography device. Receiving motion data can include receiving raw motion data from at least one gyroscope and at least one accelerometer of the wearable monitor. Calculating the musculoskeletal burden score can include calculating the musculoskeletal burden score on a personal computing device of the user that is coupled in a communicative relationship with the wearable monitor. Calculating the musculoskeletal burden score can include calculating the musculoskeletal burden score on a remote server that is coupled in a communicative relationship with the wearable monitor. The predetermined load threshold can be an estimated maximum amount that indicates an upper threshold of repetitions of the strength training activity that the user can perform without injury. Implementations of the technology can include hardware, a method or process, computer software on a computer-accessible medium, and a system.

[0010] In an aspect, the systems disclosed herein can include a wearable health monitor including one or more motion sensors; and one or more processors configured to calculate a user-specific musculoskeletal stress score for a user of the wearable health monitor by performing the steps of receiving motion data obtained from the one or more motion sensors during a strength training activity, identifying a type of the strength training activity, identifying a set of the strength training activity including one or more repetitions, for each of the repetitions, calculating a raw intensity score indicative of musculoskeletal movement based on a feature of the motion data, and scaling the raw intensity score relative to a maximum intensity at which the user performs the strength training activity to obtain a per-repetition user intensity score, the maximum intensity being indicative of the user’s ability to perform the strength training activity based on an exercise history of the user, for each of the repetitions, calculating an individualized scale based on a ratio of an effective load of the user during the strength training activity to a predetermined load threshold of the user when performing the strength training activity, calculating a per-repetition musculoskeletal stress for each of the repetitions as a product of the per-repetition user intensity score and the individualized scale, calculating a musculoskeletal stress score for the strength training activity by summing the per-repetition musculoskeletal stresses for all of the repetitions in the set, and taking an action based on the musculoskeletal stress score. Taking the action can include communicating the user-specific musculoskeletal stress score to a personal computing device associated with the user for display to the user. Taking the action can include generating a coaching recommendation for the user. Other embodiments of this aspect can also or alternatively include methods and / or computer program products.

[0011] In an aspect, the methods disclosed herein can include receiving movement data from one or more movement sensors of a wearable health monitor worn by a user during a strength training activity; calculating individualized musculoskeletal stress for the user during the strength training activity by adjusting intensity associated with the movement data according to a workout history of the user associated with the strength training activity, a load during the strength training activity, and a maximum volume of the user associated with the strength training activity; and taking an action based on the individualized musculoskeletal stress. Other embodiments of this aspect can also or alternatively include a computer program product including a computer-readable medium comprising computer-executable code that, when executed on one or more computing devices, causes the one or more computing devices to carry out one or more of the above steps. Other embodiments of this aspect can also or alternatively include a system having a wearable health monitor including one or more movement sensors and one or more processors configured to calculate a user-specific musculoskeletal stress score for a user of the wearable health monitor by carrying out one or more of the above steps.

[0012] In an aspect, the methods disclosed herein can include receiving movement data from one or more movement sensors of a wearable health monitor worn by a user during a strength training activity; calculating an original intensity score for a plurality of repetitions of the strength training activity based on the movement data; calculating an effective load for the strength training activity based on one or more load parameters, the load parameters including at least a body weight of the user and an added weight of the strength training activity; calculating an individualized musculoskeletal stress score based on a combination of the original intensity score calculated from the movement data and the effective load calculated based on the one or more load parameters; and presenting information to the user based on the individualized musculoskeletal stress score. Other embodiments of this aspect can also or alternatively include a system having a wearable health monitor including one or more movement sensors and one or more processors configured to calculate a user-specific musculoskeletal stress score for a user of the wearable health monitor by carrying out one or more of the above steps. BRIEF DESCRIPTION OF DRAWINGS

[0013] The foregoing and other objects, features, and advantages of the devices, systems, and methods described herein will be apparent to those skilled in the art from the following description of particular embodiments thereof, as shown in the accompanying drawings. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the devices, systems, and methods described herein. In the drawings, like reference numerals generally refer to corresponding parts throughout.

[0014] Figure 1 A physiological monitoring device is shown.

[0015] Figure 2 A physiological monitoring system is shown.

[0016] Figure 3 A sensing system is shown.

[0017] Figure 4 Methods for generating and using musculoskeletal (MSK) loading data are shown.

[0018] Figure 5 Loading repetition profiles for scaling exercise repetition intensity are shown.

[0019] Figure 6 A graph of velocity measured during a bench press exercise over time is shown.

[0020] Figure 7 Three-axis acceleration data for one repetition of a bench press exercise is shown.

[0021] Figure 8 An integral of normalized acceleration amplitude from data Figure 7 is shown.

[0022] Figure 9 A system for monitoring MSK burden is shown.

[0023] Figure 10 A system for monitoring MSK burden is shown.

[0024] Figure 11 A system for monitoring MSK burden is shown.

[0025] Figure 12 A user interface for a strength training system with MSK burden score is shown.

[0026] Figure 13 A user interface for a strength training system with MSK burden score is shown. DETAILED DESCRIPTION

[0027] Embodiments will now be described more fully with reference to the accompanying drawings, in which preferred embodiments are shown. However, the foregoing can be implemented in any number of different forms, and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided as illustrative examples so as to convey the scope of the disclosure to the skilled person.

[0028] All documents mentioned herein are hereby incorporated by reference in their entirety. References to singular shall include the plural and vice versa unless otherwise explicitly specifically indicated. Grammatical conjunctions are intended to express any and all transitive and intransitive combinations of conjunctive phrases, clauses, sentences, words, and the like, unless otherwise specifically indicated or clear from the context.

[0029] Unless otherwise indicated, the enumeration of numerical ranges herein is not intended to be limiting, but rather to individually refer to any and all values falling within that range, and each individual value within such ranges is incorporated into the specification as if it were individually enumerated herein. As will be appreciated by one of ordinary skill in the art, the words "about," "approximately," and the like, when used in connection with a numerical value, should be interpreted as indicating a deviation, satisfactory for the intended or stated purpose. Similarly, approximating language, such as "about" or "substantially" when used in connection with a physical property, such as "approximately" or "substantially," should be understood to refer to a range of deviation, satisfactory for the corresponding use, function, purpose, etc., as will be appreciated by one of ordinary skill in the art. Values and / or numerical ranges provided herein are provided only as examples, and do not constitute a limitation on the scope of the described embodiments. Where a range of values is provided, they are intended to include every value within that range, as if such values were individually stated, unless an expressly contrary intention is indicated. The use of any and all examples, or exemplary language (e.g., "such as" "for instance" and the like) provided herein, is intended merely to better illuminate embodiments and does not pose a limitation on the scope of the disclosed embodiments. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the embodiments.

[0030] In the following description, it is understood that terms such as "first," "second," "top," "bottom," "upper," "lower," "over," "under," and the like, are words of convenience and are not to be construed as limiting terms unless otherwise indicated by specific context.

[0031] As used herein, the term "user" refers to any type of animal, human or non-human, whose physiological information can be monitored using the exemplary wearable physiological monitoring system.

[0032] The term "continuous" as used herein in connection with heart rate data refers to the collection of heart rate data at a sufficient frequency to enable detection of an individual's heartbeats, and also refers to the collection of heart rate data over an extended period such as an hour, a day, or longer, including all day and night collection. More generally, with respect to physiological signals that can be monitored by a wearable device, "continuous" or "continuously" will be understood to mean continuously at a rate and duration suitable for intended time-based processing, and physically at a rate (e.g., multiple times per heartbeat, breath, etc.) sufficient to resolve desired physiological characteristics such as heart rate, heart rate variability, heart rate peak detection, pulse shape, etc. At the same time, continuous monitoring is not intended to exclude ordinary data collection interruptions, such as temporary displacement of the monitoring hardware due to sudden movement, changes in external lighting, loss of power, physical manipulation and / or adjustment by the wearer, physical displacement of the monitoring hardware due to external forces, etc. It will also be noted that, in this context, heart rate data or monitored heart rate can more generally refer to raw sensor data such as light intensity signals, or data processed therefrom, such as heart rate data, signal peak data, heart rate variability data, or any other physiological or digital signal suitable for recovering heart rate information as contemplated herein. Further, such heart rate data can generally be captured over some historical period, which can be subsequently correlated with various other data or metrics, for example related to sleep state, identified exercise activity, resting heart rate, maximum heart rate, etc.

[0033] The term "computer-readable medium" as used herein refers to a non-transitory storage medium that is not a signal, such as hardware, storage devices, computer memory accessible by a controller, microcontroller, microprocessor, computing system, and / or any other module or component of a computing system to encode thereon computer-executable instructions, software programs, and / or other data. The "computer-readable medium" is accessed by a computing system or module of a computing system to retrieve and / or execute the computer-executable instructions or software programs encoded on the medium. Non-transitory computer-readable media can include, but are not limited to, one or more types of hardware memory, non-transitory tangible media (e.g., one or more magnetic storage disks, one or more optical disks, one or more USB flash drives), virtual or physical computer system memory, physical memory hardware such as random access memory (e.g., DRAM, SRAM, EDO RAM), etc. Although not depicted, any of the devices or components described herein can include a computer-readable medium or other memory for storing program instructions, data, etc.

