GAIT COACHING IN FITNESS TRACKING SYSTEMS
A method of providing gait coaching is disclosed. Run data is received and stored regarding runs of a broad and diverse population of users, as well as a more narrow set of expert users. A gait metric model is developed for determining an ideal stride length or cadence based on pace and at least one physiological characteristic. Regression coefficients for at the model are determined based on a regression of the run data from the broad and diverse population of users. In contrast, a regression constant for the model is determined based on a regression of the run data from expert users. Using the model, an ideal stride length or cadence for a particular user on a particular run can be determined and utilized to provide useful monitoring, comparison, and feedback to the user regarding his or her stride length or cadence.
A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all copyright rights whatsoever.
CROSS-REFERENCE TO RELATED APPLICATIONSThis application is a continuation of U.S. patent application Ser. No. 16/150,095, filed Oct. 2, 2018, and entitled “Gait Coaching in Fitness Tracking Systems,” the entire content of which is incorporated herein by reference.
FIELDThe device and method disclosed in fitness tracking systems and, more particularly, to gait coaching in fitness tracking systems.
BACKGROUNDActivity tracking devices are increasingly utilized by individuals interested in tracking metrics related to their personal health and fitness activity. These activity tracking devices include, for example, heart rate monitors, step counters, stair counters, global positioning system (“GPS”) tracking devices, as well as various other motion and biometric tracking devices. One of the most popular fitness activities for weight loss and general health is running. However, a common problem for maintaining a long term running habit is the risk of injury. It is well established that proper running gait (also referred to herein as running form) is one the best ways for runners to minimize the risk of injury. Additionally, proper running gait also improves running economy or, in other words, the amount of effort required to run at a given pace. Unfortunately, typical guidelines for proper running gait fall short of providing beginner and intermediate runners with the necessary tools to achieve and maintain a proper running gait. Particularly, typical guidelines are one-size-fits-all standards that fail to consider the unique physiological characteristics of the runner. Furthermore, even with appropriate guidelines, it is challenging for users to know how their running gait differs from the recommended gait. Accordingly, for many runners, the typical guidelines may be difficult to apply and sometimes counterproductive. In view of the foregoing, it would be advantageous to provide a method of gait coaching that was unique to the individual runner. It would also be advantageous if the method provided the user with specific guidance for how to change his or her gait to achieve and maintain the proper running gait.
SUMMARYIn accordance with one exemplary embodiment of the disclosures, a method of displaying run data is disclosed. The method comprises: receiving first historical run data regarding runs of a first plurality of users, the first historical run data including, for each run, a gait metric for the respective run, a pace during the respective run, and at least one physiological characteristic of the respective user, the gait metric being at least one of (i) a stride cadence and (ii) a stride length; determining regression coefficients for at least one gait metric model by performing a regression of the first historical run data, the at least one gait metric model being configured to output the gait metric given inputs of pace and the at least one physiological characteristic; receiving second historical run data regarding runs of a second plurality of users, the second historical run data including, for each run, the gait metric for the respective run, a pace during the respective run, and the at least one physiological characteristic of the respective user; determining a regression constant for the at least one gait metric model by performing a regression of the second historical run data; receiving first run data from an activity monitoring device carried by a first user during a first run of the first user; determining the gait metric for the first run based on the first run data; determining a pace during the first run based on the first run data; determining a gait metric target for the first run based on the at least one gait metric model, the determined regression coefficients, the determined regression constant, the pace during the first run, and the at least one physiological characteristic of the first user; and displaying a comparison of the gait metric with the gait metric target to the first user on a personal electronic device associated with the first user.
Pursuant to another exemplary embodiment of the disclosures, a fitness tracking system is disclosed. The fitness tracking system comprises a database configured to store: first historical run data regarding runs of a first plurality of users, the first historical run data including, for each run, a gait metric for the respective run, a pace during the respective run, and at least one physiological characteristic of the respective user, the gait metric being at least one of (i) a stride cadence and (ii) a stride length; and second historical run data regarding runs of a second plurality of users, the second historical run data including, for each run, the gait metric for the respective run, a pace during the respective run, and the at least one physiological characteristic of the respective user. The fitness tracking system comprises a data processor in communication with the database, the data processor being configured to: receive the first historical run data and the second historical run data from the database; determine regression coefficients for at least one gait metric model by performing a regression of the first historical run data, the at least one gait metric model being configured to output the gait metric given inputs of pace and the at least one physiological characteristic; determine a regression constant for the at least one gait metric model by performing a regression of the second historical run data; and transmit the regression coefficients and the regression constant for the at least one gait metric model to at least one personal electronic device of at least one user.
In accordance with yet another exemplary embodiment, a further method of displaying run data is disclosed. The method comprises: receiving first historical run data regarding runs of a first plurality of users, the first historical run data including, for each run, a gait metric for the respective run, a pace during the respective run, and at least one physiological characteristic of the respective user, the gait metric being at least one of (i) a stride cadence and (ii) a stride length; determining regression coefficients for at least one gait metric model by performing a regression of the first historical run data, the at least one gait metric model being configured to output the gait metric given inputs of pace and the at least one physiological characteristic; receiving second historical run data regarding runs of a second plurality of users, the second historical run data including, for each run, the gait metric for the respective run, a pace during the respective run, and the at least one physiological characteristic of the respective user; determining a regression constant for the at least one gait metric model by performing a regression of the second historical run data; receiving first real-time run data from an activity monitoring device carried by a first user during a first run of the first user; determining a real-time value of the gait metric during the first run based on the first real-time run data; determining a real-time pace during the first run based on the first real-time run data; determining a real-time gait metric target during the first run based on the at least one gait metric model, the determined regression coefficients, the determined regression constant, the real-time pace during the first run, and the at least one physiological characteristic of the first user; and providing perceptible feedback to the first user during the first run depending on a comparison of the real-time value of the gait metric with the real-time gait metric target to the first user using a personal electronic device associated with the first user.
These and other aspects of the disclosure shall become apparent when considered in light of the disclosure provided herein.
The foregoing aspects and other features of a fitness tracking system are explained in the following description, taken in connection with the accompanying drawings.
All Figures © Under Armour, Inc. 2018. All rights reserved.
DETAILED DESCRIPTIONIn the following detailed description, reference is made to the accompanying figures which form a part hereof wherein like numerals designate like parts throughout, and in which is shown, by way of illustration, embodiments that may be practiced. It is to be understood that other embodiments may be utilized, and structural or logical changes may be made without departing from the scope of the present disclosure. Therefore, the following detailed description is not to be taken in a limiting sense, and the scope of embodiments is defined by the appended claims and their equivalents.
Aspects of the disclosure are disclosed in the accompanying description. Alternate embodiments of the present disclosure and their equivalents may be devised without parting from the spirit or scope of the present disclosure. It should be noted that any discussion herein regarding “one embodiment”, “an embodiment”, “an exemplary embodiment”, and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, and that such particular feature, structure, or characteristic may not necessarily be included in every embodiment. In addition, references to the foregoing do not necessarily comprise a reference to the same embodiment. Finally, irrespective of whether it is explicitly described, one of ordinary skill in the art would readily appreciate that each of the particular features, structures, or characteristics of the given embodiments may be utilized in connection or combination with those of any other embodiment discussed herein.
Various operations may be described as multiple discrete actions or operations in turn, in a manner that is most helpful in understanding the claimed subject matter. However, the order of description should not be construed as to imply that these operations are necessarily order dependent. In particular, these operations may not be performed in the order of presentation. Operations described may be performed in a different order than the described embodiment. Various additional operations may be performed and/or described operations may be omitted in additional embodiments.
For the purposes of the present disclosure, the phrase “A and/or B” means (A), (B), or (A and B). For the purposes of the present disclosure, the phrase “A, B, and/or C” means (A), (B), (C), (A and B), (A and C), (B and C), or (A, B and C).
The terms “comprising,” “including,” “having,” and the like, as used with respect to embodiments of the present disclosure, are synonymous.
Fitness Tracking SystemWith reference to
The term “fitness data” as used herein refers to data relating to a user's fitness and performance during an activity or workout, but also data regarding the user's health and general well-being outside of the activity or workout, and may also be referred to herein as “fitness information” or “fitness parameters.” Fitness data may include activity data and physiological data. Fitness data may be in a raw measured form or in a processed form. Fitness data may be automatically measured, sensed, or collected by the activity monitoring devices 20a, 20b and/or the electronic display device 30, but may also be entered manually by the user via the activity monitoring devices 20a, 20b and/or the electronic display device 30. The term “activity data” as used herein is a subset of fitness data, and refers to data related to physical activity (i.e., movement or lack thereof) of the user. Examples of activity data include body motion/acceleration data, step data, stride length data, stride cadence data, foot strike data, distance traversal data, pace/speed data, altitude data, environmental/positional data (such that provided by a GPS receiver), exercise weight/resistance data, exercise repetition data, and/or any of various other types of personal activity metrics that may be relevant the user's physical activity for a given period of time. The term “physiological data” as used herein is a subset of fitness data, and refers to data related to the physiological status and health of the user. Examples of physiological data include age, gender, height, body weight, body fat, heart rate, aspiration rate, blood oxygenation, blood glucose, hydration, caloric expenditure, or any of various other types of physiological metrics that may be relevant the user's physiological health for a given period of time.
