Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This action is responsive to the application filed February 7, 2025. Claims 1-28 are presented for examination. Claims 1, 11 and 21 is an independent claim.
Priority
Examiner acknowledges the claims for domestic priority under 35 U.S. C. 119 (e) to provisional patent application 63552183, which was filed February 11, 2024.
Oath/Declaration
The Office acknowledges receipt of a properly signed Oath/Declaration submitted February 7, 2025.
Information Disclosure Statement
The Applicant’s Information Disclosure Statement filed (August 20, 2025) has been received, entered into the record, and considered.
Drawings
The drawings filed February 7, 2025 are accepted by the examiner.
Abstract
The abstract filed February 7, 2025 is accepted by the examiner.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-28 are rejected under 35 U.S.C. 103 as being unpatentable over Chang et al. (US 20170188894 A1) in view of Albiston et al. (WO 2022261247 A1).
As to Claim 1:
Chang et al. discloses a predictive analysis system for athletic performance (Chang, see Abstract, where Chang discloses a system and method for utilizing an activity monitoring device that includes, during a set of initial activity sessions, collecting the kinematic data from an activity monitoring device and generating a temporal record of at least one biomechanical signal that is calculated from the kinematic data; analyzing temporal changes in the biomechanical signals during the initial activity sessions and characterizing a fatigue model; and, during a subsequent activity session collecting current kinematic data of a participant and generating at least one current biomechanical signal from the current kinematic data, monitoring the fatigue state through processing the at least one current biomechanical signal according to the fatigue model, and triggering feedback in a user interface based on the fatigue state), comprising: a data ingestion module configured to aggregate structured and unstructured data from diverse sources related to athlete performance (Chang, see figure 5 and paragraph [0042], where Chang discloses that as shown in FIG. 5, a method for sensing and responding to fatigue during a physical activity of a preferred embodiment includes establishing a fatigue model based on at least one biomechanical signal of a participant Sl00, collecting kinematic data and generating at least one biomechanical signal S210, monitoring fatigue state through processing the at least one current biomechanical signal according to the fatigue model S220, and triggering feedback in a user interface in response to a fatigue state S230. Establishing a fatigue model preferably includes collecting kinematic data and generating a set of biomechanical signals Sll0 and analyzing temporal changes in the set of biomechanical signals and characterizing the fatigue model S120); a predictive modeling engine configured to implement machine learning algorithms (Chang, see paragraph [0044], where Chang discloses that machine intelligences may be performed on a set of participants, and the results of the training can be applied to one or more participants who may or may not have been part of the training set. In some cases, the data used to train the machine intelligence is collected with particular conditions so as to be most applicable to a set of target audiences) to construct predictive models based on the aggregated data and sports principles (Chang, see paragraph [0027], where Chang discloses that the set of biomechanical signals may form a primitive set of signals from which a wide variety of activities can be monitored and analyzed. Herein, the system and method is particularly applied to running, but the method can additionally or alternatively be applied to other physical activities. For example, the system and method may be applied to activity use-cases such as gait-analysis, walking, running, lifting, swimming, skiing, skating, biking, rowing, golfing, baseball, basketball, bowling, soccer, football, dancing/choreography, ballet and/or any suitable activity. The activity is preferably characterized by predictable, repetitive, or predefined movements. The system method can be applied to helping a participant improve performance, track progress, and/or avoid injury in the sporting field); an insights generator configured to perform contextual analysis of outputs from the predictive models to derive personalized insights and recommendations (Chang, see paragraph [0041], where Chang discloses that the system can be configured to provide user feedback when the biomechanical signals of a participant indicate fatigue. In another implementation, training recommendations may be generated and presented so as to target different fatigue objectives. For example, interval training could be used to transition a runner between non fatigued state and a fatigue state multiple times until the level of fatigue indicates the activity session should conclude. In another implementation, the system could generate running route options based on a predicted onset of fatigue. For example, a user application could direct a runner where to run so as to satisfy a healthy level of fatigue during a running session. In another example, a graphical map could show where the onset of fatigue is predicted based on the runner's current state and location. The system and its capabilities to detect and respond to fatigue may alternatively be used for other suitable use cases); a continual learning module (Chang, see paragraph [0084], where Chang discloses that pattern recognition algorithms, computer vision, image recognition, neural networks, and/or other suitable machine intelligence techniques can be used to analyze and characterize the shapes and variability of the motion paths created by the runner) configured to monitor additional athlete data and refine the predictive models (Chang, see paragraph [0022], where Chang discloses sensing and responding to fatigue during a physical activity of a preferred embodiment functions to utilize a change in biomechanical signals as an indicator of fatigue. The system and method preferably uses the motion of a participant as they perform an action to determine if the participant is fatigued. The kinematic motion can be characterized as biomechanical signals. The biomechanical signals are preferably for repeated actions such as the exemplary running biomechanical signals of motion paths, ground contact time, cadence, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, foot pronation, body loading ratio, foot lift, and/or other signals. Herein, use of ground contact time and kinematic motion path are used as the primary examples in detecting fatigue); and a user interface configured to provide customized