Respiration monitoring method, device and readable storage medium

Abstract

The present application relates to a respiratory monitoring method, device and readable storage medium. The method includes: obtaining a first motion signal sampled by an IMU sensor, and obtaining a first PPG signal sampled by a PPG sensor; calculating the blood oxygen content based on the first motion signal and the first PPG signal; optimizing the parameters of the first sampling controller based on the blood oxygen content; predicting the first respiratory characteristic value in the next respiratory cycle based on the first motion signal and the first PPG signal; optimizing the parameters of the second sampling controller based on the first respiratory characteristic value; obtaining a second motion signal based on the optimized first sampling controller, and obtaining a second PPG signal based on the optimized second sampling controller; determining the index value of the physiological index related to breathing of the monitored object based on the second motion signal and the second PPG signal. The use of this method can improve the accuracy of the signal sampled by the sensor.

Description

Technical Field

[0001] The present application relates to the field of physiological indicator monitoring, and in particular to a respiratory monitoring method, device and readable storage medium. Background Art

[0002] With the development of physiological indicator monitoring technology, respiratory monitoring technology has emerged, which mainly monitors respiratory function through respiration and blood oxygen.

[0003] In traditional technology, the respiratory characteristic value corresponding to breathing is estimated by the motion signal sampled by the IMU (Inertial Measurement Unit) sensor; the blood oxygen content corresponding to blood oxygen is estimated by the motion signal and the PPG (Photo Plethysmo Graphy) sensor. Among them, when the sensor samples the signal, it is controlled by the corresponding sampling controller with fixed sampling parameters.

[0004] However, the respiratory characteristic value and the blood oxygen content generally change dynamically. Controlling the sensor to sample the corresponding signals with fixed sampling parameters will result in low accuracy of the corresponding signals obtained by sampling. Summary of the invention

[0005] Based on this, it is necessary to provide a respiratory monitoring method, device and readable storage medium that can improve the accuracy of the signal sampled by the sensor to address the above technical problems.

[0006] In a first aspect, the present application provides a respiratory monitoring method, comprising:

[0007] Acquire a first motion signal sampled by an IMU sensor, and acquire a first PPG signal sampled by a PPG sensor; the IMU sensor is controlled by a first sampling controller with a first sampling parameter, and the PPG sensor is controlled by a second sampling controller with a second sampling parameter;

[0008] Calculate the blood oxygen content based on the first motion signal and the first PPG signal;

[0009] Optimizing parameters of the first sampling controller based on the blood oxygen content;

[0010] Based on the first motion signal and the first PPG signal, predict a first respiratory signal characteristic value in a next respiratory cycle and a first time interval of a relatively static respiratory motion;

[0011] Optimizing parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval;

[0012] Based on the optimized first sampling controller, the IMU sensor is controlled to sample to obtain a second motion signal, and based on the optimized second sampling controller, the PPG sensor is controlled to sample to obtain a second PPG signal;

[0013] An indicator value of a physiological indicator related to breathing of the monitored object is determined based on the second motion signal and the second PPG signal.

[0014] In one embodiment, calculating the blood oxygen content based on the first motion signal and the first PPG signal includes:

[0015] Determine, based on the first motion signal, a second time interval of a respiratory motion in a current respiratory cycle when the respiratory motion is relatively static;

[0016] fusing the second time interval and the first PPG signal;

[0017] The blood oxygen content is determined based on the fused first PPG signal.

[0018] In one embodiment, the optimizing the parameters of the first sampling controller based on the blood oxygen content includes:

[0019] Obtaining a first target value range of the blood oxygen content by matching at least two first preset value ranges;

[0020] Obtaining a first target sampling parameter group corresponding to the first target numerical range by matching at least two first preset sampling parameter groups;

[0021] Parameters of the first sampling controller are optimized based on the first target sampling parameter group.

[0022] In one embodiment, predicting the first respiratory signal characteristic value in the next respiratory cycle and the first time interval of the respiratory motion when it is relatively static based on the first motion signal and the first PPG signal includes:

[0023] Determine, based on the first motion signal, a second time interval when the respiratory motion in the current respiratory cycle is relatively static, and a second respiratory signal characteristic value of the previous respiratory cycle and a third time interval when the respiratory motion is relatively static;

[0024] fusing the second time interval and the first PPG signal;

[0025] determining a heart rate value based on the fused first PPG signal;

[0026] Predicting a first time interval of a relatively static respiratory movement in a next respiratory cycle based on the heart rate value and the third time interval;

[0027] The first respiratory signal characteristic value in the next respiratory cycle is predicted based on the heart rate value, the blood oxygen content and the second respiratory signal characteristic value.

