Somatosensory synchronization motion respiration rhythm optimization method, system and equipment based on smart clothing and medium

Abstract

The invention relates to a motion breathing rhythm optimization method, system and device based on somatosensory synchronization of smart clothing and a medium, and the method comprises the steps: collecting human motion posture data in real time through a sensor assembly, extracting the main frequency and phase features of a motion rhythm through a time-frequency mixed analysis method, and recognizing the type and intensity of a current motion; according to the current motion type and intensity, calling a matched inspiration and expiration ratio parameter in a preset respiration database, predicting a starting point of a next period by combining the phase characteristics, and generating a target respiration rhythm template containing a phase compensation amount; generating a pneumatic tactile waveform parameter group based on the target respiratory rhythm template, controlling the working time sequence and the pressure gradient of a flexible pneumatic assembly of the intelligent garment according to the pneumatic tactile waveform parameter group, and forming simulated respiratory fluctuating waves propagating along the direction of the intercostal muscles on the body surface of the human body. Therefore, implicit accurate regulation and control of the motion respiratory rhythm are achieved through the synergistic effect of pneumatic tactile feedback and an intelligent algorithm.

Description

Technical Field

[0001] This invention relates to the field of exercise physiology, and in particular to a method, system, device, and medium for optimizing exercise breathing rhythm based on somatosensory synchronization using smart clothing. Background Technology

[0002] In the field of exercise physiology, the coordination between respiratory rhythm and movement rhythm directly affects athletic performance and safety. Studies have shown that respiratory rhythm dysregulation can lead to decreased oxygen uptake efficiency, increased cardiopulmonary load, and even exercise-related injuries.

[0003] Existing technologies primarily guide breathing through visual or auditory cues. For example, displaying breathing rhythm icons on a screen or playing beat sounds. However, this method requires the user to actively look at the screen or listen to the sound, actively responding to external cues, thus failing to achieve "imperceptible intervention." Furthermore, due to the drastic changes in human posture during high-dynamic movements, traditional rigid sensors or wearable devices are prone to displacement or compression of muscle groups, thereby interfering with the continuity and comfort of movement. Simultaneously, existing interaction methods mostly employ explicit command output modes, lacking a real-time phase matching mechanism between the cue signals and the user's actual movement rhythm, resulting in a lag in breathing regulation.

[0004] Therefore, there is an urgent need for a motion breathing optimization scheme that has low interference and implicit guidance capabilities in highly dynamic scenarios. Summary of the Invention

[0005] (a) Technical problems to be solved In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a method, system, device and medium for optimizing the movement breathing rhythm based on smart clothing and somatosensory synchronization, which solves the systemic defects and technical problems of existing breathing guidance technology, such as attention interference, wearability mismatch and rhythm desynchronization.

[0006] (II) Technical Solution To achieve the above objectives, the main technical solutions adopted by the present invention include: In a first aspect, embodiments of the present invention provide a method for optimizing motion-breathing rhythm based on somatosensory synchronization using smart clothing, comprising: By using sensor components embedded in smart clothing to collect human motion posture data in real time, and using time-frequency hybrid analysis to extract the main frequency and phase characteristics of the motion rhythm, the current motion type and intensity can be identified. Based on the current exercise type and intensity, the system calls the preset respiratory database to match the inspiratory-to-expiratory ratio parameter, combines phase characteristics to predict the start point of the next respiratory cycle, and generates a target respiratory rhythm template containing phase compensation. Based on the target respiratory rhythm template, a set of pneumatic tactile waveform parameters is generated. The working sequence and pressure gradient of the flexible pneumatic components of the smart clothing are controlled according to the set of pneumatic tactile waveform parameters. This forms a simulated respiratory fluctuation wave that propagates along the intercostal muscles on the human body surface, so as to guide the human body's breathing rhythm and movement rhythm to adjust synchronously.

[0007] Optionally, sensor components embedded in smart clothing are used to collect human motion posture data in real time, and a time-frequency hybrid analysis method is used to extract the dominant frequency and phase characteristics of the motion rhythm to identify the current motion type and intensity, including: By embedding sensor components into smart clothing, the acceleration and angular velocity signals of the user's movement are collected in real time to generate a multi-channel continuous motion data stream; The system performs time-domain periodic signal analysis on continuous motion data streams, calculates step frequency as a time-domain rhythm feature through zero-point crossing detection, synchronously captures the waveform start point of periodic signals, and generates real-time phase offset representing the temporal position within the motion cycle. Frequency domain energy spectrum analysis is performed on continuous motion data streams to extract the dominant frequency component with the largest energy proportion, and the phase angle information corresponding to the dominant frequency component is obtained by analysis. The real-time phase offset is converted into an equivalent phase angle. By comparing the difference between the equivalent phase angle and the phase angle information corresponding to the main frequency component, if the difference exceeds a preset threshold, the phase is determined to be inaccurate. Based on the difference value, the phase angle information corresponding to the main frequency component is corrected to generate noise-resistant optimized phase features. The temporal rhythm features, frequency domain dominant frequency components, and noise-resistant optimized phase features are input into the motion classifier, which matches the motion types in the preset motion type library. Based on the amplitude of the temporal rhythm features and the energy intensity of the frequency domain dominant frequency components, the current motion intensity level is determined by a predefined intensity grading rule. The sensor components include reconfigurable modular sensors. The density distribution ratio of the modular sensors is determined based on the fusion evaluation results of the contribution rate of the time-domain periodic signal variance and the proportion of the frequency-domain dominant frequency energy in the user's historical motion data.

[0008] Optionally, performing time-domain periodic signal analysis on the continuous motion data stream, and calculating the step frequency as a time-domain rhythmic feature through zero-point crossing detection, includes: The acceleration signal is filtered by axial component selection, and the acceleration component that is consistent with the direction of human motion is selected. The selected acceleration components are smoothed and filtered. Based on the amplitude range of the filtered signal waveform, the baseline threshold range for zero-point crossing is adaptively adjusted to distinguish between the effective action period and the noise fluctuation period. Capture the rising and falling edges of the filtered signal waveform that continuously cross the baseline threshold, record the timestamps of adjacent valid crossing points, and take the moment when the first rising edge crosses the baseline threshold as the start point of the valid action cycle phase. The rotational motion judgment threshold is generated synchronously based on the amplitude change of the angular velocity signal and the historical amplitude standard deviation of the angular velocity signal to identify rotational motion characteristics. If rotational motion characteristics are detected, the timing alignment correction of the effective motion cycle phase start point is performed by combining the peak point of the angular velocity signal. The effective action cycle duration formed by N consecutive effective crossings is counted. If the deviation between the durations of adjacent effective action cycles is less than the preset tolerance range, step frequency calculation is triggered. The duration of an action cycle is calculated based on the time difference between the start times of adjacent effective action cycles, and the reciprocal of the duration of the action cycle is converted into step frequency as a time-domain rhythm feature.