visualization of model forecasts, insights, and recommendations (Chang, see paragraph [0039] and [0040], where Chang discloses that the user application can be any suitable type of user interface component. Preferably, the user application is a graphical user interface operable on a user computing device. The user computing device can be a smart phone, a tablet, a desktop computer, a TV based computing device, a wearable computing device (e.g., a watch, glasses, etc.), or any suitable computing device. The user application may facilitate part or all of signal processing. Portions of the signal processing may alternatively be implemented on the activity monitoring device 110 or in the computing platform 120. Various forms of feedback can be delivered and/or controlled by the user application. For example, the detection of fatigue may be applied to notifying a participant of information relating to fatigue, analyzing performance and fatigue in one or more sessions, and guiding a participant when training or performing. Feedback could be in the form of audio cues ( e.g., sounds and/or spoken audio), visual representation of information on a screen, haptic feedback, and/or other forms of feedback).
Chang differs from the claimed subject matter in that Chang does not explicitly disclose sports science.
However in an analogous art, Albiston discloses sports science (Albiston, see paragraph [0766], where Albiston discloses that modern neuroscience techniques now allow us, for the first time, to look into the brain and obtain novel metrics about its performance. Because of their cutting-edge nature as well as the critical importance of the brain to sports performance - in contrast to the above-listed metrics - neuroscience-based metrics can very realistically offer teams a meaningful competitive advantage).
It would have been obvious to one of ordinary skill in the art to modify the invention of Chang with Albiston. One would be motivated to modify Chang by disclosing sports science as taught by Albiston, and thereby enabling people to more effectively and quickly improve their decision-making, perception, cognition and motor performance (Albiston, see paragraph [0003]).
As to Claim 2:
Chang in view of Albiston discloses that the system of claim 1, wherein the data ingestion module is configured to aggregate data including player statistics (Chang, see paragraph [0120], where Chang discloses that a user application can present performance changes (e.g., running speed)), biomechanical data (Chang, see paragraph [0120], where Chang discloses that a user application can present changes in the biomechanical signals), training regimens (Chang, see paragraph [0121], where Chang discloses providing pacing and distance targets before or during an activity session. For example, before starting a run, the method may recommend a distance and a target mile split time so as to hit an acceptable (non-injury) fatigue state. The predicted fatigue state can alternatively be used in generating a map of running route options using a prediction of the current biomechanical signals satisfying a fatigue condition in a fatigue model and/or selecting a recommended route for the participant. The prediction can use previous activity history and current status to determine when a participant would experience fatigue. The prediction may additionally account for a planned running route and terrain on that route), and health metrics (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 3:
Chang in view of Albiston discloses the system of claim 1, wherein the predictive modeling engine is configured to forecast performance metrics including speed (Chang, see paragraph [0120], where Chang discloses that a user application can present performance changes (e.g., running speed)), endurance (Chang, see paragraph [0123], where Chang discloses that providing analysis can additionally include determining a top comfort-speed. The top comfort-speed is a rate at which a participant can operate at without expressing kinematic traits of fatigue. The top-comfort speed may additionally be a speed at which injury is less likely compared to higher speeds and endurance is higher), power (Chang, see paragraph [0033], [0055] and [0032], where Chang discloses that an inertial measurement system 112 can be coupled to a point on the participant's body. For example, a set of inertial measurement systems 112 can be positioned at the waist region, the shank of one or two legs, one or two feet, the thigh of one or two legs, the upper body, the upper arm, the lower arm, the head, or any suitable position on the body. Alternatively, an inertial measurement system 112 can be coupled to a point on a piece of equipment used during the activity such as a golf club, a bike wheel or pedal, a rowing oar, a basketball, a baseball, a baseball bat, a weight lifting bar, a tennis racket, or any suitable piece of equipment. For example one or more inertial measurement system(s) 112, The sensing device provides acceleration as detected by an accelerometer and angular velocity as detected by a gyroscope along three orthonormal axes. The inertial measurement system 112 can additionally include an integrated processor that, among other functionality, provides sensor fusion, which effectively provides a separation of forces caused by gravity from forces caused by speed changes on the sensor. The integrated processor may additionally provide post processing of kinematic data, it is noted that power can be calculated from angular velocity and force measurements as power = force x velocity) and agility tailored to individual athlete profiles (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 4:
Chang in view of Albiston discloses that the system of claim 1, wherein the predictive modeling engine is configured to quantify injury risks based on biomechanical factors (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 5:
Chang in view of Albiston discloses that the system of claim 1, wherein the insights generator is configured to identify key performance drivers and potential injury risks (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 6:
Chang in view of Albiston discloses that the system of claim 1, wherein the continual learning module is configured to incrementally augment training datasets to keep models up-to-date (Chang, see paragraph [0048], where Chang discloses collecting kinematic data and generating a set of biomechanical signals, functions to obtain motion data of a participant used to analyze fatigue. Block Sll0 is preferably substantially similar to Block S210 wherein kinematic data is collected and transformed into biomechanical signals. In some cases, the collected kinematic data and generated biomechanical signals can be used in establishing or updating a fatigue model).
