WO2025122645A1

WO2025122645A1 - Computer implemented method for human motion diagnosis and treatment

Info

Publication number: WO2025122645A1
Application number: PCT/US2024/058506
Authority: WO
Inventors: Michael Garrett; Julian Henry MORRIS
Original assignee: Patrizia Evans
Current assignee: Patrizia Evans
Priority date: 2023-12-06
Filing date: 2024-12-04
Publication date: 2025-06-12
Anticipated expiration: 2026-06-06

Abstract

Apparatus and associated methods relate to a system configured to automatically identify a kinematic profile of a user and generate a recommendation library. In an illustrative example, a dynamic kinematic intelligence platform (DKIP) may activate a sensor module in response to a neuromuscular activation signal. A sequence of N kinematic evaluation, for example, may be retrieved to assess a user's health conditions. For example, a movement code generation operation may include, for i = 1 to N, transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device, and generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user. For example, the movement code may include a first key comprising balance, core, and flexibility values, and a second key comprising posterior, vertical, lateral, anterior, and core lines values. Various embodiments may advantageously generate an individualized full-body enhancement library.

Description

COMPUTER IMPLEMENTED METHOD FOR HUMAN MOTION DIAGNOSIS AND TREATMENT

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application Serial No. 63/607,071, titled “COMPUTER IMPLEMENTED METHOD FOR HUMAN MOTION DIAGNOSIS AND TREATMENT,” filed by Michael Garrett, on December 6, 2023.

[0002] This application incorporates the entire contents of the foregoing application(s) herein by reference.

TECHNICAL FIELD

[0003] Various embodiments relate generally to biomechanical motion analysis and personalized rehabilitation systems.

BACKGROUND

[0004] Physiotherapy, also known as physical therapy, is a healthcare discipline that focuses on improving movement, function, and overall quality of life through physical interventions. It is grounded in evidence-based practices, applying techniques such as neuromuscular activation, manual therapy, and education to address a wide range of conditions, including musculoskeletal, neuromuscular, and cardiopulmonary disorders. By assessing each patient's specific needs, physiotherapists design individualized treatment plans aimed at restoring mobility, reducing pain, and preventing further injury.

[0005] Physiotherapy has a broad range of applications that extend beyond traditional injury rehabilitation. It plays a vital role in preventive care by addressing posture-related issues, reducing fall risks among older adults, and improving sports performance for athletes. In clinical settings, for example, physiotherapists may manage chronic conditions like arthritis, stroke, and heart disease by improving patients' strength and mobility through targeted interventions.

[0006] Physiotherapy may, in some cases, be valuable for injury recovery. For example, physiotherapy may help patients regain function and return to daily activities safely and efficiently. For musculoskeletal injuries, physiotherapists may use a combination of modalities, including manual therapy, therapeutic activations, and modalities like ultrasound or electrical stimulation, to reduce pain and inflammation while promoting tissue healing, for example. In sports injuries, for example, physiotherapy may focus on restoring strength, flexibility, and/or range of motion to prevent future injuries. Whether addressing acute injuries like fractures or chronic conditions like tendonitis, physiotherapy may offer a comprehensive approach to restoring function and empowering patients to take control of their recovery journey. SUMMARY

[0007] Apparatus and associated methods relate to a system configured to automatically identify a kinematic profile of a user and generate a recommendation library. In an illustrative example, a dynamic kinematic intelligence platform (DKIP) may activate a sensor module in response to a neuromuscular activation signal. A sequence of N kinematic evaluation, for example, may be retrieved to assess a user’s health conditions. For example, a movement code generation operation may include, for i = 1 to N, transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device, and generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user. For example, the movement code may include a first key comprising balance, core, and flexibility values, and a second key comprising posterior, vertical, lateral, anterior, and core lines values. Various embodiments may advantageously generate an individualized full-body enhancement library.

[0008] Various embodiments may achieve one or more advantages. For example, some embodiments may advantageously generate kinematic intelligence findings based on prioritizing a user’s critical movement deficiency. Some embodiments may, for example, advantageously promote long-term movement enhancement of the user. For example, some embodiments may advantageously identify injury risks by analyzing movement patterns. Some embodiments may, for example, advantageously provide detailed instructions or demonstrations for performing neuromuscular activations in various neuromuscular activation categories. For example, some embodiments may advantageously provide targeted interventions for skeletal alignment and overall functional improvement. Some embodiments may, for example, advantageously provide a mechanism for the user to specify preferences and/or feedback to the individualized full-body enhancement library. For example, some embodiments may advantageously provide fast generation of individualized kinematic assessments and/or neuromuscular activation recommendations in near real-time.4

[0009] The details of various embodiments are set forth in the accompanying drawings and the description below. Other features and advantages will be apparent from the description and drawings, and from the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG. 1A, FIG. IB, and FIG. 1C depict an exemplary dynamic kinematic intelligence platform (DKIP) employed in an illustrative use-case scenario.

[0011] FIG. 2 is a block diagram depicting an exemplary DKIP. 100121 FIG. 3A, FIG. 3B, and FIG. 3C are block diagrams depicting an exemplary kinematic evaluation database, an exemplary neuromuscular activation library, and an exemplary kinematic intelligence finding.

[0013] FIG. 4 is a flowchart illustrating an exemplary kinematic intelligence findings generation method.

[0014] FIG. 5 is a flowchart illustrating an exemplary kinematic guidance platform.

[0015] FIG. 6A, FIG. 6B, FIG. 6C, FIG. 6D, FIG. 6E, FIG. 6F, FIG. 6G, and FIG. 6H depict exemplary kinematic evaluations.

[0016] FIG. 7 depicts an exemplary archival kinematic profile display.

[0017] FIG. 8 depicts an exemplary machine learning system of an exemplary DKIP.

[0018] FIG. 9 is a block diagram depicting an exemplary neuromuscular activation creation large language model (NACLLM).

[0019] FIG. 10 is a flowchart illustrating an exemplary interactive neuromuscular activation creation method using the exemplary NACLLM described with reference to FIG. 9.

[0020] FIG. 11 is a flowchart illustrating an exemplary machine learning model training method. [0021] Like reference symbols in the various drawings indicate like elements.

DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS

[0022] To aid understanding, this document is organized as follows. First, to help introduce discussion of various embodiments, a dynamic kinematic intelligence platform (DKIP) is introduced with reference to FIGS. 1 A-1C. Second, that introduction leads into a description with reference to FIGS. 2-3C of some exemplary embodiments of the DKIP. Third, with reference to FIGS. 4-5, various exemplary methods of operating the DKIP are described. Fourth, with reference to FIGS. 6A-8, the discussion turns to exemplary embodiments that illustrate a dynamic kinematic assessment application. Fifth, and with reference to FIGS. 9-10, this document describes exemplary apparatus and methods useful for dynamically applying artificial intelligence to generate neuromuscular activations targeting a user’s health condition and/or neuromuscular activation sequences. Finally, the document discusses further embodiments, exemplary applications and aspects relating to DKIP.

[0023] FIG. 1A, FIG. IB, and FIG. 1C depict an exemplary dynamic kinematic intelligence platform (DKIP) employed in an illustrative use-case scenario. As shown in FIG. 1 A, a DKIP 100 includes a user communication engine 105 and a kinematic profile generation engine (KPGE 110). For example, the DKIP 100 may generate kinematic recommendations to a user based on an assessment of a sequence of motions performed by the user. For example, the user may use the DKIP 100 to mitigate pain and improve functionality. 100241 In this example, the user communication engine 105 is coupled to a computing device 115. The KPGE 110 is operably coupled to a sensor module 120. For example, the DKIP 100 may be coupled to the computing device 115 and/or the sensor module 120 through one or more communication networks (e.g., a local area network (LAN), a wide area network (WAN), a wireless network, a wired network).

[0025] In some implementations, the DKIP 100 may transmit to the computing device 115 a sequence of kinematic evaluations 125 to be performed by the user. For example, the computing device 115 may be a smart device of the user (e.g., a mobile phone). In some implementations, the DKIP 100 may be a web application assessed by the computing device 115. In some implementations, the DKIP 100 may be a native application installed in the computing device 115. In some examples, the DKIP 100 may be a business application (e.g., to be used in a sports team, a health clinic, an elderly home, a gym). In some examples, the DKIP 100 may be a home application to be used privately by the user.

[0026] For example, the sensor module 120 may receive sensor measurement data from the user when the user is engaged in the sequence of kinematic evaluations 125. As shown, the sensor module 120 includes a camera 130 and an inertial motion unit (IMU 135). For example, the camera 130 may be an image capture device configured to transmit a series of images to the DKIP 100. For example, the IMU 135 may include one or more sensors (e.g., a (three-dimensional) accelerometer, a (three-dimensional) gyroscope, a Bluetooth location sensor) operably coupled to the user. For example, the IMU 135 may detect a movement of the user’s body or a portion of the user’s body. In some examples, the IMU 135 may include a sensor on the lower back (e.g., at a Posterior Superior Iliac Spine) of the user.

[0027] For example, the computing device 115 and the sensor module 120 may be incorporated in a same mobile device (e.g., having the camera 130 and operably coupled to sensors in the IMU 135). For example, the IMU 135 may harvest movement data at a predetermined frequency (e.g., 20Hz, 30 Hz, or higher for elite sports). For example, the IMU 135 may combine sensor data received from more than one sensor (e.g., including 3D gyroscope data (XYZ), 3D accelerometer data, and/or magnetometer data).

