Control method of self-adaptive respiratory training system and training system

Abstract

The invention discloses a control method of a self-adaptive respiratory training system and the training system. The method comprises the steps that a motion signal and a respiratory signal of a user are collected; determining a training protocol of the user according to the motion signal; according to the breathing signal and the protocol type of the training protocol, training parameters of the training protocol are dynamically adjusted, and initial training parameters are determined; determining whether a triggering result of event judgment is triggered or not according to the breathing signal; according to the motion signal, the breathing signal and the triggering result, determining an event type for indicating that the physiological state of the user changes; and dynamically adjusting the initial training parameter according to the event type, and determining a target training parameter for controlling the training system. According to the invention, control can be carried out based on the motion state, the physiological state and the event type triggering the change of the physiological state of the user so as to adapt to the demand difference of the user in different states.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a control method and training system for an adaptive breathing training system. Background Technology

[0002] An electronically adjustable breathing training system is a medical rehabilitation device that trains respiratory muscles by adjusting inspiratory resistance. However, existing electronic breathing training systems have the following main problems in real-world use: 1. The equipment is usually controlled with the goal of increasing training intensity, and lacks a real-time, proactive safety monitoring mechanism for the user's physiological state, which is especially unsuitable for specific groups with weak cardiopulmonary function; 2. Unable to sense the user's exercise state and unable to automatically adjust the training mode according to the physiological needs of different states, resulting in training interruption or poor experience; 3. It is easy to misjudge the physiological state due to the user's non-training actions, which may cause unnecessary interruption of the training process and affect the continuity and convenience of use.

[0003] Therefore, existing electronic breathing training systems cannot control based on the user's exercise state, physiological state, and the types of events that trigger changes in physiological state, and cannot adapt to the different needs of users in different states. Summary of the Invention

[0004] In order to overcome the shortcomings of the prior art, the present invention aims to provide a control method and training system for an adaptive breathing training system, which can be controlled based on the user's exercise state, physiological state and the types of events that trigger changes in physiological state, so as to adapt to the user's different needs in different states.

[0005] This invention is implemented according to the following scheme: A control method for an adaptive breathing training system is provided, including: Collect the user's motion and respiratory signals; The user's training protocol is determined based on the motion signals; Based on the respiratory signal and the protocol type of the training protocol, the training parameters of the training protocol are dynamically adjusted to determine the initial training parameters; Based on the respiratory signal, determine whether the event judgment trigger result is triggered; Based on the motion signal, the breathing signal, and the triggering result, determine the type of event used to indicate a change in the user's physiological state; Based on the event type, the initial training parameters are dynamically adjusted to determine the target training parameters used to control the training system.

[0006] Compared with the prior art, the beneficial effects of the control method of the adaptive breathing training system of the present invention are as follows: the training protocol when the user uses the training system is determined based on the motion signal that reflects the user's motion state, and the training parameters of the training protocol are adjusted based on the breathing signal that reflects the user's physiological state. The event type that triggers the change of the user's physiological state is determined in combination with the motion signal, so as to realize control based on the user's motion state, physiological state and event type that triggers the change of physiological state, thereby adapting to the user's different needs in different states.

[0007] Optionally, based on the motion signal, determining the user's training protocol includes: Based on the motion signal, determine the signal variance of the motion signal; Frequency domain analysis is performed on the motion characteristics to determine the periodic pattern of the motion signal; The training protocol is determined based on the signal variance and the periodic pattern.

[0008] Optionally, the training protocol includes a first training protocol and a second training protocol; Determining the training protocol based on the signal variance and the periodic pattern includes: When the signal variance is less than a first preset threshold and the periodic pattern is without gait period, the training protocol is a first training protocol for static activities. When the signal variance is greater than a second preset threshold and the periodic pattern is a gait period, the training protocol is a second training protocol for dynamic activities.

[0009] Optionally, based on the respiratory signal and the protocol type of the training protocol, the training parameters of the training protocol are dynamically adjusted to determine the initial training parameters, including: Frequency extraction is performed on the respiratory signal to determine the respiratory frequency. When the respiratory rate is less than or equal to the safety threshold, the training parameters of the training protocol are used as the initial training parameters. When the breathing rate is greater than the safety threshold, the training parameters of the training protocol are dynamically adjusted according to the protocol type of the training protocol to determine the initial training parameters.