As to Claim 7:
Chang in view of Albiston discloses that the system of claim 1, wherein the user interface is configured to adapt based on user roles (Chang, see paragraph [0027], where Chang discloses that the system and method may be applied to activity use-cases such as gait-analysis, walking, running, lifting, swimming, skiing, skating, biking, rowing, golfing, baseball, basketball, bowling, soccer, football, dancing/choreography, ballet and/or any suitable activity. The activity is preferably characterized by predictable, repetitive, or predefined movements).
As to Claim 8:
Chang in view of Albiston discloses that the system of claim 1, wherein the predictive modeling engine implements explainable AI techniques to facilitate understanding of model behaviors (Chang, see paragraph [0084], where Chang discloses that pattern recognition algorithms, computer vision, image recognition, neural networks, and/or other suitable machine intelligence techniques can be used to analyze and characterize the shapes and variability of the motion paths created by the runner).
As to Claim 9:
Chang in view of Albiston discloses that the system of claim 1, further comprising a data lake architecture on cloud infrastructure for secure, scalable storage of the aggregated data (Albiston, see paragraph [0876], where Albiston discloses that examples of storage implemented by the storage hardware include a database (such as a relational database or a NoSQL database), a data store, a data lake, a column store, a data warehouse. Example of storage hardware include nonvolatile memory devices, volatile memory devices, magnetic storage media, a storage area network (SAN), network-attached storage (NAS), optical storage media, printed media (such as bar codes and magnetic ink), and paper media (such as punch cards and paper tape). The storage hardware may include cache memory, which may be collocated with or integrated with processing hardware).
As to Claim 10:
Chang in view of Albiston discloses that the system of claim 1, wherein the predictive modeling engine is configured to implement model architectures ranging from linear regression (Albiston, see paragraph [0011], where Albiston discloses that the method may include training a Long Short-Term Memory (LSTM) network with sequences of brain states represented by corresponding sequences of the unique identifiers. In some embodiments, the method may include training a logistic regression model with sequences of brain states represented by corresponding sequences of the unique identifiers) to convolutional neural networks (Albiston, see paragraph [0667], where Albiston discloses that a method for improving decision-making or performance on a conscious activity. The feature selection process involves a non-trivial series of derivations, transformations, convolutions).