While the activity monitoring device(s) 20a, 20b are described herein as the primary devices for collecting and transmitting fitness data to the electronic display device 30, it will be recognized that additional data may also be collected or otherwise obtained and/or input in to the electronic display device 30 via various other mechanisms. In at least one embodiment, the user may manually input data directly into the activity monitoring device 20b and/or the electronic display device 30. For example, the user may manually collect exercise weight/resistance data or exercise repetition data and input such data into the activity monitoring device 20b and/or the electronic display device 30 without the use of a sensor and/or other device for transmitting the fitness data to the electronic display device 30.
Fitness data from the activity monitoring device(s) 20a, 20b are delivered to the electronic display device 30. As represented by the arrow 55 in
The remote system server 40 comprises a computerized device or data processing system configured to run one or more software applications on a processor thereof for storing and processing fitness data. The activity monitoring device(s) 20a, 20b and electronic display device 30 may communicate via the network 55 to the system server 40 for storage and/or processing of the fitness data, thereby decreasing the processing capacity required at either user device (e.g., the activity monitoring device(s) 20a, 20b or electronic display device 30). In at least one embodiment, the remote system server 40 maintains a database of fitness data received from the electronic display device 30 and/or the activity monitoring device(s) 20a, 20b, as well as fitness data received from further electronic display devices and/or activity monitoring devices associated with a plurality of other users.
In at least one embodiment, the transmission of data from the activity monitoring device(s) 20a, 20b to the electronic display device 30 or to the system server 40 occurs automatically without requiring the user to prompt or initiate the transmission. In another embodiment, the activity monitoring device(s) 20a, 20b may be configured to begin transmissions once it receives a confirmation that the electronic display device 30 is within an appropriate range of the activity monitoring device(s) 20a, 20b. In yet another embodiment, data transmission may occur periodically at predetermined intervals of time. In other embodiments, where communications between the activity monitoring device(s) 20a, 20b and the electronic display device 30 are made with a wired connection, communications only occur when the wired connection is established between the activity monitoring device(s) 20a, 20b and the electronic display device 30. Similar logic applies to the transmission of data from the activity monitoring device(s) 20a, 20b and/or the electronic display device 30 to the system server 40.
Activity Monitoring DevicesWith continued reference to
As discussed above, in the embodiment shown in
In the embodiment shown in
It will be recognized that in other embodiments, further activity monitoring devices may be provided in any of various different configurations to be worn on any of various locations on the body of the user, such as via a module that clips on to clothing, is worn on a chest strap, fits in a pocket of the user, and/or is incorporated into a garment other than a shoe. Additional or alternative examples of activity monitoring devices include those sold under the trademarks FITBIT®, JAWBONE®, POLAR®, SAMSUNG®, APPLE® and UNDER ARMOUR®.
As shown in
With continued reference to
The sensors 26a, 26b of the activity monitoring device 20a, 20b may comprise any of various devices configured to collect the fitness data, including step data, stride length data, stride cadence data, pronation/supination angle data, ground contact time data, foot strike force/direction data, other motion data, distance traversal data, pace data, GPS data, altitude data, heart rate data, breathing data, environmental/positional data, and/or any of various other types of fitness data that may be relevant to determining activities of the wearer. In at least one embodiment, the sensors 26a of the activity monitoring device 20a include a 3-axis accelerometer configured to detect the motions of the wearer during running or walking, in particular the user's gait or form while running or walking. Of course, it will be recognized by those of ordinary skill in the art that numerous other sensors may be used, depending on the type of activity the respective activity monitoring device 20a, 20b is designed to detect.
With continued reference to
The memory 28a, 28b is configured to store information, including both data and instructions. The data may be retrieved from the processor 27a, 27b and generally includes fitness data, but may also include various types of operational data that may be ancillary to the basic operation of the respective activity monitoring device 20a, 20b. The instructions which are stored at the memory 28a, 28b generally include firmware and/or software for execution by the processor 27a, 27b, such as a program that controls the settings for the sensors 26a, 26b, a program that controls the output of the display screen 24 on the activity monitoring device 20b, a program that controls the receipt of information via the sensors 26a, 26b, a program that controls the transmission and reception of data via the transmitter/receiver 29a, 29b, as well as any of various other programs that may be associated with the respective activity monitoring device 20a, 20b. Such instructions may be present on the device 20a, 20b at the time of manufacture or may be downloaded thereto via well-known mechanisms. The memory 28a, 28b may be of any type capable of storing information accessible by the processor 27a, 27b, such as a memory card, ROM, RAM, write-capable, read-only memories, or other computer-readable medium. The data may be stored in the memory 28a, 28b in a relational database as a table having a plurality of different fields and records, XML documents, or flat files. The data may also be formatted in any computer-readable format such as, but not limited to, binary values, ASCII or Unicode.
The transmitter/receiver 29a, 29b in one embodiment comprises an RF transmitter and receiver configured to transmit and receive communications signals over a short range using a wireless communications technology, such as Wi-Fi or Bluetooth®, using any of various communications protocols, such as TCP/IP. Such transmitter/receivers are well known and will be recognized by those of ordinary skill in the art. The transmitter/receiver 29a, 29b is particularly configured to communicate with the electronic display device 30 when the respective activity monitoring device 20a, 20b is within a given range of the electronic display device 30, and transmit collected fitness data to the electronic display device 30.
Electronic Display DeviceWith continued reference to
The I/O interface 36 of the electronic display device 30 includes software and hardware configured to facilitate communications with the one or more activity monitoring devices 20 and/or communications to the user him/herself. The hardware includes a display screen 34 configured to visually display graphics, text, and other data to the user. The hardware may also include a microphone and/or speakers to facilitate audio communications with the user and/or verbal entry of commands to the device 30. In at least one embodiment, the display screen 34 is a touch screen display that allows the user to see data presented on the display screen 34 and input data into the electronic display device 30 via a virtual keyboard or other interface on the touch screen. However, other means for receiving user input, such as a physical keyboard, may also be provided with equal success.
The processor 37 of the electronic display device 30 may be any of various processors as will be recognized by those of ordinary skill in the art. The processor 37 is connected to the I/O interface 36, the memory 38, and the transmitter/receiver 39, and is configured to deliver data to and/or receive data from each of these components. It will be recognized by those of ordinary skill in the art that a “processor” as used herein includes any hardware system, hardware mechanism or hardware component that processes data, signals, and/or other information. A processor can include a system with a central processing unit, multiple processing units, dedicated circuitry for achieving functionality, and/or other systems.
The memory 38 is configured to store information, including both data and instructions. The data may be, for example, fitness data as discussed above, which may be related to the activities, workouts, health and fitness profile, etc. of the user, along with other operational data that may be ancillary to the basic operation of the electronic display device 30 and any applications retained on the electronic display device 30. The instructions which are stored at the memory 38 generally include firmware, an operating system, and/or other software for execution by the processor 37, such as one or more programs that control the settings for the electronic display device, one or more programs that control the output of the display screen 34 on the electronic display device 30, one or more programs that control various applications on the electronic display device 30, one or more programs that control the transmission and reception of data via the transmitter/receiver 39, as well as any of various other programs that may be associated with the electronic display device 30. In at least one embodiment, the instructions stored in the memory 38 include a client-side activity tracking application, discussed in greater detail below, which is executed by the processor 37 to process fitness data and present the fitness data in a graphical format on the display screen 34. The memory 38 may be of any type of device capable of storing information accessible by the processor, such as a memory card, ROM, RAM, write-capable memories, read-only memories, hard drives, discs, flash memory, or any of various other computer-readable medium serving as data storage devices, as will be recognized by those of ordinary skill in the art.
The transmitter/receiver 39 is, in one embodiment, an RF transmitter and receiver configured to transmit and receive communications signals using a wireless communications technology, such as Wi-Fi or Bluetooth®, using any of various communications protocols, such as TCP/IP. Such transmitter/receivers are well known and will be recognized by those of ordinary skill in the art. The transmitter/receiver 39 is particularly configured to communicate with a transmitter/receiver 29a, 29b of the activity monitoring device(s) 20a, 20b. In at least one embodiment, the transmitter/receiver 39 is configured to allow the electronic display device 30 to communicate with a wireless telephony network, as will be recognized by those of ordinary skill in the art. The wireless telephony network may comprise any of several known or future network types. For example, the wireless telephony network may comprise commonly used cellular phone networks using CDMA or FDMA communications schemes. Some other examples of currently known wireless telephony networks include Wi-Fi, WiMax, GSM networks, as well as various other current or future wireless telecommunications arrangements.