[0034] Figure 1A physiological monitoring system is shown. The system 100 can include a wearable monitor 104 configured for physiological monitoring. The system 100 can also include a removable and replaceable battery 106 for recharging the wearable monitor 104. The wearable monitor 104 can include a strap 102 or other holding system(s) for securing the wearable monitor 104 in position on the wearer's body for collecting physiological data as described herein. For example, the strap 102 can include an elongated elastic band formed of any suitable elastic material, such as rubber or textile polymer fibers, e.g., textile polyester, polypropylene, nylon, spandex, etc. The strap 102 can be adjustable to accommodate different wrist sizes and can include any latches, clasps, etc. to secure the wearable monitor 104 in the desired position for monitoring physiological signals. While a wrist-worn device is depicted, it will be appreciated that the wearable monitor 104 can be configured for positioning on the user's body in any suitable location based on the sensing modality and the nature of the signals to be acquired. For example, the wearable monitor 104 can be configured for use on the wrist, ankle, bicep, chest, or any other suitable location(s), and the strap 102 can be or include a belt or other elastic band within clothing or accessories, etc. The wearable monitor 104 can also or instead be structurally configured to be placed on or within clothing, e.g., permanently or in a removable and replaceable manner. To this end, the wearable monitor 104 can be shaped and sized to be placed within a pocket, slot, and / or other housing that is coupled to or embedded within clothing. In such configurations, the pocket or other holding arrangement on the clothing can include a sensing window or the like so that the wearable monitor 104 can operate when placed in use in the clothing. U.S. Patent No. 11,185,292 describes non-limiting example embodiments of suitable wearable monitors 104 and is incorporated by reference herein in its entirety.

[0035] System 100 may include any hardware components, subsystems, etc., to support various functions of the wearable monitor 104, such as data collection, processing, display, and communication with external resources. For example, system 100 may include hardware for a heart rate monitor that uses, for example, photoplethysmography, electrocardiography, or one or more other techniques. System 100 may be configured such that when the wearable monitor 104 is used while placed around the wrist (or in some other body position), system 100 initiates the acquisition of physiological data from the wearer. In some embodiments, pulse or heart rate may be acquired optically based on a light source (e.g., a light-emitting diode (LED)) and optical detectors in the wearable monitor 104. The LED may be positioned to direct illumination toward the user's skin, and optical detectors such as photodiodes may be used to capture measurements of illumination intensity indicating the illumination reflected and / or transmitted from the wearer's skin to the LED.

[0036] System 100 can be configured to record other physiological and / or biomechanical parameters, including but not limited to skin temperature (using a thermometer), conductance of skin (using a conductance of skin sensor), motion (using one or more multi-axis accelerometers and / or gyroscopes), blood pressure, and environmental or contextual parameters such as ambient light, ambient temperature, humidity, time of day, etc. For example, wearable monitor 104 may include sensors such as accelerometer and / or gyroscope sensors for motion detection, sensors for ambient temperature sensing, sensors for measuring conductance of skin activity (EDA), sensors for measuring conductance of skin response (GSR), etc. System 100 may also or alternatively include other systems or subsystems supporting additional functionality of wearable monitor 104. For example, system 100 may include communication systems supporting, for example, near-field communication, proximity sensing, Bluetooth communication, Wi-Fi communication, cellular communication, satellite communication, etc. Wearable monitor 104 may also or alternatively include components such as a geolocation system (GPS), a display and / or user interface, a clock and / or timer, etc.

[0037] Wearable monitor 104 may include one or more battery power sources, such as a first battery within wearable monitor 104 and a second battery 106 removable and replaceable from wearable monitor 104 for recharging the batteries in wearable monitor 104. Additionally or alternatively, system 100 may include multiple wearable monitors 104 (and / or other physiological monitors) that may share battery power or provide power to each other. System 100 can perform various functions related to continuous monitoring, such as automatically detecting when a user is asleep, awake, exercising, etc., and this detection may be performed locally at wearable monitor 104 or at a remote service communicatively coupled to and receiving data from wearable monitor 104. Generally, system 100 can support continuous, independent monitoring of physiological signals such as heart rate, and the acquired data may be stored on wearable monitor 104 for an extended period until it can be uploaded to a remote processing resource for more complex computational analysis.

[0038] In one respect, wearable monitors can be wrist-worn photoplethysmography devices.

[0039] Figure 2 A physiological monitoring system is shown. More specifically, Figure 2 A physiological monitoring system 200 is shown that can be used with any of the methods or devices described herein. Generally, system 200 may include a physiological monitor 206, a user device 220, a remote server 230 with remote data processing resources (such as any processor or processing resources described herein), and one or more other resources 250, all of which may be interconnected via a data network 202.

[0040] Data network 202 can be any data network described herein. For example, data network 202 can be any network(s) or interconnection network(s) suitable for transmitting data and information between participants in system 200. This can include public networks such as the Internet, private networks, telecommunications networks such as the public switched telephone network, or cellular networks using third-generation (e.g., 3G or IMT-200), fourth-generation (e.g., LTE (E-UTRA) or WiMAX-Advanced (IEEE 802.16m)), fifth-generation (e.g., 5G) and / or other technologies, as well as any various enterprise area or local area networks that can be used to transmit data between participants in system 200, and other switches, routers, hubs, gateways, etc. This can also include local or short-range communication infrastructure suitable for, for example, coupling physiological monitor 206 to user equipment 220 or supporting communication with local resources. As a non-limiting example, short-range communication can include Wi-Fi communication, Bluetooth communication, infrared communication, near-field communication, communication with RFID tags or readers, etc.

[0041] The physiological monitor 206 can typically be any physiological monitoring device or system, such as any wearable monitor or other monitoring device or system described herein. In one aspect, the physiological monitor 206 can be a wearable physiological monitor shaped and sized to fit on the wrist or other body position. The physiological monitor 206 may include a wearable housing 211, a network interface 212, one or more sensors 214, one or more light sources 215, a processor 216, a haptic device 217 or other user input / output hardware, a memory 218, and a strip 210 for holding the physiological monitor 206 in a desired position on the user. In one aspect, the physiological monitor 206 can be configured to acquire heart rate data and / or other physiological data from the wearer in an intermittent or substantially continuous manner. In another aspect, the physiological monitor 206 can be configured to support extended, continuous acquisition of physiological data, such as over several days, a week, or longer.

[0042] The network interface 212 of the physiological monitor 206 can be configured to couple the physiological monitor 206 to one or more other components of the system 200 in a communication relationship, directly (e.g., via a cellular data connection) or indirectly via a short-range wireless communication channel to a wireless access point, router, computer, laptop, tablet, cellular phone, or other device capable of locally processing data, and / or relay data from the physiological monitor 206 to a remote server 230 or (one or more) other resources 250, which is necessary or helpful for acquiring and processing data from the physiological monitor 206.

[0043] One or more sensors 214 may include any of the sensors described herein, or any other sensor or subsystem suitable for physiological monitoring or supporting functions. By way of example and not limitation, one or more sensors 214 may include one or more of the following: light source, optical sensor, accelerometer, gyroscope, temperature sensor, skin conductance response sensor, capacitive sensor, resistive sensor, environmental sensor (e.g., for measuring ambient temperature, humidity, lighting, etc.), geolocation sensor, GPS, proximity sensor, RFID tag reader and RFID tag, time sensor, skin conductance activity sensor, etc. One or more sensors 214 may be disposed in wearable housing 211, or otherwise positioned and configured for physiological monitoring or other functions described herein. In one aspect, one or more sensors 214 include a light detector configured to provide light intensity data to processor 216 (or remote server 230) for calculating heart rate and heart rate variability. One or more sensors 214 may also, or alternatively, include accelerometers, gyroscopes, etc., configured to provide motion data to processor 216, for example, for detecting activities such as sleep states, rest states, wake-up events, exercise, and / or other user activities. In implementation, one or more sensors 214 may include sensors for measuring a user's skin conductance response. One or more sensors 214 may also, or alternatively, include electrodes for capturing electronic signals, for example, to obtain an electrocardiogram and / or other electrically derived physiological measurements.

[0044] Processor 216 and memory 218 can be any processor and memory described herein. In one aspect, memory 218 can store physiological data obtained by monitoring a user with one or more sensors 214, and / or any other sensor data, program data, or other data useful for the operation of physiological monitor 206 or other components of system 200. It will be understood that although only memory 218 on the physiological monitor is shown, any other device or component(s) of system 200 may or alternatively include memory for storing program instructions, raw data, processed data, user input, etc. In one aspect, processor 216 of physiological monitor 206 can be configured to obtain heart rate data from the user, such as heart rate data including or based on raw data from sensor 214. Processor 216 can also or alternatively be configured to determine or assist in determining user conditions related to, for example, health, physical fitness, fatigue, recovery sleep, or any other condition described herein.