As to Claim 11:
Chang et al. discloses a method for predictive analysis of athletic performance (Chang, see Abstract, where Chang discloses a system and method for utilizing an activity monitoring device that includes, during a set of initial activity sessions, collecting the kinematic data from an activity monitoring device and generating a temporal record of at least one biomechanical signal that is calculated from the kinematic data; analyzing temporal changes in the biomechanical signals during the initial activity sessions and characterizing a fatigue model; and, during a subsequent activity session collecting current kinematic data of a participant and generating at least one current biomechanical signal from the current kinematic data, monitoring the fatigue state through processing the at least one current biomechanical signal according to the fatigue model, and triggering feedback in a user interface based on the fatigue state), comprising: aggregating, by a data ingestion module, structured and unstructured data from diverse sources related to athlete performance (Chang, see figure 5 and paragraph [0042], where Chang discloses that as shown in FIG. 5, a method for sensing and responding to fatigue during a physical activity of a preferred embodiment includes establishing a fatigue model based on at least one biomechanical signal of a participant Sl00, collecting kinematic data and generating at least one biomechanical signal S210, monitoring fatigue state through processing the at least one current biomechanical signal according to the fatigue model S220, and triggering feedback in a user interface in response to a fatigue state S230. Establishing a fatigue model preferably includes collecting kinematic data and generating a set of biomechanical signals Sll0 and analyzing temporal changes in the set of biomechanical signals and characterizing the fatigue model S120); implementing, by a predictive modeling engine, machine learning algorithms (Chang, see paragraph [0044], where Chang discloses that machine intelligences may be performed on a set of participants, and the results of the training can be applied to one or more participants who may or may not have been part of the training set. In some cases, the data used to train the machine intelligence is collected with particular conditions so as to be most applicable to a set of target audiences) to construct predictive models based on the aggregated data and sports principles (Chang, see paragraph [0027], where Chang discloses that the set of biomechanical signals may form a primitive set of signals from which a wide variety of activities can be monitored and analyzed. Herein, the system and method is particularly applied to running, but the method can additionally or alternatively be applied to other physical activities. For example, the system and method may be applied to activity use-cases such as gait-analysis, walking, running, lifting, swimming, skiing, skating, biking, rowing, golfing, baseball, basketball, bowling, soccer, football, dancing/choreography, ballet and/or any suitable activity. The activity is preferably characterized by predictable, repetitive, or predefined movements. The system method can be applied to helping a participant improve performance, track progress, and/or avoid injury in the sporting field); performing, by an insights generator, contextual analysis of outputs from the predictive models to derive personalized insights and recommendations (Chang, see paragraph [0041], where Chang discloses that the system can be configured to provide user feedback when the biomechanical signals of a participant indicate fatigue. In another implementation, training recommendations may be generated and presented so as to target different fatigue objectives. For example, interval training could be used to transition a runner between non fatigued state and a fatigue state multiple times until the level of fatigue indicates the activity session should conclude. In another implementation, the system could generate running route options based on a predicted onset of fatigue. For example, a user application could direct a runner where to run so as to satisfy a healthy level of fatigue during a running session. In another example, a graphical map could show where the onset of fatigue is predicted based on the runner's current state and location. The system and its capabilities to detect and respond to fatigue may alternatively be used for other suitable use cases); monitoring, by a continual learning module (Chang, see paragraph [0084], where Chang discloses that pattern recognition algorithms, computer vision, image recognition, neural networks, and/or other suitable machine intelligence techniques can be used to analyze and characterize the shapes and variability of the motion paths created by the runner), additional athlete data and refining the predictive models (Chang, see paragraph [0022], where Chang discloses sensing and responding to fatigue during a physical activity of a preferred embodiment functions to utilize a change in biomechanical signals as an indicator of fatigue. The system and method preferably uses the motion of a participant as they perform an action to determine if the participant is fatigued. The kinematic motion can be characterized as biomechanical signals. The biomechanical signals are preferably for repeated actions such as the exemplary running biomechanical signals of motion paths, ground contact time, cadence, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, foot pronation, body loading ratio, foot lift, and/or other signals. Herein, use of ground contact time and kinematic motion path are used as the primary examples in detecting fatigue); and providing, by a user interface, customized visualization of model forecasts, insights, and recommendations (Chang, see paragraph [0039] and [0040], where Chang discloses that the user application can be any suitable type of user interface component. Preferably, the user application is a graphical user interface operable on a user computing device. The user computing device can be a smart phone, a tablet, a desktop computer, a TV based computing device, a wearable computing device (e.g., a watch, glasses, etc.), or any suitable computing device. The user application may facilitate part or all of signal processing. Portions of the signal processing may alternatively be implemented on the activity monitoring device 110 or in the computing platform 120. Various forms of feedback can be delivered and/or controlled by the user application. For example, the detection of fatigue may be applied to notifying a participant of information relating to fatigue, analyzing performance and fatigue in one or more sessions, and guiding a participant when training or performing. Feedback could be in the form of audio cues ( e.g., sounds and/or spoken audio), visual representation of information on a screen, haptic feedback, and/or other forms of feedback).
Chang differs from the claimed subject matter in that Chang does not explicitly disclose sports science.