[0028] In some implementations, the sensor module 120 may transmit the movement data to the DKIP 100 in real-time. As an illustrative example, the DKIP 100 may gather human movement data (e.g., the movement data) through a motion screening through the computing device 115. As shown, the user communication engine 105 may retrieve the sequence of kinematic evaluations 125 from a kinematic evaluation database (KED 155). For example, the KED 155 may include a specific neuromuscular activation sequence configured to assess a human's movement pattern. |0029| The KPGE 110 receives the movement data from the sensor module 120. For example, the KPGE 110 may process the movement data. In some implementations, the KPGE 110 may apply an artificial intelligence (Al) motion analysis model to the movement data. In some implementations, the KPGE 110 may also be an IMU movement analysis model to the movement data.

[0030] In this example, the KPGE 110 generates a movement code 145 associated with the user based on the user’s performance in the sequence of kinematic evaluations 125. In some implementations, the KPGE 110 may aggregate the movement data to generate the movement code 145. For example, the movement code 145 may include indexes of the movement data.

[0031] As shown, the movement code 145 is received by a kinematic guidance platform (KGE 150). For example, the KPGE 110 may apply the movement data to an Al-trained model to generate the movement code 145. The KGE 150, for example, may process the movement code 145 using a machine learning or an Al-based motion computation.

[0032] For example, the KGE 150 may generate a kinematic profile 160 associated with the user. In some implementations, the kinematic profile 160 may include a balance index. For example, the KGE 150 may select neuromuscular activation and/or treatment for the user as a function of the kinematic profile 160. As shown, the KGE 150 may select neuromuscular activation and/or sequence of neuromuscular activation for the user from an neuromuscular activation library 165. [0033] In this example, the KGE 150 generates a kinematic analysis result 170. For example, the KGE 150 may generate the kinematic analysis result 170 based on the kinematic profile 160. For example, the kinematic analysis result 170 may include a diagnosis of human motion and treatment associated with the user. In some examples, the kinematic analysis result 170 may be used to generate future kinematic outcomes. For example, the kinematic analysis result 170 may be used to decode pathology (e.g., through pattern matching ).

[0034] In some implementations, the KGE 150 may decode the movement code 145 by pattern matching the neuromuscular activation library 165 using an artificial intelligent model (e.g., a classification model, a support-vector machine, a supervised learning model). As shown, the user communication engine 105 may receive a selected neuromuscular activation sequence from the KGE 150. For example, the user communication engine 105 may digitally send the selected neuromuscular activation sequence to the computing device 115. In some examples, the selected neuromuscular activation sequence may be selected to alleviate discomfort and optimize performance immediately.

[0035] In this example, an information storage system 175 of the DKIP 100 also includes an archival kinematic analytic findings 180. For example, the KGE 150 may apply the Al model to predict and generate recommendations to improve the movement health of the user by selecting the neuromuscular activation sequence based on the archival kinematic analytic findings 180. For example, the archival kinematic analytic findings 180 may be updated periodically (e.g., monthly, weekly, daily).

[0036] For example, the neuromuscular activation sequence may include day-to-day conditioning neuromuscular activation. In some implementations, the user communication engine 105 may also transmit enhanced neuromuscular activation libraries of special purpose (e.g., sports performance enhancement, fall risk reduction). Various embodiments of neuromuscular activation sequence are described in further details with reference to FIG. 3B.

[0037] As shown in FIG. IB, the movement code 145 may include a subgroup 185 and a subgroup 190. For example, the subgroup 185 may include primary movement attributes associated with the user (e.g., balance, core stability, flexibility). For example, the subgroup 190 may include myofascial lines representing interconnected muscle and/or body supporting fascial structures.

[0038] In this example, the subgroup 185 includes three primary attributes. A Balanced Ground Force Reaction (GFR 185A) may include an individual's ability to maintain equilibrium. For example, the GFR 185 A may evaluate the user’s upright posture during standing, walking, and/or performing dynamic movements. The subgroup 185 includes a Core Deep Stabilization System (CDSS 185B): The CDSS 185B attribute may represent stabilization and support provided by deep muscles of the user (e.g., muscles surrounding the spine and pelvis). The deep muscles, for example, may be distinct from superficial power muscles. For example, the deep muscle may be influential in controlling precise movements. Flexibility 185C, for example, may be assessed dynamically based on a range of motion achievable by the user’s joints or joint groups (e.g., without pain or discomfort). The flexibility 185C may evaluate factors including muscle elasticity, joint structure, and/or neural system. Various embodiments of the subgroup 185 may be advantageously generated based on prioritizing a user’s critical movement deficiency.

[0039] The myofascial lines, for example, may include interconnected muscle and fascial pathways. The myofascial lines, for example, may be critical in movement, stability, and/or overall body function of a human body. The subgroup 190 includes a Posterior Superficial Backline 190A, a Ventral Line 190B, a Lateral Line 190C, and an Anterior Deep Front Line 190D.

[0040] For example, the Posterior Superficial Backline 190A may include a line that runs along a back of a body, connecting structures from the plantar fascia of the feet to the muscles at the back of the neck. For example, the Ventral Line 190B may represent an interconnected fascia and muscles on the anterior side of the body. For example, the Lateral Line 190C may extend along the sides of the body (e.g., connecting muscles and fascia from the feet through the lateral leg, hip, and ribcage up to the neck). For example, the Anterior Deep Front Line 190D may connect deeper muscles and fascia from the soles of the feet (e.g., through the inner legs and pelvic floor, up to the deep abdominal muscles and neck). The subgroup 185 and the subgroup 190 both include the CDSS 185B in this example.

[0041] In some implementations, the KPGE 110 may assign the subgroup 185 to individuals who can stand and walk. In some examples, the KGE 150 may prioritize one or more of the subgroup 185, the CDSS 185B and/or the flexibility 185C in generating the kinematic analysis result 170. For example, if balance is compromised, the KGE 150 may prioritize the GFR 185 A. In some implementations, the KGE 150 may assess health of a user using the subgroup 190 without requiring the user to stand. In some implementations, the KGE 150 may integrate the subgroup 185 and the subgroup 190 to generate the kinematic analysis result 170.

[0042] As shown in FIG. 1C, the KGE 150 may generate the kinematic analysis result 170 using the movement code 145 having the subgroup 185 and/or the subgroup 190. In this example, the kinematic analysis result 170 includes an individualized recommendation package 195. The individualized recommendation package 195 includes an individualized neuromuscular activation sequence 195A. For example, the individualized neuromuscular activation sequence 195A may be generated to target identified movement deficiencies (e.g., to improve flexibility, balance, stabilization).

[0043] The individualized recommendation package 195 also includes a kinematic intelligence finding 195B and a kinematic projection report 195C. For example, the KGE 150 may classify an individual with the attributes the subgroup 185. The KGE 150 may generate a current kinematic assessment in the kinematic intelligence finding 195B and a kinematic projection (e.g., injury probability analysis, diseases projection) in the kinematic projection report 195C to the computing device 115.

[0044] For example, the KGE 150 may classify that a user needs attention in core stabilization. The individualized recommendation package 195 may focus on core stabilization neuromuscular activations (e.g., including activities benefiting the posterior chain of muscles, and/or lateral balance activities). In some implementations, the KGE 150 may dynamically adjust the individualized recommendation package 195 based on progresses identified from the archival kinematic analytic findings 180. Various embodiments may advantageously promote long-term movement enhancement of the user.

[0045] In various implementations, a kinematic encryption code (KEC) (e.g., the movement code 145) may uniquely be generated based on sensor data (e.g., data received from the sensor module 120) received as a result of movement detections of a user (e.g., from performing the sequence of kinematic evaluations 125) for generating neuromuscular activation recommendations to promote health and performance. For example, the KEC may include a first key and a second key (e.g., the subgroup 185 and the subgroup 190). For example, the first key of the KEC may include balance, core, and flexibility. For example, the second key may include posterior/superficial back, lateral, vertical, anterior, and core lines.

[0046] As an illustrative example, the individualized recommendation package 195 may promote short-term and/or long-term health benefits. For example, the individualized neuromuscular activation sequence 195 A may be generated to quickly reduce pain and improve performance with targeted body activation. For example, the user, upon receiving the individualized neuromuscular activation sequence 195 A at the computing device 115, may obtain improvement in a short time period (e.g., noticeable improvements within a short space of time, contingent on an individual's response rate). In some examples, the individualized recommendation package 195 may be generated to alleviate discomfort with consistent motion (e.g., according to the individualized neuromuscular activation sequence 195A) in the long run.

[0047] In some examples, surgical interventions and medications remain the primary approaches to addressing pain and performance issues. However, some surgical procedures and medication may offer partial easing of symptoms. The DKIP 100 may, for example, advantageously generate an individualized recommendation package 195 to achieve total-body enhancement for individuals of multiple different profiles.

[0048] FIG. 2 is a block diagram depicting an exemplary DKIP 200. The DKIP 200 includes a processor 205. The processor 205 may, for example, include one or more processing units. The processor 205 is operably coupled to a communication module 210. The communication module 210 may, for example, include wired communication. The communication module 210 may, for example, include wireless communication. In the depicted example, the communication module 210 is operably coupled to the computing device 115, the camera 130, the IMU 135, and a communication network 215. For example, the KPGE 110 may receive measurement data from the camera 130 and the IMU 135 via the communication module 210. For example, the computing device 115 may communicate with the DKIP 100 through the communication module 210. In some implementations, the computing device 115 may transmit neuromuscular activation signals to the DKIP 100 to begin assessing motion of a user. In some implementations, the computing device 115 may receive the individualized recommendation package 195 generated by the KGE 150 through the communication module 210.