[0010] Optionally, the protocol type includes a first protocol type and a second protocol type; When the respiratory rate exceeds the safety threshold, the training parameters of the training protocol are dynamically adjusted according to the protocol type of the training protocol to determine the initial training parameters, including: When the protocol type is the first protocol type, the training parameters are linearly reduced by a preset decreasing value to determine the initial training parameters; When the protocol type is the second protocol type, a dynamic decrease value is determined according to the training parameters of the training protocol, and the training parameters are reduced in a stepwise manner using the dynamic decrease value to determine the initial training parameters.

[0011] Optionally, based on the respiratory signal, determine whether to trigger the event judgment result, including: Based on the respiratory signal, determine the instantaneous value of the respiratory signal; When the instantaneous value is less than the dynamic artifact threshold, the triggering result is a decision not to trigger the event. When the instantaneous value is greater than or equal to the dynamic artifact threshold, the triggering result is a triggering event judgment.

[0012] Optionally, based on the motion signal, the breathing signal, and the triggering result, a type of event used to indicate a change in the user is determined, including: When the trigger is determined to be a trigger event, feature extraction is performed on the motion signal and the breathing signal to obtain motion features and breathing features; The event type is determined based on the described motion and breathing characteristics.

[0013] Optionally, the motion features include local change features and drastic change features, the respiratory features include extremely high peak features and moderate change features, and the event types include physiological artifact interference events and state switching events. Based on the described motion characteristics and respiratory characteristics, the event type is determined, including: When the motion feature is a local variation feature and the breathing feature is an extremely high peak feature, the event type is a physiological artifact interference event; When the motion feature is a drastic change feature and the breathing feature is a moderate change feature, the event type is a state switching event.

[0014] Optionally, based on the event type, the initial training parameters are dynamically adjusted to determine the target training parameters used to control the training system, including: When the event type is a physiological artifact interference event, the initial training parameters are adjusted to preset training parameters. After the training device is controlled with the preset training parameters for a preset training time, the initial training parameters are used as the target training parameters. When the event type is a state switching event, the user's training protocol and the initial training parameters determined based on the training protocol are redefined, and the initial training parameters are used as the target training parameters.

[0015] An adaptive breathing training system is also provided, which is controlled using the control method of the aforementioned adaptive breathing training system, including: Motion sensing module, used to collect the user's motion signals; The respiratory sensing module is used to collect the user's breathing signals; The main controller is used to determine the target training parameters based on the motion signal and the breathing signal; The resistance adjustment module is used to output the resistance when the user uses the device, based on the target training parameters. Attached Figure Description

[0016] Figure 1 This is a flowchart of the control method of the present invention. Detailed Implementation

[0017] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0018] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0019] See Figure 1 As shown, a control method for an adaptive breathing training system according to the present invention includes: S1: Collects the user's motion and breathing signals; the motion signals include three-axis acceleration and three-axis angular velocity data, and the attitude angle is obtained by fusing the three-axis acceleration and three-axis angular velocity. It is multi-dimensional inertial data, which not only includes acceleration, but also angular velocity and attitude information, and can more comprehensively represent the user's motion state when using the training system; the breathing signals include the user's breathing frequency when using the training system for training.

[0020] S2: Determine the user's training protocol based on the motion signal, including: determining the signal variance of the motion signal; performing frequency domain analysis on the motion features to determine the periodicity pattern of the motion signal; and determining the training protocol based on the signal variance and the periodicity pattern.

[0021] This invention detects the presence of gait cycles in motion signals by combining acceleration variance and frequency domain analysis, which can more accurately distinguish between static and dynamic activities. At the same time, through multi-dimensional motion signals, it can accurately identify the user's motion state in complex scenarios, and further match more accurate training protocols for the user.

[0022] In one embodiment of the present invention, frequency domain analysis of motion characteristics is performed to determine the periodic pattern of the motion signal, including: performing a fast Fourier transform on the vertical axis acceleration in the motion signal to obtain the power spectrum, so as to obtain the energy distribution of the motion signal at different frequencies; then, within a typical walking frequency range (e.g., 0.5-3.0Hz), if a significant single main peak appears in the power spectrum and its energy is significantly higher than the noise floor, it is determined that there is a significant and stable gait period, that is, the periodic pattern is a gait period; and the frequency corresponding to the main peak in the power spectrum is the step frequency; finally, the activity scenario is determined based on the energy peak of the power spectrum at the octave. For example, harmonic features such as both feet touching the ground in gait will show a secondary peak at the octave (e.g., twice the step frequency) to further confirm the user's activity scenario.