However in an analogous art, Albiston discloses sports science (Albiston, see paragraph [0766], where Albiston discloses that modern neuroscience techniques now allow us, for the first time, to look into the brain and obtain novel metrics about its performance. Because of their cutting-edge nature as well as the critical importance of the brain to sports performance - in contrast to the above-listed metrics - neuroscience-based metrics can very realistically offer teams a meaningful competitive advantage).
It would have been obvious to one of ordinary skill in the art to modify the invention of Chang with Albiston. One would be motivated to modify Chang by disclosing sports science as taught by Albiston, and thereby enabling people to more effectively and quickly improve their decision-making, perception, cognition and motor performance (Albiston, see paragraph [0003]).
As to Claim 12:
Chang in view of Albiston discloses that the method of claim 11, wherein aggregating data includes collecting player statistics (Chang, see paragraph [0120], where Chang discloses that a user application can present performance changes (e.g., running speed)), biomechanical data (Chang, see paragraph [0120], where Chang discloses that a user application can present changes in the biomechanical signals), training regimens (Chang, see paragraph [0121], where Chang discloses providing pacing and distance targets before or during an activity session. For example, before starting a run, the method may recommend a distance and a target mile split time so as to hit an acceptable (non-injury) fatigue state. The predicted fatigue state can alternatively be used in generating a map of running route options using a prediction of the current biomechanical signals satisfying a fatigue condition in a fatigue model and/or selecting a recommended route for the participant. The prediction can use previous activity history and current status to determine when a participant would experience fatigue. The prediction may additionally account for a planned running route and terrain on that route), and health metrics (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 13:
Chang in view of Albiston discloses that the method of claim 11, wherein implementing machine learning algorithms includes forecasting performance metrics including speed (Chang, see paragraph [0120], where Chang discloses that a user application can present performance changes (e.g., running speed)), endurance (Chang, see paragraph [0123], where Chang discloses that providing analysis can additionally include determining a top comfort-speed. The top comfort-speed is a rate at which a participant can operate at without expressing kinematic traits of fatigue. The top-comfort speed may additionally be a speed at which injury is less likely compared to higher speeds and endurance is higher), power (Chang, see paragraph [0033], [0055] and [0032], where Chang discloses that an inertial measurement system 112 can be coupled to a point on the participant's body. For example, a set of inertial measurement systems 112 can be positioned at the waist region, the shank of one or two legs, one or two feet, the thigh of one or two legs, the upper body, the upper arm, the lower arm, the head, or any suitable position on the body. Alternatively, an inertial measurement system 112 can be coupled to a point on a piece of equipment used during the activity such as a golf club, a bike wheel or pedal, a rowing oar, a basketball, a baseball, a baseball bat, a weight lifting bar, a tennis racket, or any suitable piece of equipment. For example one or more inertial measurement system(s) 112, The sensing device provides acceleration as detected by an accelerometer and angular velocity as detected by a gyroscope along three orthonormal axes. The inertial measurement system 112 can additionally include an integrated processor that, among other functionality, provides sensor fusion, which effectively provides a separation of forces caused by gravity from forces caused by speed changes on the sensor. The integrated processor may additionally provide post processing of kinematic data, it is noted that power can be calculated from angular velocity and force measurements as power = force x velocity), and agility tailored to individual athlete profiles (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 14:
Chang in view of Albiston discloses that the method of claim 11, wherein implementing machine learning algorithms includes quantifying injury risks based on biomechanical factors (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
.
As to Claim 15:
Chang in view of Albiston discloses that the method of claim 11, wherein performing contextual analysis includes identifying key performance drivers and potential injury risks (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 16:
Chang in view of Albiston discloses that the method of claim 11, wherein monitoring additional athlete data includes incrementally augmenting training datasets to keep models up-to-date (Chang, see paragraph [0048], where Chang discloses collecting kinematic data and generating a set of biomechanical signals, functions to obtain motion data of a participant used to analyze fatigue. Block Sll0 is preferably substantially similar to Block S210 wherein kinematic data is collected and transformed into biomechanical signals. In some cases, the collected kinematic data and generated biomechanical signals can be used in establishing or updating a fatigue model).
As to Claim 17:
Chang in view of Albiston discloses that the method of claim 11, wherein providing customized visualization includes adapting the user interface based on user roles (Chang, see paragraph [0027], where Chang discloses that the system and method may be applied to activity use-cases such as gait-analysis, walking, running, lifting, swimming, skiing, skating, biking, rowing, golfing, baseball, basketball, bowling, soccer, football, dancing/choreography, ballet and/or any suitable activity. The activity is preferably characterized by predictable, repetitive, or predefined movements).