As discussed above, in at least some embodiments, the electronic display device 30 also functions as a further activity monitoring device and collects certain fitness data independent of the dedicated activity monitoring devices 20a, 20b. Particularly, in at least one embodiment, the electronic display device 30 includes a GPS receiver 31 configured to record a global position of the user during an activity or workout. Additionally, in some embodiments, the electronic display device 30 also includes sensors, such as a 3-axis accelerometer, altimeter, etc. (not shown), configured to record fitness data during an activity or workout.
In at least one embodiment, the electronic display device 30 includes a camera 33 having at least one photo-sensitive element configured to capture an image and/or video of the surroundings. The processor 37 is configured to operate the camera 33 to capture the image and/or video, to receive the image and/or video from the camera 33, and to store the image and/or video in the memory 38. A user may initiate capture of the image and/or video by pressing virtual buttons (not shown) on the display screen 34 or by pressing physical buttons (not shown) of the electronic display device 30.
The electronic display device 30 generally includes a protective outer shell or housing 32 designed to retain and protect the electronic components positioned within the housing 32. The housing 32 may comprise any number of shapes, configurations, and/or materials, the description herein being merely exemplary. In at least one embodiment, the housing 32 includes a relatively rigid portion that securely retains the electronic components, and a more resilient portion which functions as an outer layer to provide shock absorption features in the event the device 30 is dropped, falls, or otherwise withstands an amount of force. In embodiments wherein the electronic display device 30 also functions as a further activity monitoring devices, the housing 32 may serve as a common housing for components of the electronic display device 30 and components of the further activity monitoring device.
In at least one embodiment, the instructions stored in the memory 38 of the electronic display device 30 includes a client-side activity tracking application (which may also be referred to herein as the “workout tracking application”), which is executed by the processor 37 to provide a graphical user interface that enables the user to track, view, and manage his or her fitness data. An exemplary client-side activity tracking application will be discussed in further detail below. In some embodiments, the memory 28b of the activity monitoring device 20b may also include instructions corresponding to the client-side activity tracking application, and may work in combination with the electronic display device 30 to provide the features of the client-side activity tracking application.
System ServerWith reference to
The processor 47 is operative, configured and/or adapted to operate the system server 40 including the features, functionality, characteristics and/or the like as described herein. To this end, the processor 47 is operably connected to the memory 48 and the network communications module 49. It will be recognized by those of ordinary skill in the art that a “processor” as used herein includes any hardware system, hardware mechanism or hardware component that processes data, signals, and/or other information. A processor can include a system with a central processing unit, multiple processing units, dedicated circuitry for achieving functionality, and/or other systems.
The memory 48 may be of any type of device capable of storing information accessible by the processor, such as a memory card, ROM, RAM, write-capable memories, read-only memories, hard drives, discs, flash memory, or any of various other computer-readable medium serving as data storage devices as will be recognized by those of ordinary skill in the art. The memory 48 is configured to store instructions including a network-side activity tracking application for execution by the processor 47, as well as a database of fitness data 44 and expert fitness data 46 for use by at least the network-side activity tracking application. As discussed in greater detail below, the processor 47 is configured to collect and store fitness data 44 and/or expert fitness data 46 relating to a plurality of workouts of a plurality of users of the fitness tracking system 10.
The network communications module 49 of the system server 40 provides an interface that allows for communication with any of various devices using various means. In particular, the network communications module 49 includes a local area network port that allows for communication with any of various local computers housed in the same or nearby facility. In some embodiments, the network communications module 49 further includes a wide area network port that allows for communications with remote computers over the network 50 (e.g., the Internet). Alternatively, the system server 40 communicates with the network 50 via a modem and/or router of the local area network. In one embodiment, the network communications module is equipped with a Wi-Fi transceiver or other wireless communications device. Accordingly, it will be appreciated that communications with the system server 40 may occur via wired communications or via the wireless communications. Communications may be accomplished using any of various known communications protocols.
The system server 40 may further include a power module (not shown) which is operative, adapted and/or configured to supply appropriate electricity to the system server 40 (i.e., including the various components of the system server 40). The power module may operate on standard 120 volt AC electricity, but may alternatively operate on other AC voltages or include DC power supplied by a battery or batteries.
The system server 40 may be accessed locally by an authorized user (i.e., an administrator or operator). To facilitate local access, the system server 40 may include an interactive user interface (not shown). Via the user interface, an operator may access the instructions, including the network-side activity tracking application, and may collect data from and store data to the memory 48. In at least one embodiment, the user interface may suitably include an LCD touch screen or the like, a mouse or other pointing device, a keyboard or other keypad, speakers, and a microphone, as will be recognized by those of ordinary skill in the art. Accordingly, the user interface is configured to provide an administrator or other authorized user with access to the memory 48 and allow the authorized user to amend, manipulate and display information contained within the memory.
Activity Tracking ApplicationThe client-side activity tracking applications, stored in the memory 38 of the electronic display device 30 and/or the memory 28b of the activity monitoring device 20b, at least includes instructions for enabling a user to track a plurality of performance metrics during an activity or workout. Particularly, the activity tracking application includes instructions for collecting and processing fitness data during an activity or workout to provide various performance metrics to the user. The term “performance metric” as used herein refers to any standard of measurement relevant to an assessment of the performance, fitness, and health of the user during an activity or workout, or series of activities or workouts. In some cases, the raw measured fitness data is processed substantially to provide a performance metric, but in other cases, measured fitness data may simply be organized into a more presentable form to provide the performance metric. Performance metrics can be generally be considered a further type of fitness data, as defined above. Some examples of performance metrics include heart rate sensor data expressed as beats per minute during an activity or workout, acceleration data expressed a total number of steps during an activity or workout, GPS data expressed as a total distance traversed during an activity or workout, GPS data expressed as positions over time and/or a route/path of the user during an activity or workout, GPS data expressed as an speed/pace over time or average speed/pace during an activity or workout, GPS data or altimeter data expressed as an elevation over time during an activity or workout, fitness data expressed as an estimated number of calories burned, time data expressed a total amount of time spent during an activity or workout, and fitness data express as a total number of workouts or number of workouts during a particular time period (e.g., workouts per week). Further exemplary performance metrics may include any parameter of fitness data expressed as an average over a particular duration of time (e.g. the duration of the workout), as a data plot over the particular duration of time, as a maximum or minimum over the particular duration of time, as a value for some point in time of particular interest, or as a percentage of a user's health or fitness goal or other standard.
Returning to
Finally, the real-time tracking screen 100b includes a pause/end option 128 which enables the user to pause and end tracking of the plurality of performance metrics during the activity or workout. In one embodiment, in response to the user pressing the pause/end option 128, the processor 37 stops collecting fitness data and displays a menu (not shown) on the display screen 34 from which the user can either resume the tracking the workout or end the workout. In at least one embodiment, once the user has ended the workout, the processor 37 is configured to perform additional processing of the collected fitness data to provide additional performance metrics to the user.
In addition to the screens 100a and 100b, which are shown on the display screen 34 of the electronic display device 30, in some embodiments, the user can interact with the activity tracking application via an interface of the activity monitoring device(s) 20a, 20b. Particularly, in at least one embodiment, the user can start and stop the tracking of the activity or workout using an interface of the activity monitoring device 20b. In one embodiment, the user can press one of the buttons 23 of the activity monitoring device 20b to begin tracking a workout. More particularly, in response to the user pressing one of the buttons 23, the processor 27b is configured to initiate collection of fitness data by the sensors 26b of the activity monitoring devices 20b and, optionally, transmit a start command to the electronic display device 30 using the transmitter/receiver 29. In response to receiving the start command, the processor 37 of the electronic display device 30 is configured to initiate collection of fitness data by any sensors of the electronic display device 30, such as the GPS receiver 31 and/or initiate reception of fitness data from other activity monitoring device(s) 20a. Similarly, the user can press one of the buttons 23 of the activity monitoring device 20b to end and/or pause tracking of the workout. Particularly, in response to the user pressing one of the buttons 23 again, the processor 27b is configured to stop collecting fitness data from sensors 26b of the activity monitoring devices 20b and, optionally, transmit a pause and/or end command to the electronic display device 30 using the transmitter/receiver 29. In response to receiving the pause and/or end command, the processor 37 of the electronic display device 30 stops collecting fitness data. In one embodiment, the user taps one of the buttons 23 to pause tracking and either taps one of the buttons 23 again to restart tracking or taps another of the buttons 23 to end tracking. In one embodiment, in response to the ending of the collection of fitness data, the processor 37 of the electronic display device 30 is configured to operate the transmitter/receiver 39 to transmit the fitness data to the system server 40 for processing.