[0009] Optionally, frequency domain energy spectrum analysis is performed on the continuous motion data stream to extract the dominant frequency component with the largest energy proportion, and the phase angle information corresponding to the dominant frequency component is obtained by analysis, including: The rotational motion determination threshold is generated based on the amplitude change of the angular velocity signal and the historical amplitude standard deviation of the angular velocity signal, so as to identify the characteristics of rotational motion. If more than k rotational motion features are identified within the continuous time window of the continuous motion data stream, the continuous motion data stream is determined to be rotation-dominated, and the angular velocity signal is selected as the selected signal. If no more than k rotational motion features are identified, the continuous motion data stream is determined to be linearly dominant, and the acceleration signal is used as the selected signal. A windowed Fourier transform is performed on the selected signal to generate a complex spectrum in the frequency domain containing amplitude and phase information, and the complex spectrum is then smoothed in the frequency domain. The energy values ​​of each frequency point in the smoothed complex spectrum are traversed, and the frequency point with the largest energy proportion is selected as the dominant frequency component in the frequency domain. Phase angle information is extracted from the position of the complex spectrum corresponding to the main frequency component in the frequency domain, and combined with the effective action cycle phase start point, a time-frequency synchronization reference is generated by interpolation alignment.

[0010] Optionally, based on the current exercise type and intensity, the inspiratory-to-expiratory ratio parameter is matched using a preset respiratory database, and the starting point of the next respiratory cycle is predicted by combining phase characteristics, generating a target respiratory rhythm template that includes phase compensation, including: Based on the current exercise type and intensity level, the corresponding inspiratory-to-expiratory ratio parameter is matched from the preset breathing database; The product of the reciprocal of the real-time cadence and the target inspiratory-to-expiratory ratio parameter is converted into the duration of a respiratory cycle in milliseconds. Based on the effective action cycle phase start point and combined with the millisecond-level respiratory cycle duration, the start timestamp of the next respiratory cycle is predicted by linear interpolation. Based on the time offset between the current respiratory phase and the target time reference point, a phase compensation amount is generated using a proportional-integral algorithm. By integrating the inspiratory-to-expiratory ratio parameter, phase compensation amount, and the predicted start timestamp of the next respiratory cycle, a target respiratory rhythm template is generated.

[0011] Optionally, a set of pneumatic tactile waveform parameters is generated based on the target respiratory rhythm template. The working sequence and pressure gradient of the flexible pneumatic components of the smart garment are controlled according to the set of pneumatic tactile waveform parameters to form simulated respiratory fluctuation waves propagating along the intercostal muscles on the human body surface, so as to guide the human body's breathing rhythm and movement rhythm to adjust synchronously, including: Analyze the target respiratory rhythm template and divide it into inspiratory and expiratory phases; By introducing state machine switching conditions and combining the predicted start timestamp of the next respiratory cycle, the segmented working sequence of the inspiratory and expiratory phases of the flexible airbag is generated based on the acquired intercostal muscle direction data. The timing deviation of the switching points between adjacent respiratory cycles is corrected by the phase compensation amount, so that the working timing of the airbag triggering is aligned with the actual action rhythm. Based on the inspiratory-to-expiratory ratio parameter, determine the stepwise pressure gradient during the inspiratory phase and the gradual pressure gradient during the expiratory phase; The segmented working sequence of the inspiratory and expiratory phases, the stepped pressure increase gradient of the inspiratory phase, and the slow pressure decrease gradient of the expiratory phase are used as a set of pneumatic tactile waveform parameters to drive the flexible pneumatic components. During the driving process of the flexible pneumatic unit, the duration of the respiratory cycle is dynamically compressed or extended based on the real-time acquired user motion acceleration and angular velocity, and the rate of change of the step-by-step pressure gradient in the inspiratory phase and the slow-fall pressure gradient in the expiratory phase are adjusted according to a preset ratio.

[0012] Optionally, the state machine transition conditions include: A two-state machine is used to control the switching of inhalation and exhalation phases. If the current phase is maintained for more than half the duration of the respiratory cycle, it will automatically switch to the opposite phase. After the phase switch, the timer will be reset immediately and the duration of the next respiratory cycle will be replanned.

[0013] Secondly, embodiments of the present invention provide a motion-breathing rhythm optimization system based on smart clothing with motion-synchronized sensing, comprising: The preliminary processing module is used to collect human motion posture data in real time using sensor components embedded in smart clothing, and to extract the main frequency and phase characteristics of the motion rhythm using a time-frequency hybrid analysis method to identify the current motion type and intensity. The rhythm determination module is used to call the preset respiratory database to match the inspiratory-to-expiratory ratio parameters according to the current exercise type and intensity, combine phase characteristics to predict the start point of the next respiratory cycle, and generate a target respiratory rhythm template containing phase compensation. The guidance and adjustment module is used to generate a set of pneumatic tactile waveform parameters based on the target respiratory rhythm template. The working sequence and pressure gradient of the flexible pneumatic components of the smart clothing are controlled according to the set of pneumatic tactile waveform parameters to form a simulated respiratory fluctuation wave that propagates along the intercostal muscles on the human body surface, so as to guide the human body's breathing rhythm and movement rhythm to adjust synchronously.