[0049] The processor 205 is operably coupled to a memory module 220. The memory module 220 may, for example, include one or more memory modules (e.g., random-access memory (RAM)). The processor 205 includes a storage module 225. The storage module 225 may, for example, include one or more storage modules (e.g., non-volatile memory). In the depicted example, the storage module 225 includes the KPGE 110, the KGE 150, an Intelligent Kinematic Categorization Engine (IKCE 230), and a Neuro-Muscular Activation Programming Framework (NAPF 235). |0050| For example, the KPGE 110 may receive movement measurements from the camera 130 and/or the IMU 135 to generate the movement code 145. Based on the movement code 145, the KGE 150 may generate the kinematic analysis result 170 to the computing device 115. In some implementations, the KGE 150 may invoke the IKCE 230 to classify the movement code 145 with pathology, and performance signatures trained in a machine learning model stored in a data store 245.

[0051] As shown, the processor 205 is further operably coupled to the data store 245. The data store 245 includes the KED 155, the neuromuscular activation library 165, the archival kinematic analytic findings 180, an individual kinematic objective 250, a Kinematic Assessment Output model (KAO model 255), and a neuromuscular activation creation ELM (NACLLM 260). For example, the IKCE 230 may classify the movement code 145 by applying the KAO model 255. For example, the KAO model 255 may be trained periodically to match a pattern of pathology, and/or performance signatures. In some implementations, the KAO model 255 may include one Al model. In some implementations, the KAO model 255 may include multiple (nested) Al models. For example, the KGE 150 may apply the KAO model 255 to a pattern matching result to generate a dynamic neuromuscular activation sequencing to be transmitted to the computing device 115.

[0052] In some implementations, the KGE 150 may generate the individualized recommendation package 195 based on the individual kinematic objective 250. For example, the individual kinematic objective 250 may include a health target associated with a user. For example, the individual kinematic objective 250 may be set by the user. In some implementations, the individual kinematic objective 250 may be dynamically identified by the IKCE 230. For example, the individual kinematic objective 250 may be generated as a function of the movement code 145, the archival kinematic analytic findings 180, and/or a user profile of the user (e.g., age, gender, racial profile, user’s habits).

[0053] The NAPF 235, for example, may use the NACLLM 260 to dynamically generate neuromuscular activation sequencing. For example, the NAPF 235 may automatically create neuromuscular activations to facilitate health enhancement of one or more target users using the NACLLM 260. Various embodiments of dynamic self-generation of neuromuscular activation using the NACLLM 260 are further described with reference to FIGS. 9-10.

[0054] FIG. 3 A, FIG. 3B, and FIG. 3C are block diagrams depicting an exemplary kinematic evaluation database, an exemplary neuromuscular activation library, and an exemplary kinematic intelligence finding. As shown in FIG. 3A, the KED 155 includes a standing test 302, a stork test 304, a leg balance test 306, a neck test 308, a shoulder test 310, a trunk test 312, a side flexion test 314, and an age specific test 316. |0055 | For example, the standing test 302 may include functionality configured to evaluate an individual's ability to maintain balance and stability while standing in a neutral posture for a specified duration. The stork test 304 may, for example, include functionality configured to assess single-leg balance and stability by requiring the individual to stand on one foot with the other foot placed against the opposite knee. The leg balance test 306 may, for example, include functionality configured to measure dynamic and static balance capabilities through specific movements involving one or both legs. The neck test 308 may, for example, include functionality configured to evaluate the range of motion, flexibility, and stability of the cervical spine through guided head and neck movements. The shoulder test 310 may, for example, include functionality configured to assess the mobility, strength, and flexibility of the shoulder joint through a series of arm movements.

[0056] The trunk test 312 may, for example, include functionality configured to evaluate core stability, strength, and flexibility by analyzing movements involving the lower back and abdominal regions. The side flexion test 314 may, for example, include functionality configured to measure the lateral flexibility and mobility of the spine and torso through side-bending movements. The age specific test 316 may, for example, include functionality configured to provide tailored assessments considering the unique physical and mobility characteristics of individuals in different age groups.

[0057] As shown in FIG. 3B, the neuromuscular activation library 165 includes a fall risk library 322, a back ache library 324, a fibromyalgia library 326, an osteoarthritis hip or knee library (OHOKP 328), a Parkinson’s library 330, a sport performance library 332, a balance library 334, and other health benefits (OHB 336). For example, the fall risk library 322 may include neuromuscular activations targeted at improving stability, coordination, and strength to reduce the risk of falls. The back ache library 324 may, for example, include neuromuscular activations targeted at alleviating back pain by improving posture, flexibility, and core strength. The fibromyalgia library 326 may, for example, include neuromuscular activations targeted at alleviating pain and improving physical endurance for individuals with fibromyalgia. The OHOKP 328 may, for example, include neuromuscular activations targeted at improving joint mobility, reducing stiffness, and strengthening muscles around the hip and knee joints.

[0058] In some implementations, the neuromuscular activation library 165 may include neuromuscular activation libraries targeting motion diseases. The Parkinson’s library 330 may, for example, include neuromuscular activations targeted at addressing movement challenges associated with Parkinson’s disease by enhancing mobility, balance, and coordination. The sport performance library 332 may, for example, include neuromuscular activations targeted at optimizing athletic performance by improving strength, speed, and agility. The balance library 334 may, for example, include neuromuscular activations targeted at enhancing an individual’s ability to maintain equilibrium by strengthening stabilizing muscles and improving proprioception. The ADB 336 may, for example, include neuromuscular activations targeted at achieving general health improvement and addressing unique individual needs for overall physical and functional enhancement.

[0059] As shown in FIG. 3C, a kinematic intelligence finding 300 may include the kinematic intelligence finding 195B and the kinematic projection report 195C as described with reference to FIG. 1C. In this example, the kinematic intelligence finding 300 includes an injury probability analysis 342, a wellbeing projections 344, a neuromuscular activation projections 346, a progress projections 348, a performance projections 350, a balance score 352, a biomechanical efficiency score 354, and a longevity score 356.

[0060] For example, the balance score 352 may include assessments targeted at identifying potential risks for physical injuries based on an individual’s movement patterns and health data. The wellbeing projections 344 may, for example, include assessments targeted at forecasting an individual’s overall health and quality of life outcomes through motion analysis. The neuromuscular activation projections 346 may, for example, include assessments targeted at determining a predicted outcome based on the individualized neuromuscular activation sequence 195 A transmitted to the computing device 115.

[0061] In some implementations, the KGE 150 may generate the kinematic intelligence finding 195B based on the archival kinematic analytic findings 180. The progress projections 348 may, for example, include assessments targeted at evaluating an individual’s advancement in their health or fitness journey over time. The performance projections 350 may, for example, include assessments targeted at projecting improvements in physical capabilities, such as strength, endurance, or flexibility, based on a current progress determined as a function of the archival kinematic analytic findings 180. The balance score 352 may, for example, include an evaluation targeted at quantifying an individual’s ability to maintain stability and equilibrium during various movements (e.g., while performing the KED 155 and/or the neuromuscular activation library 165). The biomechanical efficiency score 354 may, for example, include an evaluation targeted at measuring physical strength and muscle performance. The longevity score 356 may, for example, include an evaluation targeted at estimating life expectancy and/or long-term health outcomes based on the archival kinematic analytic findings 180.

[0062] FIG. 4 is a flowchart illustrating an exemplary kinematic intelligence findings generation method 400. For example, the method 400 may be performed by the KPGE 110. For example, the KPGE 110 may perform the generation method 400 to generate the movement code 145. In this example, the method 400 begins in step 405 when a pose detection sensor module is activated. For example, the sensor module 120 may be activated by the computing device 115 to assess health of an individual (e.g., a user).

[0063] In step 410, it is determined whether a user is detected. For example, the IMU 135 may analyze movement data to confirm the presence of the user. At a decision point 415, if no user is detected, an error message is generated, and the method 400 ends. For example, the user communication engine 105 may send a notification to the computing device 115 indicating the detection issue. If a user is detected, in step 420, a sequence of N kinematic evaluation is retrieved and a first set of tests is transmitted to the user. For example, the user communication engine 105 may retrieve a sequence of kinematic evaluations 125 from the KED 155 and transmit them to the computing device 115.

[0064] At a decision point 425, it is determined whether motion is detected. For example, the IMU 135 may process movement data captured during the transmitted tests to confirm user motion. If no motion is detected, the decision point 425 is repeated. If motion is detected, in step 430, a movement analysis is performed based on IMU analysis and/or Al. For example, the IMU 135 may measure parameters including, for example, acceleration and angular velocity to analyze user motion. For example, the KPGE 110 may apply an Al motion analysis model to evaluate the movement data and identify patterns related to the user’s motion. After the movement analysis, a movement code of the user is generated corresponding to the movement analysis in step 435.

[0065] In step 440, a primary risk of the user is identified based on the movement analysis. For example, the KGE 150 may classify the user’s motion data into risk categories (e.g., fall risk, compromised balance, reduced mobility, potential Parkinson’s diseases).

[0066] At a decision point 445, it is determined whether the user’s primary carer should be contacted. For example, the KPGE 110 may analyze the risk level to decide whether intervention by a primary carer is required. If contact with the primary carer is required, in step 450, a notification is generated to the user to contact primary carer, and the method 400 ends. For example, the user communication engine 105 may send a message prompting the user to contact their primary carer (e.g., doctor, an emergency clinic nearby).

[0067] If contact is not required, in step 455, the next test is selected based on the user’s profile and the identified primary risk. For example, the KPGE 110 may retrieve a subsequent test from the KED 155 based on a user profile (e.g., user’s age) and movement data received from previous tests. For example, if the movement data indicates one or more risks of the user, the KPGE 110 may skip one or more sequence assessment tests.