Methods for operating the fitness tracking system 10 are described below. In particular, methods of operating the electronic display device 30 and/or the activity monitor device(s) 20a, 20b to provide running gait coaching. In the description of the methods, statements that a method is performing some task or function refers to a controller or general purpose processor executing programmed instructions stored in non-transitory computer readable storage media operatively connected to the controller or processor to manipulate data or to operate one or more components in the fitness tracking system 10 to perform the task or function. Particularly, the processor 37 of the electronic display device 30, the processor 47 of the system server, and/or the processor 27a, 27b of the activity monitoring device(s) 20a, 20b above may be such a controller or processor. Alternatively, the controller or processor may be implemented with more than one processor and associated circuitry and components, each of which is configured to form one or more tasks or functions described herein. Additionally, the steps of the methods may be performed in any feasible chronological order, regardless of the order shown in the figures or the order in which the steps are described.
Method of Modeling Ideal Gait MetricsThe method 200 begins with a step of receiving first historical run data regarding runs of a first plurality of users, the first historical run data including, for each run, a gait metric for the respective run, a pace during the respective run, and at least one physiological characteristic of the respective user, the gait metric being at least one of (i) a stride cadence and (ii) a stride length (block 210). Particularly, with respect to the embodiments described in detail herein, the processor 47 of the system server is configured to execute instructions of the network-side activity tracking application to receive and/or read from the memory 48 fitness data 44 corresponding to a plurality of runs of a plurality of users (which may also be referred to as “run data”), which was received from a plurality of electronic display devices (e.g., the electronic display device 30) and/or activity tracking devices (e.g., the activity tracking devices 20a, 20b). Particularly, as discussed above, the client-side activity tracking application of the electronic display device 30 and/or the activity tracking device 20b enables a user to collect fitness data during an activity, such as running. After a run has been completed, the processor 37 of the electronic display device 30 and/or the processor 27b of the activity tracking device 20b is configured to operate the transmitter/receiver 39 and/or the transmitter/receiver 29b to transmit the fitness data to the system server 40 for processing and storage.
Over time, the processor 47 of the system server 40 is configured to receive, and store in the memory 48, fitness data 44 corresponding to a large number of runs performed by a broad and diverse population of users. For each run, the collected fitness data 44 comprises a pace/speed during the respective run, at least one physiological characteristic of the respective user, and at least one gait metric for the respective run. In at least one embodiment, the at least one physiological characteristic includes a height of the respective user, a sex of the respective user, a weight of the respective user, and/or an age of the respective user. In at least one embodiment, the at least one gait metric is a stride cadence or frequency during the respective run and/or a stride length during the respective run. In further embodiments, the at least one gait metric may include ground contact time and/or foot strike forces/directions.
The method 200 continues with a step of determining regression coefficients for at least one gait metric model by performing a regression of the first historical run data, the at least one gait metric model being configured to output the gait metric given inputs of pace, and the at least one physiological characteristic (block 220). Particularly, the processor 47 of the system server 40 is configured to execute instructions of the network-side activity tracking application to generate at least one gait metric model, equation, and/or function configured to output a target value for a gait metric based on inputs at least including a pace and at least one physiological characteristic. In one embodiment, the at least one gait metric model is configured to output the target value for the gait metric based on inputs at least including a pace, a height, an age, a sex, and a weight. In some embodiments, the at least one gait metric model is configured to output a target value for one of stride length and stride cadence. In some embodiments, the processor 47 is configured to generate a plurality of gait metric models, each configured to output a target value for a different gait metric (e.g., stride cadence, stride, ground contact time, and foot strike forces or directions) based on inputs at least including a pace and at least one physiological characteristic (e.g., height, age, sex, and weight).
The processor 47 is configured to generate the at least one gait metric model based on the fitness data 44 corresponding to a large number of runs performed by a broad and diverse population of users. Particularly, in at least one embodiment, the fitness data 44 includes data corresponding to inputs (e.g., pace, height, age, sex, and weight) and the outputs (e.g., stride cadence, stride, ground contact time, and foot strike forces or directions) of the at least one gait metric model. The processor 47 is configured to perform a regression of the fitness data 44 to determine a plurality of regression coefficients and, optionally, a regression constant. Particularly, in one embodiment, each gait metric model takes the form of equation 1:
gait metric=A*height+B*weight+C*sex+D*age+E*pace+F*pace2+G (1),
where A, B, C, D, E, and F are regression coefficients and G is a regression constant. We note that, as used herein the term “regression coefficient” refers to a value that is multiplied by a variable input term in the gait metric model and the term “regression constant” refers to a value that is added or subtracted in the gait metric model. Additionally, it will be appreciated that the regression coefficients define the ‘shape’ of the model, whereas the regression constant defines the offset or so-called ‘Y-intercept’ of the model. As can be seen in equation 1, the influence of pace on the target value for the gait metric is expressed in a polynomial manner by including both a pace term and a pace2 term. In other embodiments, the influence of other inputs may also be expressed with higher ordered terms or in a polynomial manner.
The processor 47 is configured to determine and store in the memory 48 a set of regression coefficients A, B, C, D, E, and F for each gait metric model. Thus, for example, if the at least one gait metric model includes a stride length model and a stride cadence model, then a unique set of regression coefficients A, B, C, D, E, and F are determined and stored for each gait metric model. Additionally, a value for the regression constant G may also be determined in the regression of the fitness data 44. However, as discussed below, this value for the regression constant G will be replaced and/or updated based on a further regression of a more limited set of expert fitness data 46.
The method 200 continues with a step of receiving second historical run data regarding runs of a second plurality of users, the second historical run data including, for each run, the gait metric for the respective run, a pace during the respective run, and the at least one physiological characteristic of the respective user (block 230). Particularly, the processor 47 of the system server 40 is configured to execute instructions of the network-side activity tracking application to receive and/or read from the memory 48 expert fitness data 46 corresponding to a plurality of runs of a plurality of expert users (which may also be referred to as “expert run data”). The plurality of expert users comprises a limited set of runners considered to be experts at running. In one embodiment, the expert fitness data 46 is a manually curated set of fitness data which is similar to the fitness data 44, but corresponds only to runs performed by expert runners. In another embodiment, the expert fitness data 46 is a subset of the fitness data 44 corresponding only to runs performed by users who have recorded a predetermined threshold number of runs (e.g. users who have recorded fitness data for over 100 runs) or have met some other criteria indicative of running expertise. In either case, the expert fitness data 46 differ from the fitness data 44 in that, rather than corresponding to a large number of runs performed by a broad and diverse population of users, the expert fitness data 46 corresponds to a more limited number of runs performed by a more narrowly defined population of expert runners.
The method 200 continues with a step of determining a regression constant for at least one gait metric model by performing a regression of the second historical run data (block 240). Particularly, the processor 47 of the system server 40 is configured to execute instructions of the network-side activity tracking application to modify the at least one gait metric model, discussed above, based on the expert fitness data 46 corresponding to the more limited number of runs performed by the more narrowly defined population of expert runners. Particularly, in at least one embodiment, much like the fitness data 44, the expert fitness data 46 includes data corresponding to inputs (e.g., pace, height, age, sex, and weight) and the outputs (e.g., stride cadence, stride, ground contact time, and foot strike forces or directions) of the at least one gait metric model. The processor 47 is configured to perform a regression of the expert fitness data 46 to determine at least a regression constant for the at least one gait metric model. Particularly, in the exemplary embodiment in which each gait metric model takes the form of equation 1 above, the processor 47 is configured to perform a regression of the expert fitness data 46 to determine the value G. Any initial value for G previous determined based on the previous regression of the fitness data 44 may be ignored and/or updated. The processor 47 is configured to determine and store in the memory 48 a regression constant G for each gait metric model. Thus, for example, if the at least one gait metric model includes a stride length model and a stride cadence model, then a unique value for G is determined and stored for each model.
In at least one embodiment, the processor 47 is configured to transmit the values for the regression coefficients and the regression constant to the electronic display device 30 and/or the activity monitoring device(s) 20a, 20b for usage of the at least one gait metric model thereat.
In summary, the values of the regression coefficients A, B, C, D, E, and F are determined based on a regression of the fitness data 44, whereas the regression constant G is determined based on a regression of the expert fitness data 46. As a result, the ‘shape’ of each gait metric model is determined based on running data from a broad diverse population of users, thereby providing a robust estimation of how pace and physiological characteristics such height, age, weight, and sex influence the value for the corresponding gait metric (e.g., stride cadence, stride, ground contact time, and foot strike forces or directions). At the same time, the offset and/or Y-axis intercept of each gait metric model is determined based on running data from a more limited set of expert users, thereby providing a better indication of what an optimal and/or efficient value for the at least one gait metric.
