Evaluating user breathing and generating customized, data-driven training programs

Abstract

Methods and systems for generating customized, data-driven training plans are disclosed herein. In some implementations, an exemplary system comprises a torso wearable device including a wireless transmitter and a sensor, and non-transitory computer-readable media (CRM). The CRM, when executed by a computing device in communication with the wireless transmitter, can perform operations comprising: receiving input signals representing respiration of a user, generating a first score, a second score, and a third score based on the input signals, selecting one of a first plurality of training sets based on the first score, selecting one of a second plurality of training sets based on the second score, selecting one of a third plurality of training sets based on the third score, and generating a training plan comprising a permutation of one or more of each of the selected ones of the first, second, and third pluralities of training sets.

Description

EVALUATING USER BREATHING AND GENERATING CUSTOMIZED,DATA-DRIVEN TRAINING PROGRAMSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims the benefit of U.S. Provisional Patent Application No. 63 / 633,636, filed April 12, 2024, the disclosure of which is incorporated herein by reference in its entirety. The present application is related to U.S. Patent Application No. 18 / 345,221, filed June 30, 2023, titled “COMPUTER-IMPLEMENTED TRAINING PROGRAMS, SUCH AS FOR IMPROVING USER PERFORMANCE,” the disclosure of which is incorporated herein by reference in its entirety.TECHNICAL FIELD

[0002] This present disclosure relates to evaluating user breathing, generating customized, data- driven training programs, and associated systems, devices, and methods. Particular implementations of the present disclosure relate to scoring various domains of user breathing and generating training programs based on the scores for improving user outcomes.BACKGROUND

[0003] Athletes and other individuals that operate under high-pressure conditions and / or competitive environments often experience high anxiety and stress, which can lead to autonomic responses (e.g., fight or flight responses) including increased heart rate and / or fast and shallow breathing. As a result of these physiological responses, individuals can easily lose focus and perform at less than peak levels. Training for such individuals is essential in order to teach the mind and body to prepare for and cope with these physiological responses when high-pressure conditions arise. However, conventional trainers, coaches, techniques, and training devices are often not effective due to, e.g., their inability to process raw physiological data from the user in real time. Moreover, conventional devices vary widely on how they evaluate user breathing, leading to inconsistent or potentially ineffective evaluations and solutions. As such, conventional devices are unable to effectively and consistently train users to breathe in a way that more efficiently supports the autonomic nervous system or physiology of the user. Therefore, a need exists to develop improvedmethods and / or programs to enable users to better respond to stressful conditions and perform in high- pressure environments.BRIEF DESCRIPTION OF THE DRAWINGS

[0004] Features, aspects, and advantages of the presently disclosed technology may be better understood with regard to the following drawings.

[0005] FIG. 1 is a schematic block diagram of a computing device, in accordance with implementations of the present technology.

[0006] FIG. 2 is a schematic block diagram illustrating a suitable environment in which the disclosed system can operate, in accordance with implementations of the present technology.

[0007] FIG. 3A is a front view of a system including a belt and a sensor being worn by a user, in accordance with implementations of the present technology.

[0008] FIG. 3B is an isometric view of the system of FIG. 3 A.

[0009] FIG. 3C is a side view of the system of FIG. 3 A.

[0010] FIG. 4 is a schematic block diagram of a system illustrating data communication to and from the computing device of FIG. 1, in accordance with implementations of the present technology.

[0011] FIG. 5 is a process flow diagram of a method of generating a biomechanical score in accordance with implementations of the present technology.

[0012] FIG. 6 is a process flow diagram of a method of generating a psychophysiological score in accordance with implementations of the present technology.

[0013] FIG. 7 is a process flow diagram of a method of generating a biochemical score in accordance with implementations of the present technology.

[0014] FIG. 8 is a process flow diagram of a method of generating an overall score in accordance with implementations of the present technology.

[0015] FIG. 9 is a process flow diagram of a method for generating a data-driven training plan, in accordance with implementations of the present technology.

[0016] A person skilled in the relevant art will understand that the features shown in the drawings are for purposes of illustrations, and variations, including different and / or additional features and arrangements thereof, are possible.DETAILED DESCRIPTIONI. Overview

[0017] Implementations of the present disclosure relate to generating one or more scores that evaluate various domains of a user’s respiration and / or heart rate variability (HRV) based on data signals received from a device sensor worn by the user, and generating a customized, data-driven training plan based on the one or more scores. The field of evaluating a person’s breathing lacks a unified industry standard, and this absence has far-reaching implications for various aspects of healthcare, fitness, and research. Currently, different methods and tools are utilized to assess breathing patterns, lung function, and respiratory health, leading to a lack of consistency and comparability across assessments. This diversity in measurement approaches complicates efforts to establish baseline norms, track changes over time, and share findings across different disciplines.

[0018] In healthcare, for example, different clinicians use different devices, protocols, and metrics, leading to potential inconsistencies in evaluating respiratory health. Moreover, in the burgeoning field of digital health and wearable technologies, the absence of a standard creates challenges for comparing data across devices and platforms. This issue is particularly significant as individuals increasingly use wearable devices to monitor their health, including aspects of their respiratory function.

[0019] The establishment of an industry standard for evaluating a person’s breathing is imperative to address these challenges. The present technology is generally directed to a uniform data measurement and processing protocol that is both agnostic to and capable of handling data from different types of wearable technologies, different types of medical and diagnostic tools and devices, different types of users, and more. Implementations of the present technology can provide one or more uniform data measurement and processing protocols by scoring biomechanical, psychophysiological, and biochemical domains of a person’s breathing based on input signals from a wearable device and / or user inputs. The scores can then be used to generate a customized, data-driven training plans for the user. For example, implementations of the present technology include systems,methods, and / or computer-readable media for receiving one or more input signals from a device sensor operably coupled to a user, and generating one or more scores that reflect evaluations of various domains of the user’s respiration based on the input signals. A first score can represent a biomechanical evaluation of the user’s respiration, a second score can represent a psychophysiological evaluation of the user’ s respiration, and a third score can represent a biochemical evaluation of the user’s respiration. Accordingly, the first score can represent an evaluation of the performance of the user’s various muscles that contribute to breathing, the second score can represent an evaluation of the user’s ability to recover from a fight-or-flight state, and the third score can represent an evaluation of the user’s resilience to carbon dioxide (and other gases) buildup in the body. The biomechanical, psychophysiological, and biochemical scores can also be combined (e.g., weighted) to generate an overall score that represents an evaluation of the user’s respiration as a whole.

[0020] The system can also produce training plans based on the biomechanical, psychophysiological, biochemical, and / or overall scores. For example, implementations of the present technology include systems, methods, and / or computer-readable media for selecting one of a plurality of biomechanical training sets based on the first score, selecting one of a plurality of psychophysiological training sets based on the second score, and selecting one of a plurality of biochemical training sets based on the third score. The training set selected for each of the domains can reflect a training intensity or pattern deemed appropriate for the user based on the user’s score in that particular domain. The system can then generate a training plan comprising a permutation of one or more of each of the selected ones of the pluralities of training sets. Thus, the generated training plan can be customized based on the evaluations of the user’s respiration and / or HRV.

[0021] As previously mentioned, the field of evaluating a person’s breathing is currently inundated with various types of devices and techniques that are difficult to meaningfully compare against one another. Thus, for example, athletes using different wearables or other technologies may be unable to compare their performances with one another. As yet another example, everyday users using a multitude of different wearables or other technologies may be overwhelmed by the different measurement results and may be unable to effectively interpret the different forms of data. Further, interventions for these users can ignore the underlying data and prescribe “one-size-fits all” training protocols that may be inappropriate based on the user’s unique respiration and / or HRV.