[0068] At a decision point 460, it is determined whether additional tests are selected. For example, the KPGE 110 may have reached an end of the list of tests in the KED 155. For example, the KPGE 110 may determine that, based on the user’s current conditions and movement results, no further tests are required (e.g., and/or suitable). If an additional test is selected, the selected test is transmitted to the user in step 470, and the decision point 425 is repeated. If no additional test is selected, in step 465, the analysis result from all tests performed by the user is saved. For example, the KPGE 110 may store the kinematic intelligence finding 195B in the data store 245, and the method 400 ends.

[0069] FIG. 5 is a flowchart illustrating an exemplary kinematic guidance platform 500. For example, the method 500 may be performed by the KGE 150. For example, the KGE 150 may generate an individualized recommendation package 195 based on a kinematic intelligence finding 195B. In this example, the method 500 begins in step 505 when a kinematic profile is generated based on movement data. For example, the KPGE 110 may process the movement data received from the IMU 135 to generate a kinematic profile 160.

[0070] In step 510, an archival kinematic analytic findings is retrieved. For example, the KGE 150 may retrieve the archival kinematic analytic findings 180 from the data store 245 to compare with the generated kinematic profile 160. In step 515, a KAO model is applied to generate a kinematic index and a kinematic projection. For example, the KGE 150 may use the KAO model 255 to process the archival kinematic analytic findings 180 and the kinematic profile 160 to compute a kinematic index and predict future health outcomes.

[0071 ] In step 520, a kinematic intelligence finding is generated as a function of the kinematic index and the kinematic projection. For example, the KGE 150 may generate the kinematic intelligence finding 195B, including projections such as injury risks and performance metrics, based on the computed kinematic index. At a decision point 525, it is determined whether a new neuromuscular activation sequence is needed. For example, the KGE 150 may evaluate whether the kinematic intelligence finding 195B indicates a need for a new neuromuscular activation plan. [0072] If no new neuromuscular activation sequence is needed, in step 530, a neuromuscular activation sequence is selected from the neuromuscular activation library based on the kinematic intelligence finding. For example, the KGE 150 may retrieve a suitable neuromuscular activation sequence from the neuromuscular activation library 165 tailored to the user’s kinematic intelligence finding 195B. If a new neuromuscular activation sequence is needed, in step 535, the NACLLM is applied to dynamically generate a new neuromuscular activation sequence based on the kinematic intelligence finding. For example, the NAPF 235 may invoke the NACLLM 260 to create a personalized sequence of neuromuscular activations. Various embodiments for using a large language model to dynamically generate new neuromuscular activation sequences are described in further details with reference to FIGS. 9-10.

[0073] In step 540, an individualized recommendation library is generated, including the neuromuscular activation sequence and the kinematic intelligence finding. For example, the KGE 150 may compile the selected or newly generated neuromuscular activation sequence along with the kinematic intelligence finding 195B into the individualized recommendation package 195 (e.g., to be transmitted to the computing device 115), and the method 500 ends.

[0074] FIG. 6 A, FIG. 6B, FIG. 6C, FIG. 6D, FIG. 6E, FIG. 6F, FIG. 6G, and FIG. 6H depict exemplary kinematic evaluations. As shown in FIG. 6A, a motion screen 600 may be captured by an image capture device (e.g., the camera 130). In this example, the motion screen 600 includes a test subject 605. For example, the test subject 605 may be a user. For example, the test subject 605 may be a professional soccer player aiming at improving sport performance and/or identifying potential injury risks.

[0075] As shown, the motion screen 600 is processed (e.g., by the KPGE 1 10) to generate a stick figure 610. The stick figure 610, as shown in this example, is overlaid on the test subject 605. For example, the stick figure 610 may be generated based on images captured from the camera 130 and/or data received from the IMU 135. For example, the KPGE 110 may analyze movement patterns as a function of the stick figure 610. This data is used to generate recommendations for neuromuscular activations to prevent injuries. For example, the stick figure 610 may be generated by identifying various angles from joints including, for example, ankles, knees, hip, neck, shoulders, and/or elbows.

[0076] As shown, the stick figure 610 may trace a movement of the test subject 605 during various kinematic evaluations. For example, the kinematic evaluations may include a neck movement (e.g., FIGS. 6B-C). For example, the kinematic evaluations may include a flexibility movement (e.g., FIGS. 6D-F). For example, the kinematic evaluations may include stork test motions (e.g., FIGS. 6G-H). Various embodiments may advantageously identify injury risks by analyzing movement patterns. As an illustrative example, the DKIP 100 may identify a potential knee injury of the test subject 605 by identifying a wobble during a knee bend in a stork test motion.

[0077] FIG. 7 depicts an exemplary archival kinematic profile display (AKPD 700). For example, the AKPD may be generated by the user communication engine 105 and presented on the computing device 115. In this example, the AKPD 700 includes a motion assessment result 705 from a standing single-leg heel raise test 710 performed on the left leg. For example, the standing single-leg heel raise test 710 may be transmitted to the computing device 115 as part of the sequence of kinematic evaluations retrieved from the KED 155.

[0078] The AKPD 700, in this example, includes a video 715 of the user performing the standing single-leg heel raise test 710. For example, the video 715 may be captured by the camera 130. For example, the video 715 may provide visual feedback to the user and/or their primary carer regarding the performance of the assessed motion. |0079| For example, the motion assessment result 705 may include quantitative metrics derived from a motion assessment. For example, a body-mounted sensor value may be calculated based on movement data such as X, Y, and Z values gathered by the IMU 135 during the test. In this example, the X value is shown as 26.92, the Y value as 28.83, and the Z value as 25.78, each contributing to the aggregated body-mounted sensor value of 81.53 (18.12%). In some implementations, the body-mounted sensor value may include an angular rotation from zero identified from the stick figure 610. In some examples, the KPGE 110 may identify fall risk based on whether a user in the video touches the floor. In some examples, the fall risk may be identified by a spike in an accelerometer of the IMU 135.

[0080] The pose landmark detection value, for example, may be a composite index based on advanced analysis of ground force reactions captured during the test. For example, this index includes individual metrics such as LX value (19.84), LY value (32.94), LZ value (15.13), RX value (31.07), RY value (32.96), and RZ value (15.13), which together result in an aggregated GFR Screening Value of 148.23 (32.94%). These values may be used by the KGE 150 to assess the user’s balance, stability, and core strength during the motion. In some implementations, the kinematic profilel60 may include the motion assessment result 705

[0081] In some implementations, the archival kinematic profile display may provide actionable insights based on the computed screening values. For example, the KGE 150 may classify the results and/or generate recommendation adjustments to the neuromuscular activation sequence dynamically. The AKPD 700 may dynamically update as new motion assessments are performed. [0082] FIG. 8 depicts an exemplary machine learning system 800 of an exemplary DKIP. For example, the exemplary machine learning system 800 may be embodied in the KPGE 110, the KGE 150, and/or the user communication engine 105. In this example, the exemplary machine learning system 800 includes a kinematic Al model (KAI model 805). The KAI model 805, as shown, receives a range of input measures (ROIMs 810). For example, the ROIMs 810 may include sensors data from the IMU 135 and/or the camera 130. For example, the ROIMs 810 may include the movement code 145. For example, the ROIMs 810 may include a balance index (e.g., the balance score 352). For example, the ROIMs 810 may include a Trendelenburg sign. For example, the KAI model 805 may generate the kinematic analysis result 170 based on the ROIMs 810.

[0083] The KAI model 805 includes an artificial neural network (ANN 815). For example, the ANN 815 may be trained by supervised learning. For example, the ANN 815 may be trained by unsupervised learning. In the depicted example, the KAI model 805 receives inputs from a supervised training module 820. For example, the supervised training module 820 may include a user interface (e.g., a graphical user interface) to receive supervised training input from a training user.

[0084] In some implementations, the KAI model 805 may initiate training when a subject performs a series of standard motion screen exercises (e.g., the sequence of kinematic evaluations 125). For example, the exemplary machine learning system 800 may record a performance of the exercise.

[0085] For example, the recorded exercises may be analyzed by a pose detection engine 825. In some implementations, the pose detection engine 825 may generate pose data (e.g., angles and coordinates associated with the recorded exercises). For example, the training user may, through the supervised training module 820, score the recorded exercises to establish a signature for the subject and determine a set of 3 neuromuscular reactivations (e.g., the movement code 145).

[0086] In some implementations, the exemplary machine learning system 800 may use the scores and neuromuscular reactivations to label the pose data. In some implementations, the KAI model 805 may repeat the labeling process for a sufficient number of subjects to train the ANN 815. For example, the sufficient number of subjects may be determined by an accuracy of the ANN 815 to replicate determination of the training user in the scores and neuromuscular reactivations.

[0087] In some implementations, the KAI model 805 may adjust training parameters based on user feedback. For example, the user feedback may be generated as a function of multiple users’ subsequent motion screens (e.g., the sequence of kinematic evaluations 125) and reinforcement learning based on user’s other outcomes (e.g. sport performance, injury).

[0088] In the depicted example, the KAI model 805 includes risk projection tensor network 830. For example, the risk projection parameters 830 may use tensor mathematics to correlate the ROIMs 810 with data on longevity, fall-risk, and neurological conditions (e.g., Parkinson’s, Alzheimer’s). In some examples, the risk projection tensor network 830 may provide projections to users, insurers and others stakeholders. Accordingly, the exemplary machine learning system 800 may advantageously provide effective intervention and/or prevention measures.