.
As to Claim 18:
Chang in view of Albiston discloses that the method of claim 11, further comprising implementing explainable AI techniques to allow understanding of model behaviors (Chang, see paragraph [0084], where Chang discloses that pattern recognition algorithms, computer vision, image recognition, neural networks, and/or other suitable machine intelligence techniques can be used to analyze and characterize the shapes and variability of the motion paths created by the runner).
As to Claim 19:
Chang in view of Albiston discloses that the method of claim 11, further comprising storing the aggregated data in a data lake architecture on cloud infrastructure (Albiston, see paragraph [0876], where Albiston discloses that examples of storage implemented by the storage hardware include a database (such as a relational database or a NoSQL database), a data store, a data lake, a column store, a data warehouse. Example of storage hardware include nonvolatile memory devices, volatile memory devices, magnetic storage media, a storage area network (SAN), network-attached storage (NAS), optical storage media, printed media (such as bar codes and magnetic ink), and paper media (such as punch cards and paper tape). The storage hardware may include cache memory, which may be collocated with or integrated with processing hardware).
As to Claim 20:
Chang in view of Albiston discloses that the method of claim 11, wherein implementing machine learning algorithms includes using model architectures ranging from linear regression (Albiston, see paragraph [0011], where Albiston discloses that the method may include training a Long Short-Term Memory (LSTM) network with sequences of brain states represented by corresponding sequences of the unique identifiers. In some embodiments, the method may include training a logistic regression model with sequences of brain states represented by corresponding sequences of the unique identifiers) to convolutional neural networks (Albiston, see paragraph [0667], where Albiston discloses that a method for improving decision-making or performance on a conscious activity. The feature selection process involves a non-trivial series of derivations, transformations, convolutions).
As to Claim 21:
Chang et al. discloses a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform a method for predictive analysis of athletic performance (Chang, see Abstract, where Chang discloses a system and method for utilizing an activity monitoring device that includes, during a set of initial activity sessions, collecting the kinematic data from an activity monitoring device and generating a temporal record of at least one biomechanical signal that is calculated from the kinematic data; analyzing temporal changes in the biomechanical signals during the initial activity sessions and characterizing a fatigue model; and, during a subsequent activity session collecting current kinematic data of a participant and generating at least one current biomechanical signal from the current kinematic data, monitoring the fatigue state through processing the at least one current biomechanical signal according to the fatigue model, and triggering feedback in a user interface based on the fatigue state), the method comprising: aggregating, by a data ingestion module, structured and unstructured data from diverse sources related to athlete performance (Chang, see figure 5 and paragraph [0042], where Chang discloses that as shown in FIG. 5, a method for sensing and responding to fatigue during a physical activity of a preferred embodiment includes establishing a fatigue model based on at least one biomechanical signal of a participant Sl00, collecting kinematic data and generating at least one biomechanical signal S210, monitoring fatigue state through processing the at least one current biomechanical signal according to the fatigue model S220, and triggering feedback in a user interface in response to a fatigue state S230. Establishing a fatigue model preferably includes collecting kinematic data and generating a set of biomechanical signals Sll0 and analyzing temporal changes in the set of biomechanical signals and characterizing the fatigue model S120); implementing, by a predictive modeling engine, machine learning algorithms (Chang, see paragraph [0044], where Chang discloses that machine intelligences may be performed on a set of participants, and the results of the training can be applied to one or more participants who may or may not have been part of the training set. In some cases, the data used to train the machine intelligence is collected with particular conditions so as to be most applicable to a set of target audiences) to construct predictive models based on the aggregated data and sports principles (Chang, see paragraph [0027], where Chang discloses that the set of biomechanical signals may form a primitive set of signals from which a wide variety of activities can be monitored and analyzed. Herein, the system and method is particularly applied to running, but the method can additionally or alternatively be applied to other physical activities. For example, the system and method may be applied to activity use-cases such