[0028] In one embodiment, the optimizing the parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval includes:

[0029] Obtaining a second target value range corresponding to the first respiratory signal characteristic value and the first time interval by matching at least two second preset value ranges;

[0030] Obtaining a second target sampling parameter group corresponding to the second target numerical range by matching at least two second preset sampling parameter groups;

[0031] Parameter optimization is performed on the second sampling controller based on the second target sampling parameter group.

[0032] In one embodiment, the second target sampling parameter group includes at least a second sampling frequency and a second sampling resolution, and the parameter optimization of the second sampling controller based on the first respiratory signal characteristic value and the first time interval includes:

[0033] determining the second sampling resolution based on the first breathing signal characteristic value;

[0034] comparing the first time interval with the third time interval;

[0035] If the first time interval is greater than the third time interval, the second sampling frequency is reduced.

[0036] In a second aspect, the present application further provides a respiratory monitoring device, the device comprising a processor, an IMU sensor, a first sampling controller, a PPG sensor, and a second sampling controller;

[0037] The IMU sensor is used to sample and obtain a first motion signal;

[0038] The first sampling controller is used to control the IMU sensor to perform sampling with a first sampling parameter;

[0039] The PPG sensor is used to sample and obtain a first PPG signal;

[0040] The second sampling controller is used to control the PPG sensor to perform sampling with a second sampling parameter;

[0041] The processor is used to execute the steps of the above method.

[0042] In one embodiment, the device further comprises an electrode;

[0043] The electrode is used to output current to intervene in the sleep breathing state of the monitored object when the evaluation result of the sleep breathing quality meets the preset intervention condition; wherein the evaluation result includes the predicted respiratory movement.

[0044] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0045] Acquire a first motion signal sampled by an IMU sensor, and acquire a first PPG signal sampled by a PPG sensor; the IMU sensor is controlled by a first sampling controller with a first sampling parameter, and the PPG sensor is controlled by a second sampling controller with a second sampling parameter;

[0046] Calculate the blood oxygen content based on the first motion signal and the first PPG signal;

[0047] Optimizing parameters of the first sampling controller based on the blood oxygen content;

[0048] Based on the first motion signal and the first PPG signal, predict a first respiratory signal characteristic value in a next respiratory cycle and a first time interval of a relatively static respiratory motion;

[0049] Optimizing parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval;

[0050] Based on the optimized first sampling controller, the IMU sensor is controlled to sample to obtain a second motion signal, and based on the optimized second sampling controller, the PPG sensor is controlled to sample to obtain a second PPG signal;

[0051] An indicator value of a physiological indicator related to breathing of the monitored object is determined based on the second motion signal and the second PPG signal.

[0052] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0053] Acquire a first motion signal sampled by an IMU sensor, and acquire a first PPG signal sampled by a PPG sensor; the IMU sensor is controlled by a first sampling controller with a first sampling parameter, and the PPG sensor is controlled by a second sampling controller with a second sampling parameter;

[0054] Calculate the blood oxygen content based on the first motion signal and the first PPG signal;

[0055] Optimizing parameters of the first sampling controller based on the blood oxygen content;

[0056] Based on the first motion signal and the first PPG signal, predict a first respiratory signal characteristic value in a next respiratory cycle and a first time interval of a relatively static respiratory motion;

[0057] Optimizing parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval;

[0058] Based on the optimized first sampling controller, the IMU sensor is controlled to sample to obtain a second motion signal, and based on the optimized second sampling controller, the PPG sensor is controlled to sample to obtain a second PPG signal;

[0059] An indicator value of a physiological indicator related to breathing of the monitored object is determined based on the second motion signal and the second PPG signal.

[0060] The above-mentioned respiratory monitoring method, device and readable storage medium optimize the parameters of the first sampling controller and the second sampling controller by sampling the first motion signal and the first PPG signal, and then obtain the second motion signal and the second PPG signal based on the optimized first sampling controller and the second sampling controller respectively, and use them to evaluate the sleep breathing quality of the monitored object to achieve respiratory monitoring. The above-mentioned method realizes the optimization of sampling parameters based on respiratory movement and blood oxygen content, so that the sampling controller can dynamically adjust the sampling parameters of the control sensor when sampling according to the characteristic value of the first respiratory signal, the first time interval and the blood oxygen content, so that the optimized sampling controller is more suitable for the upcoming sampling control, thereby improving the accuracy of the signal obtained by sensor sampling. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A schematic diagram of a respiratory monitoring method according to an embodiment;

[0063] Figure 2 is a schematic diagram of a respiratory motion (left) and a motion signal (right) in one embodiment;

[0064] Figure 3is a schematic diagram of a motion signal in another embodiment;

[0065] Figure 4 is a schematic diagram of a PPG signal in one embodiment;

[0066] Figure 5 is a schematic diagram of a PPG signal in another embodiment;

[0067] Figure 6 is a flow chart of a respiratory monitoring method in another embodiment;

[0068] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0070] The respiratory monitoring method provided in the embodiment of the present application can be applied to a respiratory monitoring device, which can be a medical respiratory monitor, a tongue muscle stimulator, or a hypoglossal nerve stimulator.