[0089] In some implementations, the ANN 815 may be trained to use a combination of the kinematic analysis result 170, the movement code 145, user’s injury records, and/or the pose data (e.g., obtained from the sequence of kinematic evaluations 125, from the user’s performance on the field, track, pitch, pool) to identify ways for the user to improve their performance through improved biomechanics (e.g., additional neuromuscular reactivations, specific strength training exercises).

[0090] In some implementations, the ANN 815 may be trained to analyze same-time multiple users’ performance (e.g., in a team sport, in a team working environment). For example, the ROIMs 810 may include data from video recordings of matches. For example, the ANN 815 may be trained to identify ways for the team to improve their performance through adjustments to team strategy and tactics.

[0091 ] In some implementations, the KAI model 805 may combine public data on the performance with pose-detection data from video recordings to train an algorithm that can then be used to predict performance of individual players and teams for one or more teams in a tournament (e.g., in a league, in a cup tournament). For example, the DKIP 100 may make the kinematic analysis result 170 and/or the subgroup 190 available to be incorporated to train an algorithm for developing performance projections for the multiple teams.

[0092] In some implementations, the pose detection engine 825 may be trained (e.g., by the supervised training module 820, by an unsupervised training algorithm) to ascertain whether a user is performing the neuromuscular reactivations correctly. For example, the risk projection tensor network 830 may generate an output to the user communication engine 105 to provide feedback to users (e.g., to confirm that they are performing the reactivations correctly, offer advice for improvement). In some implementations, the user communication engine 105 may (e.g., upon being authorized by the user) share a completion confirmation that the user has performed prescribed neuromuscular activations.

[0093] In some implementations, the KAI model 805 may include a multi-modal Al model. For example, the multi-modal Al model may be used to develop empathetic avatars. For example, the avatars may provide instructions, offer feedback, and/or explain the neuromuscular reactivations to be performed to users. For example, the multi-modal Al model may provide an automatic customer service (e.g., as a customer care bot) for responding to user queries.

[0094] FIG. 9 is a block diagram depicting an exemplary neuromuscular activation creation large language model (NACLLM). In this example, the NACLLM 260 is configured to dynamically generate new neuromuscular activations 905 and new neuromuscular activation sequences 910 dynamically. For example, the NAPF 235 may update the neuromuscular activation library 165 using the NAPF 235. As shown, the NACLLM 260 receives inputs from the individual kinematic objective 250, the neuromuscular activation library 165, and the archival kinematic analytic findings 180. For example, the NAPF 235 may retrieve the individual kinematic objective 250, the neuromuscular activation library 165, and the archival kinematic analytic findings 180 from the data store 245.

[0095] In this example, the NAPF 235 may apply instructions received from LLM inputs 915 to the individual kinematic objective 250, the neuromuscular activation library 165, and the archival kinematic analytic findings 180 to generate the new neuromuscular activations 905 and/or the new neuromuscular activation sequences 910. The LLM inputs 915 may, for example, include instruction prompts (e.g., for specifying the desired focus areas, for improving balance, for improving core strength). In some examples, the LLM inputs 915 may include comments (e.g., for modifying an existing neuromuscular activation library 165, adjusting the difficulty of neuromuscular activations, customizing the individualized neuromuscular activation sequence 195A).

[0096] For example, the LLM inputs 915 may be manually provided by a user through the computing device 115. For example, the NAPF 235 may advantageously provide a mechanism for the user to specify preferences and/or feedback to the individualized neuromuscular activation sequence 195 A received from the DKIP 100.

[0097] In some implementations, the LLM inputs 915 may be created by an admin user. For example, an administrator overseeing the system (e.g., in a professional or clinical setting) may generate detailed instructions to address specific user profiles. For example, the admin user may review a health progress of the user (e.g., from the archival kinematic analytic findings 180 and/or other electronic health records of the user) to modify the individualized neuromuscular activation sequence 195 A.

[0098] In some implementations, the LLM inputs 915 may be dynamically generated by another instruction-generating module. For example, the LLM inputs 915 may be generated by one or more separate LLM. For example, the NAPF 235 may integrate with an (external) LLM to generate instructions and/or natural language queries based on the individual kinematic objective 250, the neuromuscular activation library 165, and/or the archival kinematic analytic findings 180. In some implementations, the NAPF 235 may feed the movement code 145 to the LLM in real-time to generate the LLM inputs 915. For example, the separate LLMs may synthesize information from multiple sources (e.g., including research databases, archival user trends, broader population data) to generate inputs to the NACLLM 260.

[0099] Based on the LLM inputs 915, the NACLLM 260 may generate the new neuromuscular activations 905 and/or the new neuromuscular activation sequences 910. For example, the NACLLM 260 may combine existing neuromuscular activations from the neuromuscular activation library 165 with dynamically created variations to address specific weaknesses or goals identified from the individual kinematic objective 250 and archival kinematic analytic findings 180. The new generated neuromuscular activations 905 and/or the new neuromuscular activation sequences 910 may be stored as an individualized neuromuscular activation library specially generated for a user. In some implementations, the new neuromuscular activations 905 and/or the new neuromuscular activation sequences 910 may be used to update the neuromuscular activation library 165.

[0100] FIG. 10 is a flowchart illustrating an exemplary interactive neuromuscular activation creation method 1000 using the exemplary NACLLM described with reference to FIG. 9. For example, the method 1000 may be performed by the NAPF 235. In this example, the method 1000 begins when an individual health objective, a neuromuscular activation library, and an archival kinematic analytic findings are retrieved from the information storage system in step 1005. For example, the NAPF 235 may query the data store 245 to obtain data related to user-specific goals, pre-defined neuromuscular activations, and past kinematic assessments.

[0101] In step 1010, an individualized neuromuscular activation sequence is received from the system for the user. For example, the KGE 150 may transmit the individualized neuromuscular activation sequence 195A to the NAPF 235 for dynamic customization based on the 260//.

[0102] At a decision point 1015, it is determined whether an LLM input is received. For example, the NAPF 235 may monitor whether any prompt is received from the computing device 115. In some examples, the NAPF 235 may check whether any input is received from external LLMs. If no input is received, the method proceeds directly to its conclusion, and the method 1000 ends. If an LLM input is received, in step 1020, the input is applied to the neuromuscular activation library or the individualized neuromuscular activation sequence to generate a new neuromuscular activation sequence based on a content of the received input, and the decision point 1015 is repeated. For example, the NAPF 235 may integrate instruction prompts from the LLM inputs 915 with the existing neuromuscular activation library 165. For example, the NAPF 235 may modify the individualized neuromuscular activation sequence 195 A using the user feedback and/or comments received from the computing device 115. For example, the NAPF 235 may modify the individualized neuromuscular activation sequence 195 A based on admin-defined instructions received as the LLM inputs 915.

[0103] In some implementations, the NAPF 235 may, after the method 1000 ends, store the modified or newly generated neuromuscular activation sequence is stored in an information storage system. For example, the NAPF 235 may save the new neuromuscular activations 905 and/or the new neuromuscular activation sequences 910 to the neuromuscular activation library 165.

[0104] FIG. 11 is a flowchart illustrating an exemplary machine learning model training method 1100. For example, the method 1100 may be performed by the machine learning system 800. In this example, the method 1100 begins when a new subject performs a series of standard motion screen exercises, which are recorded, in step 1105. For example, the pose detection engine 825 may receive movement data from the IMU 135 and the camera 130 to generate the ROIMs 810. For example, the KAI model 805 may receive the movement code 145 from the KPGE 110. For example, the , capturing the subject's motion at a specified frequency to generate a raw dataset for analysis. |0105 | In step 1110, the recorded exercises are analyzed by using pose detection software that generates angles and coordinates. For example, the pose detection engine 825 may process the sensor data to create pose data. For example, the pose data may include joint angles, body coordinates, trajectories, and/or other biometrics. For example, the pose detection engine 825 may overlay the metrics onto a virtual stick figure representation of the subject’s movements.

[0106] In step 11 15, scores are received from a training user to establish a signature for the subject and determine a set of three neuromuscular reactivations. For example, the supervised training module 820 may provide a graphical user interface that allows a training user to input scores based on specific performance metrics (e.g., balance, core stability, flexibility) and recommend corresponding neuromuscular reactivations.

[0107] In step 1120, the pose data is labeled with the scores and the identified reactivations. For example, the KAI model 805 may integrate the labeled data, associating specific pose landmarks (e.g., detected by the pose detection engine 825) with the scores and neuromuscular reactivations. These labeled datasets may be used to fine-tune the artificial neural network (ANN 815) within the KAI model 805.

[0108] At a decision point, it is determined whether a sufficient number of subjects have been recorded and labeled to train the model. For example, the ANN 815 may analyze the diversity and accuracy of the training dataset by simulating projections and comparing them against expert- assigned scores. If the dataset is insufficient, the step 1105 is repeated to gather more data. If the dataset is determined to be sufficient, the method proceeds to its conclusion, and the method 1100 ends.

[0109] Although various embodiments have been described with reference to the figures, other embodiments are possible. For example, the DKIP 100 may include a Digital Goniometer. For example, the digital goniometer may measure angles. For example, a pose estimation algorithm may detect anatomical landmarks and/or calculate angles between adjacent segments. For example, the digital goniometer may include a method for evaluating range of motion using the digital goniometer. For example, deviations from standard motion patterns are identified and reported. For example, a portable digital goniometer may include a camera device, software for pose detection, and/or an interface for displaying joint angle measurements.

[0110] In some implementations, the DKIP 100 may include a digital, pelvic orientation hip stability system (DPOHSS). For example, the DPOHSS may measure dynamic pelvic orientation. For example, the DPOHSS may include a pose estimation module configured to detect anatomical landmarks on the pelvis using computer vision. For example, the DPOHSS may include a processing unit to calculate angles representing pelvic tilt, obliquity, and/or rotation in sagittal, frontal, and/or transverse planes. For example, the DPOHSS may include a display interface providing real-time visualization of pelvic orientation during motion activities.