[0022] The scoring protocols described herein are not only compatible with different forms of data from various devices (e.g., different wearable technologies, different diagnostic tools), but are also capable of processing the different forms of data to provide quantitative outputs that are (i) agnostic to the source of data and (ii) standardized, allowing users to easily compare, track, and communicate their results. Moreover, embodiments of the present technology can identify customized training plans for users based on the scoring protocols described herein, and therefore regardless of what devices the users are using. Accordingly, embodiments of the present technology provide a technical solution to a technical problem.

[0023] The system can be utilized in markets / fields of use in which users operate under high- pressure conditions and / or competitive environments, such as sports. Additionally, the present technology can be utilized to aid substance cessation (e.g., for smoking, drinking, prohibited substances, gambling, etc ), as well as for general healthcare (e.g., addressing hypertension), fitness, meditation / mental training, sleep quality, and yoga.

[0024] In the Figures, identical reference numbers identify generally similar, and / or identical, elements. Many of the details, dimensions, and other features shown in the Figures are merely illustrative of particular implementations of the disclosed technology. Accordingly, other implementations can have other details, dimensions, and features without departing from the spirit or scope of the disclosure. In addition, those of ordinary skill in the art will appreciate that further implementations of the various disclosed technologies can be practiced without several of the details described below.II. System Architecture of Computer-implemented Training Programs for Improving User Performance

[0025] FIGS. 1 and 2 and the following discussion provide a brief, general description of suitable computing environments in which aspects of the present technology can be implemented. Although not required, aspects of the system will be described in the general context of computer-executable instructions, such as routines executed by a general-purpose computer, e.g., a server or personal computer (e.g., a cellular or mobile device). Those skilled in the relevant art will appreciate that the present technology can be practiced with other computer system configurations, including Internet appliances, hand-held devices, wearable computers, multi-processor systems, microprocessor-basedor programmable consumer electronics, set-top boxes, mini-computers, mainframe computers, and the like. The present technology can be embodied in a special purpose computer or data processor that is specifically programmed, configured, or constructed to perform one or more of the computerexecutable instructions explained in detail below. In some implementations, the disclosed functionality may be implemented by instructions encoded in a non-transitory computer-readable storage medium.

[0026] The present technology can also be practiced in distributed computing environments, where tasks or modules are performed by remote processing devices, which are linked through a communications network, such as a Local Area Network (“LAN”), Wide Area Network (“WAN”) or the Internet. In a distributed computing environment, program modules or sub-routines may be located in both local and remote memory storage devices. Aspects of the present technology described below can be stored or distributed on computer-readable media, stored as firmware in chips (e.g., Electrically-Erasable Programmable Read-Only Memory chips, EEPROM chips), as well as distributed electronically over the Internet or over other networks (e.g., wireless networks). Those skilled in the relevant art will recognize that portions of the present technology can reside external to a mobile device (e.g., on a server computer or a sensor), while corresponding portions reside on a mobile device. Data structures and transmission of data particular to aspects of the present technology are also encompassed within the scope of the present technology.

[0027] FIG. 1 is a schematic block diagram illustrating components of a computing device 100, such as a smartphone, desktop computer, tablet computer, phablet, laptop, wearable computer, etc., in which the interface for visualizations of physiological (e.g., breathing-related and / or heart / related) metrics and training plans can be generated and displayed. As shown in FIG. 1, the computing device 100 includes a processor 101, an input component 103, a data storage component 105, a display component 107, and a communication component 109. The processor 101 is configured to couple with and control other components in the computing device 100. The computing device 100 can communicate with other systems (e.g., web servers or other devices) through the communication component 109 via a network 111. In some implementations, the computing device 100 can communicate with an output device (e.g., printers, speakers, tactile output devices, etc.) through the communication component 109. Network 111 can be any private or public network, such as theIntemet, a corporate intranet, a wireless communication network (e.g., Wi-Fi, cellular, Bluetooth®, Zigbee, etc.) or a wired communication network.

[0028] The input component 103 is configured to receive an input (e.g., an instruction or a command) from a device user. The input can include user specific data, such as weight, height, gender, demographics, etc. The input component 103 can include a touch pad, a touchscreen, a microphone, a keyboard, a mouse, a camera, a joystick, a pen, a game pad, a scanner, and / or the like. The data storage component 105 can include any type of computer-readable media that can store data accessible to the processor 101. In some implementations, the data storage component 105 can include random-access memories (RAMs), read-only memories (ROMs), flash memory cards, magnetic hard drives, optical disc drives, digital video discs (DVDs), cartridges, smart cards, etc.

[0029] The display component 107 is configured to display information to the user, e.g., via a mobile device. In some implementations, the display component 107 can include flat panel displays such as liquid crystal displays (LCDs), light emission diode (LED) displays, plasma display panels (PDPs), electro-luminescence displays (ELDs), vacuum fluorescence displays (VPDs), field emission displays (FEDs), organic light emission diode (OLED) displays, surface conduction electron emitter displays (SEDs), or carbon nano-tube (CNT) displays.

[0030] FIG. 2 is a schematic block diagram of an environment 200 in which the system for generating an interface for displaying visualizations of physiological metrics of the user and training plans for the user can operate. The environment 200 can include one or more server computers 201 that access data stores 202 containing information on a plurality of unique items. The server computers 201 communicate with computing devices 100 via a network 205. The computing devices 100 may send search queries to the server computers 201 pertaining to the unique items. The search queries are processed by the server computers 201 against the data in the data stores 202. The server computers 201 may retrieve, analyze, and / or format (e.g., in datasets) unique item information that is responsive to the received search queries. The server computer 201 transmits data responsive to the search queries to a requesting computing device 100 through the network 205. The network 205 can include the Internet, an intranet, a wireless communication, or a wired communication.

[0031] The server computer 201 includes a query processing component 211, a management component 212, a visualization component 213, and a database management component 214. Thequery component 211 is configured to perform query processing and analysis, e.g., of physiological data to produce one or more metrics (e.g., respiration, consistency, heart rate variability, performance, etc.). The management component 212 is configured to handle creation, display and / or routing of suitable information, e.g., amongst different layers or in the form of web pages. The visualization component 213 is configured to serve visualizations as described herein in a manner that generates a display of an item or metric. The visualization component 213 may be separate from, or incorporated within, the management component 212. The database management component 214 is configured to manage access to and maintenance of data stores 202. The server computer 201 can employ security measures (e g., firewall systems, secure socket layers (SSL), password protection schemes, encryption, and / or the like) to inhibit malicious attacks and to preserve integrity of the information stored in the data stores 202.