[0014] Thirdly, embodiments of the present invention provide a smart garment, comprising: a flexible integrated carrier; a sensor assembly including modular sensors arranged at least one part of the flexible integrated carrier, the density distribution ratio of the modular sensors being determined based on the fusion evaluation results of the contribution rate of the variance of the time-domain periodic signal and the proportion of the frequency-domain main frequency energy in the user's historical motion data; a flexible pneumatic assembly including a flexible airbag and an air duct disposed on the flexible integrated carrier, the flexible airbag being arranged along the direction of the intercostal muscles; and an integrated control assembly disposed on the flexible integrated carrier and connected to the sensor assembly, the flexible pneumatic assembly, and a preset memory, the integrated control assembly including: a micro air pump, a solenoid valve, a controller, a built-in sensor assembly, and a lithium battery assembly, the micro air pump and the solenoid valve constituting a pneumatic drive unit, forming a pneumatic circuit with the flexible airbag through the air duct, and the controller being connected to the solenoid valve, the built-in sensor assembly, and the lithium battery assembly; The memory stores instructions that can be executed by the controller. These instructions are executed by the controller to enable the controller to perform the motion-breathing rhythm optimization method based on smart clothing as described above.

[0015] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a controller, implement the above-described method for optimizing the motion-breathing rhythm based on smart clothing with haptic synchronization.

[0016] (III) Beneficial Effects The beneficial effects of this invention are: through the synergistic effect of pneumatic tactile feedback and intelligent algorithms, this invention achieves implicit and precise control of the rhythm of breathing during exercise.

[0017] First, based on the multimodal sensors embedded in smart clothing, motion posture data is collected in real time. The dominant frequency and phase characteristics of the motion rhythm are extracted using a time-frequency hybrid analysis method. This can accurately identify the type and intensity of motion without the need for active user feedback, thereby avoiding the active occupation of user attention by traditional visual / auditory cues and realizing implicit motion state monitoring.

[0018] Secondly, by calling a preset respiratory database and combining phase characteristics to predict the start point of the next cycle, a respiratory rhythm template containing dynamic phase compensation is generated, which effectively solves the problem of respiratory-motor rhythm asynchrony caused by fixed timing commands in existing technologies, and ensures that the respiratory regulation signal matches the actual motion state in real time.

[0019] Furthermore, by generating simulated respiratory fluctuation waves on the body surface through flexible pneumatic components that propagate along the direction of the intercostal muscles, and using pressure gradients and timing control to form tactile guidance signals that conform to the biomechanical characteristics of the human body, the breathing adjustment process can be completed naturally without relying on conscious intervention. It also effectively avoids the limitation of high dynamic range of motion by traditional rigid components, taking into account both wearing comfort and freedom of movement.

[0020] Ultimately, through the synergistic effect of the above technologies, the user's breathing rhythm and movement form a continuous closed-loop synchronization, thereby reducing the burden of subjective intervention, systematically optimizing exercise efficiency, delaying fatigue accumulation, and reducing the risk of injury caused by breathing disorders. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the overall process of the method provided in the embodiments of the present invention; Figure 2 This is a schematic diagram illustrating the specific process of step S1 of the method provided in this embodiment of the invention; Figure 3 This is a schematic diagram of the specific process of step S12 of the method provided in the embodiment of the present invention; Figure 4 This is a detailed flowchart illustrating step S13 of the method provided in this embodiment of the invention; Figure 5 This is a detailed flowchart illustrating step S2 of the method provided in this embodiment of the invention; Figure 6 This is a detailed flowchart illustrating step S3 of the method provided in this embodiment of the invention; Figure 7 This is a schematic diagram of the structure of the device provided in an embodiment of the present invention; Figure 8 A schematic diagram of the structure of the integrated control component of the device provided in an embodiment of the present invention.

[0022] [Explanation of Labels in the Attached Image] 1: Zipper; 2: Air delivery tube; 3: Flexible pneumatic components; 4: Integrated control components; 4-1: Lithium battery assembly; 4-2: Miniature air pump; 4-3: Solenoid valve; 4-4: Controller; 4-5: Magnet plate; 5: Sensor components. Detailed Implementation

[0023] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] like Figure 1 As shown in the embodiment of the present invention, a method for optimizing the circadian rhythm of motion based on somatosensory synchronization of smart clothing includes: real-time acquisition of human motion posture data using sensor components embedded in smart clothing; extraction of the dominant frequency and phase characteristics of the circadian rhythm using a time-frequency hybrid analysis method; identification of the current motion type and intensity; matching the inspiratory-to-expiratory ratio parameters in a preset respiratory database based on the current motion type and intensity; predicting the start point of the next respiratory cycle by combining phase characteristics; generating a target circadian rhythm template containing phase compensation; generating a set of pneumatic tactile waveform parameters based on the target circadian rhythm template; controlling the working sequence and pressure gradient of the flexible pneumatic components of the smart clothing according to the set of pneumatic tactile waveform parameters; forming a simulated respiratory fluctuation wave propagating along the intercostal muscles on the human body surface to guide the human breathing rhythm to adjust synchronously with the circadian rhythm.

[0025] This invention achieves implicit and precise control of the rhythm of breathing during exercise through the synergistic effect of pneumatic tactile feedback and intelligent algorithms.

[0026] First, based on the multimodal sensors embedded in smart clothing, motion posture data is collected in real time. The dominant frequency and phase characteristics of the motion rhythm are extracted using a time-frequency hybrid analysis method. This can accurately identify the type and intensity of motion without the need for active user feedback, thereby avoiding the active occupation of user attention by traditional visual / auditory cues and realizing implicit motion state monitoring.

[0027] Secondly, by calling a preset respiratory database and combining phase characteristics to predict the start point of the next cycle, a respiratory rhythm template containing dynamic phase compensation is generated, which effectively solves the problem of respiratory-motor rhythm asynchrony caused by fixed timing commands in existing technologies, and ensures that the respiratory regulation signal matches the actual motion state in real time.

[0028] Furthermore, by generating simulated respiratory fluctuation waves on the body surface through flexible pneumatic components that propagate along the direction of the intercostal muscles, and using pressure gradients and timing control to form tactile guidance signals that conform to the biomechanical characteristics of the human body, the breathing adjustment process can be completed naturally without relying on conscious intervention. It also effectively avoids the limitation of high dynamic range of motion by traditional rigid components, taking into account both wearing comfort and freedom of movement.

[0029] Ultimately, through the synergistic effect of the above technologies, the user's breathing rhythm and movement form a continuous closed-loop synchronization, thereby reducing the burden of subjective intervention, systematically optimizing exercise efficiency, delaying fatigue accumulation, and reducing the risk of injury caused by breathing disorders.

[0030] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0031] Specifically, embodiments of the present invention provide a method for optimizing motion-breathing rhythm based on smart clothing with motion-synchronized sensing, including: S1. Real-time acquisition of human motion posture data is achieved by using sensor components embedded in smart clothing. The main frequency and phase characteristics of the motion rhythm are extracted using a time-frequency hybrid analysis method to identify the current motion type and intensity.