[0023] In one embodiment of the present invention, the training protocol includes a first training protocol and a second training protocol; determining the training protocol based on the signal variance and periodicity pattern includes: when the signal variance is less than a first preset threshold and the periodicity pattern is without gait period, the training protocol is a first training protocol for static activities; when the signal variance is greater than a second preset threshold and the periodicity pattern is gait period, the training protocol is a second training protocol for dynamic activities.

[0024] In one embodiment of the present invention, the first preset threshold is less than the second preset threshold to establish a hysteresis interval. When the motion intensity increases from low to high, it must exceed the higher second preset threshold to be determined as the user being in dynamic activity, preventing false triggering due to brief jitter. When the motion intensity decreases from high to low, it must fall below the lower first preset threshold to be determined as the user being in static activity, preventing frequent mode switching when the intensity fluctuates, and effectively enhancing the stability of the control of the training system.

[0025] In one embodiment of the present invention, when the user is identified as being in a static or low-intensity activity by the signal variance and periodic pattern, a first training protocol is used to apply a constant or slowly varying resistance control mode to the training system; for example, providing a constant base resistance to the training system, or slowly cycling according to a preset breathing rhythm, to perform basic lung function training or relaxation for the user.

[0026] In one embodiment of the present invention, when the periodic pattern is the gait cycle, the vertical axis acceleration in the motion signal is filtered and peak detection is performed to calculate the peak value per unit time to obtain the user's supplement. Then, it is detected whether the vertical axis acceleration has a significant pulse peak synchronized with the gait frequency to determine the user's activity scenario. Based on the activity scenario and gait cycle, the training parameters of the second training protocol are determined. The training parameters include breathing frequency and resistance curve parameters, thereby realizing adaptive adjustment of the training system according to the user's movement state to achieve better training results.

[0027] When the signal variance and periodic patterns identify that the user is engaged in dynamic activities such as walking or running, a second training protocol is used to control the training system to synchronize the resistance of the training system with the detected real-time gait cycle. For example, at the beginning of the gait swing phase (foot off the ground), the inspiratory phase resistance is triggered, and the training system is controlled to provide higher resistance to the user, simulating the deep inhalation needs under climbing or weight-bearing conditions. At the beginning of the gait support phase (foot on the ground), the expiratory phase resistance is triggered, and the training system is controlled to switch to providing lower resistance to the user, promoting deep exhalation. The resistance magnitude can be proportionally adjusted according to the real-time calculated cadence or exercise intensity. For example, the faster the cadence, the slightly higher the peak inspiratory resistance, achieving training parameters that match the exercise intensity.

[0028] S3: Based on the respiratory signal and the protocol type of the training protocol, dynamically adjust the training parameters of the training protocol to determine the initial training parameters, including: extracting the frequency of the respiratory signal to determine the respiratory frequency; when the respiratory frequency is less than or equal to the safety threshold, use the training parameters of the training protocol as the initial training parameters; when the respiratory frequency is greater than the safety threshold, dynamically adjust the training parameters of the training protocol according to the protocol type of the training protocol to determine the initial training parameters.

[0029] In one embodiment of the present invention, the method further includes determining a security threshold, including: Based on clinical medical experience and physiological statistics of the target population, the upper limit of safe respiratory rate for healthy adults and specific rehabilitation groups (such as COPD patients) during moderate-intensity exercise is taken as the safe threshold. Alternatively, based on the user's recent training history data, which includes the user's average and peak respiratory rates under different exercise intensities and training protocols, a baseline model of the user's exercise intensity and respiratory rate is established. Finally, the product of the baseline peak frequency and the safety factor is used as the safety threshold, with the safety factor ranging from 1.2 to 1.3, or the percentile of the historical peak frequency is used as the safety threshold, with the percentile value including but not limited to 95%.

[0030] In the process of determining the safety threshold, if the user is in the initial training stage or is a new user with insufficient historical data, a conservative safety threshold is adopted to ensure the safety of the user when using the training system; for example, the safety threshold is set to greater than or equal to 30 times / minute; if the user uses the training system and accumulates enough personal historical data, the safety threshold can be determined based on the user's historical data to achieve more accurate control that is tailored to individual abilities.

[0031] In one embodiment of the present invention, the protocol type includes a first protocol type and a second protocol type; when the respiratory rate is greater than a safety threshold, the training parameters of the training protocol are dynamically adjusted according to the protocol type of the training protocol to determine the initial training parameters, including: when the protocol type is the first protocol type, the training parameters are linearly reduced by a preset decreasing value to determine the initial training parameters; when the protocol type is the second protocol type, a dynamic decreasing value is determined according to the training parameters of the training protocol, and the training parameters are reduced in a stepwise manner by the dynamic decreasing value to determine the initial training parameters.