[0032] The computing device 100 may include one or more programs that submit queries to the server computers and receive responsive results. For example, a browser application 207 on a mobile device 204 is configured to access and exchange data with the server computer 201 through the network 205. Results of data queries may be displayed in a browser (e.g., Firefox, Chrome, Internet Explorer, Safari, etc.) of the mobile device 204 for viewing by the device user. Similarly, a browser application 217 on a desktop computer 203 is configured to access and exchange data with the server computer 201 through the network 205, and the results of the data queries may be displayed in the browser for review by the device user. As another example, a dedicated application 209 on the mobile device 204 is configured to display or present received information to a mobile device user via the application. Data may be received from the server computer 201, e.g., via an application programming interface (API), and the received data formatted for display by the application on the computing device 100. The server computer 201 and the computing device 100 can include other programs or modules such as an operating system, one or more productivity application programs (e.g., word processing or spread sheet applications), and the like.III. Computer-Implemented Training Programs for Improving User Performance, and Associated Systems, Devices, and Methods

[0033] FIG. 3A-3C are various views of a system 300 including a belt 305 (e.g., a strap) and a sensor 310 detachably coupled to the belt 305, with FIG. 3A being a front view of the system 300being worn by a user / person (P), FIG. 3B being an isometric view of the system 300, and FIG. 3C being a side view of the system 300. Referring to FIGS. 3A-3C together, the belt 305 can be worn across the torso (e.g., chest or stomach) of a user, such that the sensor 310 is positioned at the base of (e.g., two fingers below) the user’s sternum (as shown in FIG. 3A) or at other positions, and moves toward and / or away from the user’s torso with each respective inhale and exhale. For example, in some implementations the sensor 310 moves in an angular direction in response to inhalation and / or exhalation, such that a pitch of the sensor 310 relative to a base position corresponds to an amount of inhalation / exhalation and / or expansion / contraction of the diaphragmatic region.

[0034] The sensor 310 and / or the belt 305 can include an accelerometer, a gyroscope, a strain gauge / load cell, a source of light, and other hardware that individually or together measures and / or enables measurement of “raw” physiological data from the user. For example, as the user inhales and exhales, the sensor 310 can be angularly displaced from a base position, and the amount of angular displacement can be provided (e.g., on a continuous or periodic basis) to an external device or system for processing. In some implementations, the sensor 310 measures (e.g., via the gyroscope and accelerometer) respiration amplitude and frequency using kinematics. The raw data generated via the sensor 310 can be used to determine numerous metrics, including heart rate, respiration (e.g., respiration rate), R-R interval, volume displacement (e.g., during inhalation and / or exhalation), heart rate variability, consistency, symmetry, and / or coherence, as explained elsewhere herein (e.g., with reference to FIG. 4). In some implementations, the sensor 310 and / or the belt 305 correspond in whole or in part to the respective Movesense sensor and belt designed by Movesense of Vantaa, Finland.

[0035] As shown in FIG. 3C, the sensor 310 can include coupler portions 312a / b, and the belt 305 can include receiver portions 307a / b configured to receive the coupler portions 312a / b, thereby attaching the sensor 310 to the belt 305. In some implementations, the coupler portions 312a / b and receiver portions 307a / b are made from conductive materials and thereby electrically couple the sensor 310 to the belt 305, which may be electrically coupled to the user. In doing so, the sensor 310, and system 300 generally, can obtain electrical signals from the user.

[0036] A person of ordinary skill in the art will appreciate the sensor 310 and belt 305 shown in FIGS. 3A-3C represent just one implementation of the system 300. In other implementations, the sensor 310 is one of multiple sensors (e.g., two sensors, five sensors, etc ), and individual sensors may be configured to obtain specific data from a single source. For example, in such implementationsa first sensor is configured to obtain heart rate or R-R interval data, a second sensor is configured to obtain air displacement or diaphragmatic contraction and expansion, and so on and so forth. Additionally or alternatively, the sensor 310 can be operably coupled to the user at areas other than the torso, such as the wrist, leg, arm, neck, heart, ear, etc. A person or ordinary skill in the art will also appreciate that the system 300 can include other components not shown in FIGS. 3A-3C, such as a wireless transmitter coupled to the sensor and configured to transmit signals from the sensor to an external computing device.

[0037] FIG. 4 is a schematic block diagram of a system 400 illustrating data communication to and from the computing device 100 of FIG. 1, in accordance with the system. As shown in FIG. 4, the computing device 100 can be configured to receive user inputs 406 from a user 405, and one or more input signals 411 (“input signal(s) 411”) from a sensor 410. The sensor 410 can correspond to the sensor 310 of FIGS. 3A-3C or other sensors that can provide similar functionality (e.g., the ability to provide raw physiological data of the user). The sensor can be wirelessly connected to computing device 100, or physically connected to the computing device 100. Additionally, the computing device 100 can be configured to process the input signal(s) 411 and / or direct the input signal(s) 411 to a remote server 415 to produce metrics 416.

[0038] The user inputs 406 can include user-specific data (e.g., age, weight, height, build, and / or gender), respiration settings, and / or physiologic data obtained from the user during a training session in which the user’s breathing patterns (e.g., inhalation, exhalation, and / or diaphragmatic expansion and contraction, etc.) are monitored. The respiration settings can include parameters or times that correspond to inhale, hold after inhale, exhale, and / or hold after exhale. The combination of these individual respiration settings can produce a desired respiration metric or data for the user (e.g., an ideal metric or data; sometimes referred to herein “pacer data” or a “pacer signal”). In some implementations, the desired data or signal is obtained via breathing patterns of the user obtained during a training session. For example, during the training session, the user can be instructed to sequentially inhale, hold, exhale, and hold (and afterward repeat) for a predetermined period of time (e g., 1-10 minutes or longer), as set by the system or the user. In addition to the desired signal, other coefficients (e.g., shift and scale coefficients) can be generated based on the user inputs and be used to alter visualizations or the display of one or more of the metrics 416.

[0039] The input signal(s) 411 received from the sensor 410 can include the raw physiological data, e.g., as described with reference to FIGS. 3A-3C. As such, the raw physiological data can include heart rate or R-R interval of the user, as well as an angular displacement of the sensor, which is used to generate an amount of air displaced during inhalation and / or exhalation or a relative measurement of physical movement of the abdomen area. The amount of air displaced and / or the relative measurement of physical movement of the abdomen area can correlate to inhalation or exhalation, and the values corresponding to the inhale, exhale, and hold values can produce reference points for a curve that models an nthorder (e.g., second order) polynomial. Such a curve can be displayed to the user via a display of the computing device 100, and can be updated in real time as current input signals are received. In some implementations, the displayed curve is a real time representation of the user’s breathing as they inhale, exhale, hold their breath, and / or the like. In some implementations, the displayed curve corresponds to values that are a continuously updated rolling average (e.g., of the previous five seconds, 10 seconds, or 30 seconds of measurements). The inhale, exhale, and hold values can be obtained continuously or periodically (e.g., at least once every 100 milliseconds, every second, every five seconds, etc.).

[0040] The metrics 416 can be generated from the input signal(s) 411 received from the sensor 410 and, in some implementations, the user inputs 406. For example, the metrics 416 can be generated based predominantly on the input signal(s) 411, but be based in part on or altered by the user inputs 406 (e g., the data obtained during the training session described above). The generated metrics 416 can include respiration volume, heart rate variability (HRV) (e.g., high frequency HRV, low frequency HRV, and very low frequency HRV), consistency, performance (sometimes referred to herein as “NTEL”), symmetry, and coherence. These metrics can be generated simultaneously and be updated in real time, such that each can be displayed to the user via the computing device 100 simultaneously, e.g., as a value, a visualization, or both. For example, multiple metrics can be overlayed on a single display with one another and other signals (e.g., the desired respiration signal).

[0041] The respiration metric value is generated based on the displacement input signal, as well as the shift and scale coefficients, which can be generated from the user inputs or data obtained during the user’s training session. The respiration metric generally corresponds to the abdominal displacement for a particular breath, increasing in value during inhalation to a maximum value and decreasing in value during exhalation to a minimum value. The respiration metric value and othermetric values disclosed herein (e.g., the HRV metric value, the consistency metric value, etc.) can be adjusted based on the shift and scale coefficients, which can align the respiration metric (e.g., along an x-axis and / or a y-axis) with a corresponding value of the desired respiration signal. For example, in some implementations the shift coefficient adjusts (e.g., along a y-axis) the height or amplitude of the inhalation / exhalation such that the height or amplitude are aligned or approximately aligned with those of the desired respiration signal. Stated differently, the shift coefficient can indicate how much to alter (e.g., add to or subtract from) the respiration metric before it is displayed to the user, and the scale coefficient can indicate how much to alter (e.g., shrink or grow) the respiration metric before it is displayed to the user.