[0032] Furthermore, such as Figure 2 As shown, step S1 includes: S11. Real-time acquisition of user motion acceleration and angular velocity signals via sensor components embedded in smart clothing, generating a multi-channel continuous motion data stream; here, the sensor components include reconfigurable modular sensors, integrating sensors such as IMU (Inertial Measurement Unit), specifically distributed in areas such as the upper arm and torso, synchronously acquiring triaxial acceleration (α). x ,a y ,a z ) and triaxial angular velocity (w x ,w y ,w z The signal generates a time-series continuous multi-channel motion data stream. The density distribution ratio of the modular sensor is determined based on the fusion evaluation results of the contribution rate of the time-domain periodic signal variance and the proportion of the frequency-domain main frequency energy in the user's historical motion data.

[0033] S12. Perform time-domain periodic signal analysis on the continuous motion data stream, calculate the step frequency through zero-point crossing detection as a time-domain rhythm feature, synchronously capture the waveform start point of the periodic signal, and generate a real-time phase offset that characterizes the temporal position within the motion cycle.

[0034] Furthermore, such as Figure 3 As shown, step S12 includes: S121. The acceleration signal is filtered by axial component selection, and the acceleration component aligned with the direction of human motion is selected as the main analysis channel. In this step, based on the dominant direction of human motion (such as the vertical axis direction during walking / running), the acceleration is selected from the three-axis acceleration (a... x ,a y ,a zIn the process, the component that is consistent with the direction of motion is selected as the main analysis channel to suppress non-dominant axial noise interference.

[0035] S122. Perform smoothing filtering on the selected acceleration component. Based on the amplitude range of the filtered waveform (e.g., the peak-to-valley span ΔA), adaptively adjust the baseline threshold range for zero-point crossing judgment to distinguish between effective motion cycles and noise fluctuation cycles. Generally, the upper limit of the threshold is set to ΔA×15%, and the lower limit is ΔA×5%. If the waveform amplitude is lower than ΔA×3%, it is judged as noise fluctuation, and the cycle count is skipped.

[0036] S123. Capture the rising edge (cycle start) and falling edge (cycle end) of the continuously crossing baseline threshold in the waveform of the captured filtered signal, record the timestamps of adjacent valid crossing points, and take the moment when the first rising edge crosses the baseline threshold as the effective action cycle phase start. Simultaneously generate a rotation action judgment threshold based on the amplitude change of the angular velocity signal and the historical amplitude standard deviation of the angular velocity signal to identify rotation action characteristics. If rotation action characteristics are detected, i.e. in the case of limb or torso rotation, perform time alignment correction on the effective action cycle phase start by combining the peak point of the angular velocity signal. Specifically, align the peak point of the angular velocity signal with the rising edge of the acceleration to correct the phase start deviation.

[0037] S124. Calculate the effective action cycle duration formed by N consecutive effective crossings. If the deviation between adjacent effective action cycle durations is less than the preset tolerance range, it is determined to be a stable periodic action, triggering step frequency calculation. Generally, N is taken as 3~5.

[0038] S125. Calculate the duration of the movement cycle based on the time difference between the start times of adjacent effective movement cycles, and convert it into step frequency based on the reciprocal of the cycle duration as a temporal rhythm feature. Calculate the duration of the movement cycle based on the time difference between the start times of adjacent effective movement cycles: T step =t now -t start In the formula t now t is the start timestamp of the current period. start The starting timestamp of the previous period is used, and then according to formula F... step =6000 / T step (Unit: steps / minute) Total motion cycle time T step Converted to step frequency values, the time-domain rhythm characteristic values ​​are output.

[0039] S13. Perform frequency domain energy spectrum analysis on the continuous motion data stream, extract the frequency domain dominant frequency component with the largest energy proportion, and analyze the phase angle information corresponding to the frequency domain dominant frequency component.

[0040] Furthermore, such as Figure 4 As shown, step S13 includes: S131. A rotational motion determination threshold is generated based on the amplitude variation of the angular velocity signal and the historical amplitude standard deviation of the angular velocity signal to identify rotational motion characteristics. The angular velocity signal (w) is calculated in real time. x ,w y ,w z The instantaneous amplitude of the rotation motion is calculated and the standard deviation of the historical amplitude σω is statistically analyzed. The dynamic generation of the rotation motion judgment threshold is calculated as: judgment threshold = baseline coefficient × σω (the baseline coefficient is preset according to the type of motion, for example, 1.3 for running and 1.8 for badminton).

[0041] S132. If more than a preset number of rotational motion features are identified within the continuous time window of the continuous motion data stream, the continuous motion data stream is determined to be rotation-dominated, and the angular velocity signal is selected as the selected signal; k is generally taken as 3.

[0042] S133. If no more than k rotational motion features are identified, the continuous motion data stream is determined to be linearly dominant, and the acceleration signal is used as the selected signal.

[0043] S134. Perform a windowed Fourier transform on the selected signal, such as using a Hanning window to suppress spectral leakage, to generate a complex spectrum in the frequency domain containing amplitude and phase information, and then perform frequency domain smoothing on the complex spectrum.

[0044] S135. Traverse the energy values ​​of each frequency point in the smoothed complex spectrum and select the frequency point with the largest energy proportion as the dominant frequency component in the frequency domain.

[0045] S136. Extract phase angle information from the complex spectrum position corresponding to the main frequency component in the frequency domain, combine it with the effective action cycle phase start point, and generate a time-frequency synchronization reference through interpolation alignment.

[0046] S14. Convert the real-time phase offset into an equivalent phase angle. By comparing the difference between the equivalent phase angle and the phase angle information corresponding to the main frequency component, if the difference exceeds a preset threshold, phase misalignment is determined. Based on the difference value, the phase angle information corresponding to the main frequency component is corrected to generate noise-optimized phase features. Specifically, based on the real-time phase offset Δφ in the time domain and the current action cycle duration T... step Calculate the equivalent phase angle: θe=(Δφ / T) step The absolute deviation between the equivalent phase angle and the phase angle information corresponding to the main frequency component is calculated by multiplying the angle by 360°. If the deviation exceeds the preset threshold θth (e.g., 15°), it is determined to be phase misalignment. The main frequency phase angle is dynamically adjusted based on the phase deviation. The difference between the equivalent phase angle and the main frequency phase angle is proportionally fused using the gain coefficient α to generate noise-optimized phase features.

