Intervention method and device for apnea events

Abstract

The application discloses an intervention method and device for an apnea event, and a method implementation thereof, which comprises the following steps: acquiring a pressure signal collected by a pressure detection unit, and predicting a sleeping posture and position information of a target object based on the pressure signal, wherein the position information comprises a chest position and an abdominal position; extracting a chest respiration signal and an abdominal respiration signal based on the chest position and the abdominal position; determining whether the target object has an apnea event based on the chest respiration signal and the abdominal respiration signal; and if the target object has an apnea event, determining an intervention scheme corresponding to the apnea event based on the sleeping posture and the position information, and adjusting the air pressure of a corresponding air bag based on the intervention scheme. The application effectively reduces the influence of different sleeping positions and postures of a user on the accuracy of measurement results, reduces the influence of apnea on the user under the premise of not affecting the sleep of the user as much as possible, realizes accurate apnea judgment and individualized intervention, and reduces monitoring cost.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart home, and in particular to a method and device for intervention of apnea event, a computer device and a storage medium. BACKGROUND

[0002] Sleep apnea includes obstructive sleep apnea (OSA), central sleep apnea (CSA) and other types, which is widely harmful and deeply related to the length, frequency and degree of hypoxia of apnea, and seriously threatens the health of multiple organ systems.

[0003] At present, polysomnography (PSG) as a laboratory standard device for measuring sleep apnea can accurately calculate apnea-hypopnea index (AHI), respiratory disturbance index (RDI) and oxygen desaturation index (ODI), and accurately distinguish central and obstructive events and evaluate sleep structure by collecting multi-dimensional information such as electroencephalogram (EEG), electrooculography (EOG), electromyography (EMG), oral and nasal airflow, chest and abdominal respiratory movement, and blood oxygen. However, PSG has problems such as complex equipment, in-hospital monitoring, high single cost, and poor comfort, which limits its application scenarios mainly to laboratory and hospital sleep departments. Although portable diagnostic devices can reduce the collection of some physiological signals and achieve home application, the comfort and convenience of long-term use are still insufficient, hindering its large-scale promotion. In recent years, emerging monitoring methods such as millimeter wave radar, piezoelectric film mattress and smart watch have advantages in user experience and long-term monitoring feasibility, but are easily disturbed by factors such as environment, device wearing and motion state, resulting in poor monitoring accuracy and inability to intervene in time. SUMMARY

[0004] Therefore, it is necessary to provide a method and device for intervention of apnea event to solve at least one of the above problems.

[0005] In a first aspect, a method for intervention of apnea event is provided, which is applied to a respiratory intervention device, the respiratory intervention device is provided with a plurality of pressure detection units and an airbag, and the method comprises the following steps.

[0006] acquire a pressure signal collected by the pressure detection unit, and based on the pressure signal, predict a sleeping posture and position information of the target object, the position information including a chest position and an abdomen position;

[0007] extract a chest respiration signal and an abdomen respiration signal based on the chest position and the abdomen position;

[0008] determine whether the target object has a respiratory pause event based on the chest respiration signal and the abdomen respiration signal;

[0009] if the target object has the respiratory pause event, determine an intervention scheme corresponding to the respiratory pause event based on the sleeping posture and the position information, and adjust air pressure of a corresponding air bag based on the intervention scheme.

[0010] In a possible implementation, the determining whether the target object has the respiratory pause event based on the chest respiration signal and the abdomen respiration signal includes:

[0011] determining a chest-abdomen signal feature, a chest-abdomen respiration correlation feature, and a chest-abdomen respiration time dimension feature based on the chest respiration signal and the abdomen respiration signal;

[0012] determining whether the target object has the respiratory pause event based on the chest-abdomen signal feature, the chest-abdomen respiration correlation feature, and the chest-abdomen respiration time dimension feature.

[0013] In a possible implementation, after the adjusting the air pressure of the corresponding air bag based on the intervention scheme, the method further includes:

[0014] detecting whether the chest-abdomen respiration correlation feature changes;

[0015] if the chest-abdomen respiration correlation feature changes, determining whether the change of the chest-abdomen respiration correlation feature meets a preset intervention condition;

[0016] if the preset intervention condition is not met, increasing an adjustment range of the corresponding air bag;

[0017] if the preset intervention condition is met, restoring the current air pressure of the corresponding air bag to the air pressure before the intervention.