[0042] The HRV metric value is generated based on the heart rate input signal. In some implementations, the HRV metric value is generated by processing the heart rate input signal using a three-point median filter, and then creating buffered data over a predetermined rolling period of time (e.g., the previous 2 minutes, 3 minutes, 4 minutes, etc.). In some implementations, the buffered data captured over the period of time undergoes a zero-mean shift and utilizes a Fourier transform (e.g., a chirp Z-transform and / or Bluestein’s algorithm) to produce “power” values at different frequencies or frequency ranges of the HRV spectrum. The power values generally correspond to the units of electrical activity during breathing and fit into one of the three frequency ranges, which include (i) a high frequency (HF) range, e.g., 0.4-0.15 Hertz (Hz) (or 2.5-6.67 seconds (s)), (ii) a low frequency (LF) range (also referred to herein as “balance”), e.g., 0.15-0.04 Hz (or 6.67-25 s), and (iii) a very low frequency (VLF) range, e g., 0.04-0.016 Hz (or 25-62.5 s). The HRV metric value for each frequency range can correspond to the percentage each frequency range represents of the combined three frequency ranges. For example, an HRV metric value for the LF range of 30% indicates that 30% of the HRV metric values calculated over the predetermined rolling period of time were within the LF range. The frequency ranges, or more particularly the proportion of the HRV metric values that fall within a particular frequency range can reflect particular levels of activity and serve as an indication of desirable progress for the user over time. For example, the LF range can be used as an indication of autonomic nervous system balance, with a higher proportion being associated with more sympathetic activity, which is generally desired. The individual frequency ranges can be subsequently utilized to generate other metrics and / or displays.

[0043] The consistency metric value is based on the average of and / or the difference in respiration for multiple breaths or inhalations / exhalations of the user (e.g., over 2, 3, 4, 5, 6, or more breathing cycles). For example, in some implementations the consistency metric value is based on a respiration rate (e.g., the number or average number of breaths per minute the user takes) and a displacement volume metric (e.g., a degree to which the abdomen is expanding / contracting with each breath). The consistency metric value can be weighted equally by the respiration rate and the displacement volume metric (e.g., be weighted 50% by the respirate rate and 50% by the displacement volume metric), or be weighted more heavily by one of the respiration rate of displacement volume metric. The consistency metric value can be between 0-100, with a higher value corresponding to more consistent breathing between multiple breaths and a lower value corresponding to less consistent breathing between multiple breaths. For example, a user having low variability for respiration volumes of multiple breaths will have a higher consistency metric value than a user having high variability for respiration volumes. The consistency metric value can be subsequently utilized to generate other metrics and / or displays.

[0044] The performance metric (sometimes referred to herein as the “NTEL Metric”) can be based on the consistency metric and the HRV metric. For example, in some implementations the performance metric value is an average of the consistency metric value and the HRV metric value for the LF range (i .e., the sum of the consistency metric value and the HRV metric value for the LF range multiplied by 0.5). As such, the performance metric can provide the user with a single metric that incorporates both the variability of the user’s respiration and the proportion of sympathetic activity, and thus enable the user to gauge the consistency and quality of the training over time. In some implementations, the performance metric is not provided to users.

[0045] The performance metric can be used to generate a performance score (sometimes referred to herein as the “NTEL Score”), which can be based on the performance metric as well as on the time spent training over a previous period of time (e.g., seven days). In some implementations, the performance score is based on (i) the amount of minutes that a user trained beyond a minimum total time threshold (e.g., 60 minutes) over a predetermined period of time (e.g., 7 days), and (ii) the amount of days that a user trained beyond a minimum daily time threshold (e.g., five days) over the predetermined period of time. In such implementations, and for a given performance metric value, a user that trained more than 60 minutes over the prior seven days and more than 5 days over the lastseven days would have a higher performance score than a user that trained less than 60 minutes over the last seven days or less than five days over the last seven days.

[0046] The performance metric can also be used to generate performance points (sometimes referred to herein as the “NTEL Points”). The performance points can be a percentage (e.g., 10-90%) of the performance metric, and can be displayed as a weekly tally or an all-time cumulative tally of the performance points earned. In some implementations, the performance points are earned on a predetermined point scale (e.g., 0-600 points) that accumulates over time (e.g., days, weeks, months, or years) or the course of a training session. The performance points can be compared to that of other users, and thus enable users to compete against one other. As the performance points are linked to the amount and quality of training, as well as the consistency of training over time, users are motivated to spend more time training and improving the quality of their breathing. In some implementations, the performance score is calculated based at least in part on the performance points earned. For example, the performance score can be based on the total performance points accumulated by the user within a period of time (e.g., a day) and / or the rate at which the user has accumulated performance points (e.g., during a session).

[0047] Other metrics generated from the input signal(s) 411 can include symmetry and coherence. The symmetry metric value can be based on the correlation between the respiration metric value and the corresponding value for the desired signal, with a better correlation corresponding to a higher symmetry metric value. The coherence metric value (e.g., an alignment or sequence metric value) can be based on a correlation between the respiration metric value (or the user’ s physical respiration wave) and the heart rate, or stated differently the correlation between the respiration metric value and the respiratory sinus arrythmia. In some implementations, the symmetry and coherence metric values both utilize and are generated using the shift and scale coefficients.III. Scoring Methodologies for Evaluating Respiration of a User

[0048] In some implementations, the metrics 416 and / or other values can be used in various ways to generate one or more scores that evaluate the respiration of the user. FIGS. 5-8 illustrate process flow diagrams for evaluating different aspects, features, or domains of the respiration and / or HRV of the user, and generating corresponding scores. More specifically, embodiments of the present technology can score the biomechanical, psychophysiological, and biochemical domains of a user’sbreathing. The generated scores can then be used to generate a customized, data-driven training plan for the user. FIG. 9 illustrates a computer-implemented process for generating a training plan.

[0049] FIG. 5 is a process flow diagram of a method 500 of generating a biomechanical score (also referred to as “the BM score” or “the first score”) in accordance with implementations of the present technology. The biomechanical score can represent an evaluation of the performance of the user’s various muscles that contribute to breathing.

[0050] The method 500 can include receiving input signals representing a respiration of a user (process portion 502). As discussed in further detail herein, various features or aspects of the user’s respiration can be measured by a sensor system, such as the system 300 (FIGS. 3A-3C). Once the sensor system takes one or more relevant measurements, the measurements can be communicated (e.g., by a communication module of the sensor system) to a computing device (e.g., the computing device 100) and / or a server (e.g., the server 415) as one or more input signals (e.g., the input signal(s) 411).

[0051] The method 500 can include determining a first respiration data component and a second respiration data component from the received input signals (process portion 504). In some embodiments, each of the first and second respiration data components relates to the respiration rate of the user, and / or a breathing depth utilization ratio of the user. For example, as discussed above with reference to FIGS. 3A-3C, the sensor 310 can measure the amount of angular displacement from the base position of the sensor 310 as the user inhales and exhales.

[0052] The method 500 can include obtaining a first respiration score by referencing the first respiration data component against a first table (process portion 506). The first table can list a plurality of different first respiration data components (e.g., various individual values, various ranges thereof) and a plurality of first respiration scores (e.g., out of a maximum of 100) that correspond to the different first respiration data components. The computing device and / or server can reference the table to obtain or determine the corresponding first respiration score.