[0111] For example, the DPOHSS may include a Dynamic Movement Analysis. For example, the pose estimation module may track pelvic motion in dynamic activities, the motion screen and/or includes walking, running, squatting, and/or twisting, providing quantitative metrics on functional movement patterns. For example, the DPOHSS may include a calibration module that compensates for occlusions or misalignment by referencing adjacent body landmarks, such as the hip and/or lumbar spine. For example, the DPOHSS may include a method to monitor rehabilitation progress by comparing pelvic orientation metrics across multiple sessions.

[0112] For example, the processing unit may integrate data from inertial measurement units (IMUs) for enhanced accuracy in 3D space. For example, motion data may be stored in a cloud database for longitudinal tracking and/or comparative analysis. For example, users may adjust the detection algorithm sensitivity to accommodate variations in body anatomy and/or activity type. [0113] In some implementations, the DKIP 100 may include a digital Trendelenburg gait system (DTGS). For example, the DTGS may evaluate Trendelenburg gait. For example, the DTGS may include a pose estimation module for detecting anatomical landmarks. For example, the DTGS may include a processor configured to calculate pelvic tilt angles during gait cycles. For example, the DTGS may include a display interface for presenting a Trendelenburg sign.

[0114] For example, the DTGS may include a method for assessing gait asymmetry. For example, the DTGS may detect compensatory trunk movements and/or quantify lateral pelvic shifts. For example, the pose estimation module integrates with cloud-based analytics for longitudinal tracking of rehabilitation progress.

[0115] In some implementations, the DKIP 100 may include a functional motion test system (FMTS). For example, the FMTS may include a pose estimation model for detecting and/or tracking anatomical landmarks. For example, the FMTS may include a processing unit configured to calculate functional motion scores based on detected landmarks. For example, the FMTS may include a method for evaluating motion performance. For example, the FMTS may determine metrics (e.g., range of motion joint alignment, and/or balance). For example, test-specific scoring algorithms may be customizable for different motion tasks, including but not limited to squats, lunges, and/or balance tests. For example, the FMTS may include a real-time feedback mechanism to guide users toward improving movement efficiency and/or safety.

[0116] For example, the DKIP 100 may include a system for assessing balance. For example, a pose estimation model may detect body landmarks and/or calculates a numerical balance index based on the displacement of the center of mass (COG) over the base of support (BOS) and/or postural sway (e.g., Indicating ‘Good’, ‘Moderate’, ‘Poor’ or ‘Fall Risk Identification). 101171 For example, the system may include a method of providing balance training using realtime feedback from the system of claim 1. For example, the feedback includes corrective posture recommendations. For example, data is stored in a cloud database for longitudinal tracking of balance performance over time.

[0118] In some implementations, the DKIP 100 may include a gait analysis system. For example, the gait analysis system may include a pose estimation model configured to detect anatomical landmarks of the human body during motion. For example, the gait analysis system may include a processing module that computes gait parameters, including stride length, cadence, and/or joint angles. For example, the gait analysis system may include a method for diagnosing gait abnormalities. For example, the gait analysis system may identify deviations in symmetry and/or stability metrics.

[0119] In some implementations, the gait analysis system may be portable. For example, a portable gait analysis system may include a camera for capturing user motion. For example, the portable gait analysis system may include software for pose detection and/or gait phase segmentation. For example, the portable gait analysis system may include a user interface for displaying diagnostic data. For example, the gait analysis system may be operably coupled to a cloud-based gait monitoring system. For example, the gait analysis system may upload kinematic data to the cloudbased gait monitoring system for longitudinal analysis.

[0120] In some implementations, the DKIP 100 may include a sports performance system. For example, the sports performance system may include a pose estimation module configured to detect and/or track anatomical landmarks. For example, the sports performance system may include a kinematic analysis engine that computes joint angles, velocities, and/or other motion metrics. For example, the sports performance system may include a risk assessment module that identifies high-risk movements and/or provides corrective feedback. For example, the sports performance system may include a method for injury preventions. For example, the sports performance system may determine movements including jumps, throws, and/or sprints and/or flags biomechanical inefficiencies.

[0121] For example, the DKIP 100 may include a cloud-integrated system for longitudinal monitoring. For example, the DKIP 100 may track athlete performance over time to identify trends in injury risk. For example, the DKIP 100 may include a portable injury prevention device. For example, the portable injury prevention device may include a camera for capturing motion. For example, the portable injury prevention device may include software for real-time pose detection and/or kinematic analysis. For example, the portable injury prevention device may include a feedback interface for delivering corrective insights. 101221 Although an exemplary system has been described with reference to the figures, other implementations may be deployed in other industrial, scientific, medical, commercial, and/or residential applications.

[0123] For example, the DKIP 100 may be utilized as a sports coaching assistant to optimize athletic performance and minimize injury risks. For example, the DKIP 100 may analyze motion data collected from athletes performing drills or playing in matches. The pose detection engine 825 and the KAI model 805 may generate kinematic analysis results, identifying inefficiencies in movement patterns (e.g., improper joint alignment or imbalance in ground force reactions). Based on this data, for example, the DKIP 100 may provide personalized neuromuscular activation sequences to improve flexibility, core stability, and balance. In some implementations, the DKIP 100 may classify team-level performance metrics by analyzing multiple athletes simultaneously, generating insights to improve team strategies and tactics. For example, the KAI model 805 may recommend adjustments in running mechanics or jumping techniques for a soccer team to enhance agility and reduce injury risks during high-intensity matches.

[0124] For example, the DKIP 100 may include a weight management or dieting assistant. For example, the DKIP 100 may process data on physical activities (e.g., walking, running, strength training) using the IMU 135 and camera 130. The KAI model 805 may analyze this data to provide insights into calorie expenditure and movement efficiency. The neuromuscular activation library 165 may generate tailored physical activity routines aimed at enhancing metabolic function, increasing energy expenditure, or addressing specific health issues such as joint pain or reduced mobility. For example, the DKIP 100 may interact with external dietary management tools to recommend complementary meal plans based on user activity levels, promoting balanced weight management. For instance, the system could suggest modifications to exercise routines to accommodate caloric deficits or surpluses detected through integrated health tracking.

[0125] For example, the DKIP 100 may provide guidance on improving overall physical, mental, and/or emotional well-being. For example, the DKIP 100 may analyze a user’s daily activities and/or posture data to identify areas requiring improvement (e.g., prolonged sedentary behavior , stress-related movement patterns). For example, the pose detection engine 825 may generate routines (e.g., mindfulness exercises, gentle physical activity, stretching sequences) tailored to reduce stress and improve relaxation. In some implementations, the DKIP 100 may provide motivational feedback, progress tracking, and/or personalized recommendations to encourage users to achieve long-term goals (e.g., better work-life balance, improved posture, enhanced fitness levels). For example, the DKIP 100 may recommend short, guided stretching sessions during work hours to alleviate back pain and enhance productivity. |0126| Some embodiments may include further adaptive data processing and Al models designed for real-time pattern recognition, streamlining screening workflows and minimizing delays. For example, the DKIP 100 may advantageously provide fast generation of individualized kinematic assessments and/or neuromuscular activation recommendations in near real-time.

[0127] In various embodiments, some bypass circuits implementations may be controlled in response to signals from analog or digital components, which may be discrete, integrated, or a combination of each. Some embodiments may include programmed, programmable devices, or some combination thereof (e.g., PLAs, PLDs, ASICs, microcontroller, microprocessor), and may include one or more information storage systems (e.g., cell, register, block, page) that provide single or multi-level digital data storage capability, and which may be volatile, non-volatile, or some combination thereof. Some control functions may be implemented in hardware, software, firmware, or a combination of any of them.

[0128] Computer program products may contain a set of instructions that, when executed by a processor device, cause the processor to perform prescribed functions. These functions may be performed in conjunction with controlled devices in operable communication with the processor. Computer program products, which may include software, may be stored in an information storage system tangibly embedded on a storage medium, such as an electronic, magnetic, or rotating storage device, and may be fixed or removable (e.g., hard disk, floppy disk, thumb drive, CD, DVD).

[0129] Although an example of a system, which may be portable, has been described with reference to the above figures, other implementations may be deployed in other processing applications, such as desktop and networked environments.

[0130] Temporary auxiliary energy inputs may be received, for example, from chargeable or single use batteries, which may enable use in portable or remote applications. Some embodiments may operate with other DC voltage sources, such as (nominal) batteries, for example. Alternating current (AC) inputs, which may be provided, for example from a 50/60 Hz power port, or from a portable electric generator, may be received via a rectifier and appropriate scaling. Provision for AC (e.g., sine wave, square wave, triangular wave) inputs may include a line frequency transformer to provide voltage step-up, voltage step-down, and/or isolation.

[0131] Although particular features of an architecture have been described, other features may be incorporated to improve performance. For example, caching (e.g., LI, L2, . . .) techniques may be used. Random access memory may be included, for example, to provide scratch pad memory and or to load executable code or parameter information stored for use during runtime operations. Other hardware and software may be provided to perform operations, such as network or other communications using one or more protocols, wireless (e.g., infrared) communications, stored operational energy and power supplies (e.g., batteries), switching and/or linear power supply circuits, software maintenance (e.g., self-test, upgrades), and the like. One or more communication interfaces may be provided in support of data storage and related operations.