[0018] In a possible implementation, the determining the chest-abdomen signal feature, the chest-abdomen respiration correlation feature, and the chest-abdomen respiration time dimension feature based on the chest respiration signal and the abdomen respiration signal includes:

[0019] extract chest signal features corresponding to the chest respiratory signals and abdominal signal features corresponding to the abdominal respiratory signals, wherein the chest signal features comprise chest signal phase information and chest signal amplitude information, and the abdominal signal features comprise abdominal signal phase information and abdominal signal amplitude information;

[0020] determine the chest-abdominal respiratory correlation features based on the chest signal phase information, abdominal signal phase information, chest signal amplitude information, and abdominal signal amplitude information;

[0021] determine the chest-abdominal respiratory signal time dimension features based on the chest signal phase information, abdominal signal phase information, chest signal amplitude information, and abdominal signal amplitude information.

[0022] In a possible implementation, the extracting the chest signal features corresponding to the chest respiratory signals and the abdominal signal features corresponding to the abdominal respiratory signals comprises:

[0023] analyzing the chest respiratory signals and abdominal respiratory signals respectively, and obtaining chest signal phase information and abdominal signal phase information based on the analyzed chest respiratory signals and abdominal respiratory signals;

[0024] determining chest respiratory amplitude information and abdominal respiratory signal amplitude information based on effective peak points and effective trough points of the chest respiratory signals and abdominal respiratory signals;

[0025] calculating respiratory cycle variability based on effective peak points of the chest respiratory signals and abdominal respiratory signals.

[0026] In a possible implementation, the analyzing the chest respiratory signals and abdominal respiratory signals respectively, and obtaining chest signal phase information and abdominal signal phase information based on the analyzed chest respiratory signals and abdominal respiratory signals comprises:

[0027] performing band-pass filtering on the chest respiratory signals and abdominal respiratory signals respectively;

[0028] performing Hilbert transform on the filtered chest respiratory signals and abdominal respiratory signals to obtain transformed chest respiratory signals and abdominal respiratory signals;

[0029] obtaining chest respiratory signal phase and abdominal respiratory signal phase based on the analyzed chest respiratory signals and abdominal respiratory signals;

[0030] performing phase unwrapping on the chest respiratory signal phase and abdominal respiratory signal phase to obtain the chest signal phase information and abdominal signal phase information.

[0031] In a possible implementation, the position information comprises a body inclination of the target object, and the intervention scheme corresponding to the apnea event is determined based on the sleep posture and the position information, comprising:

[0032] The contact state between the target object and each air bag is determined based on the position information;

[0033] Each air bag is classified based on the body inclination of the target object to obtain a corresponding type of each air bag;

[0034] The intervention scheme corresponding to the apnea event is determined based on the sleep posture, the contact state, and the corresponding type of each air bag.

[0035] In a possible implementation, the intervention scheme corresponding to the apnea event is determined based on the sleep posture, the contact state, and the corresponding type of each air bag, comprising:

[0036] If the sleep posture is supine or prone, whether there are multiple contact air bags of the same type in contact with the target object is determined based on the contact state;

[0037] If there are multiple contact air bags of the same type, a distribution mode corresponding to the multiple contact air bags of the same type is determined, and the air pressure of the contact air bags is adjusted based on the distribution mode;

[0038] If there are no multiple contact air bags of the same type, the air pressure of air bags of different types is adjusted respectively.

[0039] In a possible implementation, the chest respiratory signal and the abdominal respiratory signal are extracted based on the chest position and the abdominal position, comprising:

[0040] The chest region and the abdominal region are determined based on the chest position and the abdominal position, respectively, wherein the chest region and the abdominal region are composed of a first pressure matrix and a second pressure matrix by corresponding pressure detection units;

[0041] A first pressure mean value corresponding to the first pressure matrix is determined, and the first pressure mean value is taken as the chest respiratory signal;

[0042] A second pressure mean value corresponding to the second pressure matrix is determined, and the second pressure mean value is taken as the abdominal respiratory signal.