[0032] The training protocol types are as follows: the first training protocol corresponds to the first protocol type, and the second training protocol corresponds to the second protocol type. If it is the first protocol type (first training protocol), the real-time resistance of the training system is controlled to decrease linearly to the preset minimum resistance within a preset time. The preset decrease value is determined based on the initial resistance of the training system, the preset time, and the preset minimum resistance, so that the training system can output resistance at a constant or slowly changing speed to avoid danger to the user when using the training system. If it is the second protocol type (second training protocol), the synchronization between the second training protocol and the gait cycle obtained by motion signal detection is first desynchronized, and the resistance peak and resistance valley values ​​within the current gait cycle are stepped down to the preset minimum value within the preset gait cycle. The dynamic decrease value is determined based on the resistance peak, resistance valley value, preset gait cycle, and preset minimum value. That is, the initial training parameters of this invention are all preset minimum values.

[0033] In one embodiment of the present invention, when the user's breathing rate is detected to have recovered to a safe threshold and stabilized for a preset time, the control training system resumes the training protocol used last time.

[0034] S4: Based on the respiratory signal, determine whether to trigger the event judgment, including: based on the respiratory signal, determine the instantaneous value of the respiratory signal; when the instantaneous value is less than the dynamic artifact threshold, the trigger result is not to trigger the event judgment; when the instantaneous value is greater than or equal to the dynamic artifact threshold, the trigger result is to trigger the event judgment.

[0035] S5: Based on motion signals, respiratory signals, and trigger results, determine the event type used to indicate changes in the user's physiological state, including: when the trigger is determined to be a trigger event, extract features from the motion signals and respiratory signals to obtain motion features and respiratory features; and determine the event type based on the motion features and respiratory features.

[0036] In one embodiment of the present invention, motion features include local change features and drastic change features, respiratory features include extremely high peak features and moderate change features, and event types include physiological artifact interference events and state switching events; the event type is determined based on motion features and respiratory features, including: when the motion feature is a local change feature and the respiratory feature is an extremely high peak feature, the event type is a physiological artifact interference event; when the motion feature is a drastic change feature and the respiratory feature is a moderate change feature, the event type is a state switching event.

[0037] S6: Based on the event type, dynamically adjust the initial training parameters to determine the target training parameters used to control the training system, including: when the event type is a physiological artifact interference event, adjust the initial training parameters to the preset training parameters, and after the preset training time is reached by controlling the training device with the preset training parameters, use the initial training parameters as the target training parameters; when the event type is a state switching event, redetermine the user's training protocol and the initial training parameters determined based on the training protocol, and use the initial training parameters as the target training parameters.

[0038] In this invention, the physiological artifact interference event indicates that when a user's motion and respiratory signals change and the training parameters need to be adjusted, the change is due to physiological phenomena such as coughing, not because the user is using the training system. In this case, this set of motion and respiratory signals is removed to avoid a decrease in the accuracy of subsequent control of the training system using historical data. The state switching event indicates that when a user's motion and respiratory signals change and the training parameters need to be adjusted, the change is due to the user using the training system, not because of physiological phenomena such as coughing. In this case, the user's physiological and activity states are re-determined to readjust the training protocol for the user's use of the training system.

[0039] This invention adjusts training parameters based on event types, which can effectively reduce frequent adjustments or unnecessary training interruptions when users use the training system, and improve the robustness of the training system in complex environments and the user experience.

[0040] An adaptive breathing training system of the present invention is controlled by the control method of the aforementioned adaptive breathing training system, comprising: Motion sensing module, used to collect the user's motion signals; The respiratory sensing module is used to collect the user's breathing signals; The main controller is used to determine the target training parameters based on motion and breathing signals; The resistance adjustment module is used to output the resistance when the user uses the device, based on the target training parameters.

[0041] This invention determines the training protocol when a user uses the training system based on motion signals that reflect the user's motion state, and adjusts the training parameters of the training protocol based on breathing signals that reflect the user's physiological state. It also combines motion signals to determine the types of events that trigger changes in the user's physiological state, thereby enabling control of the training system based on the user's motion state, physiological state, and the types of events that trigger changes in physiological state. This allows for better adaptation to the user's different needs under different conditions.