[0053] The method 500 can include obtaining a second respiration score by referencing the second respiration data component against a second table (process portion 508). The table can list a plurality of different second respiration data components (e.g., various individual values, various ranges thereof) and a plurality of second respiration scores (e.g., out of a maximum of 100) that correspondto the different second respiration data components. The computing device and / or server can reference the table to obtain or determine the corresponding second respiration score.

[0054] The method 500 can include generating a biomechanical score by combining the first respiration score and the second respiration score (process portion 510). In some embodiments, combining the first and second respiration scores comprises weighing the first and second respiration scores according to a predetermined weighing scale and summing them. For example, the predetermined weighing scale can be 10% and 90% (e.g., 10% of the first respiration score and 90% of the second respiration score), 20% and 80%, 30% and 70%, 40% and 60%, 50% and 50%, 60% and 40%, 70% and 30%, 80% and 20%, 90% and 10%, or other weighing scales. In other embodiments, the biomechanical score can be generated via other combinations of the first and second respiration scores, such as a geometric mean, a ratio, etc.

[0055] As previously mentioned, the biomechanical score can represent an evaluation of the performance of the user’s various muscles that contribute to breathing, such as the neuromuscular respiratory pump. The generated biomechanical score can also indicate the user’s muscle imbalance and ability to create changes in the intra-abdominal and intra-thoracic pressure to drive the movement of air, lymph, and blood . Therefore, following a training plan to improve one’s biomechanical score, as described further herein, can lead to improvements in slow breathing and achieving a calmer mind, increases in lung volume, oxygen uptake in the blood, ventilation perfusion, spine stabilization, movement efficiency, and lymphatic drainage, and / or a reduction in energy cost (e.g., delaying fatigue).

[0056] FIG. 6 is a process flow diagram of a method of generating a psychophysiological score (also referred to as “the PP score” or “the second score”) in accordance with implementations of the present technology. The psychophysiological score can represent an evaluation of the user’s autonomic nervous system.

[0057] The method 600 can include receiving input signals representing a heart rate (e.g., HRV) of a user (process portion 602). As discussed in further detail herein, various features or aspects of the user’s heart rate can be measured by a sensor system, such as the system 300 (FIGS. 3A-3C). Once the sensor system takes one or more relevant measurements, the measurements can be communicated (e.g., by a communication module of the sensor system) to a computing device (e.g.,the computing device 100) and / or a server (e.g., the server 415) as one or more input signals (e.g., the input signal(s) 411).

[0058] The method 600 can include determining a first HRV data component and a second HRV data component from the received input signals (process portion 604). In some embodiments, each of the first and second HRV data components relates to a HRV metric curve for the HF range (also referred to as "HF%"), the LF range (also referred to as “LF%” or “balance”), or the VLF range (“also referred to as “VLF%”) over a measurement period of time (e.g., as measured by the system 300). The measurement period of time can be 15 seconds, 30 seconds, 1 minute, 2 minutes, 3 minutes, 4 minutes, 5 minutes, etc.

[0059] In some embodiments, the measurement period of time begins after an initial period of time during which the user is instructed to “warm up” or otherwise begin breathing. For example, the computing device may request the user to breathe at a first respiration rate during the initial period of time, and to breathe at a second respiration rate that is different from the first respiration rate during the measurement period of time. The initial period of time can be 15 seconds, 30 seconds, 1 minute, 2 minutes, 3 minutes, 4 minutes, 5 minutes, etc. In some implementations, the computing device provides a breathing pacer to assist the user in breathing at the requested respiration rate (e.g., 4 breaths per minute (bpm), 6 bpm, 8 bpm, 10 bpm, 12 bpm, 14 bpm, 16 bpm, or any value therebetween). In some cases, requesting the user to change (e.g., slow) their respiration rate between the initial period of time and the measurement period of time can help induce the user to breathe diaphragmatically during the measurement period of time. For example, the second respiration rate can be set to correspond to when the nervous system functions optimally.

[0060] The method 600 can include generating a psychophysiological score by combining the first HRV data component and the second HRV data component (process portion 606). In some embodiments, combining the first and second HRV data components comprises taking their ratio. In other embodiments, the psychophysiological score can be generated via other combinations of the first and second HRV data components. The Vagus Nerve, which is a key component of the parasympathetic nervous system, is the longest cranial nerve extending from the brain to the abdomen so diaphragmatic engagement can directly affect the autonomic nervous system and influence the stress response (fight or flight / rest and digest). Therefore, the psychophysiological score can indicate or otherwise provide insight into the user’s autonomic nervous system, including the user’s ability torecover from a fight-or-flight or stress state (e.g., ability to relax). In some implementations, the psychophysiological score is additionally or alternatively determined based on how quickly and efficiently the user’s nervous system can recover from the fight-or-flight state. For example, the psychophysiological score can be based on (i) how quickly the HRV metric curve rises, (ii) how high the HRV metric curve rises, and / or (iii) whether the HRV metric curve is maintained at the high value or drops (e.g., efficiency). One of ordinary skill in the art will appreciate that the psychophysiological score can be determined via other metrics or methods.

[0061] As previously mentioned, the psychophysiological score can represent an evaluation of the user’s autonomic nervous system. The generated psychophysiological score can also indicate the user’s ventilatory drive and breathing pattern with a higher sympathetic drive associated with faster or more shallow breathing. Therefore, following a training plan to improve one’s psychophysiological score, as described further herein, can lead to stimulation of the vagus nerve, improvements in alveolar ventilation, HRV, sleep, respiratory sinus arrhythmia, balancing of the autonomic nervous system, and achieving a calmer mind, and / or a reduction in sensitivity to carbon dioxide. Slower deeper breathing is associated with increased ventilation, perfusion, increased delivery of oxygen to cells and tissues, and less sympathetic drive of the autonomic nervous system.

[0062] FIG. 7 is a process flow diagram of a method of generating a biochemical score (also referred to as “the BC score” or “the third score”) in accordance with implementations of the present technology. The biochemical score can represent an evaluation of the user’s resilience to carbon dioxide (and other gases) buildup in the body.

[0063] The method 700 can include receiving input signals representing a respiration of a user (process portion 702). As discussed in further detail herein, various features or aspects of the user’s respiration can be measured by a sensor system, such as the system 300 (FIGS. 3A-3C). Once the sensor system takes one or more relevant measurements, the measurements can be communicated (e.g., by a communication module of the sensor system) to a computing device (e.g., the computing device 100) and / or a server (e.g., the server 415) as one or more input signals (e.g., the input signal(s) 411).

[0064] The method 700 can include determining a first respiration data component and a second respiration data component from the received input signals (process portion 704). In someembodiments, the third respiration data component relates to a body oxygen level test (BOLT) and / or a breath hold test (BHT) result. The BOLT / BHT result can be determined by the user taking in a normal breath through the nose, exhaling gently through the nose, pinching the nose to prevent airflow therethrough, and counting how many seconds pass until the user feels an urge to breathe. In some embodiments, the fourth respiration data component relates to a maximum breathlessness test (MBT) result. The MBT result can be determined by the user exhaling normally through the nose, walking at a normal pace while holding their breath, and counting the maximum number of steps that the user can take while holding their breath. In some implementations, the computing device can provide a pacer to assist the user in walking at a constant pace (e.g., 90 steps per minute, 100 steps per minute, 110 steps per minute, 120 steps per minute, 130 steps per minute). In some cases, if a user lasts n seconds for the BOLT / BHT, then it may be expected on average that the user will take 2n steps for the MBT.