[0045] One or more light sources 215 may be coupled to the wearable housing 211 and controlled by a processor 216. At least one light source 215 may be directed toward the user's skin adjacent to the wearable housing 211. Light from the light source 215, or more generally, light of one or more wavelengths from the light source 215, may be detected by one or more sensors 214 and processed by the processor 216 as described herein.

[0046] System 200 may also include a remote data processing resource executing on a remote server 230. The remote data processing resource may include any processor and associated hardware described herein and may be configured to receive data transmitted from the memory 218 of the physiological monitor 206 and process the data to detect or infer physiological signals of interest, such as heart rate, heart rate variability, respiratory rate, pulse oxygen saturation, blood pressure, etc. The remote server 230 may also, or alternatively, assess the user's condition, such as recovery status, sleep status, exercise activity, type of exercise, sleep quality, daily activity load, and any other health or health condition that can be detected based on such data.

[0047] System 200 may include one or more user devices 220 that can work with physiological monitor 206, for example, to provide displays for user data and analysis, or more generally, user input / output, and / or to provide communication bridges from the network interface 212 of physiological monitor 206 to data network 202 and remote server 230. For example, physiological monitor 206 may communicate locally with user device 220 (e.g., a user's smartphone) via short-range communication (e.g., Bluetooth) for data exchange between physiological monitor 206 and user device 220, and user device 220 may further communicate with remote server 230 via data network 202 to forward data from physiological monitor 206 and receive analysis and results from remote server 230 for presentation to the user. In one aspect, user device(s) 220 may support physiological monitoring by processing or preprocessing data from physiological monitor 206 to support the extraction of heart rate or heart rate variability data from the raw data obtained from physiological monitor 206. On the other hand, computationally intensive processing can be advantageously performed at a remote server 230, which can have greater storage and processing power than the physiological monitor 206 and / or user equipment 220.

[0048] User device 220 may include one or more suitable computing devices, including but not limited to smartphones, desktop computers, laptop computers, network computers, tablets, mobile devices, portable digital assistants, cellular phones, portable media or entertainment devices, or any other computing devices described herein. User device 220 may provide a user interface 222 for user access to data and analysis, and / or support user control of the operation of physiological monitor 206. User interface 222 may be maintained by one or more applications running locally on user device 220, or user interface 222 may be remotely served and presented on user device 220, for example, from remote server 230 or one or more other resources 250.

[0049] Typically, remote server 230 may include data storage, network interface, and / or other processing circuitry. Remote server 230 may process data from physiological monitor 206 and perform physiological and / or health monitoring / analysis or any other analysis described herein (e.g., analyzing sleep, determining fatigue, assessing recovery, etc.), and may host a user interface for, for example, remotely accessing that data from user device 220. Remote server 230 may include a web server or other programmable front-end that facilitates network-based access by user device 220 or physiological monitor 206 to remote server 230 or other components of system 200.

[0050] System 200 may include other resources 250, such as any resources that can be effectively used in the devices, systems, and methods described herein. For example, these other resources 250 may include other data networks, databases, processing resources, cloud data storage, data mining tools, computing tools, data monitoring tools, algorithms, and so on. In another aspect, other resources 250 may include one or more management or programming interfaces for human participants such as programmers, researchers, commentators, editors, analysts, coaches, etc., to interact with any of the foregoing. Other resources 250 may also, or alternatively, include any other software or hardware resources that can be effectively used in networked applications as envisioned herein. For example, other resources 250 may include a payment processing server or platform for authorizing payment access, content, or option / feature purchases. In another aspect, other resources 250 may include certificate servers or other security resources for third-party authentication, data encryption or decryption, etc. On the other hand, other resources 250 may include desktop computers or similar devices that are co-located with user equipment 220, wearable strip 210, or remote server 230 (e.g., on the same local area network as user equipment 220, wearable strip 210, or remote server 230, or directly coupled via a serial or USB cable). In this case, other resources 250 can provide supplementary functionality to components of system 200, such as firmware upgrades, user interface, and storage and / or preprocessing of data from physiological monitor 206 before transmission to remote server 230.

[0051] Other resources 250 may also or alternatively include one or more web servers that provide network-based access to and from any other participant in system 200. Although depicted as separate network entities, it will be readily understood that other resources 250 (e.g., web servers) may also or alternatively be logically and / or physically associated with one of the other devices described herein, and may include, for example, a user interface 222 for network access to remote server 230 or database or (one or more) other resources, to facilitate user interaction via data network 202, such as from physiological monitor 206 or user device 220.

[0052] On the other hand, other resources 250 may include health equipment or other health infrastructure. For example, a strength training machine may automatically record repetitions and / or increases in weight during repetitions, which may be wirelessly accessed by a physiological monitor 206 or some other user device 220. More generally, a gym may be configured to track user movement from one machine to another and report activity from each machine to track various strength training activities in a trial. Other resources 250 may also or alternatively include other monitoring devices or infrastructure. For example, system 200 may include one or more cameras to track the movement of a user's free weight and / or body position during repetitive strength training activities, etc. Similarly, a user may wear or embed tracking references in clothing, such as visually distinguishable objects for image-based tracking, or radio beacons for other tracking. On the other hand, the weight itself may be equipped, for example, with sensors to record and transmit detected motion, and / or beacons, etc., to self-identify type, weight, etc., to facilitate automatic detection and tracking of exercise activities with other connected devices.

[0053] Figure 3 A sensing system is illustrated. Generally, system 300 may include a physiological monitor 302 with a processor 304, a light source 306, a first photodetector 308, a second photodetector 310, one or more accelerometers 312, one or more gyroscopes 318, and any other hardware or other components and systems suitable for physiological monitoring as described herein. The physiological monitor 302 may be positioned for use against a surface 313 of a user's skin 314, wherein the light source 306 and sensors 308, 310 may contact the skin 314 to acquire physiological data. Although not depicted, it will be understood that the physiological monitor 302 can typically be held in place using any strips, clothing, etc., described herein.

[0054] Processor 304 may be any microprocessor, microcontroller, application-specific integrated circuit or other processing circuit or combination thereof, suitable for controlling the operation of the physiological monitor and acquiring physiological data.

[0055] Light source 306 may include one or more light-emitting diodes or other illumination sources and may be located within physiological monitor 302 such that when physiological monitor 302 is placed on skin 314 for use, light source 306 directs illumination toward skin 314, and the illumination is reflected back to sensors 308, 310, as indicated by arrow 316, at which intensity can be measured. In one aspect, light source 306 may include light-emitting diodes that emit light in the infrared or near-infrared wavelength range, which provides good light transmission through human skin, facilitating low-power transmission of measurable illumination to sensors 308, 310, although other illumination sources and wavelengths may also be used or alternatively.

[0056] When the physiological monitor 302 is placed on the skin 314 for use, sensors 308 and 310 can be oriented to contact the skin 314 and positioned such that sensors 308 and 310 can capture illumination reflected and / or transmitted from the skin by the light source 306. Generally, sensors 308 and 310 may include photodiodes, photodetectors, or one or more other sensors that respond to illumination from the light source 306. This can include broadband optical sensors, narrowband optical sensors, filtered sensors, etc. Generally, the first sensor 308 may be positioned closer to the light source 306 than the second sensor 310 to detect different intensities in one or more of the measured wavelengths. For example, the first sensor 308 may be located 1-4 mm from the light source 306, and the second sensor 310 may be located 2-8 mm from the light source, or approximately twice the distance of the first sensor 310 from the light source 306.

[0057] Depending on factors such as the intensity of light source 306, the sensitivity of sensors 308 and 310, the contact force of physiological monitor 302 on skin 314, the degree of ambient light intrusion, and the physiological measurement / characteristic of interest, other spacing may or may be used. In one aspect, sensors 308 and 310 may be arranged linearly in a straight line away from light source 306. While this provides consistency in comparative measurements, it is not strictly required, and sensors 308 may be displaced in any direction away from light source 306, as long as they all contact skin 314 in a manner that allows capture of light passing through skin 314 from light source 306. In another aspect, physiological monitor 302 may include one or more other light sources and / or light sensors, which may be arranged to improve accuracy and / or provide redundancy for contact detection, or to support other measurements, such as oxygenation or skin thickness. This may include light sources / sensors using different wavelength ranges, different illumination modes, etc. On the other hand, the two sensors 308 and 310 can be located at different distances from the perimeter of the physiological monitor 302, so that the sensors 308 and 310 can acquire different intensity values ​​of ambient light incident on the skin and transmitted to the sensors 308 and 310 through the skin.

[0058] In operation, the processor 304 can acquire raw intensity data from the sensors 308 and 310 and perform local calculations, such as preprocessing raw data for heart rate measurement or assessing whether the physiological monitor 302 is correctly positioned for use on the skin 314.