[0043] In a second aspect, an intervention device for an apnea event is provided, which is applied to a respiratory intervention apparatus, and the respiratory intervention apparatus is provided with a plurality of pressure detection units and air bags. The device comprises:

[0044] a prediction unit configured to acquire a pressure signal collected by the pressure detection unit, and predict a sleeping posture and position information of the target object based on the pressure signal, the position information including a chest position and an abdomen position;

[0045] a chest-abdomen signal extraction unit configured to extract a chest respiration signal and an abdomen respiration signal based on the chest position and the abdomen position, respectively;

[0046] an apnea event determination unit configured to determine whether the target object has an apnea event based on the chest respiration signal and the abdomen respiration signal;

[0047] an apnea intervention unit configured to, if the target object has an apnea event, determine an intervention scheme corresponding to the apnea event based on the sleeping posture and the position information, and adjust air pressure of a corresponding air bag based on the intervention scheme.

[0048] In a third aspect, a computer device is provided, including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor implementing the intervention method for apnea event when executing the computer readable instructions.

[0049] In a fourth aspect, a readable storage medium is provided, the computer readable instructions executable by one or more processors, causing the one or more processors to execute the intervention method for apnea event as described above.

[0050] The intervention method and device for the respiratory pause event, and the method implementation thereof, include: acquiring a pressure signal collected by the pressure detection unit, and predicting a sleep posture and position information of a target object based on the pressure signal, the position information including a chest position and an abdominal position; extracting a chest respiration signal and an abdominal respiration signal based on the chest position and the abdominal position; determining whether the target object has a respiratory pause event based on the chest respiration signal and the abdominal respiration signal; and if the target object has a respiratory pause event, determining an intervention scheme corresponding to the respiratory pause event based on the sleep posture and the position information, and adjusting the air pressure of a corresponding air bag based on the intervention scheme. In the embodiment of the present application, the pressure detection unit is used to collect the pressure signal in real time, and advanced algorithms are used to deeply analyze the pressure data and accurately lock the sleep posture, chest position, and abdominal position of the target object. This unique design effectively avoids the interference of user sleep position movement and frequent changes in sleep posture on the monitoring results, and significantly improves the stability and accuracy of data acquisition compared with the traditional monitoring method. On this basis, the system can accurately identify different types of respiratory pause events through intelligent extraction and comparative analysis of the chest and abdominal respiration signals. No matter what type of sleep apnea, the system can quickly and accurately determine. When a respiratory pause event is detected, the system will automatically match the pre-set personalized intervention scheme according to the real-time sleep posture of the user, and accurately adjust the air pressure of the corresponding air bag, thereby minimizing the interference with the user's sleep, effectively relieving the symptoms of respiratory pause, and reducing the health risks of cardiovascular diseases, cognitive impairment, and other diseases caused by respiratory pause. This technical solution not only realizes a comfortable and convenient home monitoring experience, and gets rid of the limitations of traditional polysomnography (PSG) requiring hospitalization, complex equipment, and high cost, but also breaks through the technical bottlenecks of poor comfort of portable devices and insufficient accuracy of emerging monitoring technologies, and provides a more efficient and feasible solution for the monitoring and treatment of sleep apnea in a low-cost, high-precision, and user-friendly manner. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0052] Figure 1 is an implementation environment schematic diagram of the pressure detection unit and the air bag deployment method of the respiratory intervention device in an embodiment of the present application;

[0053] Figure 2 is a flowchart of the intervention method for the respiratory pause event in an embodiment of the present application;

[0054] Figure 3 This is a schematic diagram of a model structure for a prediction model method in one embodiment of this application;

[0055] Figure 4 This is a schematic diagram of the imaging result of the target object in a supine position in one embodiment of this application;

[0056] Figure 5 This is a schematic diagram illustrating the movement of the chest and abdomen position boxes when the chest and abdomen positions of the target object change in one embodiment of this application.