[0047] S15. Input the temporal rhythm features, frequency domain dominant frequency components, and noise-resistant optimized phase features into the motion classifier, match the motion types in the preset motion type library, and determine the current motion intensity level according to the amplitude of the temporal rhythm features and the energy intensity of the frequency domain dominant frequency components through predefined intensity grading rules.

[0048] The feature vector is input into a pre-trained motion classifier (such as SVM or neural network), matched with a preset motion type library, and the motion type label is output. The initial intensity level is divided according to the peak acceleration amplitude in the time domain (low: <0.5g, medium: 0.5g~1.2g, high: ≥1.2g), and the final intensity level is dynamically corrected based on the proportion of the dominant frequency energy in the frequency domain (>70% increases one level, <30% decreases one level).

[0049] S2. Based on the current exercise type and intensity, call the preset respiratory database to match the inspiratory-to-expiratory ratio parameters, combine phase characteristics to predict the starting point of the next cycle, and generate a target respiratory rhythm template containing phase compensation.

[0050] Furthermore, such as Figure 5 As shown, step S2 includes: S21. Based on the current exercise type and intensity level, match the corresponding inspiratory-to-expiratory ratio parameter from the preset breathing database.

[0051] S22. Convert the product of the reciprocal of the real-time cadence and the target inspiratory-to-expiratory ratio parameter into a millisecond-level respiratory cycle duration. Specifically, the formula for the millisecond-level respiratory cycle duration is: T breath =(60000 / F step )×β (unit: milliseconds), where β is the target inspiratory-to-expiratory ratio, β=t inhale / t exhale , t inhale t is the duration of inhalation. exhale This refers to the duration of exhalation.

[0052] S23. Based on the effective action cycle phase start point and the respiratory cycle duration, predict the start timestamp of the next respiratory cycle through linear interpolation.

[0053] S24. Based on the time offset between the current respiratory phase and the target time reference point, generate the phase compensation amount using a proportional-integral algorithm. Calculate the time offset Δt between the current respiratory phase and the target time reference point, and generate the dynamic phase compensation amount Δφ using a proportional-integral algorithm. f Δφ f =K p ×Δt+K i ×ΣΔt(K p K i (This is a control coefficient, the value of which is determined by historical data) to eliminate accumulated phase error.

[0054] S25. By integrating the inspiratory-to-expiratory ratio parameter, respiratory cycle duration, phase compensation amount, and the predicted start timestamp of the next respiratory cycle, a target respiratory rhythm template that can dynamically adapt to changes in exercise intensity and movement phase drift is generated.

[0055] S3. Generate a set of pneumatic tactile waveform parameters based on the target respiratory rhythm template. Control the working sequence and pressure gradient of the flexible pneumatic components of the smart clothing according to the set of pneumatic tactile waveform parameters to form a simulated respiratory fluctuation wave that propagates along the intercostal muscles on the human body surface, so as to guide the human body's breathing rhythm and movement rhythm to adjust synchronously.

[0056] Furthermore, such as Figure 6 As shown, step S3 includes: S31. Analyze the target respiratory rhythm template and divide it into inspiratory and expiratory phases. Analyze the target respiratory rhythm template based on the target inspiratory-expiratory ratio β and respiratory cycle T. breath The cycle is divided into an inhalation phase (duration = T). breath ×β / (β+1)) and expiratory phase (duration = T) breath / (β+1)).

[0057] S32. Introducing state machine switching conditions, and combining the predicted start timestamp of the next respiratory cycle, the segmented working sequence of the inspiratory and expiratory phases of the flexible airbag is generated based on the acquired intercostal muscle direction data. The state machine switching conditions include: using a two-state machine to control the switching between inspiratory and expiratory phases; if the current phase duration exceeds half the respiratory cycle length, it automatically switches to the opposite phase, and immediately resets the timer and replans the duration of the next respiratory cycle after the phase switch. Here, a two-state machine (S = "Inspiratory, Expiratory") is used to control phase switching; if the current phase duration exceeds the half-cycle threshold (Δt ≥ T),... breath If the phase is ×0.5, then immediately switch to the opposite phase (S). t+1 =-St), and reset the timer to reschedule the next cycle. For strength training movements, the force phase is determined by an angular velocity threshold: if w x >w th Trigger exhalation, when |w x | < 0.3w th At that time, inhalation is triggered.

[0058] S33. Based on the phase compensation amount, correct the timing deviation of the switching points between adjacent respiratory cycles to align the working timing of the airbag trigger with the actual action rhythm.

[0059] S34. Based on the inspiratory-to-expiratory ratio (IPR) parameter, determine the inspiratory phase stepwise pressure gradient and the expiratory phase slow-descent pressure gradient. The number of inspiratory phase steps is positively correlated with the IPR (e.g., when the IPR parameter = 1 / 2, the inspiratory duration accounts for 1 / 3 of the entire cycle, so 3 steps are set; when the IPR parameter = 2 / 1, 5 steps are set). Each step corresponds to a discrete mechanical increment in thoracic cavity expansion. The expiratory phase pressure descent rate is inversely correlated with the expiratory phase duration, ensuring that the pressure release rhythm matches the lung contraction dynamics.

[0060] S35. The segmented working sequence of the inspiratory and expiratory phases, the stepped pressure gradient of the inspiratory phase, and the slow pressure gradient of the expiratory phase are used as a set of pneumatic tactile waveform parameters to drive flexible pneumatic components.

[0061] S36. During the operation of the flexible pneumatic unit, the respiratory cycle duration is dynamically compressed or extended based on the real-time acquired user acceleration and angular velocity. The rate of change of the inspiratory phase stepwise pressure gradient and the expiratory phase slow-descent pressure gradient is adjusted according to a preset ratio determined by the user's historical data. This ensures that the rate of change of airbag pressure matches the exercise intensity in real time, avoiding tactile guidance that is either lagging or leading. In addition, vibration, sound, or light cues can be superimposed to achieve multimodal guidance.