[0071] The respiratory monitoring device includes a processor, an IMU sensor, a first sampling controller, a PPG sensor and a second sampling controller; the IMU sensor is used to sample and obtain a first motion signal; the first sampling controller is used to control the IMU sensor to sample with a first sampling parameter; the PPG sensor is used to sample and obtain a first PPG signal; the second sampling controller is used to control the PPG sensor to sample with a second sampling parameter; the processor is used to control the first sampling controller, the second sampling controller, and process the first motion signal and the first PPG signal.

[0072] In one embodiment, the respiratory monitoring device also includes an electrode; the electrode is used to output current to intervene in the sleep respiratory state of the monitored object when the evaluation result of the sleep respiratory quality meets the preset intervention condition; wherein the evaluation result includes the predicted respiratory movement.

[0073] The evaluation result may be of high quality or low quality, and accordingly, the preset intervention condition is that the evaluation result is of low quality. That is, when the sleep breathing quality is of low quality, the preset intervention condition is met, and at this time, the electrode output current can be controlled to improve the sleep breathing quality.

[0074] It should be noted that the electrode achieves the purpose of intervening in breathing during sleep by stimulating the tongue muscle or the hypoglossal nerve. Specifically, the tongue muscle or the hypoglossal nerve is stimulated to cause the movement of the tongue, thereby relieving the upper airway obstruction and improving the quality of sleeping breathing.

[0075] It should be noted that since the evaluation results include predicted respiratory movements, sleep breathing intervention can be carried out in advance, thereby avoiding intervention when the quality of sleep breathing is actually monitored to be low, thereby improving the timeliness of intervention.

[0076] In an exemplary embodiment, Figure 1 As shown, a respiratory monitoring method is provided, which is described by taking the method applied to a respiratory monitoring device as an example, and includes the following steps 102 to 108. Among them:

[0077] Step 102, obtaining a first motion signal sampled by an IMU sensor, and obtaining a first PPG signal sampled by a PPG sensor; the IMU sensor is controlled by a first sampling controller with a first sampling parameter, and the PPG sensor is controlled by a second sampling controller with a second sampling parameter.

[0078] The sampling parameters include but are not limited to sampling time, sampling frequency and sampling resolution. Sampling resolution refers to sampling intensity, which affects the accuracy of the signal, and the two are positively correlated.

[0079] Among them, the motion signal is used to determine the respiratory characteristic value. When the monitored object performs respiratory movement, the chest movement will be driven, that is, the respiratory movement can at least be represented by the chest movement angle β. The respiratory movement includes exhalation movement and inhalation movement, such as Figure 2 As shown, when the monitored subject performs an exhalation movement, the chest movement angle β changes from large to small, that is, changes from the inhalation saturation area to the exhalation completion area; when the monitored subject performs an inhalation movement, the chest movement angle β changes from small to large, that is, changes from the exhalation saturation area to the inhalation completion area. It can be understood that the chest movement angle β changes periodically with the periodic breathing movement of the monitored subject.

[0080] The respiratory characteristic values ​​include respiratory signal characteristic values ​​and a time interval of a relatively static respiratory movement, and the respiratory signal characteristic values ​​include but are not limited to amplitude, period and phase.

[0081] Among them, the IMU sensor is a sensor that integrates an accelerometer and a gyroscope, which is used to accurately measure and monitor information such as the acceleration, angular velocity, and direction of an object. The acceleration, angular velocity, and direction information can be used to generate motion signals.

[0082] Among them, the PPG sensor is a sensor that uses optical technology to measure changes in blood volume. It can collect PPG signals for detecting changes in the intensity of reflected light from the blood, thereby obtaining heart rate values, blood oxygen content, and respiratory characteristic values ​​corresponding to heart rate, blood oxygen, and respiration, including but not limited to heart rate, blood oxygen, and respiration, respectively. Among them, heart rate, blood oxygen, and respiration are physiological indicators.

[0083] Exemplarily, the measurement principle of the PPG signal collected by the PPG sensor is related to the reflection of light by cells in the blood. When there are more blood oxygen cells in the blood, the reflected light is strong, that is, the reflected signal is strong, and when there are fewer blood oxygen cells in the blood vessels, the reflected light is weak, that is, the reflected signal is weak. It can be understood that the number of blood oxygen cells in the blood is related to respiratory movement, that is, during the inhalation movement, the blood oxygen cells will increase accordingly, and during the exhalation movement, the blood oxygen cells will decrease accordingly. Therefore, the PPG signal also changes periodically.