It will be appreciated that, if the regression coefficients A, B, C, D, E, and F and the regression constant G were all determined based only on a regression of the fitness data 44, the resulting gait metric model would be one that predicts an expected value for the corresponding gait metric, rather than an optimal and/or efficient value for the corresponding gait metric. Similarly, if the regression coefficients A, B, C, D, E, and F and the regression constant G were all determined based only on a regression of the expert fitness data 46, the resulting gait metric model would lack a robust understanding of how physiological characteristics such height, age, weight, and sex influence the corresponding gait metric, because the more limited set of expert runners are likely to have much less diverse physiological characteristics than the broader population. Accordingly, the gait metric model developed according to the method 200 is clearly improved compared to models developed from a regression of a single data set.
Method of Providing Coaching of Ideal Gait MetricsIt will be appreciated that, although the method 300 is discussed below primarily with respect to the processor 37 of the electronic display device 30, at least the processor 27b of the activity monitoring device 20b, which is provided in the form of a so-called “smart” watch, may also execute instructions of a client-side activity tracking application to perform some or all of the steps of the method 300. Additionally, in some embodiments, the processor 47 of the system server 40 may execute instructions of a network-side activity tracking application to perform certain steps of the method 300.
The method 300 begins with a step of receiving first run data from an activity monitoring device associated with a first user, the activity monitoring device having at least one biometric sensor configured to measure the first run data during a first run of the first user (block 310). Particularly, with respect to the embodiments described in detail herein, the processor 37 of the electronic display device 30 is configured to execute instructions of the client-side activity tracking application to receive fitness data corresponding to a run of a user from the activity monitoring device(s) 20a, 20b and any sensors of the electronic display device 30. In some embodiments, as discussed above, in response to the user pressing the start option 102 (see
The method 300 continues with a step of determining a gait metric for the first run based on the first run data, the gait metric being at least one of (i) a stride cadence and (ii) a stride length (block 320). Particularly, the processor 37 is configured to execute instructions of the client-side activity tracking application to calculate a value for at least one gait metric for the run based on the received fitness data corresponding to the run. In at least one embodiment, the processor 37 is configured to calculate an average value for at least one gait metric for the run based on the received fitness data corresponding to the run. In at least one embodiment, the processor 37 is configured to calculate a plurality of timestamped values for at least one gait metric over the duration of the run based on the received fitness data corresponding to the run. In at least one embodiment, the processor 37 is configured to calculate real-time values for the at least one gait metric based on fitness data received in real time during the run. In one embodiment, the processor 37 is configured to calculate the at least one gait metric for the run based on acceleration data or the like received from the sensors 26a of the activity monitoring device 20a. In at least one embodiment, the at least one gait metric is one or more of a stride length over time, an average stride length, a stride cadence over time, and an average stride cadence. In further embodiments, the at least one gait metric may further include ground contact time and/or foot strike forces or directions.
The method 300 continues with a step of determining a pace during the first run based on the first run data (block 330). Particularly, the processor 37 is configured to execute instructions of the client-side activity tracking application to calculate a pace/speed of the run based on the received fitness data corresponding to the run. In at least one embodiment, the processor 37 is configured to calculate an average pace/speed of the run based on the received fitness data corresponding to the run. In at least one embodiment, the processor 37 is configured to calculate a plurality of timestamped values for pace/speed over the duration of the run based on the received fitness data corresponding to the run. In at least one embodiment, the processor 37 is configured to calculate real-time values for pace/speed based on fitness data received in real time during the run. In one embodiment, the processor 37 is configured to calculate the pace of the run based on position data received from the GPS receiver 31. In another embodiment, the processor 37 is configured to calculate the pace of the run based on acceleration data, speed data, position data, or the like received from the sensors 26a of the activity monitoring device 20a.
The method 300 continues with a step of determining a gait metric target for the first run based on at least one gait metric model, determined regression coefficients of the at least one gait metric model, a determined regression constant of the at least one gait metric model, the pace during the first run, and at least one physiological characteristic of the first user (block 340). Particularly, the processor 37 is configured to execute instructions of the client-side activity tracking application to calculate a target value for the at least one gate metric using at least one gait metric model (i.e. one or more of the gait metric models developed in the method 200, above) based on the determined pace and at least one physiological characteristic of the user. Particularly, the processor 37 is configured to receive the calculated regression coefficients (e.g., A, B, C, D, E, and F of equation 1) and regression constant (e.g., G of equation 1) for the at least one gait metric model from the system server 40 and/or read the calculated regression coefficients and regression constant from the memory 38. Using the at least one gait metric model, the processor 37 is configured to calculate a target value for the at least one gait metric based on the determined pace and at least one physiological characteristic of the user. In one embodiment, the at least one physiological characteristic of the user includes a height of the user, an age of the user, a sex of the user, and/or a weight of the user. The at least one physiological characteristic may be stored in the memory 38 in association with a user profile of the user or received from the system server 40. In one embodiment, target value for the at least one gate metric include a target value for stride length and/or a target value for stride cadence. In further embodiments, target value for the at least one gate metric may further include a target value for ground contact time and/or a target value for foot strike force or direction.
As illustrated in more detail below, the target values can take various forms. Particularly, in at least one embodiment, the target values are average target values that are determined using an average pace for the run. In at least one embodiment, the target values are a plurality of timestamped target values over the duration of the run that are determined using a plurality of timestamped pace values over the duration of the run. In at least one embodiment, the target values are real-time target values that are determined using real-time pace values during the run. In at least one embodiment, the processor 37 is configured to determine a target range around the target value for the gait metric. In one embodiment, a size of the range around the target value for the gait metric depends on a confidence factor of the at least one gait metric model. In one embodiment, a size of the range around the target value for the gait metric is predetermined for each type of gait metric model.
The method 300 continues with a step of displaying a comparison of the gait metric with the gait metric target to the first user on a personal electronic device associated with the first user (block 350). Particularly, the processor 37 is configured to execute instructions of the client-side activity tracking application to display a comparison of the determined value for the at least one gait metric with the target value for the at least one gait metric. In at least one embodiment, the processor 37 is configured to display a comparison of the average value for the at least one gait metric for the run with the target average value for the at least one gait metric for the run. In at least one embodiment, the processor 37 is configured to display a comparison in the form of a graph of the plurality of timestamped values for the at least one gait metric over the duration of the run with the plurality of timestamped target values for the at least one gait metric over the duration of the run. In at least one embodiment, the processor 37 is configured to display a comparison of the real-time value for the at least one gait metric during the run with the real-time target value for the at least one gait metric during the run. In at least one embodiment, the processor 37 is configured to display a comparison of the determined value for the at least one gait metric with a predetermined range around the target value for the at least one gait metric. In at least one embodiment, the processor 37 is configured to operate the display screen 34 of the electronic display device to display the comparison. In another embodiment, the processor 27b is configured to operate the display screen 24 of the activity monitoring device 20b to display the comparison.
In at least one embodiment, the processor 37 is configured to enable the user to view the comparison of the determined gait metric value with the gait metric target value after the run has already been performed via a post-workout screen of the client-side activity tracking application.
Exemplary Post-Workout Gait Metric Comparison and AnalysisThe post-workout screen 400 includes gait coaching banner 414 (e.g., “You Have a Personalized Coach Tip! Tap Here to View”), which can be pressed by the user to display gait coaching information including the comparison of the determined gait metric value with the gait metric target value. Particularly, in response the user pressing or otherwise selecting the coaching banner 414, the processor 37 is configured to operate the display screen 34 to display one or more gait coaching screens of the client-side activity tracking application which compare the user's gait with an ideal gait for the particular user, and provide guidance for how to adjust his or her gait to achieve the ideal gait. It will be appreciated that, in some embodiments, the processor 27b is configured to operate the display screen 24 of the activity monitoring device 20b to display an analogous post-workout screen and/or gait coaching screens.
The gait metric comparison 508 includes a gait metric 510 having a value and label (e.g., a value “168” for the “AVG CADENCE” gait metric) and a gait metric target 512 having a value and label (e.g., a value “172-188” for the “TARGET RANGE”). The gait metric 510 shows the value (e.g., 168 steps per minute) of one of the determined gait metrics for the run (see block 320 of
The gait metric comparison 508 further includes a title 514 (e.g., “YOUR CADENCE”) and a comparison summary 516 (e.g., “OUTSIDE OF RANGE”). The title 514 indicates which gait metric or gait metrics that are the subject of the gait metric comparison 508. The comparison summary 516 includes a short summary of how the runner's gait metric (e.g., cadence or stride length) compares with the corresponding target value for the gait metric. In one embodiment, the processor 37 is configured to display a first summary (e.g., “OUTSIDE OF RANGE”) in response to the determined gait metric (e.g., 168 steps per minute) being outside of a first predetermined range around (e.g., ±8 steps per minute) the determined gait metric target value (e.g., 180 steps per minute). In one embodiment, the processor 37 is configured to display a second summary (e.g., “IN RANGE”) in response to the determined gait metric (e.g., 173 steps per minute) being within the first predetermined range (e.g., ±8 steps per minute) around the determined gait metric target value (e.g., 180 steps per minute). In one embodiment, the processor 37 is configured to display a third summary (e.g., “IDEAL RANGE”) in response to the determined gait metric (e.g., 178 steps per minute) being within a second predetermined range (e.g., ±3 steps per minute) around the determined gait metric target value (e.g., 180 steps per minute) that is smaller than the first predetermined range.