[0062] Additionally, this invention provides a motion-synchronized respiratory rhythm optimization system based on smart clothing, comprising: a preliminary processing module, used to collect human motion posture data in real time using sensor components embedded in the smart clothing, extract the dominant frequency and phase characteristics of the motion rhythm using a time-frequency hybrid analysis method, and identify the current motion type and intensity; a rhythm determination module, used to match the inspiratory-to-expiratory ratio parameters in a preset respiratory database according to the current motion type and intensity, predict the start point of the next respiratory cycle based on the phase characteristics, and generate a target respiratory rhythm template including phase compensation; and a guidance and adjustment module, used to generate a set of pneumatic tactile waveform parameters based on the target respiratory rhythm template, and control the working sequence and pressure gradient of the flexible pneumatic components of the smart clothing according to the set of pneumatic tactile waveform parameters to form simulated respiratory fluctuation waves propagating along the intercostal muscles on the human body surface, so as to guide the human breathing rhythm to adjust synchronously with the motion rhythm.

[0063] refer to Figure 7 This invention provides a smart garment, comprising: Flexible integrated carrier; adopting an elastic sportswear structure, designed to conform to the curves of the human body, integrating various functional modules to ensure wearing comfort without restricting freedom of movement, suitable for various sports scenarios such as running, cycling, and strength training. The flexible integrated carrier is equipped with a zipper 1.

[0064] Sensor component 5 includes modular sensors arranged in at least one part of the flexible integrated carrier (such as the torso, upper arm, or outer thigh; upper arm sensors can be used for upper limb resistance training such as lateral raises, presses, and push-pulls, as well as upper limb-driven core training such as jumping jacks; outer thigh sensors can be used for aerobic exercises such as brisk walking, jogging, and cycling, as well as anaerobic exercises such as squats and elliptical trainers). The density distribution ratio of the modular sensors is determined based on the fusion evaluation results of the contribution rate of the variance of the time-domain periodic signal and the proportion of the frequency-domain dominant frequency energy in the user's historical motion data. In addition, the modular sensors include acceleration and angular velocity sensor modules, micro lithium batteries, and low-power Bluetooth communication units for independently collecting limb motion data and wirelessly transmitting it to the integrated hardware to achieve auxiliary motion recognition and system data fusion. A posture sensor module can also be set.

[0065] The flexible pneumatic component 3 includes a flexible airbag and an air guide tube 2 mounted on a flexible integrated carrier. The flexible airbag is arranged along the direction of the intercostal muscles. The air guide tube 2 is connected to a micro air pump 4-2 and the flexible airbag respectively. The micro air pump 4-2 works in conjunction with a solenoid valve 4-3 to control the inflation and deflation of the airbag to generate tactile rhythm on the body surface.

[0066] In addition, an integrated control component is mounted on a flexible integrated carrier and is connected to the sensor component 5, the flexible pneumatic component 3, and the memory, respectively. Figure 8 As shown, the integrated control component includes: a miniature air pump 4-2, a solenoid valve 4-3, a controller 4-4, a built-in sensor assembly, and a lithium battery assembly 4-1. The miniature air pump 4-2 and the solenoid valve 4-3 constitute a pneumatic drive unit, forming a pneumatic circuit with the flexible airbag through an air guide tube. The controller 4-4 is connected to the solenoid valve 4-3, the built-in sensor assembly, and the lithium battery assembly. The solenoid valve 4-3 acts as an air circuit switch, and the controller 4-4 drives the solenoid valve 4-3 to open and close via a PWM signal, synchronously controlling the start and stop of the air pump to achieve the inflation / deflation sequence and pressure gradient. In addition, the integrated control component is also equipped with magnetic plates 4-5, distributed at the component interface, to realize the magnetic quick installation and removal of hardware modules such as the air pump and solenoid valve, improving garment maintenance efficiency.

[0067] The miniature air pump 4-2 features a compact diaphragm design, a rated voltage of only 3V, and a weight of 14.9 grams, making it suitable for wearable applications. Its no-load current is as low as 220mA (approximately 1W), and when combined with a φ3.5mm nozzle and air tube, it can precisely control the inflation and deflation of the flexible airbag within a flow rate range of 0.5-1.5L / min, generating a maximum negative pressure of -42kPa to drive tactile rhythm. The air pump operates at approximately 55dB noise, and combined with the solenoid valve 4-3 for rapid switching, it achieves low-interference tactile feedback on the body surface, meeting the lightweight and low-power requirements for respiratory rhythm guidance in motion scenarios. The built-in sensor components integrate acceleration, angular velocity, and attitude sensors to capture trunk motion characteristics and overall posture change signals in real time.

[0068] The memory stores instructions that can be executed by the controller 4-4. The controller 4-4 executes the instructions so that it can perform the motion breathing rhythm optimization method based on smart clothing and somatosensory synchronization as described above.

[0069] Furthermore, embodiments of the present invention provide a computer-readable storage medium storing computer-executable instructions, characterized in that, when the executable instructions are executed by a controller, they implement the above-described method for optimizing the motion-breathing rhythm based on smart clothing with haptic synchronization.

[0070] In summary, this invention provides a method, system, device, and medium for optimizing the respiratory rhythm of movement based on haptic synchronization using smart clothing. Modular sensors are deployed in key areas of the smart clothing (such as the upper arm or torso) to collect user movement parameters in real time, monitoring the user's movement state and breathing characteristics. Based on the matching relationship between the movement rhythm and a predetermined exercise type (such as jogging, brisk walking, or stretching), a suitable target breathing rhythm is mapped. This rhythm can be provided by a preset database (e.g., a two-step inhale, two-step exhale suggestion for jogging) or manually set and adjusted by the user. Next, flexible pneumatic components (airbags + micro-pumps) embedded in the clothing create tactile fluctuations on the body surface simulating chest cavity rise and fall, guiding the user to adjust their breathing unconsciously. Furthermore, the exercise state is continuously monitored; when the user speeds up or slows down their exercise rhythm, the algorithm synchronously adjusts the airbag inflation and deflation frequency to ensure the feedback matches the current exercise state. This invention achieves natural coupling of breathing and movement rhythms through pneumatic tactile guidance without relying on visual or auditory cues, reducing distraction and improving exercise efficiency. Meanwhile, the present invention specifically adopts an integrated flexible garment that integrates sensing, control and feedback units to ensure high fit and dynamic freedom.