[0132] Some systems may be implemented as a computer system that can be used with various implementations. For example, various implementations may include digital circuitry, analog circuitry, computer hardware, firmware, software, or combinations thereof. Apparatus can be implemented in a computer program product tangibly embodied in an information carrier, e.g., in a machine-readable storage device, for execution by a programmable processor; and methods can be performed by a programmable processor executing a program of instructions to perform functions of various embodiments by operating on input data and generating an output. Various embodiments can be implemented advantageously in one or more computer programs that are executable on a programmable system including at least one programmable processor coupled to receive data and instructions from, and to transmit data and instructions to, a data storage system, at least one input device, and/or at least one output device. A computer program is a set of instructions that can be used, directly or indirectly, in a computer to perform a certain activity or bring about a certain result. A computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0133] Suitable processors for the execution of a program of instructions include, by way of example, both general and special purpose microprocessors, which may include a single processor or one of multiple processors of any kind of computer. Generally, a processor will receive instructions and data from a read-only memory or a random-access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memories for storing instructions and data. Generally, a computer will also include, or be operatively coupled to communicate with, one or more mass storage devices for storing data files; such devices include magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and optical disks. Storage devices suitable for tangibly embodying computer program instructions and data include all forms of non-volatile memory, including, by way of example, semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, ASICs (applicationspecific integrated circuits).

[0134] In some implementations, each system may be programmed with the same or similar information and/or initialized with substantially identical information stored in volatile and/or non- volatile memory. For example, one data interface may be configured to perform auto configuration, auto download, and/or auto update functions when coupled to an appropriate host device, such as a desktop computer or a server.

[0135] In some implementations, one or more user-interface features may be custom configured to perform specific functions. Various embodiments may be implemented in a computer system that includes a graphical user interface and/or an Internet browser. To provide interaction with a user, some implementations may be implemented on a computer having a display device. The display device may, for example, include an LED (light-emitting diode) display. In some implementations, a display device may, for example, include a CRT (cathode ray tube). In some implementations, a display device may include, for example, an LCD (liquid crystal display). A display device (e.g., monitor) may, for example, be used for displaying information to the user. Some implementations may, for example, include a keyboard and/or pointing device (e.g., mouse, trackpad, trackball, joystick), such as by which the user can provide input to the computer.

[0136] In various implementations, the system may communicate using suitable communication methods, equipment, and techniques. For example, the system may communicate with compatible devices (e.g., devices capable of transferring data to and/or from the system) using point-to-point communication in which a message is transported directly from the source to the receiver over a dedicated physical link (e.g., fiber optic link, point-to-point wiring, daisy-chain). The components of the system may exchange information by any form or medium of analog or digital data communication, including packet-based messages on a communication network. Examples of communication networks include, e.g., a LAN (local area network), a WAN (wide area network), MAN (metropolitan area network), wireless and/or optical networks, the computers and networks forming the Internet, or some combination thereof. Other implementations may transport messages by broadcasting all or substantially all devices that are coupled together by a communication network, for example, by using omni-directional radio frequency (RF) signals. Still other implementations may transport messages characterized by high directivity, such as RF signals transmitted using directional (i.e., narrow beam) antennas or infrared signals that may optionally be used with focusing optics. Still other implementations are possible using appropriate interfaces and protocols such as, by way of example and not intended to be limiting, USB 2.0, Firewire, ATA/IDE, RS-232, RS-422, RS-485, 802.11 a/b/g, Wi-Fi, Ethernet, IrDA, FDDI (fiber distributed data interface), token-ring networks, multiplexing techniques based on frequency, time, or code division, or some combination thereof. Some implementations may optionally incorporate features such as error checking and correction (ECC) for data integrity, or security measures, such as encryption (e.g., WEP) and password protection. 101371 In various embodiments, the computer system may include Internet of Things (loT) devices. loT devices may include objects embedded with electronics, software, sensors, actuators, and network connectivity which enable these objects to collect and exchange data. loT devices may be in-use with wired or wireless devices by sending data through an interface to another device. loT devices may collect useful data and then autonomously flow the data between other devices.

[0138] Various examples of modules may be implemented using circuitry, including various electronic hardware. By way of example and not limitation, the hardware may include transistors, resistors, capacitors, switches, integrated circuits, other modules, or some combination thereof. In various examples, the modules may include analog logic, digital logic, discrete components, traces and/or memory circuits fabricated on a silicon substrate including various integrated circuits (e.g., FPGAs, ASICs), or some combination thereof. In some embodiments, the module(s) may involve execution of preprogrammed instructions, software executed by a processor, or some combination thereof. For example, various modules may involve both hardware and software.

[0139] In an illustrative aspect, a system may include an information storage system may include a program of instructions. For example, the system may include a processor operably coupled to the information storage system. For example, when the processor executes the program of instructions, the processor causes operations to be performed to automatically identify a kinematic profile of a user and generate a recommendation library.

[0140] For example, the operations may include, in response to a neuromuscular activation signal, activate a sensor module operably coupled to the user. For example, the operations may include retrieve a sequence of A kinematic evaluation from a kinematic evaluation database.

[0141 ] For example, the operations may include, for i = 1 to N, perform movement code generation operations. For example, the operations may include transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device. For example, the operations may include generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user. For example, the movement code may be generated as a function of sensor measurements received from the sensor module. For example, the movement code may include a first key. For example, the first key may include balance, core, and flexibility values. For example, the movement code may include a second key. For example, the second key may include posterior, vertical, lateral, anterior, and core lines values.

[0142] For example, the operations may include determine a primary risk based on at least one of the movement code, each corresponding to one of (1, 2, . . ., i-th) kinematic evaluations previously performed by the user. For example, the operations may include dynamically select a next kinematic evaluation to be an (i+k)-th of the sequence based on the primary risk. For example, the

T1 operations may include generate a kinematic signature of the user based on a plurality of the movement codes associated with the sequence of kinematic evaluation.

[0143] For example, the operations may include apply a machine learning model to the kinematic profile to generate a kinematic analysis result may include a set of active neuromuscular activation. For example, the operations may include transmit the kinematic analysis result to be displayed on the user device.

[0144] For example, the system may include one or more of the following features:

• For example, the kinematic analysis result may include kinematic assessment of the user. For example, the kinematic assessment may include an injury probability analysis of the user.

• For example, the set of active neuromuscular activation may be selected from a neuromuscular activation database based on the kinematic profile and an individual health objective of the user. For example, the individual health objective may include reducing fall risks, alleviating back ache, mitigating Parkinson’s diseases, enhancing sport performance, and improving balance.

• For example, generating the movement code may include receive a sequence of images from an image capture device of the sensor module. For example, generating the movement code may include receive a sequence of sensor data from an inertial measurement unit of the sensor module releasably coupled to the user. For example, generating the movement code may include perform an inertial measurement analysis on the sequence of sensor data and an artificial intelligence analysis on the sequence of images.

• For example, generate the i-th movement code may include perform pose estimation operations to automatically detect anatomical landmarks and calculates angles between adjacent segments. For example, the pose estimation operations may include generate goniometric measurement values from the sensor measurements. For example, the goniometric measurement values may include joint angles. For example, the pose estimation operations may include determine the i-th movement code as a function of the goniometric measurement values and deviations from predefined motion patterns.

• For example, the primary risk may include a fall risk.

|0145 | In an illustrative aspect, a computer- implemented method performed by at least one processor to automatically identify a kinematic profile of a user and generate a recommendation library may include, in response to a neuromuscular activation signal, activate a sensor module. For example, the method may include retrieve a sequence of N kinematic evaluation from a kinematic evaluation database. |0146| For example, the method may include, for i = 1 to N, perform movement code generation operations. For example, the operations may include transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device. For example, the operations may include generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user. For example, the movement code may be generated as a function of sensor measurements received from the sensor module. For example, the movement code may include a first key. For example, the first key may include balance, core, and flexibility values. For example, the movement code may include a second key. For example, the second key may include posterior, vertical, lateral, anterior, and core lines values. For example, the operations may include select a next kinematic evaluation of the sequence.

[0147] For example, the method may include generate a kinematic profile of the user based on a plurality of the movement codes associated with the sequence of kinematic evaluation. For example, the method may include apply a machine learning model to the kinematic profile to generate a kinematic analysis result may include a set of active neuromuscular activation. For example, the method may include transmit the kinematic analysis result to be displayed on the user device.

[0148] For example, the system may include one or more of the following features:

• For example, generate the i-th movement code may include perform pose estimation operations to automatically detect anatomical landmarks and calculates angles between adjacent segments. For example, the pose estimation operations may include generate goniometric measurement values from the sensor measurements. For example, the goniometric measurement values may include joint angles. For example, generate the i-th movement code may include determine the i-th movement code as a function of the goniometric measurement values and deviations from predefined motion patterns.

• For example, selecting the next kinematic evaluation of the sequence may include dynamically select the next kinematic evaluation to be an (i+k)-th of the sequence based on a primary risk. For example, the primary risk may be determined based on at least one of the movement code, each corresponding to one of (1, 2, ..., i-th) kinematic evaluations previously performed by the user.

• For example, the primary risk may include a fall risk.

[0149] In an illustrative aspect, a computer program product may include a program of instructions tangibly embodied on a non-transitory computer readable medium wherein, when the instructions may be executed on a processor, the processor causes biomechanical data processing operations to be performed to automatically identify a kinematic profile of a user and generate a recommendation library, the operations.

[0150] For example, the operations may include, in response to a neuromuscular activation signal, activate a sensor module. For example, the operations may include retrieve a sequence of N kinematic evaluation from a kinematic evaluation database. For example, the operations may include, for i = 1 to N, perform movement code generation operations. For example, the operations may include transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device. For example, the operations may include generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user.