The gait metric comparison 508 further includes gait metric tips 518 (e.g., “Your cadence is slower than expected for your height and pace.” and “This may impact your injury risk. On your next run, keep your posture upright and take faster steps”). In at least one embodiment, the memory 38 stores a plurality of possible messages to include in the gait metric tips 518. In one embodiment, over several runs the processor 37 is configured to select which messages to include in the gait metric tips 518 according to a predetermined sequence. In one embodiment, the processor 37 is configured select at least some of the possible messages to include in the gait metric tips 518 depending on whether the determined gait metric is greater than or less than the determined gait metric target. In one embodiment, the processor 37 is configured select at least some of the possible messages to include in the gait metric tips 518 depending on whether the determined gait metric is within or without the first predetermined range (e.g., ±8 steps per minute) around the determined gait metric target value or within the second predetermined range (e.g., ±3 steps per minute), as similarly described with respect to the comparison summary 516.
In some embodiments, the processor 37 is configured select at least some of the possible messages to include in the gait metric tips 518 depending special circumstances of the run (e.g., the run was on a treadmill or the run was on a hill). For example, since it is known that a treadmill impacts running gait for most runners, the processor 37 is configured select unique messages for the gait metric tips 518 when records a treadmill run (e.g., “It's common for runners to see a decrease in their cadence when on a treadmill, so next time make an extra effort to think ‘quick feet! ’”). Similarly, if analysis of the run data reveals that the run was performed on a hill, the processor 37 is configured select unique messages for the gait metric tips 518 when records a hill run (e.g., “It's common for a runners to see a decrease in stride length when running up hill, so next time make an extra effort to maintain a consistent stride length when going up a hill.”).
In some embodiments, the processor 37 is configured select the messages included in the encouragement message 506, the comparison summary 516, and/or the gait metric tips 518 depending not only the gait metric 510 and gait metric target 512 for the particular run, but also on the performance of the user during a previous run. Particularly, the messages included in the encouragement message 506, the comparison summary 516, and/or the gait metric tips 518 may include a ‘follow up’ message that relates the user's performance to his or her previous performance. For example, if during the previous run the user's determined gait metric fell below the respective gait metric target range but during this particular run the user's determined gait metric fell within the target range or was closer to the target range, then the encouragement message 506 or the comparison summary 516 might include a message that acknowledges that the user has now achieved his or her target gait metric (e.g., “You increased you cadence. Good Job!”). Similarly, if during the previous run the user's determined gait metric fell within the respective gait metric target range but during this particular run the user's determined fell outside the target range, then the gait metric tips 518 might include a tip that points out that the gait metric is trending in the wrong direction (e.g., “On this run, your stride length is longer than expected for your height and pace. Stride length can vary run to run but, this may impact your injury risk. On your next run, try to match the form of your previous run.”).
As discussed above the at least one gait metric model may include individual models for several different gait metrics. Particularly, the gait metric models may include a stride cadence model, a stride length model, a ground contact time model, and a foot strike model. In one embodiment, after each run performed by the user, the processor 37 is configured to select which gait metric to be subject of the gait coaching screen 500a based on a how many runs the user has recorded. For example, in one embodiment, for the first predetermined number of runs (e.g., 15 runs), the gait coaching screen 500a may only relate to stride length or stride cadence, but after the predetermined number of runs, more advanced gait metrics may be introduced, such as ground contact time and foot strike. In one embodiment, over several runs the processor 37 is configured to select which gait metric to be subject of the gait coaching screen 500a according to a predetermined sequence.
The gait coaching screen 500c further includes a projected pace input 536 having a value and label (e.g., a value “8:10” for the “PROJECTED AVG PACE”), as well as adjustment options 538 (e.g., plus and minus buttons) which can be pressed by the user to adjust the value of the projected pace input 536. In response to the user adjusting the value of the projected pace input 536, the processor 37 is configured to recalculate the target value for the gait metric and/or the range around the target value based on the value of the projected pace input 536 in the same manner described above with respect to block 340 of
Finally, the gait coaching screen 500c further includes a reminder option 540 having a check box and a description (e.g., “Remind Me Before Next Workout” and “Get a reminder about what your cadence should be before your next workout”). In response to the user selecting the check box of the reminder option 540, the processor 37 is configured to display a reminder which includes the gait metric target 534 to the user before his or her next workout. In one embodiment, the processor 37 is configured to display the reminder in response to the user pressing the start option 102 (see
In some embodiments, the gait coaching will change over time as the user records more runs and becomes a more experienced runner. Particularly, in one embodiment, if the user has recorded run data for less than a predetermined number of runs (e.g., less than 5 runs), then the processor 37 is configured to display the gait coaching screen 500a having the gait metric comparison 508 in which an average of the gait metric in is displayed in comparison with an average of the gait metric target for the respective run. However, if the user has recorded run data for greater than or equal to the predetermined number of runs, then the processor 37 is configured to display a gait coaching screen having a more detailed comparison of the gait metric with the gait metric target. Alternatively, in some embodiments, the processor 37 is configured to process the run data to determine whether the runner has achieved a stable and/or consistent gait metric. In one embodiment, if the user has not yet achieved a stable and/or consistent gait metric, then the processor 37 is configured to display the gait coaching screen 500a. However, if the user has achieved a stable and/or consistent gait metric, then the processor 37 is configured to display the gait coaching screen having the more detailed comparison of the gait metric with the gait metric target. In at least one embodiment, the more detailed gait metric comparison is in the form of a graph depicting the gait metric in comparison with the gait metric target over time during the respective run.
The gait metric comparison 542 includes a title 544 (e.g., “YOUR CADENCE”), a comparison summary 546 (e.g., “87% IN TARGET RANGE”), and a gait metric tips 548 (e.g., “As your speed fluctuates up or down, your cadence should also fluctuate up or down”). The title 514 indicates which gait metric or gait metrics are the subject of the gait metric comparison 542. The comparison summary 546 includes a short summary of how the runner's gait metric (e.g., cadence or stride length) compares with the corresponding target value for the gait metric. In one embodiment, the processor 37 is configured to calculate a percentage of time during the run that the user's gait metric was within a predetermined range of the target value for the gait metric and the comparison summary indicates the percentage (e.g., 87%). The gait metric tips 548, which are similar to those of previously described gait coaching screens, provide coaching or advice regarding the gait metric, such as a message indicating how the gait metric should change over time with changes in pace/speed.
The gait metric comparison 542 includes a graph 550 which depicts a gait metric value 552 over time during the run in comparison with a range 554 around the gait metric target value over time during the run. In one embodiment, the processor 37 is configured to determine, for a plurality of different timestamped gait metric values, whether the gait metric is within or without a first predetermined range (e.g., ±8 steps per minute) around the gait metric target value or within a second predetermined range (e.g., ±3 steps per minute) that is smaller than the first predetermined range.
In one embodiment, the processor 37 is configured to shade or color the range 554 different depending on the whether the gait metric is within or without the first predetermined range or within the second predetermined range. The gait metric comparison 542 includes a legend 556 which indicates the meaning of the shading or coloring of the range 554. In one embodiment, the processor 37 is configured to display a region of the range 554 with a first shading or coloring (e.g., “OUT OF RANGE”) in response to the determined gait metric being outside of the first predetermined range around (e.g., ±8 steps per minute) the determined gait metric target value. In one embodiment, the processor 37 is configured to display a region of the range 554 with a second shading or coloring (e.g., “IN RANGE”) in response to the determined gait metric being within the first predetermined range (e.g., ±8 steps per minute) around the determined gait metric target value. In one embodiment, the processor 37 is configured to display a region of the range 554 with a third shading or coloring (e.g., “IDEAL RANGE”) in response to the determined gait being within the second predetermined range (e.g., ±3 steps per minute) around the determined gait metric target value.