[0065] The method 700 can include obtaining a third respiration score by referencing the third respiration data component against a third table (process portion 706). The table can list a plurality of different third respiration data components (e.g., various individual values, various ranges thereof) and a plurality of third respiration scores (e.g., out of a maximum of 100) that correspond to the different third respiration data components. The computing device and / or server can reference the table to obtain or determine the corresponding third respiration score.

[0066] The method 700 can include obtaining a fourth respiration score by referencing the fourth respiration data component against a fourth table (process portion 708). The table can list a plurality of different fourth respiration data components (e.g., various individual values, various ranges thereof) and a plurality of fourth respiration scores (e.g., out of a maximum of 100) that correspond to the different fourth respiration data components. The computing device and / or server can reference the table to obtain or determine the corresponding fourth respiration score.

[0067] The method 700 can include generating a biochemical score by combining the third respiration score and the fourth respiration score (process portion 710). In some embodiments, combining the third and fourth respiration scores comprises weighing the third and fourth respiration scores according to a predetermined weighing scale and summing them. For example, the predetermined weighing scale can be 10% and 90% (e g., 10% of the third respiration score and 90% of the fourth respiration score), 20% and 80%, 30% and 70%, 40% and 60%, 50% and 50%, 60% and40%, 70% and 30%, 80% and 20%, 90% and 10%, or other weighing scales. In other embodiments, the biochemical score can be generated via other combinations of the third and fourth respiration scores, such as a geometric mean, a ratio, etc.

[0068] As previously mentioned, the biochemical score can represent an evaluation of the user’s resilience to carbon dioxide (and other gases) buildup in the body. The generated biochemical score can also indicate the user’s blood pH, according to the oxygen dissociations curve, a lowering of carbon dioxide in the blood may lead to changes in blood pH (increase alkalinity during hyperventilation) and an increase in the affinity of oxygen to hemoglobin (blood more loaded with oxygen). Therefore, following a training plan to improve one’s biochemical score, as described further herein, can lead to a reduction in breathlessness (e.g., dyspnea) and sensitivity to carbon dioxide, improvements in the regulation of breathing patterns, blood circulation, and oxygen delivery, normalization of ventilation, and / or higher concentrations of nitric oxide. Normalized breathing patterns lead to a balance of blood pH which leads to favorable outcomes for delivering oxygen to cells and tissue.

[0069] FIG. 8 is a process flow diagram of a method 800 of generating an overall score in accordance with implementations of the present technology. The method 800 can include receiving input signals representing a respiration and a heart rate of a user (process portion 802). As discussed in further detail herein, various features or aspects of the user’s respiration can be measured by a sensor system, such as the system 300 (FIGS. 3A-3C). Once the sensor system takes one or more relevant measurements, the measurements can be communicated (e.g., by a communication module of the sensor system) to a computing device (e.g., the computing device 100) and / or a server (e.g., the server 415) as one or more input signals (e.g., the input signal(s) 411).

[0070] The method 800 can include generating a biomechanical score (a first score), a psychophysiological score (a second score), and a biochemical score (a third score) based on the received input signals (process portion 804). In some implementations, the biomechanical score, the psychophysiological score, and the biochemical score are generated as illustrated in and discussed above with reference to FIGS. 5, 6, and 7, respectively.

[0071] The method 800 can include generating an overall score by combining the biomechanical score, the psychophysiological score, and the biochemical score. In some embodiments, combiningthe biomechanical score, the psychophysiological score, and the biochemical score comprises weighing the biomechanical, psychophysiological, and biochemical scores according to a predetermined weighing scale and summing them. For example, the biomechanical score, the psychophysiological score, and the biochemical score can be weighted equally (e.g., 33.3% each). In other examples, the biomechanical score, the psychophysiological score, and the biochemical score can be weighted differently such that the overall score is a sum of 5-95% of the biomechanical score, 5-95% of the psychophysiological score, and 5-95% of the biochemical score, wherein the percentage weights add up to 100%. In other embodiments, the overall score can be generated via other combinations of the biomechanical, psychophysiological, and biochemical scores, such as a geometric mean, etc.IV. Generating a Customized, Data-Driven Training Plan for a User

[0072] FIG. 9 is a process flow diagram of a method 900 for generating a data-driven training plan, in accordance with implementations of the present technology. While the method 900 is described below with reference to the implementations discussed above, the method 900 can be practiced with other implementations of the present technology.

[0073] The method 900 can include receiving input signals (e.g., the input signal(s) 411) representing a respiration and a heart rate of a user (process portion 902). In some implementations, the input signals are generated by and based on measurements taken by a wearable device or other device (e.g., the system 300).

[0074] The method 900 can include generating a first score (e.g., a BM score), a second score (e.g., a PP score), and a third score (e.g., a BC score) based on the input signals (process portion 904). The method 900 can include (i) selecting one of a first plurality of training sets based on the first score (process portion 906), (ii) selecting one of a second plurality of training sets based on the second score (process portion 908), and (iii) selecting one of a third plurality of training sets based on the third score (process portion 910). Each of the first, second, and third pluralities of training sets can include training sets (e.g., involving respiration / breathing training) of various intensities and / or formats.

[0075] The method 900 can include generating a training plan comprising a permutation of one or more of each of the selected ones of the first, second, and third training sets (process portion 912). Insome implementations, the order of the permutation is determined based on a ranking of the first, second, and third scores. In some implementations, the frequency of each of the selected ones of the first, second, and third training sets is determined by the ranking of the first, second, and third scores. In some implementations, the method 900 can include iterations of one or more of the process portions 902-912. For example, after generating the training plan at process portion 912, the method 900 can return to process portion 904 (as indicated by the dashed arrow) to generate an updated first score, an updated second score, and / or an updated third score based on the user’s progress and improvement. The method 900 can then generate an updated training plan based on the updated first, second, and / or third scores. The iteration can repeat any number of times (e.g., once, twice, etc.).

[0076] In some implementations, the method 900 can further include generating an overall score based on the input signals, as discussed above with reference to FIG. 8, and selecting one of a plurality of sleep training sets based on the overall score. The plurality of sleep training sets can include training sets (e.g., involving respiration / breathing training) of various intensities and / or formats. The training plan generated at process portion 912 can further include the selected one of the plurality of sleep training sets.

[0077] The generated training plan can be for a predetermined period of time (e.g., 2 weeks, 4 weeks, 1 month, 2 months, 3 months, etc ). In some implementations, the generated training plan specifies what one or more training sets are to be performed on which day and / or in what order.

[0078] In some implementations, the system also guides or otherwise assists the user in performing the training sets recommended in the generated training plan. For example, the system can provide breathing pacers (e.g., visual and / or audio cues via the computing device) and daily reminders (e.g., notifications, alarms). The system can also request that the user perform the various tests necessary for generating the biomechanical, psychophysiological, and biochemical scores such that the system can re-calculate and track changes in the scores overtime and communicate the changes to the user (e.g., as a plot on a display). In some implementations, the system updates the training plan based on changes in the biomechanical, psychophysiological, biochemical, and / or overall scores.