[0057] Figure 6 This is a schematic diagram of the peak and trough selection method of respiratory signal in one embodiment of this application;

[0058] Figure 7 This is a schematic diagram of an implementation scenario of the airbag classification method when the target object is in a supine state, according to one embodiment of this application;

[0059] Figure 8 This is a schematic diagram of a device for intervening in a sleep apnea event according to one embodiment of this application;

[0060] Figure 9 This is a schematic diagram of a computer device according to one embodiment of this application. Detailed Implementation

[0061] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0062] In one embodiment, such as Figure 1 As shown in Figure 2, an intervention method for sleep apnea events is provided, applied to a respiratory intervention device, which is equipped with multiple pressure detection units and an airbag, including the following steps:

[0063] In step S110, the pressure signal collected by the pressure detection unit is acquired, and based on the pressure signal, the sleeping posture and position information of the target object are predicted, including the position of the chest and the position of the abdomen.

[0064] It should be noted that this respiratory intervention device can be used in smart furniture such as smart beds, smart mattresses, and sofas for users to sit, lie down, and rest. Multiple pressure-sensing units can be arranged in an array, such as rectangular, circular, or hexagonal arrays. This arrangement can evenly sense pressure changes at different locations on the surface of the respiratory intervention device. For example, on a mattress, regardless of whether the target is lying supine, on their side, or prone, the device can accurately capture the pressure distribution of different parts of the body on the mattress.

[0065] The pressure sensing unit is a component that can sense pressure changes and convert them into electrical signals or other detectable signals, such as a pressure sensor.

[0066] It should be noted that this respiratory intervention device also includes multiple airbags, which can be distributed throughout the device. These airbags can be connected to pressure sensors to monitor the pressure within them. Users can monitor pressure changes within the airbags from any position on the intelligent monitoring device. The pressure sensing unit can be positioned above the airbag, and multiple pressure sensing units can be deployed in one airbag deployment area; that is, one airbag corresponds to a pressure sub-matrix composed of multiple pressure sensing units. This design allows for precise monitoring of pressure in each airbag area. When an airbag experiences a pressure change, the corresponding pressure sub-matrix can quickly and accurately detect this change and convert it into electrical signals and other data for transmission and analysis. For example, in a smart mattress, when a user's body part presses on an area corresponding to an airbag, the pressure sub-matrix for that area can accurately measure the pressure magnitude and trend. By analyzing this data, the user's stress in that area can be inferred, providing data support for analyzing the user's sleeping posture, subtle body movements during breathing, and other related information.

[0067] like Figure 1As shown, a schematic diagram of the deployment of the pressure sensing unit of the respiratory intervention device and the air bag is provided, wherein S11 is a pressure matrix, which can be 64*32, i.e. 32 pressure sensors per row, a total of 64 rows, and the sampling accuracy can be 0.01 KPa. S12-S17 can be air bags, which can be connected with air pressure sensors, and the air pressure sensor range can be 0-40 KPa, and the sampling accuracy can be 0.5 Pa. Taking the respiratory intervention device as a mattress and the target object as a human body as an example, the air bags can be deployed according to the supine state of the human body, wherein S12 can be the position of the left user's shoulder air bag, S13 can be the position of the left user's waist air bag, S14 can be the position of the left user's hip air bag, S15 can be the position of the right user's shoulder air bag, S16 can be the position of the right user's waist air bag, and S17 can be the position of the right user's hip air bag. By deploying S12-S17 in the above manner, the changes in the air pressure of the air bags in the chest and abdomen of the human body can be effectively sensed, so that the respiratory depth measurement can be better performed. It should be noted that when the respiratory intervention device is different, the target object is different, and the deployment manner of the air bag and the air pressure matrix is different, and the specific deployment can be performed according to the actual needs. It should be noted that each air bag is connected with an air pump through a pipeline, and can be independently inflated and deflated to perform respiratory pause intervention.