The gait metric comparison 558 includes a plurality of columns corresponding to different runs that have been recorded by the user. In one embodiment, the columns correspond to the most recent predetermined number (e.g., 4) of runs. Each column includes a date label 566 (e.g., “FEB 28,” “MAR 3,” “MAR 8,” and “MAR 12”) which indicates the date and/or time of the respective run. Each column includes a distance performance metric 568 (e.g., “3.51 MI,” “3.51 MI,” “3.51 MI,” and “3.51 MI”) which indicates the distance traveled during the respective run and an average pace performance metric 570 (e.g., “AVG PACE” of “8:23,” “8:28,” “8:48,” and “9:03”) which indicates the average pace/speed during the respective run. Each column includes a first comparison 572 of a first gait metric with its respective target range (e.g., “TIME IN CADENCE RANGE (%)” of “87,” “68,” “84,” and “97”) and a second comparison 574 of a second gait metric with its respective target range (e.g., “TIME IN STRIDE LENGTH RANGE (%)” of “71,” “57,” “76,” and “88”). In one embodiment, the processor is configured to shade, color, or otherwise mark the comparisons 572 and 574 depending on values of the comparisons (e.g., the percentages, as illustrated). In the illustrated embodiment, each percentage value of the comparisons 572 and 574 is encompassed by a circle having a size that is dependent on the percentage value.
The gait metric comparison 576 includes a graph 584 which depicts gait metric values 586 for a plurality of workouts in comparison with a range 588 around gait metric target values for a plurality of workouts. In the illustrated embodiment, the gait metric value 586 for each workout date 590 is depicted as a small circle and the bounds of the range 588 are depicted as dashed lines. In one embodiment, the gait metric values 586 and dates 590 correspond to the most recent predetermined number (e.g., 4) of runs.
In some embodiments, gait coaching can be provided to the user in real-time during a run. Particularly, in one embodiment, the processor 27b of the activity monitoring device is configured to provide real-time comparisons and feedback with respect to one or more gait metrics during a run. In some embodiments, the processor 27b of the activity monitoring device 20b is configured to operate the display screen 24 to display the real-time comparisons and feedback. In further embodiments, the processor 27b may be configured to provide the real-time comparisons and feedback to the user audibly using an audio device such as a speaker or headphones worn by the user.
Method of Providing Real-Time Gait Metric FeedbackThe method 600 begins with a step of receiving first real-time run data from an activity monitoring device associated with a first user, the activity monitoring device having at least one biometric sensor configured to measure the first real-time run data during a first run of the first user (block 610). Next, the method 600 continues with steps of determining a real-time value of a gait metric during the first run based on the first real-time run data, the gait metric being at least one of (i) a stride cadence and (ii) a stride length (block 620) and determining a real-time pace during the first run based on the first real-time run data (block 630). The method 600 continues with a step of determining a real-time gait metric target during the first run based on at least one gait metric model, determined regression coefficients of the at least one gait metric model, a determined regression constant of the at least one gait metric model, the real-time pace during the first run, and at least one physiological characteristic of the first user (block 640). The steps 610, 620, 630, and 640 of the method 600 are essentially similar to the steps 310, 320, 330, and 340 of the method 300 described in detail above, except that the steps are performed in real-time during a run using real-time fitness data. Accordingly, the steps 610, 620, 630, and 640 of the method 600 are not described again in detail. Furthermore, as with the method 300, it will be appreciated that one or both of the processor 37 of the electronic display device 30 and the processor 27b of the activity monitoring device 20b may execute instructions of a client-side activity tracking application to perform some or all of the steps of the method 600. Additionally, in some embodiments, the processor 47 of the system server 40 may execute instructions of a network-side activity tracking application to perform certain steps of the method 600.
The method 600 continues with a step of providing perceptible feedback to the first user depending on a comparison of the real-time value of the gait metric with the real-time gait metric target to the first user using a personal electronic device associated with the first user (block 650). Particularly, the processor 37 of the electronic display device 30 and/or the processor 27b of the activity monitoring device 20b is configured to execute instructions of the client-side activity tracking application to provide real-time perceptible feedback to the user depending on a comparison of the determined value for the at least one gait metric with the target value for the at least one gait metric. In at least one embodiment, the processor 37 is configured to operate the display screen 34 of the electronic display device to display the feedback. In another embodiment, the processor 27b is configured to operate the display screen 24 of the activity monitoring device 20b to display the feedback. In one embodiment, the processor 37 and/or the processor 27b is configured to operate an audio device of one of the devices 30 and/or 20b (not shown), such as a speaker or headphones, to provide the feedback audibly.
In at least one embodiment, the processor 37 and/or the processor 27b is configured to display a comparison of the real-time value for the at least one gait metric during the run with the real-time target value for the at least one gait metric during the run. In at least one embodiment, the processor 37 and/or the processor 27b is configured to display a comparison of the real-time value for the at least one gait metric with a predetermined range around the real-time target value for the at least one gait metric.
In at least one embodiment, the processor 37 and/or the processor 27b is configured to provide a feedback message instructing the user to adjust the gait metric (e.g., stride length or cadence) up or down in response to the real-time value for the at least one gait metric being outside a predetermined range of the real-time target value for the at least one gait metric. In at least one embodiment, the processor 37 and/or the processor 27b is configured to provide a feedback message instructing the user to maintain the real-time target value for the at least one gait metric at one of (i) a defined time during the run and (ii) a defined distance traveled during the run. In at least one embodiment, the processor 37 and/or the processor 27b is configured to determine the defined time during the run and/or the defined distance traveled during the run based on an analysis of fitness data corresponding to previously recorded runs of the user.
Exemplary Real-Time Gait Method FeedbackIn one embodiment, during a run, the processor 37 and/or the processor 27b is configured to provide an instruction to the user to maintain the target value for the at least one gait metric during a particular interval of time during the run (herein after referred to as “form intervals”). During the form interval, the processor 37 and/or the processor 27b is configured to monitor whether the real-time value of the least one gait metric is within the predetermined range of real-time target value for the at least one gait metric. In one embodiment, the processor 37 and/or the processor 27b is configured to provide a feedback message indicating whether the real-time value of the gait metric is within predetermined range during the form interval. In one embodiment, the processor 27b is configured to operate the display screen 24 to display a comparison of the real-time value of the gait metric with the real-time gait metric target during the form interval. These form intervals motivate the user to focus on their running gait/form for a limited interval of time. By instructing the user to focus on their running form during short bursts of time, the user is better able to understand and contrast how it feels to run with an ideal gait and can more easily adopt the ideal gait as his or her normal running form.
The gait metric comparison 902 includes a title 904 (e.g., “Your Cadence (SPM)”), a gait metric 906 having a value and label (e.g., a value “167” for “YOUR AVERAGE”) and a gait metric target 908 having a value and label (e.g., a value “170-175” for the “TARGET RANGE”), which are similar to the features of previously discussed gait coaching screens. The gait metric comparison 902 includes a graph 910 which depicts a gait metric value 912 over time during the run and form intervals 914. In one embodiment, the processor 37 is configured to shade, color, or otherwise mark intervals of time in the graph 910 that correspond to the form intervals 914. Finally, the gait coaching screen 900 includes gait metric tips 916, which are similar to the gait metric tips discussed with respect to previously described gait coaching screens.
The herein described applications (e.g., the client-side activity tracking application and the network-side activity tracking application) improve the functioning of the electronic display device 30, the remote system server 40, and/or activity tracking devices 20a, 20b, respectively or in combination by enabling it/them to provide gait coaching which is individualized to a physiological characteristics of a particular user and to the pace of a particular run. As discussed above, the method 200 improves upon the functioning of the processor 47 of the system server 40 and/or the processor 37 of the electronic display device 30 by providing a gait metric model that advantageously incorporates running data from a broad diverse population of users, but also specifically considers running data from expert runners. Particularly, the ‘shape’ of the gait metric model is determined based on running data from a broad diverse population of users, thereby providing a robust estimation of how pace and physiological characteristics such height, age, weight, and sex influence the value for the at least one gait metric. At the same time, the offset and/or Y-axis intercept of the gait metric model is determined based on expert running data from a more limited set of expert users, thereby providing a better indication of what an optimal and/or efficient value for the at least one gait metric. Devices that are able to use the gait metric model developed in this way can operate more efficiently to provide useful and effective gait coaching to users.
Particularly, as discussed above, the method 300 improves upon the functioning of the processor 37 of the electronic display device 30 and/or the processor 27a, 27b of the activity monitoring device(s) 20a, 20b by advantageously providing the runner with an evaluation of his or her running gait in comparison with an optimal running gait that is determined based on the particular physiological characteristics of the individual and based on the particular pace of the individual run. In this way, the user can be confident in how to modify his or her running gait during his or her next run. Similarly, the method 600 improves upon the functioning of the processor 37 of the electronic display device 30 and/or the processor 27a, 27b of the activity monitoring device(s) 20a, 20b by advantageously providing the runner with a real-time evaluation of his or her running gait in comparison with an optimal running gait that is determined based on the particular physiological characteristics of the individual and based on the real-time pace during the run. In this way, the user can more easily learn to run with an ideal and efficient gait.