[0084] Among them, the IMU sensor and the PPG sensor can be attached to the chest of the monitored object, or implanted in the chest cavity of the monitored object.

[0085] Optionally, in the process of obtaining the motion signal and the PPG signal by the sensor, the sampling controller can control the sensor to perform sampling at different sampling times, with different sampling frequencies and different sampling resolutions. Different sampling parameters will affect the sampling results. For example, if the sampling time is determined to be more accurate, the signal obtained by sampling will be more accurate.

[0086] Step 104: Calculate the blood oxygen content based on the first motion signal and the first PPG signal.

[0087] It should be noted that, in traditional technology, the respiratory characteristic value is estimated by the motion signal collected by the IMU sensor; the blood oxygen content is estimated by the motion signal and the PPG signal collected by the PPG sensor, and the motion signal is used to eliminate motion artifacts in the PPG signal.

[0088] However, since the motion signal is specifically obtained by sampling the motion perception of the accelerometer and the gyroscope sensor, wherein the accelerometer and the gyroscope sensor constitute the IMU sensor; the PPG signal is obtained by sampling the emission and reception of light by the PPG sensor.

[0089] However, the relationship between the movement of the chest and the reflection path of light is nonlinear, that is, the motion signal and the motion features in the PPG signal cannot clearly correspond to each other, which results in the inability to accurately eliminate the motion artifacts in the PPG signal through the motion signal. Even if the motion artifacts are eliminated, the accuracy of the blood oxygen content determination cannot be guaranteed.

[0090] In one embodiment, the applicant has analyzed and found that there is a relatively static time interval for respiratory movement, that is, there is a relatively static or resting time interval after the end of the exhalation movement and before the start of the inhalation movement. In this time interval, the influence of respiratory movement on the sampling of PPG signals is minimal, that is, the motion artifact is the weakest. Therefore, this embodiment uses this time interval to determine the blood oxygen content, thereby improving the accuracy of the determination of the blood oxygen content.

[0091] Optionally, this embodiment obtains the second time interval of the respiratory movement of the current respiratory cycle when it is relatively static (i.e., a time domain feature in the motion signal) by analyzing the motion signal, and then determines the blood oxygen content through the PPG signal segment corresponding to the second time interval in the PPG signal, thereby optimizing the parameters of the first sampling controller with more accurate blood oxygen content to improve the optimization effect. That is, step 104 includes the following steps 1042 to 1048:

[0092] Step 1042: Determine a second time interval of a relatively static respiratory movement in the current respiratory cycle based on the first motion signal.

[0093] like Figure 3 As shown, the exhalation interval t can be identified from the motion signal o_start -t o_stop , inhalation interval t i_start - the end time of the current breathing cycle, and t o_stop -t i_start That is, the time interval of relative static state, and this time interval is the second time interval of the respiratory motion in the motion signal of relative static state.

[0094] Step 1044, fusing the second time interval and the first PPG signal.

[0095] Step 1046, determining the blood oxygen content based on the fused first PPG signal.

[0096] like Figure 4 As shown, the second time interval determined by the motion signal is fused with the first PPG signal, and the PPG signal segment corresponding to the second time interval can be determined in the PPG signal, that is, t o_stop -t i_start The corresponding PPG signal segment is then used to determine the blood oxygen content.

[0097] Furthermore, when the blood oxygen content is determined by the PPG signal segment, the PPG sampling value corresponding to the second time interval is obtained from the fused first PPG signal; and then the blood oxygen content is calculated by the PPG sampling value.

[0098] The calculation process is: determining the first AC component and the first DC component of the red light signal in the PPG sampling value, and the second AC component and the second DC component of the infrared signal; and obtaining the blood oxygen content based on the first AC component, the first DC component, the second AC component and the second DC component.

[0099] See the following formula 1, blood oxygen content Spo 2 can be calculated by formula 1:

[0100] (one)

[0101] in, is the first AC component of the red light signal, is the first DC component of the red light signal, is the second AC component of the infrared signal, It is the second DC component of the infrared signal.

[0102] Step 106: Optimize parameters of the first sampling controller based on the blood oxygen content.

[0103] Among them, parameter optimization refers to adjusting the sampling parameters.

[0104] Optionally, when performing parameter optimization, the optimization is determined by comparing the currently calculated blood oxygen content with the previously determined historical blood oxygen content.

[0105] In one embodiment, the difference between the current blood oxygen content and the historical blood oxygen content is calculated, and the optimized first sampling parameter is determined according to the difference. For example, the mapping relationship between a plurality of preset difference ranges and a plurality of sampling parameters can be used to determine the first sampling parameter by the difference range to which the calculated difference belongs. The preset difference range is not limited in this embodiment.