[0059] Accelerometer 312 may include, for example, one or more single-axis or multi-axis accelerometers that can effectively measure the motion of physiological monitor 302 to support calculations such as automated activity detection, device on / off assessment, and musculoskeletal activation levels, for example, as described herein. Other motion and orientation sensing hardware—such as one or more gyroscopes 318, inertial motion sensors, and / or other microelectromechanical systems (MEMS) sensors—may also be used for these purposes, or alternatively. More generally, physiological monitor 302 may include any additional components, subsystems, etc., adapted to support physiological monitoring and contextual data acquisition in the various modes described herein.

[0060] A method for calculating a load score based on heart rate is described by way of non-limiting example in U.S. Patent 11,185,292, the entire contents of which are incorporated herein by reference. In one aspect, this document discloses additional methods and systems for estimating musculoskeletal load based on movement patterns in a monitoring device, and using that load to provide improved load analysis, coaching advice, etc. Musculoskeletal (MSK) load captures a type of exertion that may be missed or underestimated when load is estimated based solely on heart rate. Motion data from wearable devices (e.g., accelerometer or gyroscope data) can advantageously be used to fill this gap and estimate muscle load based on various motion parameters during strength training activities. While users may record weight, repetitions, and subjective load, direct, objective measurement of MSK load advantageously reduces the user's manual data input, mitigates underreporting of high-load events, eliminates subjective variability in load calculation, and so on. In one aspect, the disclosed techniques include objectively quantifying the effort of strength training exercises (and other activities) and reporting corresponding load metrics that can be used to understand the physiological effects of strength training activities. On the other hand, the disclosed techniques can be used to create coaching metrics, refine cardiac-based load estimates, and so on. Furthermore, the disclosed techniques can be used to monitor whether exercise techniques or metrics—for example, the weights currently used in strength training exercises—are appropriate given the intended training stimulus and / or user goals (e.g., body shaping, gain, weight loss, etc.).

[0061] Figure 4 A method for calculating musculoskeletal (MSK) load scores is illustrated. Method 400 can be deployed on any device and system, such as those described herein, and can be equipped with computer code to perform some or all of the following steps. MSK load can be assessed in two parts—volume and intensity. As described herein, an objective measurement of MSK load can be obtained by developing metrics for measuring each of these components during strength training activities and combining them into a single MSK load score that can be reported to the user and / or used for coaching advice, etc.

[0062] In the context of strength training, "volume" generally refers to the total amount of work completed within a given workout or specific time period. There are different ways to calculate volume, but a common method is to multiply the number of sets for a particular exercise by the number of repetitions per set, and then multiply that by the weight lifted per repetition. For example, for 3 sets of 10 repetitions of 100 pounds, the volume would be 3000 pounds (3 sets x 10 repetitions x 100 pounds). Another way to consider volume is to simply count the number of sets or repetitions for a particular muscle group or exercise in the workout. For example, for 5 sets of 5 repetitions on the bench press, the volume would be 25 repetitions (5 sets x 5 repetitions). Managing volume is crucial in strength training because it has a significant impact on recovery and progress. Too much volume can lead to overtraining and an increased risk of injury, while too little volume may not provide sufficient stimulation for growth and improvement.

[0063] As described below, by determining, for example, the effective load of a user's exercise and comparing it to the user's maximum, the quantity—the total work performed in a strength training activity—can be objectively quantified for a particular user. The effective load can be based on other objective parameters, such as the physical weight the user lifts (e.g., pounds on a barbell, pounds on hand weights, pounds on a strength machine, etc.) or the user's body weight (which may affect exercises such as push-ups, squats, pull-ups, etc., where the user's weight provides some or all of the load), or some combination of these (e.g., the user performing pull-ups with an additional 10 pounds of weight). The maximum quantity for a user can be estimated based on, for example, a statistical estimate of the number of repetitions at a specific weight / volume where injury is more likely.

[0064] The concept of intensity presents different computational challenges. In strength training, "intensity" typically refers to the amount of effort or load exerted relative to maximum capacity, or how difficult a particular load is for a particular individual. This is often defined as a percentage of one-repetition maximum (1RM), which is the maximum weight that can be lifted in one repetition of a particular exercise. For example, if a user has a 1RM for a 200-pound bench press and is lifting 150 pounds, the user is training at 75% of their 1RM (150 divided by 200). Another way to measure intensity, especially with methods like High-Intensity Interval Training (HIIT), is through perceived effort or how difficult the exercise feels. This can be somewhat subjective, but tools like the Borg Perceived Effort Level (RPE) scale can help quantify it.

[0065] To capture intensity (e.g., muscle capacity measured relative to a maximum), physical movement during exercise can be tracked by a wearable monitor and used to objectively calculate motion-based intensity for a specific user and exercise type. Because different users have different abilities, this motion-based metric can be scaled based on the user's exercise history to determine how much effort the user has exerted relative to a maximum during the exercise. In some cases, synthesizing intensity based on other data can also be useful. For example, some exercises may not involve movement that a wearable monitor can detect, such as training on a leg curl or leg extension machine while using a wrist-worn monitor. In these cases, the user can report the weight and repetitions, and intensity can be estimated based on the user's history. On the other hand, some exercises do not involve movement at all. For example, isometric exercises, such as planks or wall sits, require holding a static position. For these exercises, "repetitions" can be derived based on the amount of time the exercise is performed. For example, a plank can be represented as one repetition every six seconds. In some cases, both techniques can be used, for example, when a user is performing an isometric exercise that loads muscle groups whose movement cannot be detected at the wearable monitor's location (e.g., jerking due to load). In other cases, muscle tremors caused by isometric loads can be detected by wearable monitors and used to assess the load, even if the user does not intend to exercise.

[0066] The following describes an example method for calculating musculoskeletal load based on objective measurements of intensity and quantity.

[0067] As shown in step 404, the method may include receiving user data. In one aspect, this may include receiving input from the user, such as body weight, weight gain, and other parameters used to evaluate strength training activities. This may also include manually entered information, such as the weight, repetitions, and type of one or more strength training activities. For manual data input, this may be entered by the user on their device before, during, and / or after the exercise, or it may be entered on a wearable monitor with a suitable user interface for the corresponding data input. For some activities, it may be difficult, impossible, or inconvenient for a wearable monitor to track the exercise. For example, a user performing isometric exercises that do not apply load to muscles near the wearable monitor may find it difficult or impossible to measure automatically with a wearable monitor. In these cases, the user may manually enter some or all of the relevant data to support MSK load analysis of the exercise.

[0068] On the other hand, some or all of the user data describing a particular trial or strength training activity can be automatically derived from motion data acquired, for example, by a wearable monitor or smart fitness device. For instance, a wearable monitor can detect the type of activity based on characteristics of the motion data acquired by the wearable monitor during exercise. The wearable monitor can also, or alternatively, detect individual repetitions within a set. Alternatively, the user can provide input for each repetition or each set to segment the activity, which can be used by any system such as those described herein to more easily identify sets and repetitions within those sets.

[0069] On the other hand, data can be obtained from other devices. For example, a strength training machine can count repetitions and wirelessly or otherwise report these repetitions to a wearable monitor or other user device. The strength training machine can also, or alternatively, report the weight of a specific set of repetitions, which can be retrieved by the wearable monitor or other device and used to support MSK load calculations as described herein. On the other hand, a camera can be used to track user movement and / or the device and can be used to derive strength training data from camera images. For example, image processing can be applied to identify activity, count repetitions, evaluate form, identify added weight, etc. On the other hand, weights can be fitted or tagged to support the direct acquisition of motion data, weight data, etc., from the weights. Combinations can also be used. For example, a camera can be used to count repetitions while weights are tagged to allow for automatic identification to determine the load.

[0070] In one aspect, user data includes a user's historical exercise data. This can be retrieved, for example, from a remote server or other resource, and can be used to support MSK score calculation. For example, this can include retrieving a user's load repetition profile based on their historical strength training activities, such as... Figure 5 The load repetition profile is shown. A load repetition profile typically indicates a user's repetition capacity at one or more loads during a strength training activity and can be used to scale a user's raw intensity based on motion data from a wearable device. While the use of repetition velocity to detect proximity to a maximum value is known in the art, the load repetition profile contemplated herein can advantageously utilize acceleration data to facilitate intensity estimation using data from sensors in the wearable device. If no load repetition profile is available to the user, method 400 may include creating a load repetition profile. Method 400 may also include updating the profile appropriately. For example, the method may include adding rows to the load repetition profile when the user performs a strength training activity at a new load not included in one or more loads in the load repetition profile. Method 400 may also, or alternatively, include adding columns when the user performs a new number of repetitions, or updating the load repetition profile when the user exceeds the number of repetitions or load within the load repetition profile.