[0071] Therefore, this invention replaces visual / auditory cues with pneumatic tactile feedback to achieve low-interference implicit interaction, improve the stability of breathing rhythm, thereby increasing exercise efficiency and reducing fatigue and injury risk; the algorithm can adaptively adjust the feedback rhythm according to exercise intensity to achieve personalized control. Moreover, its integrated flexible structure enhances wearability and adapts to high-dynamic sports scenarios.

[0072] This invention has wide applications in various fields, including sports training, fitness and public health, rehabilitation medicine, medical assistance, wearable devices, and human-computer interaction. In public fitness and daily exercise scenarios, it can help users develop stable breathing patterns, improve breathing-movement coordination during various exercises such as running, cycling, resistance training, and yoga, and reduce discomfort or injury caused by respiratory disturbances. Simultaneously, in the fields of rehabilitation medicine and medical assistance, this invention can be used for cardiopulmonary rehabilitation, respiratory function training, and assisted breathing guidance for postoperative rehabilitation patients, especially suitable for those who need to gradually restore their breathing ability. Furthermore, thanks to its integrated clothing design and low-interference haptic feedback characteristics, this invention can also be extended to the fields of smart wearable devices and human-computer interaction design, becoming an important component of future sports health monitoring and interactive rehabilitation training.

[0073] It should be clarified that when the type of exercise is fixed, the sensor components can be omitted, and only a fixed rhythm output pneumatic feedback can be used. The pneumatic feedback can be replaced with a vibration motor to achieve a lighter form of feedback. In addition, the rhythm mapping can be personalized by the user to adapt to the breathing habits of different groups of people. The solution of this invention can also be applied to static scenarios, such as meditation, breathing training, rehabilitation training, etc., to improve focus and breathing control ability.

[0074] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0075] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0077] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0078] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0079] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0080] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A method for optimizing the circadian rhythm of movement based on somatosensory synchronization using smart clothing, characterized in that, include: By using sensor components embedded in smart clothing to collect human motion posture data in real time, and using time-frequency hybrid analysis to extract the main frequency and phase characteristics of the motion rhythm, the current motion type and intensity can be identified. Based on the current exercise type and intensity, the system calls the preset respiratory database to match the inspiratory-to-expiratory ratio parameter, combines phase characteristics to predict the start point of the next respiratory cycle, and generates a target respiratory rhythm template containing phase compensation. Based on the target respiratory rhythm template, a set of pneumatic tactile waveform parameters is generated. The working sequence and pressure gradient of the flexible pneumatic components of the smart clothing are controlled according to the set of pneumatic tactile waveform parameters. This forms a simulated respiratory fluctuation wave that propagates along the intercostal muscles on the human body surface, so as to guide the human body's breathing rhythm and movement rhythm to adjust synchronously.

2. The method for optimizing motion-breathing rhythm based on somatosensory synchronization according to claim 1, characterized in that, By utilizing sensor components embedded in smart clothing to collect human motion posture data in real time, and employing a time-frequency hybrid analysis method to extract the dominant frequency and phase characteristics of the motion rhythm, the current motion type and intensity are identified, including: By embedding sensor components into smart clothing, the acceleration and angular velocity signals of the user's movement are collected in real time to generate a multi-channel continuous motion data stream; The system performs time-domain periodic signal analysis on continuous motion data streams, calculates step frequency as a time-domain rhythm feature through zero-point crossing detection, synchronously captures the waveform start point of periodic signals, and generates real-time phase offset representing the temporal position within the motion cycle. Frequency domain energy spectrum analysis is performed on continuous motion data streams to extract the dominant frequency component with the largest energy proportion, and the phase angle information corresponding to the dominant frequency component is obtained by analysis. The real-time phase offset is converted into an equivalent phase angle. By comparing the difference between the equivalent phase angle and the phase angle information corresponding to the main frequency component, if the difference exceeds a preset threshold, the phase is determined to be inaccurate. Based on the difference value, the phase angle information corresponding to the main frequency component is corrected to generate noise-resistant optimized phase features. The temporal rhythm features, frequency domain dominant frequency components, and noise-resistant optimized phase features are input into the motion classifier, which matches the motion types in the preset motion type library. Based on the amplitude of the temporal rhythm features and the energy intensity of the frequency domain dominant frequency components, the current motion intensity level is determined by a predefined intensity grading rule. The sensor components include reconfigurable modular sensors. The density distribution ratio of the modular sensors is determined based on the fusion evaluation results of the contribution rate of the time-domain periodic signal variance and the proportion of the frequency-domain dominant frequency energy in the user's historical motion data.

3. The method for optimizing motion-breathing rhythm based on somatosensory synchronization using smart clothing as described in claim 2, characterized in that, Time-domain periodic signal analysis of continuous motion data streams, including calculating step frequency as a time-domain rhythmic feature through zero-point crossing detection, includes: The acceleration signal is filtered by axial component, and the acceleration component that is consistent with the direction of human motion is selected. The selected acceleration components are smoothed and filtered. Based on the amplitude range of the filtered signal waveform, the baseline threshold range for zero-point crossing is adaptively adjusted to distinguish between the effective action period and the noise fluctuation period. Capture the rising and falling edges of the filtered signal waveform that continuously cross the baseline threshold, record the timestamps of adjacent valid crossing points, and take the moment when the first rising edge crosses the baseline threshold as the start point of the valid action cycle phase. The rotational motion judgment threshold is generated synchronously based on the amplitude change of the angular velocity signal and the historical amplitude standard deviation of the angular velocity signal to identify rotational motion characteristics. If rotational motion characteristics are detected, the timing alignment correction of the effective motion cycle phase start point is performed by combining the peak point of the angular velocity signal. The effective action cycle duration formed by N consecutive effective crossings is counted. If the deviation between the durations of adjacent effective action cycles is less than the preset tolerance range, step frequency calculation is triggered. The duration of an action cycle is calculated based on the time difference between the start times of adjacent effective action cycles, and the reciprocal of the duration of the action cycle is converted into step frequency as a time-domain rhythm feature.