[0068] Specifically, after generating the pressure signal through the pressure matrix, the effectiveness of the pressure signal can be detected first. If the pressure signal is effective, the pressure signal can be input into the prediction model trained in advance to predict the sleeping posture, chest position and abdominal position of the target object. For example, Figure 3As shown, the prediction model can include an input layer S21, a first convolutional layer S22, a region extraction S23, a second convolutional layer S24, a first fully connected layer S25, a second fully connected layer S26, and an output layer S27. The collected pressure signals are input into the input layer S21, and the tensor size is 64*32*1. After being input into the first convolutional layer S22 through the input layer S21 for convolution processing, a tensor with a size of 64*32*16 can be obtained. In the convolutional layer, K3 represents a convolution kernel size of 3*3, s1 represents a step size of 1, p1 represents a padding type of maxpooling, and c16 represents a number of convolution kernels of 16. The tensor with a size of 64*32*16 obtained after being processed by the first convolutional layer S22 is input into the region extraction S23 for region extraction. The region extraction method is to directly obtain a single-step sliding window through a fixed-size window. The fixed window size includes 8*4, 8*8, 8*16, 8*32, 16*4, 16*8, 16*16, 16*32, 32*4, 32*8, 32*16, 32*32, 64*4, 64*8, 64*16, and 64*32. The single-step sliding window moves only one data point in the horizontal direction or the vertical direction each time the window is updated. The second convolutional layer S24 performs a 1*1 convolution operation on the extracted tensor, i.e., flattening, to obtain a one-dimensional array with a size of 16RC, where R is the fixed window row size and C is the fixed window column size. For example, taking a fixed window with a size of 8*4, R is 8 and C is 4, and a one-dimensional array with a size of 512 is obtained after flattening. Then, the first fully connected layer S25 performs full connection processing on the one-dimensional feature array obtained after region extraction and flattening to obtain a one-dimensional array with a size of 1000. The second fully connected layer S26 performs full connection processing again on the one-dimensional array with a size of 1000 to obtain a two-dimensional array with a size of 500. Finally, the output layer S27 can output a two-dimensional vector with a length of 17. It can include four sleep posture probabilities and 13 position information. Among them, the sleep posture can include supine, prone, lateral recumbent, and other sleep postures. It can be obtained through an activation function softmax. In addition, the 13 kinds of position information can include user center horizontal coordinate , user center vertical coordinate , user box height , user box width , chest center horizontal coordinate , chest center vertical coordinate , chest box width , chest box height , abdominal center horizontal coordinate , abdominal center vertical coordinate , abdominal box width , abdominal box height , body tilt angle It is obtained by performing a linear transformation and weighting on the previous fully connected layer. The coordinate system of the horizontal and vertical axes is based on the top left corner of the pressure matrix as the origin, with the positive horizontal axis pointing to the right and the positive vertical axis pointing downwards. The body tilt angle refers to the angle between the straight line connecting the feet to the head and the vertically upward direction.

[0069] It should be noted that the parameters of models S25-S27 are not shared for different fixed window sizes; that is, the corresponding parameters are not the same. Each extracted region has a one-dimensional output of length 17. This means that for an original input of 64*32*1, there will be a total of 10080 (140*72, 59+49+33+1, 29+25+17+1) one-dimensional outputs of length 17. Taking a user lying supine on one side as an example, the imaging result is as follows... Figure 4 As shown, the white dashed box in S31 represents the user's current location. , Its center coordinates, For its high, Its width; the white dashed box S32 represents the location of the user's chest. , Its center coordinates, For its high, Its width; the white dashed box S33 indicates the location of the user's abdomen. , Its center coordinates, For its high, It is for its width.

[0070] Optionally, validating the pressure signal means determining whether the pressure corresponds to the pressure signal of the target object on the respiratory intervention device, and detecting its stability and signal quality. This is to eliminate pressure signals generated when the target object is not on or off the respiratory intervention device, pressure signals in unstable states, and pressure signals with poor signal quality, so as to avoid the signal interfering with the final measurement results and affecting the measurement accuracy.

[0071] In determining whether a pressure signal is the pressure signal collected when the target object is on the respiratory intervention device, the sum of all acquired pressure signals can be calculated. If the sum is greater than a preset value TH1; and the number of pressure signals with pressure values ​​greater than the preset value TH2 is greater than TH3; and the sum of pressure signals within a preset window time length, such as 5 seconds, is processed by bandpass filtering, such as [0.1, 2] Hz, and if the sum of the absolute values ​​of the pressure signals after bandpass filtering is greater than the preset value TH4, and all three conditions are met, then the target object is considered to exist on the respiratory intervention device; otherwise, the target object is considered not to exist on the respiratory intervention device.