[0106] In another embodiment, a first target numerical range for the blood oxygen content is obtained by matching at least two first preset numerical ranges; a first target sampling parameter group corresponding to the first target numerical range is obtained by matching at least two groups of first preset sampling parameter groups; and parameters of the first sampling controller are optimized based on the first target sampling parameter group.

[0107] For example, there are a first preset value range 1 and a first preset value range 2, and the blood oxygen content is in the first preset value range 2, that is, the first preset value range 2 is the first target value range. Accordingly, there is a mapping relationship between the first preset value range and the first preset sampling parameter group, and the first preset sampling parameter group corresponding to the blood oxygen content, that is, the first target sampling parameter group, can be directly matched through the first preset value range and the mapping relationship.

[0108] Optionally, the periodic changes in the respiratory motion of the monitored object are not fixed periods, and the period may change, such as when breathing rapidly, the period becomes shorter, and when breathing slowly, the period becomes longer. By optimizing the parameters through the motion signal and PPG signal obtained by sampling, the optimized sampling controller can adapt to the changing period.

[0109] Step 108: Based on the first motion signal and the first PPG signal, predict a first respiratory signal characteristic value in a next respiratory cycle and a first time interval when the respiratory motion is relatively static.

[0110] Wherein, step 108 includes steps 202 to 210:

[0111] Step 202: determining, based on the first motion signal, a second time interval of a relatively static respiratory motion in a current respiratory cycle, and a second respiratory signal characteristic value of a previous respiratory cycle and a third time interval of a relatively static respiratory motion.

[0112] The second respiratory signal characteristic value and the third time interval of the respiratory motion when it is relatively static can be directly identified from the first motion signal.

[0113] Step 204: fusing the second time interval and the first PPG signal.

[0114] Step 206: determining a heart rate value based on the fused first PPG signal.

[0115] like Figure 5 As shown, Figure 5 Medium H i The PPG signal carries not only blood oxygen information but also heart rate information.

[0116] Optionally, after the first PPG signal is fused with the second time interval, the heart rate value can be determined by the PPG sampling value corresponding to the second time interval. It can be understood that the heart rate value refers to the frequency of heart beats. When the heart beats, it affects the movement of blood oxygen cells, so the PPG signal also carries heart rate information. Figure 5 , which can be determined by the PPG signal changing from weak to strong and then to weak.

[0117] In one embodiment, the parameters of the second sampling controller may be optimized based on the heart rate value in a manner similar to the method of optimizing the parameters of the first sampling controller based on the blood oxygen content, and the optimization process will not be described in detail herein.

[0118] In another embodiment, the second sampling controller may be optimized in parameters in combination with the predicted first time interval of the next respiratory cycle and the respiratory characteristics, wherein the heart rate value is used to predict the first time interval.

[0119] Step 208: predicting a first time interval of a relatively static respiratory movement in a next respiratory cycle based on the heart rate value and the third time interval.

[0120] Step 210: predicting a first respiratory signal characteristic value in a next respiratory cycle based on the heart rate value, the blood oxygen content and the second respiratory signal characteristic value.

[0121] The start time of the first time interval is the end time of the exhalation movement. It can be predicted by the following formula:

[0122] (two)

[0123] in, is the heart rate value sampled in the current breathing cycle, is the starting time of the third time interval, is an empirical function.

[0124] The end time of the first time interval is the start time of the inhalation movement. It can be predicted by the following formula:

[0125] (three)

[0126] in, is the heart rate value sampled in the current breathing cycle, is the end time of the third time interval, is an empirical function.

[0127] The first breathing characteristic includes but is not limited to a first amplitude, a first period and a first phase.

[0128] Among them, the first amplitude It can be predicted by the following formula:

[0129] (Four)

[0130] in, is the second amplitude of the second respiratory signal characteristic value in the previous respiratory cycle, and is the empirical formula, is the serial number of the current breathing cycle, are multiple heart rate values ​​of the current breathing cycle, It is the multiple blood oxygen contents of the current respiratory cycle.

[0131] Accordingly, the first period and the first phase can be determined by a formula similar to Formula 4, which will not be described in detail here.

[0132] Step 110: Optimize parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval.

[0133] In one embodiment, a second target numerical range corresponding to the first respiratory signal characteristic value and the first time interval is obtained by matching from at least two second preset numerical ranges; a second target sampling parameter group corresponding to the second target numerical range is obtained by matching from at least two second preset sampling parameter groups; and parameters of the second sampling controller are optimized based on the second target sampling parameter group.

[0134] That is, the first time interval and the first respiratory signal characteristic value also have corresponding empirical values ​​of the second sampling parameter, that is, there is a one-to-one correspondence between different first time intervals and first respiratory signal characteristic values ​​and different second sampling parameters. For specific embodiments, please refer to the above-mentioned determination process of the first sampling parameter, which will not be repeated in this embodiment.