[0151] For example, the movement code may be generated as a function of sensor measurements received from the sensor module. For example, the movement code may include a first key. For example, the first key may include balance, core, and flexibility values. For example, the movement code may include a second key. For example, the second key may include posterior, vertical, lateral, anterior, and core lines values.

[0152] For example, the operations may include select a next kinematic evaluation of the sequence. For example, the operations may include generate a kinematic profile of the user based on a plurality of the movement codes associated with the sequence of kinematic evaluation. For example, the operations may include apply a machine learning model to the kinematic profile to generate a kinematic analysis result may include a set of active neuromuscular activation. For example, the operations may include transmit the kinematic analysis result to be displayed on the user device (540).

[0153] For example, the computer program product may include one or more of the following features: • For example, the kinematic analysis result further may include kinematic assessment of the user. For example, the kinematic assessment may include an injury probability analysis of the user.

• For example, generating the movement code may include receive a sequence of images from an image capture device of the sensor module. For example, generating the movement code may include receive a sequence of sensor data from an inertial measurement unit of the sensor module releasably coupled to the user. For example, generating the movement code may include perform an inertial measurement analysis on the sequence of sensor data and an artificial intelligence analysis on the sequence of images. \

• For example, the primary risk may include a fall risk.

[0154] For example, the system may include any or all of the features of the computer implemented method. For example, the system may include any or all of the features of the computer program product. For example, the computer implemented method may include any or all of the features of the system. For example, the computer implemented method may include any or all of the features of the computer program product. For example, the computer program product may include any or all of the features of the system. For example, the computer program product may include any or all of the features of the computer implemented method. |0155 | A number of implementations have been described. Nevertheless, it will be understood that various modifications may be made. For example, advantageous results may be achieved if the steps of the disclosed techniques were performed in a different sequence, or if components of the disclosed systems were combined in a different manner, or if the components were supplemented with other components. Accordingly, other implementations are contemplated within the scope of the following claims.

Claims

CLAIMS What is claimed is:

1. A system comprising: an information storage system (245) comprising a program of instructions; and, a processor (205) operably coupled to the information storage system such that, when the processor executes the program of instructions, the processor causes operations to be performed to automatically identify a kinematic profile of a user and generate a recommendation library (195), the operations comprising: in response to a neuromuscular activation signal, activate a sensor module operably coupled to the user (405); retrieve a sequence of A kinematic evaluation from a kinematic evaluation database (420); for i = 1 to N, perform movement code generation operations comprising: transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device (470); generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user (435), wherein the movement code is generated as a function of sensor measurements received from the sensor module, and comprises: a first key (185) comprising balance, core, and flexibility values; and, a second key (190) comprising posterior, vertical, lateral, anterior, and core lines values; determine a primary risk based on at least one of the movement code (440), each corresponding to one of (1, 2, ..., i-th) kinematic evaluations previously performed by the user; and, dynamically select a next kinematic evaluation to be an (i+k)-th of the sequence based on the primary risk (455); generate a kinematic signature of the user based on a plurality of the movement codes associated with the sequence of kinematic evaluation (505); apply a machine learning model to the kinematic profile to generate a kinematic analysis result comprising a set of active neuromuscular activation (515); and, transmit the kinematic analysis result to be displayed on the user device (540).

2. The system of claim 1 , wherein the kinematic analysis result further comprises kinematic assessment of the user comprising an injury probability analysis of the user.

3. The system of claim 1 , wherein the set of active neuromuscular activation is selected from a neuromuscular activation database based on the kinematic profile and an individual health objective of the user, wherein the individual health objective comprises reducing fall risks, alleviating back ache, mitigating Parkinson’s diseases, enhancing sport performance, and improving balance.

4. The system of claim 1, wherein generating the movement code comprises: receive a sequence of images from an image capture device of the sensor module; receive a sequence of sensor data from an inertial measurement unit of the sensor module releasably coupled to the user; and, perform an inertial measurement analysis on the sequence of sensor data and an artificial intelligence analysis on the sequence of images.

5. The system of claim 1 , wherein generate the i-th movement code comprises perform pose estimation operations to automatically detect anatomical landmarks and calculates angles between adjacent segments, wherein the pose estimation operations comprise: generate goniometric measurement values from the sensor measurements, wherein the goniometric measurement values comprise joint angles; and, determine the i-th movement code as a function of the goniometric measurement values and deviations from predefined motion patterns.

6. The system of claim 1, wherein the primary risk comprises a fall risk.

7. A computer-implemented method performed by at least one processor to automatically identify a kinematic profile of a user and generate a recommendation library, the method comprising: in response to a neuromuscular activation signal, activate a sensor module (405); retrieve a sequence of N kinematic evaluation from a kinematic evaluation database (420); for i = 1 to N, perform movement code generation operations comprising: transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device (470); generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user (435), wherein the movement code is generated as a function of sensor measurements received from the sensor module, and comprises: a first key (185) comprising balance, core, and flexibility values; and, a second key (190) comprising posterior, vertical, lateral, anterior, and core lines values; and, select a next kinematic evaluation of the sequence (455); generate a kinematic profile of the user based on a plurality of the movement codes associated with the sequence of kinematic evaluation (505); apply a machine learning model to the kinematic profile to generate a kinematic analysis result comprising a set of active neuromuscular activation (515); and, transmit the kinematic analysis result to be displayed on the user device (540).

8. The computer-implemented method of claim 7, wherein the kinematic analysis result further comprises kinematic assessment of the user comprising an injury probability analysis of the user.

9. The computer-implemented method of claim 7, wherein the set of active neuromuscular activation is selected from a neuromuscular activation database based on the kinematic profile and an individual health objective of the user, wherein the individual health objective comprises reducing fall risks, alleviating back ache, mitigating Parkinson’s diseases, enhancing sport performance, and improving balance.

10. The computer-implemented method of claim 7, wherein generating the movement code comprises: receive a sequence of images from an image capture device of the sensor module; receive a sequence of sensor data from an inertial measurement unit of the sensor module releasably coupled to the user; and, perform an inertial measurement analysis on the sequence of sensor data and an artificial intelligence analysis on the sequence of images.

11. The computer-implemented method of claim 7 wherein generate the i-th movement code comprises perform pose estimation operations to automatically detect anatomical landmarks and calculates angles between adjacent segments, wherein the pose estimation operations comprise: generate goniometric measurement values from the sensor measurements, wherein the goniometric measurement values comprise joint angles; and, determine the i-th movement code as a function of the goniometric measurement values and deviations from predefined motion patterns.

12. The computer-implemented method of claim 7, wherein selecting the next kinematic evaluation of the sequence comprises dynamically select the next kinematic evaluation to be an (i+k)-th of the sequence based on a primary risk, wherein the primary risk is determined based on at least one of the movement code, each corresponding to one of ( 1 , 2, . . . , i-th) kinematic evaluations previously performed by the user.

13. The computer- implemented method of claim 12, wherein the primary risk comprises a fall risk.

14. A computer program product comprising a program of instructions tangibly embodied on a non-transitory computer readable medium wherein, when the instructions are executed on a processor, the processor causes biomechanical data processing operations to be performed to automatically identify a kinematic profile of a user and generate a recommendation library, the operations comprising: in response to a neuromuscular activation signal, activate a sensor module (405); retrieve a sequence of N kinematic evaluation from a kinematic evaluation database (420); for i = 1 to N, perform movement code generation operations comprising: transmit an i-th kinematic evaluation from the sequence of kinematic evaluation to a user device (470); generate an i-th movement code of the user corresponding to the i-th kinematic evaluation performed by the user (435), wherein the movement code is generated as a function of sensor measurements received from the sensor module, and comprises: a first key (185) comprising balance, core, and flexibility values; and, a second key (190) comprising posterior, vertical, lateral, anterior, and core lines values; and, select a next kinematic evaluation of the sequence (455); generate a kinematic profile of the user based on a plurality of the movement codes associated with the sequence of kinematic evaluation (505); apply a machine learning model to the kinematic profile to generate a kinematic analysis result comprising a set of active neuromuscular activation (515); and, transmit the kinematic analysis result to be displayed on the user device (540).

15. The computer program product of claim 14, wherein the kinematic analysis result further comprises kinematic assessment of the user comprising an injury probability analysis of the user.

16. The computer program product of claim 14, wherein the set of active neuromuscular activation is selected from a neuromuscular activation database based on the kinematic profile and an individual health objective of the user, wherein the individual health objective comprises reducing fall risks, alleviating back ache, mitigating Parkinson’s diseases, enhancing sport performance, and improving balance.

31

17. The computer program product of claim 14, wherein generating the movement code comprises: receive a sequence of images from an image capture device of the sensor module; receive a sequence of sensor data from an inertial measurement unit of the sensor module releasably coupled to the user; and, perform an inertial measurement analysis on the sequence of sensor data and an artificial intelligence analysis on the sequence of images.

18. The computer program product of claim 14 wherein generate the i-th movement code comprises perform pose estimation operations to automatically detect anatomical landmarks and calculates angles between adjacent segments, wherein the pose estimation operations comprise: generate goniometric measurement values from the sensor measurements, wherein the goniometric measurement values comprise joint angles; and, determine the i-th movement code as a function of the goniometric measurement values and deviations from predefined motion patterns.

19. The computer program product of claim 14, wherein selecting the next kinematic evaluation of the sequence comprises dynamically select the next kinematic evaluation to be an (i+k)-th of the sequence based on a primary risk, wherein the primary risk is determined based on at least one of the movement code, each corresponding to one of ( 1 , 2, . . . , i-th) kinematic evaluations previously performed by the user.

20. The computer program product of claim 19, wherein the primary risk comprises a fall risk.