[0071] On the other hand, a user's maximum load can be retrieved, or it can be estimated based on other retrieved user data. Calculating the maximum load for exercise can be complex and personalized, as it depends on various factors such as current fitness level, specific exercise, training goals, and how the user responds to different training volumes. As used in this paper, the maximum load aims to provide an upper limit threshold for a user's non-injury repetitive strength training activities. Several techniques can be used to estimate this threshold. For example, in the absence of specific user data, linear regression can be used on a user group to derive a formula for the maximum load related to body weight (maximum load = a * body weight + b), which can be used as an estimate before other user data becomes available. For a large, user-specific sample, the maximum load for a safe exercise can be effectively calculated as the baseline or average load for each trial plus twice the standard deviation of the trial load. On the other hand, a range of techniques can be used based on how many user-specific volume measurements are available. More generally, any useful techniques for estimating a threshold or limit for non-injury loads, such as striving to reach or fall below a threshold that presents an acceptable risk of injury, can be used to calculate the maximum load for scaling the volume of each trial, as described in this paper.

[0072] As shown in step 406, the method may include receiving motion data. For example, this may include receiving raw motion data from one or more motion sensors of a wearable monitor, such as a wearable health monitor worn by a user during a set of one or more repetitions of strength training activities. The raw motion data may include raw motion data from at least one gyroscope and at least one accelerometer of the wearable monitor. More generally, the raw motion data may include any motion data from the motion sensors, including angular rotation data from multiple gyroscopes and linear acceleration data from multiple accelerometers. On the other hand, receiving motion data may include receiving motion data from multiple body positions, for example, in the case where the user has dual wristbands and / or anklebands, and / or in the case where the user is wearing smart clothing with appropriate motion sensors at various body positions. Motion data may also be received, or alternatively, from other sources, such as other external motion sensors, smartwatches or other wearable computing devices, external cameras for measuring motion, etc.

[0073] As shown in step 408, method 400 may include processing motion data.

[0074] In one aspect, this can include fusing raw motion data from one or more motion sensors to mitigate gravity artifacts, thus providing motion data that includes triaxial acceleration data. Data fusion, especially using sensor fusion techniques, can help mitigate the effects of gravity on accelerometer measurements. Triaxial accelerometers measure both dynamic acceleration (generated by motion) and static acceleration (the constant force of gravity pulling the device downwards). To separate gravity-induced artifacts from motion-related data, other sensors, such as gyroscopes or magnetometers, can be used in conjunction with the accelerometer. A popular technique for this is to use a Kalman filter or extended Kalman filter, a recursive algorithm that uses a series of measurements observed over time (in this case, readings from the accelerometer and gyroscope / magnetometer) and produces estimates of unknown variables that tend to be more accurate than those based on any single measurement. Another common technique is to use complementary filters, such as Mahony or Madgwick filters. These algorithms combine accelerometer and gyroscope data to provide more stable, accurate, and drift-free orientation measurements, even under constant gravity. More generally, by acquiring readings from multiple sensors and combining them, it is possible to separate the measured acceleration into acceleration due to motion and acceleration due to gravity, thereby mitigating the influence of gravity artifacts on accelerometer measurements. Any such technique can be used to process motion data and obtain the triaxial acceleration data described herein.

[0075] Generally, the motion data used in this article can refer to raw motion data from sensors, fused motion data as described above, filtered motion data, or any other raw or processed data representing the wearer's motion from a wearable monitor. Therefore, in one aspect, motion data can include raw motion data from a three-axis gyroscope and a three-axis accelerometer. In another aspect, motion data can include any such raw data that has been fused to provide repeatable three-axis acceleration data, mitigating the effects of acceleration due to gravity.

[0076] As shown in step 410, method 400 may include identifying an activity. More specifically, this may include identifying the type of strength training activity the user is performing. In one aspect, this may include receiving user input specifying the type of strength training activity, for example, in the user interface of a user device. In another aspect, this may include automatically identifying the type of strength training activity based on motion data, such as raw motion data or triaxial acceleration data, or other motion data derived from or based on raw motion data. The motion data may also be obtained from other sources, such as a camera capturing images of the activity, weight or weight training devices integrated with motion sensors, etc. Identifying the activity may, for example, include applying any suitable activity identification algorithm (e.g., machine learning algorithms, statistical classification schemes, etc.) to the motion data obtained from a wearable monitor or other sources. In another aspect, method 400 may include attempting automatic type detection and requesting user input if automatic detection cannot reliably (e.g., with sufficient statistical confidence) identify the type. In one aspect, method 400 may include continuously tracking the movement and attempting to identify known patterns of strength training activities. In another aspect, identification may be attempted only during a known trial period or in response to an explicit user request.

[0077] In the case of automatically identified activities, additional processing can be effectively applied. For example, an activity can be evaluated to determine whether each repetition was correctly completed with the full expected range of motion. Certain characteristics of the repetition can also be used, or alternatively, to measure the effort involved in the repetition. For example, repetitions with varying speeds, or those involving jerky movements, or those that are stopped and abandoned midway, may indicate greater musculoskeletal effort than would be expected from a smooth repetition performed at a speed similar to the previous repetition. Such variations are frequently observed in motion data. Various statistical measures, such as mean signal amplitude, standard deviation, and rate of change, can be used to quantify these variations. Intensity measures can then be compiled based on different statistical quantifications of the motion signal to distinguish different levels of musculoskeletal effort.

[0078] As shown in step 412, method 400 may include identifying the number of repetitions in a set of strength training activities. In one aspect, this may include receiving user input specifying the number of repetitions in the set, or otherwise determining the number of repetitions based on user input. In another aspect, this may include determining the number of repetitions in the set based on amplitude changes in triaxial acceleration data, or otherwise determining the number based on user input. For example, as... Figure 6As shown, velocity over time can be derived from triaxial acceleration data, and any data can exhibit certain periodic characteristics indicative of repetitions in an exercise. Therefore, velocity data can be used to support the automatic detection of repetitions in certain types of exercise. Cameras or other tracking devices / systems can also be used, or alternatively, to identify the number of repetitions in an activity. Alternatively, this can include using other data sources or techniques to detect the number, such as receiving repetition counts from the exercise device, extracting repetition count information from video images of the activity, such as those obtained via a smartphone, camera, or other image source, or receiving motion data from any other source described herein.

[0079] As shown in step 414, the method may include calculating the strength of the group.

[0080] In one aspect, this could include, for each repetition, calculating a raw intensity score indicative of musculoskeletal movement based on changes in triaxial acceleration data. As mentioned above, intensity is typically measured relative to a user's ability. This raw measurement of intensity can be evaluated based on motion data. For example, intensity can be assessed by calculating the difference (also known as "jumpiness," or the change in acceleration between two measurements) from one instantaneous acceleration measurement to the next, and then dividing that amount by the acceleration amplitude. The intensity of the exercise repetition can then be calculated by averaging this instantaneous intensity across all samples during the concentric phase of the repetition.

[0081]

[0082] Intensity rep =Mean(Intensity) sample )

[0083] It will be understood that other measures of intensity can be derived from motion. For example, in one aspect, the intensity of repetition can be calculated as follows:

[0084]

[0085] For certain types of exercise, the latter approach may be less sensitive to small changes in acceleration or jerk, or to changes in motion occurring at concentric phase boundaries. Therefore, in one aspect, calculating the raw intensity score for a single repetition in a set of repetitions involves calculating the average of multiple instantaneous intensity measurements for that single repetition. In another aspect, one or more of the multiple instantaneous intensity measurements are calculated based on the average of the ratios of the current change in acceleration to the current acceleration of discrete measurements. In yet another aspect, one or more of the multiple instantaneous intensity measurements are calculated based on the ratio of a first average of the current change in acceleration to a second average of the current acceleration. More generally, any measure that objectively characterizes intensity based on changes in motion during and / or a set of such repetitions of a strength training activity can also, or alternatively, be used to measure intensity and calculate musculoskeletal load, as contemplated herein. As a significant advantage, acceleration-based intensity measurements allow for the capture of the spatial range of motion directly related to the work performed, as well as any jerking in the motion indicating high individual load. Due to the cumulative effect of acceleration changes caused by jerking, such sporadic movements at relatively high speeds deviating from the typical exercise path will appear as numerically higher intensity scores. For activities where movement cannot be directly measured, intensity can be used as an alternative, such as the duration of static isometric exercises. Even in these cases where there is no obvious muscle movement, muscle tremors can still manifest in ways that can be detected, measured, and used to quantify intensity.