[0135] In another embodiment, in the conventional technology, high-frequency sampling is adopted when sampling using an IMU sensor, and high-frequency sampling consumes a lot of energy, which makes the endurance of the device poor. In this embodiment, the second sampling parameter at least includes a second sampling frequency and a second sampling resolution, and the second sampling frequency is adjusted based on the first time interval, and the second sampling resolution is adjusted based on the first respiratory signal characteristic value.

[0136] There is a corresponding relationship between the first time interval and the heart rate value. Specifically, the higher the heart rate value, the smaller the first time interval, and the lower the heart rate value, the larger the first time interval.

[0137] Optionally, the first time interval is compared with the third time interval, and if the first time interval is greater than the third time interval, the second sampling frequency is reduced. It should be noted that, since there is a stable correlation between the heart rate value and the respiratory frequency, when the heart rate value is low, it means that the respiratory frequency of the monitored object is low, so the respiratory cycle is longer, and accordingly, the first time interval is larger.

[0138] Among them, since the first respiratory signal characteristic value includes the first amplitude, the first period and the first phase, the first respiratory signal characteristic value is a feature of the signal waveform of the next respiratory cycle. Therefore, the signal waveform can be determined by the first respiratory signal characteristic value, and then the second sampling resolution is determined by the signal waveform, and specifically, there is a mapping relationship between the signal waveform and the second sampling resolution.

[0139] Step 112: Based on the optimized first sampling controller, the IMU sensor is controlled to sample to obtain a second motion signal, and based on the optimized second sampling controller, the PPG sensor is controlled to sample to obtain a second PPG signal.

[0140] Step 114 , determining a physiological index related to breathing of the monitored object based on the second motion signal and the second PPG signal.

[0141] Among them, physiological indicators include but are not limited to respiratory movement and blood oxygen content.

[0142] Optionally, the physiological index can be obtained by extracting corresponding features from the motion signal and the PPG signal.

[0143] The above method optimizes the parameters of the first sampling controller and the second sampling controller by sampling to obtain the first motion signal and the first PPG signal, and then obtains the second motion signal and the second PPG signal based on the optimized first sampling controller and the second sampling controller, respectively, and uses them to evaluate the sleep breathing quality of the monitored object to achieve respiratory monitoring. The above method realizes the optimization of sampling parameters based on respiratory movement and blood oxygen content, so that the sampling controller can dynamically adjust the sampling parameters of the control sensor when sampling according to the first respiratory signal characteristic value, the first time interval and the blood oxygen content, so that the optimized sampling controller is more suitable for the upcoming sampling control, thereby improving the accuracy of the signal obtained by sensor sampling.

[0144] In an exemplary embodiment, if Figure 6 As shown, the overall process of the method may include steps 1-16. Among them:

[0145] Step 1: The IMU sensor is controlled by the sampling controller to perform sampling. As a part of the respiratory monitoring node, the IMU sensor can be attached to the chest of the monitored object or placed in the chest cavity.

[0146] Step 2: The PPG sensor is controlled by the sampling controller to perform sampling. As another part of the respiratory monitoring node, the PPG sensor can be attached to the chest of the monitored object or placed in the chest cavity.

[0147] Step 3: Get the motion signal based on the sampling controller.

[0148] Step 4: Get the PPG signal based on the sampling controller.

[0149] Step 5: Output the motion signal to the motion cycle estimation module, so that the motion cycle estimation module can perform motion cycle estimation to obtain a second time interval.

[0150] Step 6: Output the PPG signal to the blood oxygen content estimation module, and the blood oxygen content estimation module estimates the blood oxygen content to obtain the blood oxygen content.

[0151] Step 7: Output the obtained second time interval to the motion cycle prediction module, so that the motion cycle prediction module can predict the first time interval of the next breathing cycle.

[0152] Step 8: Output the obtained second time interval to the blood oxygen content estimation module, so that the blood oxygen content estimation module can perform blood oxygen content estimation.

[0153] Step 9: Output the blood oxygen content to the sampling controller corresponding to the IMU sensor so that the sampling controller can adjust the sampling parameters.

[0154] Step 10: Input the blood oxygen content into the respiratory monitoring module.

[0155] Step 11: Input the first time interval into the respiratory monitoring module.

[0156] Step 12: Output the PPG signal to the heart rate estimation module so that the heart rate estimation module can estimate the heart rate value.

[0157] Step 13: Output the heart rate value to the exercise cycle prediction module, so that the exercise cycle prediction module can predict the first time interval of the next breathing cycle.

[0158] Step 14: Input the first time interval to a sampling controller corresponding to the PPG so that the sampling controller can adjust sampling parameters.

[0159] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0160] In an exemplary embodiment, a computer device is provided, which may be a respiratory monitoring device, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Bluetooth, WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a respiratory monitoring method is implemented.