[0079] Training plans generated in accordance with implementations of the present technology provide a customized, data-driven training program for improving the user’ s breathing and associated biological functions. The generated training plan can be communicated to the user via a display (e.g.,the display component 107 in FIG. 1), audio, etc. As discussed herein, the training plans are generated by considering the user’s biomechanical, psychophysiological, and biochemical scores, which can be determined via unique scoring methodologies, as discussed with reference to FIGS. 5-7. The scores can then be ranked, coded, and also used to generate an overall score, as discussed with reference to FIG. 8. Then, based on pluralities of training sets to choose from, implementations of the present technology can generate a training plan that recommends specific training sets to be performed on each day for a given period of time (e.g., 4 weeks), as discussed with reference to FIG. 9.V. Conclusion

[0080] It will be apparent to those having skill in the art that changes may be made to the details of the above-described implementations without departing from the underlying principles of the present disclosure. In some cases, well known structures and functions have not been shown or described in detail to avoid unnecessarily obscuring the description of the implementations of the present technology. Although steps of methods may be presented herein in a particular order, alternative implementations may perform the steps in a different order. Similarly, certain aspects of the present technology disclosed in the context of particular implementations can be combined or eliminated in other implementations. Furthermore, while advantages associated with certain implementations of the present technology may have been disclosed in the context of those implementations, other implementations can also exhibit such advantages, and not all implementations need necessarily exhibit such advantages or other advantages disclosed herein to fall within the scope of the technology. Accordingly, the disclosure and associated technology can encompass other implementations not expressly shown or described herein, and the invention is not limited except as by the appended claims.

[0081] Throughout this disclosure, the singular terms “a,” “an,” and “the” include plural referents unless the context clearly indicates otherwise. Additionally, the term “comprising,” “including,” and “having” should be interpreted to mean including at least the recited feature(s) such that any greater number of the same feature and / or additional types of other features are not precluded.

[0082] Reference herein to “one embodiment,” “an embodiment,” “some implementations” or similar formulations means that a particular feature, structure, operation, or characteristic described in connection with the embodiment can be included in at least one embodiment of the presenttechnology. Thus, the appearances of such phrases or formulations herein are not necessarily all referring to the same embodiment. Furthermore, various particular features, structures, operations, or characteristics may be combined in any suitable manner in one or more implementations.

[0083] Unless indicated otherwise, the phrase “in real time” as used herein means that a method or process step is performed simultaneously as, during the same session as, and / or immediately (e.g., less than 10 seconds, less than 5 seconds) after one or more other method or process steps described therewith. For example, a graphical curve representing a user’s breathing can be displayed on a graphical user interface in real time such that the endpoint of the curve indicates the user’s current breathing status at any given moment. As another example, scores can be generated in real time such that the scores can be displayed on a graphical user interface, available for post-processing, etc. immediately after (e.g., allowing for typical processing delays associated with computing devices) a user completes a measurement or testing session. Also, scores can be generated in real time such that different scores are generated (i) immediately after the corresponding measurement test or (ii) immediately after multiple measurement tests or the entire session in which multiple measurement tests are conducted in series.

[0084] Unless otherwise indicated, all numbers expressing numerical values used in the specification and claims, are to be understood as being modified in all instances by the term “about.” Accordingly, unless indicated to the contrary, the numerical parameters set forth in the following specification and attached claims are approximations that may vary depending upon the desired properties sought to be obtained by the present technology. At the very least, and not as an attempt to limit the application of the doctrine of equivalents to the scope of the claims, each numerical parameter should at least be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Additionally, all ranges disclosed herein are to be understood to encompass any and all subranges subsumed therein. For example, a range of “1 to 10” includes any and all subranges between (and including) the minimum value of 1 and the maximum value of 10, i.e., any and all subranges having a minimum value of equal to or greater than 1 and a maximum value of equal to or less than 10, e.g., 5.5 to 10.

[0085] The disclosure set forth above is not to be interpreted as reflecting an intention that any claim requires more features than those expressly recited in that claim. Rather, as the following claims reflect, inventive aspects lie in a combination of fewer than all features of any single foregoingdisclosed embodiment. Thus, the claims following this Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment. This disclosure includes all permutations of the independent claims with their dependent claims.

[0086] The present technology is illustrated, for example, according to various aspects described below as numbered clauses (1, 2, 3, etc.) for convenience. These are provided as examples and do not limit the present technology. It is noted that any of the dependent clauses may be combined in any combination, and placed into a respective independent clause. The other clauses can be presented in a similar manner.1. A system, comprising: at least one non-transitory computer readable media having instructions that, when executed by a computing device, perform operations comprising: receiving input signals representing respiration of a user; generating a first score based on the input signals, wherein the first score represents a biomechanical evaluation of the respiration of the user; generating a second score based on the input signals, wherein the second score represents a psychophysiological evaluation of the respiration of the user; generating a third score based on the input signals, wherein the third score represents a biochemical evaluation of the respiration of the user; selecting one of a first plurality of training sets based on the first score; selecting one of a second plurality of training sets based on the second score; selecting one of a third plurality of training sets based on the third score; and generating a training plan comprising a permutation of one or more of each of the selected one of the first plurality of training sets, the selected one of the second plurality of training sets, and the selected one of the third plurality of training sets.2. The system of the previous clause, wherein the operations further comprise displaying each of the first score, the second score, and the third score on a graphical user interface.3. The system of clause 2, wherein the operations further comprise updating each of the first score, the second score, and the third score on the graphical user interface.4. The system of the previous clause, wherein the operations further comprise displaying the generated training plan on a graphical user interface.5. The system of any one of the previous clauses, wherein an order of the permutation is determined based on a ranking of the first score, the second score, and the third score.6. The system of any one of the previous clauses, wherein a frequency of each of the selected one of the first plurality of training sets, the selected one of the second plurality of training sets, and the selected one of the third plurality of training sets is determined by a ranking of the first score, the second score, and the third score.7. The system of any one of the previous clauses, wherein generating the first score comprises: determining a first respiration data component and a second respiration data component from the input signals; obtaining a first respiration score by referencing the first respiration data component against a first table; obtaining a second respiration score by referencing the second respiration data component against a second table; and combining the first and second respiration scores to generate the first score.8. The system of any one of the previous clauses, wherein generating the second score comprises: determining a first heart rate variability (HRV) data component and a second HRV data component from the input signals; and combining the first and second HRV data components to generate the second score.9. The system of any one of the previous clauses, wherein generating the third score comprises: determining a third respiration data component and a fourth respiration data component from the input signals; obtaining a third respiration score by referencing the third respiration data component against a third table; obtaining a fourth respiration score by referencing the fourth respiration data component against a fourth table; and combining the third and fourth respiration scores to generate the third score.10. The system of any one of the previous clauses, wherein the operations further comprise: generating an overall score based on the input signals, wherein the overall score comprises a weighted average of the first score, the second score, and the third score; and selecting one of a plurality of sleep training sets based on the overall score, wherein the training plan further comprises the selected one of the plurality of sleep training sets.11. The system of any one of the previous clauses, further comprising: a torso wearable device including: a wireless transmitter; and a sensor operably coupled to the wireless transmitter and configured to generate the input signals representing the respiration of the user, wherein, in operation, the sensor is angularly displaced in response to the respiration of the user for the generation, in real time, of the input signals.12. The system of any one of the previous clauses, wherein the at least one non-transitory computer readable media are configured to receive input signals from different types of devices.13. A method, comprising: receiving input signals representing respiration of a user from a sensor;generating a first score based on the input signals, wherein the first score represents a biomechanical evaluation of the respiration of the user; generating a second score based on the input signals, wherein the second score represents a psychophysiological evaluation of the respiration of the user; generating a third score based on the input signals, wherein the third score represents a biochemical evaluation of the respiration of the user; selecting one of a first plurality of training sets based on the first score; selecting one of a second plurality of training sets based on the second score; selecting one of a third plurality of training sets based on the third score; and generating a training plan comprising a permutation of one or more of each of the selected one of the first plurality of training sets, the selected one of the second plurality of training sets, and the selected one of the third plurality of training sets.14. The method of the previous clause, wherein generating the first score, the second score, and the third score comprises generating the first score, the second score, and the third score in real time.15. The method of clause 14, further comprising displaying each of the first score, the second score, the third score, and the training plan on a graphical user interface.16. The method of any one of the previous clauses, further comprising generating a ranking of the first score, the second score, and the third score, wherein generating the training plancomprises generating the training plan based on the ranking of the first score, the second score, and the third score.17. The method of any one of the previous clauses, wherein the sensor is included in a torso wearable device.18. The method of clause 17, wherein receiving the input signals comprises receiving the input signals representing respiration of the user from a plurality of sensors including the sensor.19. A method for evaluating a user’ s breathing, the method comprising: receiving input signals representing respiration of a user from a sensor; generating a first score based on the input signals, wherein the first score represents a biomechanical evaluation of the respiration of the user, and wherein generating the first score comprises: determining a first respiration data component and a second respiration data component from the input signals, obtaining a first respiration score by referencing the first respiration data component against a first table, obtaining a second respiration score by referencing the second respiration data component against a second table, and combining the first and second respiration scores to generate the first score; generating a second score based on the input signals, wherein the second score represents a psychophysiological evaluation of the respiration of the user, and wherein generating the second score comprises: determining a first heart rate variability (HRV) data component and a second HRV data component from the input signals, and combining the first and second HRV data components to generate the second score. generating a third score based on the input signals, wherein the third score represents a biochemical evaluation of the respiration of the user, and wherein generating the third score comprises:determining a third respiration data component and a fourth respiration data component from the input signals, obtaining a third respiration score by referencing the third respiration data component against a third table, obtaining a fourth respiration score by referencing the fourth respiration data component against a fourth table, and combining the third and fourth respiration scores to generate the third score; and displaying each of the first score, the second score, and the third score on a graphical user interface in real time.20. The method of the previous clause, further comprising: generating an overall score based on the input signals, wherein the overall score comprises a weighted average of the first score, the second score, and the third score; and displaying the overall score on the graphical user interface in real time.