4. The method for optimizing motion-breathing rhythm based on somatosensory synchronization according to claim 3, characterized in that, Frequency domain energy spectrum analysis is performed on continuous motion data streams to extract the dominant frequency component with the largest energy proportion, and the phase angle information corresponding to the dominant frequency component is obtained by analysis, including: The rotational motion determination threshold is generated based on the amplitude change of the angular velocity signal and the historical amplitude standard deviation of the angular velocity signal, so as to identify the characteristics of rotational motion. If more than k rotational motion features are identified within the continuous time window of the continuous motion data stream, the continuous motion data stream is determined to be rotation-dominated, and the angular velocity signal is selected as the selected signal. If no more than k rotational motion features are identified, the continuous motion data stream is determined to be linearly dominant, and the acceleration signal is used as the selected signal. A windowed Fourier transform is performed on the selected signal to generate a complex spectrum in the frequency domain containing amplitude and phase information, and the complex spectrum is then smoothed in the frequency domain. The energy values ​​of each frequency point in the smoothed complex spectrum are traversed, and the frequency point with the largest energy proportion is selected as the dominant frequency component in the frequency domain. Phase angle information is extracted from the position of the complex spectrum corresponding to the main frequency component in the frequency domain, and combined with the effective action cycle phase start point, a time-frequency synchronization reference is generated by interpolation alignment.

5. The method for optimizing motion-breathing rhythm based on somatosensory synchronization according to claim 3, characterized in that, Based on the current exercise type and intensity, the system calls upon a preset respiratory database to match the inspiratory-to-expiratory ratio parameters, combines phase characteristics to predict the start point of the next respiratory cycle, and generates a target respiratory rhythm template including phase compensation. Based on the current exercise type and intensity level, the corresponding inspiratory-to-expiratory ratio parameter is matched from the preset breathing database; The product of the reciprocal of the real-time cadence and the target inspiratory-to-expiratory ratio parameter is converted into the duration of a respiratory cycle in milliseconds. Based on the effective action cycle phase start point and combined with the millisecond-level respiratory cycle duration, the start timestamp of the next respiratory cycle is predicted by linear interpolation. Based on the time offset between the current respiratory phase and the target time reference point, a phase compensation amount is generated using a proportional-integral algorithm. By integrating the inspiratory-to-expiratory ratio parameter, phase compensation amount, and the predicted start timestamp of the next respiratory cycle, a target respiratory rhythm template is generated.

6. The method for optimizing motion-breathing rhythm based on somatosensory synchronization using smart clothing as described in claim 5, characterized in that, Based on the target respiratory rhythm template, a set of pneumatic tactile waveform parameters is generated. The working sequence and pressure gradient of the flexible pneumatic components of the smart garment are controlled according to this set of parameters, forming simulated respiratory fluctuation waves propagating along the intercostal muscles on the human body surface. This guides the synchronized adjustment of the human breathing rhythm and movement rhythm, including: Analyze the target respiratory rhythm template and divide it into inspiratory and expiratory phases; By introducing state machine switching conditions and combining the predicted start timestamp of the next respiratory cycle, the segmented working sequence of the inspiratory and expiratory phases of the flexible airbag is generated based on the acquired intercostal muscle direction data. The timing deviation of the switching points between adjacent respiratory cycles is corrected by the phase compensation amount, so that the working timing of the airbag triggering is aligned with the actual action rhythm. Based on the inspiratory-to-expiratory ratio parameter, determine the stepwise pressure gradient during the inspiratory phase and the gradual pressure gradient during the expiratory phase; The segmented working sequence of the inspiratory and expiratory phases, the stepped pressure increase gradient of the inspiratory phase, and the slow pressure decrease gradient of the expiratory phase are used as a set of pneumatic tactile waveform parameters to drive the flexible pneumatic components. During the driving process of the flexible pneumatic unit, the duration of the respiratory cycle is dynamically compressed or extended based on the real-time acquired user motion acceleration and angular velocity, and the rate of change of the step-by-step pressure gradient in the inspiratory phase and the slow-fall pressure gradient in the expiratory phase are adjusted according to a preset ratio.

7. The method for optimizing motion-breathing rhythm based on somatosensory synchronization using smart clothing as described in claim 6, characterized in that, State machine transition conditions include: A two-state machine is used to control the switching of inhalation and exhalation phases. If the current phase is maintained for more than half the duration of the respiratory cycle, it will automatically switch to the opposite phase. After the phase switch, the timer will be reset immediately and the duration of the next respiratory cycle will be replanned.

8. A motion-breathing rhythm optimization system based on smart clothing with synchronized somatosensory perception, characterized in that, include: The preliminary processing module is used to collect human motion posture data in real time using sensor components embedded in smart clothing, and to extract the main frequency and phase characteristics of the motion rhythm using a time-frequency hybrid analysis method to identify the current motion type and intensity. The rhythm determination module is used to call the preset respiratory database to match the inspiratory-to-expiratory ratio parameters according to the current exercise type and intensity, combine phase characteristics to predict the start point of the next respiratory cycle, and generate a target respiratory rhythm template containing phase compensation. The guidance and adjustment module is used to generate a set of pneumatic tactile waveform parameters based on the target respiratory rhythm template. The working sequence and pressure gradient of the flexible pneumatic components of the smart clothing are controlled according to the set of pneumatic tactile waveform parameters to form a simulated respiratory fluctuation wave that propagates along the intercostal muscles on the human body surface, so as to guide the human body's breathing rhythm and movement rhythm to adjust synchronously.

9. A smart garment, characterized in that, include: Flexible integrated carrier; The sensor assembly includes modular sensors arranged in at least one part of a flexible integrated carrier. The density distribution ratio of the modular sensors is determined based on the fusion evaluation results of the contribution rate of the variance of the time-domain periodic signal and the proportion of the frequency-domain dominant frequency energy in the user's historical motion data. The flexible pneumatic component includes a flexible airbag and an air duct mounted on a flexible integrated carrier, with the flexible airbag arranged along the direction of the intercostal muscles. In addition, an integrated control component is set on a flexible integrated carrier and is connected to the sensor component, the flexible pneumatic component and the preset memory respectively. The integrated control component includes: a micro air pump, a solenoid valve, a controller, a built-in sensor component and a lithium battery component. The micro air pump and the solenoid valve constitute a pneumatic drive unit, which forms a pneumatic circuit with the flexible airbag through the air guide tube. The controller is connected to the solenoid valve, the built-in sensor component and the lithium battery component respectively. The memory stores instructions that can be executed by the controller, which are then executed by the controller to enable the controller to perform the motion-breathing rhythm optimization method based on somatosensory synchronization as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer-executable instructions thereon, characterized in that, When the executable instructions are executed by the controller, they implement the motion and breathing rhythm optimization method based on somatosensory synchronization as described in any one of claims 1-7.

Images