[0086] As described above, calculating intensity may also include adjusting the raw intensity score based on the user's activity history. To personalize intensity in this way, method 400 may include determining the user's maximum intensity for each repetition in a set (or for the entire set). The maximum intensity may indicate the user's ability to perform strength training activities based on their exercise history. Various techniques can be used to assess or estimate this maximum capacity and adjust the raw intensity score accordingly. For example, adjusting the raw intensity score may include adjusting the load repetition profile (e.g., ...) Figure 5A scaling factor is retrieved from the load repetition profile shown, which characterizes a set of repetitions relative to the user's maximum capacity within the range of load and repetition count. The intensity score of the set of repetitions can then be represented as the product of a (motion-based) raw intensity score and a scaling factor indicating the user's maximum capacity to perform repetitive exercises at a specific load. Alternatively, the scaling factor can be estimated or interpolated based on the observed or user-reported maximum load for a specific exercise, or the observed or reported maximum number of repetitions for multiple different loads. More generally, any technique suitable for quantifying and determining a user's maximum capacity for a strength training activity and / or scaling observed activities related to maximum capacity can be used to scale the raw intensity score of a set of repetitions and provide the user with an intensity score. All such techniques are intended to fall within the scope of this disclosure, provided they support a useful calculation of the musculoskeletal load score as further described below.

[0087] It will also be appreciated that other techniques for calculating intensity are known in the art and can be applied to wearable health monitors as described herein. For example, intensity can be assessed based on the speed, linearity, and / or continuity of movement associated with exercise, any of which can be efficiently detected using the motion sensors described herein. For example, effort can be identified based on how clean the path of the exercise movement is, or in other words, based on the amount of noise in the movement relative to the user's expected and / or historical trajectory. Various linear, continuous, and / or variable measurements are mathematically known and can be efficiently used as estimators of movement-based intensity. In one aspect, the amount of movement that varies from the overall expected value and / or exceeds the expected variation can be used for an individual. In another aspect, local measurements of changes in directionality (e.g., the number and magnitude of changes in direction) or velocity (e.g., the number and magnitude of changes in velocity) can be used to identify when an increased load causes the movement to become less smooth or less continuous. In one aspect, the load can be measured across the major muscle groups targeted by the exercise. For example, when a user performs a bicep curl, the load on the biceps can be estimated based on any of the aforementioned motion factors, as measured with a wrist-worn monitor. As another example, when a user performs a squat, a monitor located on the thigh or calf can be used to estimate the load on various leg muscles. As yet another example, when a user is performing push-ups, extensions, or another type of bodyweight exercise, a monitor on the user's torso can be used to estimate intensity based on the range of motion of the torso portion. Intensity scores can also be further contextualized using additional data, such as the user's maximum or typical body weight, other relevant training of the corresponding muscle groups, etc., as described herein.

[0088] As shown in step 416, method 400 may include updating the user profile. This typically includes updating the load repetition profile or any other user profile when new data becomes available. In one aspect, this may include adding columns or rows to the profile. In another aspect, this may include updating other entries in the profile when, for example, the current group repetition exceeds the expected maximum value.

[0089] As shown in step 418, method 400 may include calculating the amount of strength training activity. As described herein, amount typically refers to the total amount of work performed during a trial period (or other time period). The amount for a user may be personalized based on two components: maximum amount and effective load. Therefore, method 400 may include, for example, estimating the maximum amount or other predetermined threshold that the user performs when performing strength training activities based on the user's history of performing strength training activities. The maximum amount (or estimated maximum amount) may, for example, indicate an upper limit threshold for the user's non-injury repetitive strength training activities.

[0090] Method 400 may also include calculating the effective load of the user during a strength training activity. The effective load may be based, for example, on one or more load parameters to indicate the relative portion of the maximum amount of force exerted by the user during the strength training activity. The one or more load parameters may include at least the user's body weight and the increase in weight during the strength training activity. For example, calculating the effective load may include user input based on the user's body weight, for example, where the strength training activity is entirely or partially based on the user's body weight, such as pull-ups, push-ups, or squats. Calculating the effective load may also be based on user input of the increase in weight during the strength training activity, for example, when the user uses hand weights, barbell weights, or weights on a strength training machine, or when the user increases the weight in another activity (e.g., pull-ups, push-ups, or squats) to increase the volume. In some instances, for example, when using a strength training machine, body weight may be ignored, and / or other load parameters such as arm length or leg length may be included.

[0091] As shown in step 420, method 400 may include calculating a musculoskeletal load score. For example, this may include calculating the musculoskeletal load for each repetition as a product of a first ratio of effective load to maximum volume and a second ratio of original intensity score to maximum intensity, and then summing the musculoskeletal load for each repetition across all repetitions in the set to provide a musculoskeletal load score for the strength training activity. Generally, this may include calculating the musculoskeletal load score on a user's personal computing device communicatively coupled to a wearable monitor, or on a remote server communicatively coupled to a wearable monitor, or some combination thereof.

[0092] The MSK load score can then be calculated for each workout session using the following formula:

[0093]

[0094] Where M is the number of repetitions in the set. and These are the quantity and intensity of repetition i, respectively, V max and I max These are the maximum possible quantity and intensity value, respectively, and rel refers to the relative quantity and intensity of repetition. It has been replaced with V rep Because it is a set of repeating constants. On the other hand, this is not I. rep In this situation, I rep It can be calculated for each repetition based on the available motion data.

[0095]

[0096] To accumulate MSK from multiple sets of exercises:

[0097]

[0098] Where N is the number of sets of exercises.

[0099] Finally, for a session consisting of multiple exercises:

[0100]

[0101]

[0102] Where L is the number of times the exercise is performed during the session.

[0103] The maximum values ​​for quantity and intensity can be calibrated for an individual and can vary as an individual's strength changes over time.

[0104] Using these, the MSK load for each repetition of exercise can be calculated. The sum of individual MSK load scores yields a trial level score. At this level, MSK load can be summed at the muscle group level and / or the whole body level. When sensor data is available, intensity can be based on the acceleration or velocity of the movement. When sensor data is unavailable, effort can still be determined based on, for example, previous trials, demographic criteria, and / or self-reported effort levels. Therefore, the systems and methods described herein can perform MSK scoring using exercise data, without exercise data, or some combination thereof.

[0105] As described in this paper, the raw MSK burden can be an infinitely linearly cumulative score. That is, the more effort invested in the activity, or the more repetitions performed, the higher the score. To provide users with a finite range, these raw scores can be scaled to adjust the values ​​based on the user's individual performance profile. In some respects, this can be achieved through a two-stage process, including (1) exercise-specific standardization and (2) performance standardization. For example, an individual's daily MSK burden can be converted into a score of 0-21 or any other suitable range.

[0106] As shown in step 422, method 400 may include taking action based on musculoskeletal (MSK) load scores. MSK load scores provide a highly actionable metric for strength training activities, placed within the context of a specific type of exercise, proven history of ability, and the user's estimated injury limits. In one aspect, taking action may include, for example, displaying the musculoskeletal load score of the strength training activity, or any other derived metric or analysis, to the user on a user device for viewing.

[0107] In another aspect, taking action may include refining daily workload calculations for the user based on musculoskeletal load fractions (e.g., cardiac workload calculations based on heart rate and / or heart rate variability). For example, workload calculations based on cardiovascular activity (as described, for example, in U.S. Patent 11,185,292, which is incorporated herein by reference) may underestimate the actual effort exerted during strength training activities. By determining the MSK load during strength training or other exercise, the user's total daily workload can be updated to more accurately reflect the workload due to both muscular and cardiovascular effort.

[0108] On the other hand, taking action may also, or alternatively, include calculating multiple musculoskeletal load scores for each of the various types of strength training activities in a workout program. For an entire workout program consisting of multiple individual strength training activities, these may be aggregated into a single MSK load score, and / or may be reported to the user as a single score or multiple scores.

[0109] Taking action may also, or alternatively, include generating coaching suggestions to the user based on musculoskeletal load scores, and / or displaying coaching suggestions to the user. This may include generating suggestions based on stated user goals or health goals, such as suggesting increases when appropriate, or suggesting decreases when there are signs of approaching the user's maximum capacity or otherwise exceeding the recommended training limit. In one aspect, coaching suggestions may be real-time coaching suggestions presented to the user during strength training activities. For example, this may include suggestions to increase the volume (e.g., by adding extra repetitions or increasing the weight), or warnings about approaching the maximum capacity. In another aspect, coaching suggestions may relate to the user's subsequent workout activities, such as follow-up activities in the current workout, or the same (or different) activities in future workouts. Coaching suggestions may also, or alternatively, include suggestions regarding the timing of the next strength training activity.

[0110] Based on the foregoing, this document also describes a system for calculating musculoskeletal load scores. This system may include a wearable health monitor and one or more processors. The wearable health monitor may be any wearable monitor described herein and may include one or more motion sensors. The one or more processors may include, for example, a processor on the wearable health monitor, a processor on a user device, a processor on a remote server, or some combination thereof. One or more processors may be configured by computer-executable code stored in a non-transitory computer-readable medium to perform the following steps: receiving motion data acquired from one or more motion sensors during a strength training activity; identifying the type of strength training activity; identifying a set of strength training activities comprising one or more repetitions; for each repetition, calculating an original intensity score indicative of musculoskeletal movement based on features of the motion data; scaling the original intensity score relative to the maximum intensity at which the user performs the strength training activity to obtain a user intensity score for each repetition, the maximum intensity being based on the user's exercise history indicative of the user's ability to perform the strength training activity; for each repetition, calculating an individualized scale based on the ratio of the user's effective load during the strength training activity to a predetermined load threshold for the user when performing the strength training activity; calculating the musculoskeletal load per repetition of each repetition as the product of the user intensity score for each repetition and the individualized scale; calculating a musculoskeletal load score for the strength training activity by summing the musculoskeletal load per repetition of all repetitions in the set; and taking an action based on the musculoskeletal load score.