as gait-analysis, walking, running, lifting, swimming, skiing, skating, biking, rowing, golfing, baseball, basketball, bowling, soccer, football, dancing/choreography, ballet and/or any suitable activity. The activity is preferably characterized by predictable, repetitive, or predefined movements. The system method can be applied to helping a participant improve performance, track progress, and/or avoid injury in the sporting field); performing, by an insights generator, contextual analysis of outputs from the predictive models to derive personalized insights and recommendations (Chang, see paragraph [0041], where Chang discloses that the system can be configured to provide user feedback when the biomechanical signals of a participant indicate fatigue. In another implementation, training recommendations may be generated and presented so as to target different fatigue objectives. For example, interval training could be used to transition a runner between non fatigued state and a fatigue state multiple times until the level of fatigue indicates the activity session should conclude. In another implementation, the system could generate running route options based on a predicted onset of fatigue. For example, a user application could direct a runner where to run so as to satisfy a healthy level of fatigue during a running session. In another example, a graphical map could show where the onset of fatigue is predicted based on the runner's current state and location. The system and its capabilities to detect and respond to fatigue may alternatively be used for other suitable use cases); monitoring, by a continual learning module (Chang, see paragraph [0084], where Chang discloses that pattern recognition algorithms, computer vision, image recognition, neural networks, and/or other suitable machine intelligence techniques can be used to analyze and characterize the shapes and variability of the motion paths created by the runner), additional athlete data and refining the predictive models (Chang, see paragraph [0022], where Chang discloses sensing and responding to fatigue during a physical activity of a preferred embodiment functions to utilize a change in biomechanical signals as an indicator of fatigue. The system and method preferably uses the motion of a participant as they perform an action to determine if the participant is fatigued. The kinematic motion can be characterized as biomechanical signals. The biomechanical signals are preferably for repeated actions such as the exemplary running biomechanical signals of motion paths, ground contact time, cadence, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward oscillation, forward velocity properties of the pelvis, step duration, stride or step length, step impact or shock, foot pronation, body loading ratio, foot lift, and/or other signals. Herein, use of ground contact time and kinematic motion path are used as the primary examples in detecting fatigue); and providing, by a user interface, customized visualization of model forecasts, insights, and recommendations (Chang, see paragraph [0039] and [0040], where Chang discloses that the user application can be any suitable type of user interface component. Preferably, the user application is a graphical user interface operable on a user computing device. The user computing device can be a smart phone, a tablet, a desktop computer, a TV based computing device, a wearable computing device (e.g., a watch, glasses, etc.), or any suitable computing device. The user application may facilitate part or all of signal processing. Portions of the signal processing may alternatively be implemented on the activity monitoring device 110 or in the computing platform 120. Various forms of feedback can be delivered and/or controlled by the user application. For example, the detection of fatigue may be applied to notifying a participant of information relating to fatigue, analyzing performance and fatigue in one or more sessions, and guiding a participant when training or performing. Feedback could be in the form of audio cues ( e.g., sounds and/or spoken audio), visual representation of information on a screen, haptic feedback, and/or other forms of feedback).
Chang differs from the claimed subject matter in that Chang does not explicitly disclose sports science.
However in an analogous art, Albiston discloses sports science (Albiston, see paragraph [0766], where Albiston discloses that modern neuroscience techniques now allow us, for the first time, to look into the brain and obtain novel metrics about its performance. Because of their cutting-edge nature as well as the critical importance of the brain to sports performance - in contrast to the above-listed metrics - neuroscience-based metrics can very realistically offer teams a meaningful competitive advantage).
It would have been obvious to one of ordinary skill in the art to modify the invention of Chang with Albiston. One would be motivated to modify Chang by disclosing sports science as taught by Albiston, and thereby enabling people to more effectively and quickly improve their decision-making, perception, cognition and motor performance (Albiston, see paragraph [0003]).