[0042] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for an adaptive breathing training system, characterized in that, include: Collect the user's motion and respiratory signals; The user's training protocol is determined based on the motion signals; Based on the respiratory signal and the protocol type of the training protocol, the training parameters of the training protocol are dynamically adjusted to determine the initial training parameters; Based on the respiratory signal, determine whether the event judgment trigger result is triggered; Based on the motion signal, the breathing signal, and the triggering result, determine the type of event used to indicate a change in the user's physiological state; Based on the event type, the initial training parameters are dynamically adjusted to determine the target training parameters used to control the training system.

2. The control method for an adaptive breathing training system according to claim 1, characterized in that, Determining the user's training protocol based on the motion signal includes: Based on the motion signal, determine the signal variance of the motion signal; Frequency domain analysis is performed on the motion characteristics to determine the periodic pattern of the motion signal; The training protocol is determined based on the signal variance and the periodic pattern.

3. The control method for an adaptive breathing training system according to claim 2, characterized in that, The training protocol includes a first training protocol and a second training protocol; Determining the training protocol based on the signal variance and the periodic pattern includes: When the signal variance is less than a first preset threshold and the periodic pattern is without gait period, the training protocol is a first training protocol for static activities. When the signal variance is greater than a second preset threshold and the periodic pattern is a gait period, the training protocol is a second training protocol for dynamic activities.

4. The control method for an adaptive breathing training system according to claim 1, characterized in that, Based on the respiratory signal and the protocol type of the training protocol, the training parameters of the training protocol are dynamically adjusted to determine the initial training parameters, including: Frequency extraction is performed on the respiratory signal to determine the respiratory frequency. When the respiratory rate is less than or equal to the safety threshold, the training parameters of the training protocol are used as the initial training parameters. When the breathing rate is greater than the safety threshold, the training parameters of the training protocol are dynamically adjusted according to the protocol type of the training protocol to determine the initial training parameters.

5. The control method for an adaptive breathing training system according to claim 4, characterized in that, The protocol types include a first protocol type and a second protocol type; When the respiratory rate exceeds the safety threshold, the training parameters of the training protocol are dynamically adjusted according to the protocol type of the training protocol to determine the initial training parameters, including: When the protocol type is the first protocol type, the training parameters are linearly reduced by a preset decreasing value to determine the initial training parameters; When the protocol type is the second protocol type, a dynamic decrease value is determined according to the training parameters of the training protocol, and the training parameters are reduced in a stepwise manner using the dynamic decrease value to determine the initial training parameters.

6. The control method for an adaptive breathing training system according to claim 1, characterized in that, Based on the respiratory signal, determine whether the event judgment trigger result is triggered, including: Based on the respiratory signal, determine the instantaneous value of the respiratory signal; When the instantaneous value is less than the dynamic artifact threshold, the triggering result is a decision not to trigger the event. When the instantaneous value is greater than or equal to the dynamic artifact threshold, the triggering result is a triggering event judgment.

7. The control method for an adaptive breathing training system according to claim 1, characterized in that, Based on the motion signal, the breathing signal, and the triggering result, determine the event type used to indicate a change in the user, including: When the trigger is determined to be a trigger event, feature extraction is performed on the motion signal and the breathing signal to obtain motion features and breathing features; The event type is determined based on the described motion and breathing characteristics.

8. The control method for an adaptive breathing training system according to claim 7, characterized in that, The motion characteristics include local change characteristics and drastic change characteristics; the respiratory characteristics include extremely high peak characteristics and moderate change characteristics; the event types include physiological artifact interference events and state switching events. Based on the described motion characteristics and respiratory characteristics, the event type is determined, including: When the motion feature is a local variation feature and the breathing feature is an extremely high peak feature, the event type is a physiological artifact interference event; When the motion feature is a drastic change feature and the breathing feature is a moderate change feature, the event type is a state switching event.

9. The control method for an adaptive breathing training system according to claim 7, characterized in that, Based on the event type, the initial training parameters are dynamically adjusted to determine the target training parameters used to control the training system, including: When the event type is a physiological artifact interference event, the initial training parameters are adjusted to preset training parameters. After the training device is controlled with the preset training parameters for a preset training time, the initial training parameters are used as the target training parameters. When the event type is a state switching event, the user's training protocol and the initial training parameters determined based on the training protocol are redefined, and the initial training parameters are used as the target training parameters.

10. An adaptive breathing training system, controlled by the control method of any one of claims 1-9, characterized in that, include: Motion sensing module, used to collect the user's motion signals; The respiratory sensing module is used to collect the user's breathing signals; The main controller is used to determine the target training parameters based on the motion signal and the breathing signal; The resistance adjustment module is used to output the resistance when the user uses the device, based on the target training parameters.

Images