[0111] In one aspect, taking action could include transmitting a user-specific musculoskeletal load score to a personal computing device associated with the user for display. In another aspect, taking action could include generating coaching suggestions for the user.

[0112] Generally, the methods described in this article may include more or fewer steps, or refer to...Figure 4 Variations of each step described. For example, in one aspect, this document discloses a method comprising: receiving motion data from one or more motion sensors of a wearable monitor worn by a user during a set of one or more repetitions of a strength training activity; identifying the type of strength training activity; determining the number of repetitions in the set; for each repetition, calculating an original intensity score indicative of musculoskeletal movement based on features of the motion data, and scaling the original intensity score relative to the maximum intensity at which the user performs the strength training activity to obtain a user intensity score for each repetition, the maximum intensity being indicative of the user's ability to perform the strength training activity based on the user's exercise history; for each repetition, calculating an individualized scale based on a ratio of the user's effective load during the strength training activity to a predetermined load threshold for the user performing the strength training activity; calculating the per-repetition musculoskeletal load for each repetition as a product of the per-repetition user intensity score and the individualized scale; calculating a musculoskeletal load score for the strength training activity by summing the per-repetition musculoskeletal loads for all repetitions in the set; and taking an action based on the musculoskeletal load score.

[0113] On the other hand, the method described herein includes receiving motion data from one or more motion sensors of a wearable health monitor worn by the user during a strength training activity; calculating the user's individualized musculoskeletal load during the strength training activity by adjusting the intensity associated with the motion data based on the user's workout history associated with the strength training activity, the effective load during the strength training activity, and the user's maximum volume associated with the strength training activity; and taking action based on the individualized musculoskeletal load.

[0114] On the other hand, the method described herein includes receiving motion data from one or more motion sensors of a wearable health monitor worn by the user during a strength training activity; calculating a raw intensity score for multiple repetitions of the strength training activity based on the motion data; calculating the effective load of the strength training activity based on one or more load parameters, the load parameters including at least the user's body weight and the increased weight of the strength training activity; calculating an individualized musculoskeletal load score based on a combination of the raw intensity score calculated from the motion data and the effective load calculated based on one or more load parameters; and presenting information to the user based on the individualized musculoskeletal load score.

[0115] Figure 5 This illustrates a load repetition profile used for scaling exercise repetition intensity. Typically, this profile 500 can be used to scale a user's raw intensity score based on their training history. Typically, the maximum intensity value can be established at a user's maximum repetition value ( Figure 5(Load 10, Rep 1). Based on the maximum intensity of a single repetition, a scale can be developed for all intensity values ​​for a given individual and exercise, for example, by inserting an effort percentage to scale the calculated intensity based on the maximum possible value of the exercise. Profile 500 can also be adjusted when new failed repetitions are observed, and new rows can be added when the user increases the number of repetitions or the load. As additional user data becomes available, the numbers can often be adjusted, recalculated, reinterpolated, etc. In one aspect, if a user exceeds the predicted maximum value, for example by performing one or more repetitions under a load exceeding the current maximum value, Profile 500 can be adjusted before calculating the intensity, and the adjusted Profile 500 can be used to calculate the intensity for those repetitions. This advantageously avoids calculating intensity values ​​that exceed the user's theoretical maximum value.

[0116] On the other hand, before profile 500 is fully populated, the strength scale can be initially estimated based on factors such as weight or other factors to support the user's strength calculation.

[0117] Figure 6 This is a graph showing the change in velocity measured during a bench press exercise over time. Generally, velocity can be derived from triaxial acceleration data or from other motion data obtained from wearable monitors or other motion data sources. While a bench press exercise is shown, it will be understood that any other exercise with measurable repetitions can be similarly detected. As shown, the five large peaks 602 in the velocity data indicate five repetitions of the exercise, and the added vertical line 604 indicates the measurable markers at the end of each repetition. Various signal processing techniques can be used to identify such repetitions, including frequency domain techniques, time-domain peak detection, etc. Any such technique suitable for identifying periodic cycles of velocity measurements indicating exercise repetitions can be used for automated repetition detection, as described herein.

[0118] Figure 7 The data shows the triaxial acceleration data for one repetition of a bench press exercise. Figure 7 The data in this document is fused data that has been processed to mitigate gravity-based acceleration artifacts. This data can be used, for example, to calculate intensity scores and / or derive velocity data (such as...). Figure 6 As shown in the figure, this speed data can be used to identify individual repetitions in a set of strength training activities.

[0119] Figure 8 Showing from Figure 7 The integral of the normalized acceleration amplitude of the data. This can be used, for example, to quantify the intensity of the exercise and then scaled against the maximum intensity, maximum volume, and effective load described herein to obtain the MSK score for repetitive strength training activities.

[0120] Figure 9A system for monitoring musculoskeletal (MSK) stress is illustrated. System 900 may include a user 901 wearing a physiological monitor 910, a user device 920 having a display 922 adapted to provide information to the user 901, a data network 902 interconnecting one or more participants in system 900, a server 930, and a database 940. In general, Figure 9 The illustration shows user 901 performing an exercise—for example, a weight training exercise such as bicep curls, with a barbell-shaped weight 902 on which a counterweight plate is attached. As described herein, motion and / or physiological data sensed by physiological monitor 910 can be used to calculate user 901's MSK load score, which can be displayed to the user via user device 920 along with other relevant information (e.g., during and / or after the exercise).

[0121] The physiological monitor 910 may include a wrist-worn photoplethysmography device. The physiological monitor 910 may also, or alternatively, include monitors disposed at other locations on the user 901's body, such as the biceps, thigh, calf, etc. In one aspect, the physiological monitor 910 includes at least one accelerometer, gyroscope, etc., for sensing motion and providing motion data to the user 901. In other aspects, accelerometer data or other motion sensor data is obtained from a source external to the physiological monitor 910.

[0122] User 901 may be performing an exercise such as strength training, where motion data (and / or physiological data) is provided to user device 920 and / or server 930 for analysis. Generally, motion data captured by motion sensors during exercise can be analyzed to obtain an MSK load score as described herein. This score can be used, for example, to provide coaching information to user 901, such as for adjusting the exercise and / or providing other training suggestions. As an example, and not a limitation, user 901 is shown performing a bicep curl with a barbell as weight 902, where in this example, motion data from sensed motion 904 may include triaxial acceleration data describing movement during repetitive exercise. This may include motion data acquired by physiological monitor 910 as described above, or motion data acquired by motion sensors in weight 902 (including the barbell or weights added thereto), motion data acquired by a camera in user device 920, or motion data acquired from any other suitable source. While free weight exercises are described, it will be understood that the systems and methods described herein can be used to calculate MSK load in a variety of other strength training activities, such as weightlifting exercises (e.g., using free weights and / or weight training machines), body weight or isometric exercises (e.g., push-ups, sit-ups, squats, burpees, extensions, leg raises, etc.), cardiovascular exercises (e.g., walking, running, cycling, swimming, elliptical training, circuit training, rope skipping, exercise participation and / or training, dancing, etc.). Motion data can also be used for other coaching advice, such as advice related to repetition speed, range of motion, form, etc. Therefore, in one aspect, this paper describes a system and method for providing coaching advice to users engaged in strength training activities based on motion sensed during the activity. The advice may relate to one or more of speed, range of motion, and form of strength training activity.

[0123] Data network 902, user equipment 920, server 930, and database 940 can be any of those described herein. Generally, data network 902 can support communication between participants in system 901, such as motion data and / or physiological data sensed by physiological monitor 910 being provided to server 930 or user equipment 920 for processing. Such data and / or the results of its analysis can be stored in database 940, which can be a local or remote database as described herein. Database 940 can also, or alternatively, store user profiles, load repetition profiles, etc., as described herein.

[0124] The display 922 of the user device 920 may include a graphical user interface provided on the display 922 and is configured to present information to the user 901. The information 924 presented on the display 922 may include any output as described herein, including MSK load score 924, coaching suggestions, exercise plans including multiple consecutive strength training activities, repetitions completed in specific sets, etc.

[0125] In the example use case, system 900 may receive information related to the exercise being performed by user 901, such as exercise type, settings or repetition description or measurement, training goals, increased weight 902 or load being used, information related to user 901 (e.g., height, weight, gender, etc.), and so on. In some aspects, this information may include motion data from physiological monitor 910 or (one or more) other sources.