As to Claim 22:
Chang in view of Albiston discloses that the non-transitory computer-readable medium of claim 21, wherein aggregating data includes collecting player statistics (Chang, see paragraph [0120], where Chang discloses that a user application can present performance changes (e.g., running speed)), biomechanical data (Chang, see paragraph [0120], where Chang discloses that a user application can present changes in the biomechanical signals), training regimens (Chang, see paragraph [0121], where Chang discloses providing pacing and distance targets before or during an activity session. For example, before starting a run, the method may recommend a distance and a target mile split time so as to hit an acceptable (non-injury) fatigue state. The predicted fatigue state can alternatively be used in generating a map of running route options using a prediction of the current biomechanical signals satisfying a fatigue condition in a fatigue model and/or selecting a recommended route for the participant. The prediction can use previous activity history and current status to determine when a participant would experience fatigue. The prediction may additionally account for a planned running route and terrain on that route), and health metrics (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 23:
Chang in view of Albiston discloses that the non-transitory computer-readable medium of claim 21, wherein implementing machine learning algorithms includes forecasting performance metrics including speed (Chang, see paragraph [0120], where Chang discloses that a user application can present performance changes (e.g., running speed)), endurance (Chang, see paragraph [0123], where Chang discloses that providing analysis can additionally include determining a top comfort-speed. The top comfort-speed is a rate at which a participant can operate at without expressing kinematic traits of fatigue. The top-comfort speed may additionally be a speed at which injury is less likely compared to higher speeds and endurance is higher), power (Chang, see paragraph [0033], [0055] and [0032], where Chang discloses that an inertial measurement system 112 can be coupled to a point on the participant's body. For example, a set of inertial measurement systems 112 can be positioned at the waist region, the shank of one or two legs, one or two feet, the thigh of one or two legs, the upper body, the upper arm, the lower arm, the head, or any suitable position on the body. Alternatively, an inertial measurement system 112 can be coupled to a point on a piece of equipment used during the activity such as a golf club, a bike wheel or pedal, a rowing oar, a basketball, a baseball, a baseball bat, a weight lifting bar, a tennis racket, or any suitable piece of equipment. For example one or more inertial measurement system(s) 112, The sensing device provides acceleration as detected by an accelerometer and angular velocity as detected by a gyroscope along three orthonormal axes. The inertial measurement system 112 can additionally include an integrated processor that, among other functionality, provides sensor fusion, which effectively provides a separation of forces caused by gravity from forces caused by speed changes on the sensor. The integrated processor may additionally provide post processing of kinematic data, it is noted that power can be calculated from angular velocity and force measurements as power = force x velocity), and agility tailored to individual athlete profiles Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 24:
Chang in view of Albiston discloses that the non-transitory computer-readable medium of claim 21, wherein implementing machine learning algorithms includes quantifying injury risks based on biomechanical factors (Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 25:
Chang in view of Albiston discloses that the non-transitory computer-readable medium of claim 21, wherein performing contextual analysis includes identifying key performance drivers and potential injury risks Chang, see paragraph [0119], where Chang discloses that a variety of unique applications can be built on top of fatigue detection and/or measurement including providing analysis of fatigue in relationship to the activity, notifying the participant, enhancing exercises by hitting targeted fatigue levels, providing guidance on participant actions, warning of potential injury, and/or other applications).
As to Claim 26:
Chang in view of Albiston discloses that the non-transitory computer-readable medium of claim 21, wherein monitoring additional athlete data includes incrementally augmenting training datasets to keep models up-to-date (Chang, see paragraph [0048], where Chang discloses collecting kinematic data and generating a set of biomechanical signals, functions to obtain motion data of a participant used to analyze fatigue. Block Sll0 is preferably substantially similar to Block S210 wherein kinematic data is collected and transformed into biomechanical signals. In some cases, the collected kinematic data and generated biomechanical signals can be used in establishing or updating a fatigue model).
As to Claim 27:
Chang in view of Albiston discloses that the non-transitory computer-readable medium of claim 21, wherein providing customized visualization includes adapting the user interface based on user roles (Chang, see paragraph [0027], where Chang discloses that the system and method may be applied to activity use-cases such as gait-analysis, walking, running, lifting, swimming, skiing, skating, biking, rowing, golfing, baseball, basketball, bowling, soccer, football, dancing/choreography, ballet and/or any suitable activity. The activity is preferably characterized by predictable, repetitive, or predefined movements).
As to Claim 28:
Chang in view of Albiston discloses that the non-transitory computer-readable medium of claim 21, the method further comprising implementing explainable AI techniques to allow understanding of model behaviors (Chang, see paragraph [0084], where Chang discloses that pattern recognition algorithms, computer vision, image recognition, neural networks, and/or other suitable machine intelligence techniques can be used to analyze and characterize the shapes and variability of the motion paths created by the runner).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Wang (US 20170273601 A1) discloses addressing patient health through monitoring patient movement that includes, during a treatment stage, collecting kinematic data from at least one inertial measurement unit of an activity monitoring system; generating a set of biomechanical signals from the kinematic data wherein the set of biomechanical signals characterize at least one biomechanical property; updating a mobility quality score of the subject based on the set of biomechanical signals; and delivering a health assessment.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NELSON ROSARIO whose telephone number is (571)270-1866. The examiner can normally be reached on Monday through Friday, 7:30am- 5:00pm EST. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Eason can be reached on (571) 270-7230. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/NELSON M ROSARIO/Primary Examiner, Art Unit 2624
Prosecution Insights