[0161] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0162] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0163] Acquire a first motion signal sampled by an IMU sensor, and acquire a first PPG signal sampled by a PPG sensor; the IMU sensor is controlled by a first sampling controller with a first sampling parameter, and the PPG sensor is controlled by a second sampling controller with a second sampling parameter;

[0164] Calculate the blood oxygen content based on the first motion signal and the first PPG signal;

[0165] Optimizing parameters of the first sampling controller based on the blood oxygen content;

[0166] Based on the first motion signal and the first PPG signal, predict a first respiratory signal characteristic value in a next respiratory cycle and a first time interval of a relatively static respiratory motion;

[0167] Optimizing parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval;

[0168] Based on the optimized first sampling controller, the IMU sensor is controlled to sample to obtain a second motion signal, and based on the optimized second sampling controller, the PPG sensor is controlled to sample to obtain a second PPG signal;

[0169] An indicator value of a physiological indicator related to breathing of the monitored object is determined based on the second motion signal and the second PPG signal.

[0170] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0171] Determine, based on the first motion signal, a second time interval of a respiratory motion in a current respiratory cycle when the respiratory motion is relatively static;

[0172] fusing the second time interval and the first PPG signal;

[0173] The blood oxygen content is determined based on the fused first PPG signal.

[0174] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0175] Obtaining a first target value range of the blood oxygen content by matching at least two first preset value ranges;

[0176] Obtaining a first target sampling parameter group corresponding to the first target numerical range by matching at least two first preset sampling parameter groups;

[0177] Parameters of the first sampling controller are optimized based on the first target sampling parameter group.

[0178] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0179] Determine, based on the first motion signal, a second time interval when the respiratory motion in the current respiratory cycle is relatively static, and a second respiratory signal characteristic value of the previous respiratory cycle and a third time interval when the respiratory motion is relatively static;

[0180] fusing the second time interval and the first PPG signal;

[0181] determining a heart rate value based on the fused first PPG signal;

[0182] Predicting a first time interval of a relatively static respiratory movement in a next respiratory cycle based on the heart rate value and the third time interval;

[0183] The first respiratory signal characteristic value in the next respiratory cycle is predicted based on the heart rate value, the blood oxygen content and the second respiratory signal characteristic value.

[0184] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0185] Obtaining a second target value range corresponding to the first respiratory signal characteristic value and the first time interval by matching at least two second preset value ranges;

[0186] Obtaining a second target sampling parameter group corresponding to the second target numerical range by matching at least two second preset sampling parameter groups;

[0187] Parameter optimization is performed on the second sampling controller based on the second target sampling parameter group.

[0188] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0189] determining the second sampling resolution based on the first breathing signal characteristic value;

[0190] comparing the first time interval with the third time interval;

[0191] If the first time interval is greater than the third time interval, the second sampling frequency is reduced.

[0192] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0193] Acquire a first motion signal sampled by an IMU sensor, and acquire a first PPG signal sampled by a PPG sensor; the IMU sensor is controlled by a first sampling controller with a first sampling parameter, and the PPG sensor is controlled by a second sampling controller with a second sampling parameter;

[0194] Calculate the blood oxygen content based on the first motion signal and the first PPG signal;

[0195] Optimizing parameters of the first sampling controller based on the blood oxygen content;

[0196] Based on the first motion signal and the first PPG signal, predict a first respiratory signal characteristic value in a next respiratory cycle and a first time interval of a relatively static respiratory motion;

[0197] Optimizing parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval;

[0198] Based on the optimized first sampling controller, the IMU sensor is controlled to sample to obtain a second motion signal, and based on the optimized second sampling controller, the PPG sensor is controlled to sample to obtain a second PPG signal;

[0199] An indicator value of a physiological indicator related to breathing of the monitored object is determined based on the second motion signal and the second PPG signal.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0201] Determine, based on the first motion signal, a second time interval of a respiratory motion in a current respiratory cycle when the respiratory motion is relatively static;

[0202] fusing the second time interval and the first PPG signal;

[0203] The blood oxygen content is determined based on the fused first PPG signal.

[0204] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0205] Obtaining a first target value range of the blood oxygen content by matching at least two first preset value ranges;

[0206] Obtaining a first target sampling parameter group corresponding to the first target numerical range by matching at least two first preset sampling parameter groups;

[0207] Parameters of the first sampling controller are optimized based on the first target sampling parameter group.

[0208] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0209] Determine, based on the first motion signal, a second time interval when the respiratory motion in the current respiratory cycle is relatively static, and a second respiratory signal characteristic value of the previous respiratory cycle and a third time interval when the respiratory motion is relatively static;

[0210] fusing the second time interval and the first PPG signal;

[0211] determining a heart rate value based on the fused first PPG signal;

[0212] Predicting a first time interval of a relatively static respiratory movement in a next respiratory cycle based on the heart rate value and the third time interval;

[0213] The first respiratory signal characteristic value in the next respiratory cycle is predicted based on the heart rate value, the blood oxygen content and the second respiratory signal characteristic value.