[0126] Figure 10 A system for monitoring MSK load is illustrated. System 1000 may include any of the features described herein, such as those mentioned above. Figure 9 Any features discussed. For example... Figure 10 As shown, system 1000 may include a weight training machine 1002. A physiological monitor 1010 may be mounted on the user's legs to detect leg movement during leg strength training activities. In one aspect, the weight training machine 1002 may be a smart device capable of transmitting data such as current weight / load, repetitions, range of motion, and other data to the physiological monitor 1010 or other system resources for calculating the MSK load score. The weight training machine 1002 may also, or alternatively, include a camera for capturing images that can be used to export motion data.

[0127] Figure 11 A system for monitoring MSK load is illustrated. System 1100 may include any of the features described herein. As shown, user 1101 is performing isometric exercise, more specifically a plank. In this type of exercise, some adaptation to the load fraction can be used. For example, in a plank (or some other isometric exercise), there are no literal repetitions. Instead, a repetition metric can be derived, for example, based on the amount of time the exercise is held. Thus, for example, a plank can be counted as one repetition every five seconds, such that one minute of performing a plank is equivalent to twelve repetitions. Similarly, there will be no automatic detection of the periodic movement on which the repetitions are based, but in cases of high effort, there may be jerking in the shoulders, arms, or abdomen, which can be detected by a wearable physiological monitor 1102 and used to calculate the intensity of the activity.

[0128] Figure 12A user interface for a strength training system with MSK load scores is shown, for example, using the systems and methods described herein. In one aspect, the user interface 1200 may include multiple controls for configuring a training program, for example, by specifying the type of strength training activity, and the appropriate repetitions and weights for each activity. Through this interface, the user can configure the training program by adding or deleting training sets within the program, or specifying details of training sets. The training program can then be saved for future use and used as guidance in the current training session.

[0129] Figure 13 A user interface for a strength training system with an MSK load score is shown, for example, using the methods and systems described herein. In one aspect, the user interface 1300 can display an MSK load score 1302, which quantifies and summarizes the amount of musculoskeletal load the user experiences during the day or any other suitable time period. The user interface 1300 can also display other useful information, such as current or recent strength training activity, daily cardiovascular and muscular load, coaching advice, etc. In this case, the MSK load score 1302 can advantageously provide the user with concise, quantitative, and objective feedback on recent strength training activity, as informed by measurements of identified activities and physical movement.

[0130] In user interface 1300, users can also track their current workout, modify it (e.g., by changing weight, repetition, or activity), view previous workouts, create new workouts, and so on. Users can also view information describing time, weight, effort, cardiovascular burden, etc. On the other hand, user interface 1200 can provide interactive instructions on performing different types of exercise and can provide movement-based feedback on the user's form for specific exercises.

[0131] The systems, devices, methods, processes, etc., described above can be implemented in hardware, software, or any combination of these suitable for the control, data acquisition, and data processing described herein. This includes implementations in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors, or other programmable devices or processing circuits, as well as internal and / or external memory. This may also or alternatively include one or more application-specific integrated circuits, programmable gate arrays, programmable array logic components, or any other one or more devices that can be configured to process electronic signals. It will also be appreciated that implementations of the processes or devices described above may include computer-executable code created using a structured programming language such as C, an object-oriented programming language such as C++, or any other high- or low-level programming language (including assembly language, hardware description languages, and database programming languages ​​and techniques), which can be stored, compiled, or interpreted to run on one of the devices described above, as well as on one of the heterogeneous combinations of processors, processor architectures, or different combinations of hardware and software.

[0132] Therefore, in one aspect, each of the methods and combinations thereof described above can be embodied in computer-executable code, which, when executed on one or more computing devices, performs its steps. In another aspect, the method can be implemented in a system that performs its steps and can be distributed across devices in various ways, or all functionality can be integrated into a dedicated, standalone device or other hardware. The code can be stored in a non-transitory computer memory, which can be a memory from which a program is executed (e.g., random access memory associated with a processor), or a storage device such as a disk drive, flash memory, or any other optical, electromagnetic, magnetic, infrared, or other device or combination thereof. In another aspect, any system and method described above can be implemented in any suitable transmission or propagation medium carrying computer-executable code and / or any input or output from the computer-executable code. In another aspect, the components used to perform the steps associated with the processes described above can include any of the hardware and / or software described above. All such permutations and combinations are intended to fall within the scope of this disclosure.

[0133] The method steps described herein are intended to include any suitable methods for causing the method steps to be performed, consistent with the patentability of the appended claims, unless a different meaning is explicitly provided or is clear from the context. Thus, for example, performing step X includes any suitable method for causing another party, such as a remote user, a remote processing resource (e.g., a server or cloud computer), or a machine, to perform step X. Similarly, performing steps X, Y, and Z may include any combination of directing or controlling such other individuals or resources to perform steps X, Y, and Z to obtain the benefits of such steps. Therefore, the method steps described herein are intended to include any suitable methods for causing one or more other parties or entities to perform the steps, consistent with the patentability of the appended claims, unless a different meaning is explicitly provided or is otherwise clear from the context. Such parties or entities need not be subject to the direction or control of any other party or entity, nor need they be located in a particular jurisdiction.

[0134] It will be understood that the methods and systems described above are illustrated by way of example and not limitation. Many variations, additions, omissions, and other modifications will be apparent to those skilled in the art. Furthermore, the order or presentation of the method steps in the above description and figures is not intended to require that the steps be performed in such an order unless a particular order is explicitly required or otherwise apparent from the context. Therefore, although specific embodiments have been shown and described, it will be apparent to those skilled in the art that various changes and modifications in form and detail may be made therein without departing from the spirit and scope of this disclosure, and that such changes and modifications are intended to form part of the invention as defined by the appended claims.

Claims

1. A computer program product comprising computer-executable code contained in a non-transitory computer-readable medium, the computer-executable code, when executed on one or more computing devices, causing the one or more computing devices to perform the following steps: Raw motion data is received from one or more motion sensors of a wearable health monitor worn by the user during a set of one or more repetitions of strength training activities. The raw motion data includes angular rotation data from multiple gyroscopes and linear acceleration data from multiple accelerometers. The raw motion data from the one or more motion sensors are fused to reduce gravity artifacts, thereby providing motion data that includes triaxial acceleration data; Identify the type of the strength training activity; The number of repetitions in the set is determined based on the amplitude changes of the triaxial acceleration data. For each repetition, an original strength fraction indicating musculoskeletal movement is calculated based on the changes in the triaxial acceleration data; For each repetition, the maximum intensity at which the user performs the strength training activity is determined, the maximum intensity being based on the user's training history indicating the user's ability to perform the strength training activity; The maximum amount of the user and the strength training activity is estimated based on the user’s history of performing the strength training activity, wherein the maximum amount indicates an upper limit threshold for the user to repeat the strength training activity without damage. The effective load of the user during the strength training activity is calculated based on one or more load parameters, the effective load indicating the relative portion of the maximum amount exerted by the user during the strength training activity, the one or more load parameters including at least the user's body weight and the increase in weight during the strength training activity; The musculoskeletal load for each repetition of the repetition is calculated as the product of a first ratio of the effective load to the maximum amount and a second ratio of the original intensity fraction to the maximum intensity. The musculoskeletal load of each repetition in the set is summed to provide a musculoskeletal load score for the strength training activity. as well as The musculoskeletal load score of the strength training activity is displayed to the user.

2. The computer program product of claim 1, further comprising code that causes the one or more computing devices to perform the following step: generating coaching suggestions to the user based on the musculoskeletal load score.

3. The computer program product according to claim 2, wherein, The coach's advice is at least in part based on the user's health goals.

4. The computer program product according to any one of the preceding claims, wherein, Calculating the original intensity score of one of the repetitions includes calculating the average of multiple instantaneous intensity measurements of one of the repetitions.

5. The computer program product according to claim 4, wherein, One or more of the plurality of instantaneous intensity measurements are calculated based on the average of the ratios of the current acceleration change to the current acceleration based on discrete measurements.

6. The computer program product according to claim 4, wherein, One or more of the plurality of instantaneous intensity measurements are calculated based on the ratio of a first average value of the current change in acceleration to a second average value of the current acceleration.

7. The computer program product of claim 1, further comprising code that causes the one or more computing devices to perform the following step: creating a load repetition profile for the user based on the history of the user's strength training activities, the load repetition profile indicating the user's repetition capacity under one or more loads during the strength training activities.

8. The computer program product of claim 7, further comprising code that causes the one or more computing devices to perform the following step: adding a row to the load repetition profile when the user performs the strength training activity under a new load not included in the one or more loads in the load repetition profile.

9. The computer program product of claim 7, further comprising code that causes the one or more computing devices to perform the following step: updating the load repetition profile when the user exceeds the number of repetitions of one of the loads in the load repetition profile.

10. The computer program product of claim 1, further comprising code for receiving user input specifying the type of the strength training activity.

11. The computer program product of claim 1, further comprising code that causes the one or more computing devices to perform the following step: identifying the type of the strength training activity based on the raw motion data.

Images