In another embodiment, a permanent copy of the programming instructions for individual ones of the aforementioned applications (e.g., the client-side activity tracking application and the network-side activity tracking application) may be placed into permanent storage devices (such as e.g., memory 28a, 28b, memory 38, and/or memory 48) during manufacture thereof, or in the field, through e.g., a distribution medium (not shown), such as a compact disc (CD), or through the transmitter/receiver 29a, 29b and/or the transmitter/receiver 39 (from the system server 40). That is, one or more distribution media having an implementation of the agent program may be employed to distribute the agent and program various computing devices.
The foregoing detailed description of one or more exemplary embodiments of the activity tracking application has been presented herein by way of example only and not limitation. It will be recognized that there are advantages to certain individual features and functions described herein that may be obtained without incorporating other features and functions described herein. Moreover, it will be recognized that various alternatives, modifications, variations, or improvements of the above-disclosed exemplary embodiments and other features and functions, or alternatives thereof, may be desirably combined into many other different embodiments, systems or applications. Presently unforeseen or unanticipated alternatives, modifications, variations, or improvements therein may be subsequently made by those skilled in the art which are also intended to be encompassed by the appended claims. Therefore, the spirit and scope of any appended claims should not be limited to the description of the exemplary embodiments contained herein.
It will be appreciated that the various ones of the foregoing aspects of the present disclosure, or any parts or functions thereof, may be implemented using hardware, software, firmware, tangible, and non-transitory computer readable or computer usable storage media having instructions stored thereon, or a combination thereof, and may be implemented in one or more computer systems.
Claims
1. A method of displaying run data, comprising:
- receiving first historical run data regarding runs of a first plurality of users, the first historical run data including, for each run, a gait metric for the respective run, a pace during the respective run, and at least one physiological characteristic of the respective user, the gait metric being at least one of (i) a stride cadence and (ii) a stride length;
- determining regression coefficients for at least one gait metric model by performing a regression of the first historical run data, the at least one gait metric model being configured to output the gait metric given inputs of pace and the at least one physiological characteristic;
- receiving second historical run data regarding runs of a second plurality of users, the second historical run data including, for each run, the gait metric for the respective run, a pace during the respective run, and the at least one physiological characteristic of the respective user;
- determining a regression constant for the at least one gait metric model by performing a regression of the second historical run data;
- receiving first run data from an activity monitoring device carried by a first user during a first run of the first user;
- determining the gait metric for the first run based on the first run data;
- determining a pace during the first run based on the first run data;
- determining a gait metric target for the first run based on the at least one gait metric model, the determined regression coefficients, the determined regression constant, the pace during the first run, and the at least one physiological characteristic of the first user; and
- displaying a comparison of the gait metric with the gait metric target to the first user on a personal electronic device associated with the first user.
2. The method of claim 1, the displaying the comparison further comprising:
- displaying the comparison after a completion of the first run by the first user and prior to a beginning of a second run by the first user, the second run being subsequent in time compared to the first run.
3. The method of claim 2, further comprising:
- displaying instructions to the first user regarding the gait metric based on the comparison on the personal electronic device associated with the first user after the completion of the first run by the first user and prior to the beginning of the second run by the first user.
4. The method of claim 3, the displaying the instructions further comprising:
- displaying the instructions to the first user in response to the first user beginning the second run.
5. The method of claim 2, the displaying the comparison further comprising:
- if the first user has recorded run data for less than a predetermined number of runs, then displaying an average of the gait metric in comparison with an average of the gait metric target over the first run; and
- if the first user has recorded run data for at least the predetermined number of runs, then displaying a graph depicting the gait metric in comparison with the gait metric target over time during the first run.
6. The method of claim 1, the displaying the comparison further comprising:
- displaying the comparison of the gait metric with the gait metric target in relation to a previous comparison of a previous gait metric and a previous gait metric target corresponding to a previous run that was performed prior to the first run.
7. The method of claim 1, wherein the at least one physiological characteristic includes at least one of height, age, weight, and sex.
8. The method of claim 1, wherein the at least gait metric model includes a pace term multiplied by a corresponding one of the regression coefficients and a pace squared term multiplied by a corresponding one of the regression coefficients.
9. The method of claim 8, wherein the at least one gait metric model is expressed as:
- the gait metric=A*(height)+B*(weight)+C*(sex)+D*(age)+E*(pace)+F*(pace){circumflex over ( )}2+G,
- where A, B, C, D, E, and F are the regression coefficients and G is the regression constant.
10. A fitness tracking system:
- a database configured to store: first historical run data regarding runs of a first plurality of users, the first historical run data including, for each run, a gait metric for the respective run, a pace during the respective run, and at least one physiological characteristic of the respective user, the gait metric being at least one of (i) a stride cadence and (ii) a stride length; and second historical run data regarding runs of a second plurality of users, the second historical run data including, for each run, the gait metric for the respective run, a pace during the respective run, and the at least one physiological characteristic of the respective user; and
- a data processor in communication with the database, the data processor being configured to: receive the first historical run data and the second historical run data from the database; determine regression coefficients for at least one gait metric model by performing a regression of the first historical run data, the at least one gait metric model being configured to output the gait metric given inputs of pace and the at least one physiological characteristic; determine a regression constant for the at least one gait metric model by performing a regression of the second historical run data; and transmit the regression coefficients and the regression constant for the at least one gait metric model to at least one personal electronic device of at least one user.
11. The fitness tracking system of claim 10, wherein the first historical run data was generated at least in part by a plurality of activity sensors carried by users in the first plurality of users during the runs of the first plurality of users, at least some sensors in the plurality of activity sensors being integrated with footwear worn by users in the first plurality of users during the runs of the first plurality of users.
12. The fitness tracking system of claim 10, wherein the second plurality of users is a subset of the first plurality of user that have recorded run data for at least a predetermined threshold number of runs.
13. A method of displaying run data, comprising:
- receiving first historical run data regarding runs of a first plurality of users, the first historical run data including, for each run, a gait metric for the respective run, a pace during the respective run, and at least one physiological characteristic of the respective user, the gait metric being at least one of (i) a stride cadence and (ii) a stride length;
- determining regression coefficients for at least one gait metric model by performing a regression of the first historical run data, the at least one gait metric model being configured to output the gait metric given inputs of pace and the at least one physiological characteristic;
- receiving second historical run data regarding runs of a second plurality of users, the second historical run data including, for each run, the gait metric for the respective run, a pace during the respective run, and the at least one physiological characteristic of the respective user;
- determining a regression constant for the at least one gait metric model by performing a regression of the second historical run data;
- receiving first real-time run data from an activity monitoring device carried by a first user during a first run of the first user;
- determining a real-time value of the gait metric during the first run based on the first real-time run data;
- determining a real-time pace during the first run based on the first real-time run data;
- determining a real-time gait metric target during the first run based on the at least one gait metric model, the determined regression coefficients, the determined regression constant, the real-time pace during the first run, and the at least one physiological characteristic of the first user; and
- providing perceptible feedback to the first user during the first run depending on a comparison of the real-time value of the gait metric with the real-time gait metric target to the first user using a personal electronic device associated with the first user.
14. The method of claim 13, the providing the perceptible feedback further comprising:
- displaying the perceptible feedback to the first user on a display device associated with the first user.
15. The method of claim 13, the providing the perceptible feedback further comprising:
- audibly providing the perceptible feedback to the first user using an audio device associated with the first user.
16. The method of claim 13, the providing the perceptible feedback further comprising:
- providing a feedback message instructing the first user to adjust the gait metric in response to the real-time value of the gait metric being outside a predetermined range of the real-time gait metric target.
17. The method of claim 13, the providing the perceptible feedback further comprising:
- providing a feedback message instructing the first user to maintain the real-time gait metric target at one of (i) a defined time during the first run and (ii) a defined distance traveled during the first run.
18. The method of claim 13, further comprising:
- providing an instruction to the first user to maintain the real-time gait metric target during a first interval of time during the first run; and
- monitoring whether the real-time value of the gait metric is within a predetermined range of the real-time gait metric target during the first interval of time.
19. The method of claim 18, the providing the perceptible feedback further comprising:
- providing a feedback message indicating whether the real-time value of the gait metric is within the predetermined range during the first interval of time.
20. The method of claim 18, the providing the perceptible feedback further comprising:
- displaying a comparison of the real-time value of the gait metric with the real-time gait metric target during the first interval of time on a display device associated with the first user.
Type: Application
Filed: May 31, 2022
Publication Date: Sep 22, 2022
Inventors: Hesamoddin Salehian (San Francisco, CA), Jeff Knight (Austin, TX), Marlene Mayfield (San Francisco, CA), Sebastian Johnck (San Francisco, CA)
Application Number: 17/829,272