[0214] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0215] Obtaining a second target value range corresponding to the first respiratory signal characteristic value and the first time interval by matching at least two second preset value ranges;

[0216] Obtaining a second target sampling parameter group corresponding to the second target numerical range by matching at least two second preset sampling parameter groups;

[0217] Parameter optimization is performed on the second sampling controller based on the second target sampling parameter group.

[0218] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0219] determining the second sampling resolution based on the first breathing signal characteristic value;

[0220] comparing the first time interval with the third time interval;

[0221] If the first time interval is greater than the third time interval, the second sampling frequency is reduced. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0222] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0223] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0224] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A respiratory monitoring method, characterized in that: The method comprises: Acquire a first motion signal sampled by an IMU sensor, and acquire a first PPG signal sampled by a PPG sensor; the IMU sensor is controlled by a first sampling controller with a first sampling parameter, and the PPG sensor is controlled by a second sampling controller with a second sampling parameter; Calculate the blood oxygen content based on the first motion signal and the first PPG signal; Optimizing parameters of the first sampling controller based on the blood oxygen content; Determine, based on the first motion signal, a second time interval when the respiratory motion in the current respiratory cycle is relatively static, and a second respiratory signal characteristic value of the previous respiratory cycle and a third time interval when the respiratory motion is relatively static; fusing the second time interval and the first PPG signal; determining a heart rate value based on the fused first PPG signal; Predicting a first time interval of a relatively static respiratory movement in a next respiratory cycle based on the heart rate value and the third time interval; Predicting a first respiratory signal characteristic value in a next respiratory cycle based on the heart rate value, the blood oxygen content and the second respiratory signal characteristic value; Optimizing parameters of the second sampling controller based on the first respiratory signal characteristic value and the first time interval; Based on the optimized first sampling controller, the IMU sensor is controlled to sample to obtain a second motion signal, and based on the optimized second sampling controller, the PPG sensor is controlled to sample to obtain a second PPG signal; determining an index value of a physiological index related to breathing of the monitored object based on the second motion signal and the second PPG signal; The relatively static time interval refers to a resting time interval after the exhalation movement ends and before the inhalation movement begins.

2. The method according to claim 1, characterized in that The calculating the blood oxygen content based on the first motion signal and the first PPG signal includes: Determine, based on the first motion signal, a second time interval of a respiratory motion in a current respiratory cycle when the respiratory motion is relatively static; fusing the second time interval and the first PPG signal; The blood oxygen content is determined based on the fused first PPG signal.

3. The method according to claim 2, characterized in that The performing parameter optimization on the first sampling controller based on the blood oxygen content comprises: Obtaining a first target value range of the blood oxygen content by matching at least two first preset value ranges; Obtaining a first target sampling parameter group corresponding to the first target numerical range by matching at least two first preset sampling parameter groups; Parameters of the first sampling controller are optimized based on the first target sampling parameter group.

4. The method according to claim 1, characterized in that The performing parameter optimization on the second sampling controller based on the first respiratory signal characteristic value and the first time interval comprises: Obtaining a second target value range corresponding to the first respiratory signal characteristic value and the first time interval by matching at least two second preset value ranges; Obtaining a second target sampling parameter group corresponding to the second target numerical range by matching at least two second preset sampling parameter groups; Parameter optimization is performed on the second sampling controller based on the second target sampling parameter group.

5. The method according to claim 4, characterized in that The second target sampling parameter group includes at least a second sampling frequency and a second sampling resolution, and the parameter optimization of the second sampling controller based on the first respiratory signal characteristic value and the first time interval includes: determining the second sampling resolution based on the first breathing signal characteristic value; comparing the first time interval with the third time interval; If the first time interval is greater than the third time interval, the second sampling frequency is reduced.

6. A respiratory monitoring device, characterized in that: The device includes a processor, an IMU sensor, a first sampling controller, a PPG sensor, and a second sampling controller; The IMU sensor is used to sample and obtain a first motion signal; The first sampling controller is used to control the IMU sensor to perform sampling with a first sampling parameter; The PPG sensor is used to sample and obtain a first PPG signal; The second sampling controller is used to control the PPG sensor to perform sampling with a second sampling parameter; The processor is used to execute the steps of the method according to any one of claims 1 to 5.

7. The device according to claim 6, characterized in that The device also includes electrodes; The electrode is used to output current to intervene in the sleep breathing state of the monitored object when the evaluation result of the sleep breathing quality meets the preset intervention condition; wherein the evaluation result includes the predicted respiratory movement.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images