Claims

CLAIMSI / We claim:

1. A system, comprising: at least one non-transitory computer readable media having instructions that, when executed by a computing device, perform operations comprising: receiving input signals representing respiration of a user; generating a first score based on the input signals, wherein the first score represents a biomechanical evaluation of the respiration of the user; generating a second score based on the input signals, wherein the second score represents a psychophysiological evaluation of the respiration of the user; generating a third score based on the input signals, wherein the third score represents a biochemical evaluation of the respiration of the user; selecting one of a first plurality of training sets based on the first score; selecting one of a second plurality of training sets based on the second score; selecting one of a third plurality of training sets based on the third score; and generating a training plan comprising a permutation of one or more of each of the selected one of the first plurality of training sets, the selected one of the second plurality of training sets, and the selected one of the third plurality of training sets.

2. The system of claim 1 , wherein the operations further comprise displaying each of the first score, the second score, and the third score on a graphical user interface.

3. The system of claim 2, wherein the operations further comprise updating each of the first score, the second score, and the third score on the graphical user interface.

4. The system of claim 1, wherein the operations further comprise displaying the generated training plan on a graphical user interface.

5. The system of claim 1, wherein an order of the permutation is determined based on a ranking of the first score, the second score, and the third score.

6. The system of claim 1, wherein a frequency of each of the selected one of the first plurality of training sets, the selected one of the second plurality of training sets, and the selected one of the third plurality of training sets is determined by a ranking of the first score, the second score, and the third score.

7. The system of claim 1, wherein generating the first score comprises: determining a first respiration data component and a second respiration data component from the input signals; obtaining a first respiration score by referencing the first respiration data component against a first table; obtaining a second respiration score by referencing the second respiration data component against a second table; and combining the first and second respiration scores to generate the first score.

8. The system of claim 1, wherein generating the second score comprises: determining a first heart rate variability (HRV) data component and a second HRV data component from the input signals; and combining the first and second HRV data components to generate the second score.

9. The system of claim 1, wherein generating the third score comprises: determining a third respiration data component and a fourth respiration data component from the input signals; obtaining a third respiration score by referencing the third respiration data component against a third table; obtaining a fourth respiration score by referencing the fourth respiration data component against a fourth table; and combining the third and fourth respiration scores to generate the third score.

10. The system of claim 1, wherein the operations further comprise: generating an overall score based on the input signals, wherein the overall score comprises a weighted average of the first score, the second score, and the third score; and selecting one of a plurality of sleep training sets based on the overall score, wherein the training plan further comprises the selected one of the plurality of sleep training sets.11 . The system of claim 1, further comprising: a torso wearable device including: a wireless transmitter; and a sensor operably coupled to the wireless transmitter and configured to generate the input signals representing the respiration of the user, wherein, in operation, the sensor is angularly displaced in response to the respiration of the user for the generation, in real time, of the input signals.

12. The system of claim 1, wherein the at least one non-transitory computer readable media are configured to receive input signals from different types of devices.

13. A method, comprising: receiving input signals representing respiration of a user from a sensor; generating a first score based on the input signals, wherein the first score represents a biomechanical evaluation of the respiration of the user; generating a second score based on the input signals, wherein the second score represents a psychophysiological evaluation of the respiration of the user; generating a third score based on the input signals, wherein the third score represents a biochemical evaluation of the respiration of the user; selecting one of a first plurality of training sets based on the first score; selecting one of a second plurality of training sets based on the second score; selecting one of a third plurality of training sets based on the third score; andgenerating a training plan comprising a permutation of one or more of each of the selected one of the first plurality of training sets, the selected one of the second plurality of training sets, and the selected one of the third plurality of training sets.

14. The method of claim 13, wherein generating the first score, the second score, and the third score comprises generating the first score, the second score, and the third score in real time.

15. The method of claim 14, further comprising displaying each of the first score, the second score, the third score, and the training plan on a graphical user interface.

16. The method of claim 13, further comprising generating a ranking of the first score, the second score, and the third score, wherein generating the training plan comprises generating the training plan based on the ranking of the first score, the second score, and the third score.

17. The method of claim 13, wherein the sensor is included in a torso wearable device.

18. The method of claim 17, wherein receiving the input signals comprises receiving the input signals representing respiration of the user from a plurality of sensors including the sensor.

19. A method for evaluating a user’ s breathing, the method comprising: receiving input signals representing respiration of a user from a sensor; generating a first score based on the input signals, wherein the first score represents a biomechanical evaluation of the respiration of the user, and wherein generating the first score comprises: determining a first respiration data component and a second respiration data component from the input signals, obtaining a first respiration score by referencing the first respiration data component against a first table, obtaining a second respiration score by referencing the second respiration data component against a second table, andcombining the first and second respiration scores to generate the first score; generating a second score based on the input signals, wherein the second score represents a psychophysiological evaluation of the respiration of the user, and wherein generating the second score comprises: determining a first heart rate variability (HRV) data component and a second HRV data component from the input signals, and combining the first and second HRV data components to generate the second score; generating a third score based on the input signals, wherein the third score represents a biochemical evaluation of the respiration of the user, and wherein generating the third score comprises: determining a third respiration data component and a fourth respiration data component from the input signals, obtaining a third respiration score by referencing the third respiration data component against a third table, obtaining a fourth respiration score by referencing the fourth respiration data component against a fourth table, and combining the third and fourth respiration scores to generate the third score; and displaying each of the first score, the second score, and the third score on a graphical user interface in real time.

20. The method of claim 19, further comprising: generating an overall score based on the input signals, wherein the overall score comprises a weighted average of the first score, the second score, and the third score; and displaying the overall score on the graphical user interface in real time.

Images