[0072] It should be noted that TH1 is strongly related to the sensor characteristics, and the matrix pressure sensor data in the quiet scene when the target object exists on the respiratory intervention device can be collected, the matrix pressure sensor signal at the current time is summed, and the lower quartile of the sum of the signals in all scenes is calculated, TH1 is the lower quartile * a certain coefficient, for example, 0.5. TH2 can be an empirical value, for example, a fixed size (for example, 5 cm*5 cm) and a fixed weight (for example, 250 g) can be placed on different mattresses in different positions, and the maximum value of the pressure matrix of the placement area is calculated, and the average value of the maximum value is calculated as TH2. TH3 can be an empirical value, first determine the coverage area of a single sensor, for example, the coverage area of the whole pressure sensor is 150 cm*160 cm, the number of sensors is 32*32, and the coverage area of a single sensor is 4.68 cm*5 cm. Then, according to the lower quartile of the contact area of the detected object lying on the respiratory intervention device * a certain coefficient, such as a coefficient of 0.5. Finally, the area obtained is divided by the coverage area of a single sensor, and the value is rounded down to obtain the corresponding TH3. TH4 is strongly related to the sensor characteristics, and the matrix pressure sensor data in the scene where different people are distributed on the bed without obvious body movement can be collected, the matrix pressure sensor signal at the current time is summed, then the signal sum is band-pass filtered in [0.1, 2] Hz, the sum of the absolute values of the filtered signals in the window time is calculated, the window time can be 5 s, and the lower quartile of the sum of the absolute values of all window signals is calculated, and the TH4 is the lower quartile * a certain coefficient, for example, 0.3.

[0073] Wherein, when determining whether the pressure signal corresponds to the pressure signal generated in a stable state, the pressure signal can be summed to obtain a pressure signal sum, then after first-order difference processing, the absolute value thereof is taken. If the absolute value is not greater than a preset value TH5; and the absolute value of the difference between the number of pressure values greater than a preset value TH2 in the pressure signal and the number greater than TH2 at the previous time is not greater than TH6, it is considered stable, otherwise it is considered unstable.

[0074] It should be noted that TH5 is strongly related to the sensor characteristics, and the matrix pressure sensor data in the scene where different people are distributed on the bed without obvious body movement can be collected, the matrix pressure sensor signal at the current time is summed, then the upper quartile of the first-order difference of the sum of the signal absolute values is calculated, and TH5 is the upper quartile * a certain coefficient, for example, 1.5. TH6 can be an empirical value, which is used to evaluate whether a larger action occurs, that is, whether the contact area of the adjacent time pressure matrix changes greatly, which is obtained by rounding up the area threshold allowed to change divided by the coverage area of a single sensor, for example, the expected effective contact surface change (greater than TH2) is less than 25 cm*25 cm, and the coverage area of a single sensor is 4.68 cm*5 cm. The threshold is 27.

[0075] wherein, when determining whether the signal quality of the pressure signal meets the preset signal quality condition, a [0.1, 2] Hz passband signal f1 in a window time length of 5 s in the pressure matrix and a high-frequency component f2 with a cutoff frequency of 2 Hz in the pressure matrix are extracted, the ratio of the sum of absolute values of f1 to the absolute value of f2 is calculated, and if the ratio is less than a preset value TH7, it is considered that the signal quality is too low, otherwise it is considered that the signal quality meets the requirement.

[0076] It should be noted that TH7 can be an empirical value for evaluating the signal-to-noise ratio, which is related to the sensor, for example, 1.5.

[0077] In step S120, based on the chest position and the abdominal position, a chest respiration signal and an abdominal respiration signal are extracted respectively.

[0078] It should be noted that before extracting the chest respiration signal and the abdominal respiration signal, it is necessary to determine whether the sleeping posture of the target object changes or the chest and abdominal position changes. Wherein, the sleeping posture changes means that the sleeping posture at the current time is different from the sleeping posture at the previous time, such as converting from supine to lateral recumbency, then it is considered that the sleeping posture changes, the sleeping posture at the current time refers to the sleeping posture with the largest proportion in a preset time window TH8, such as 5 seconds. Wherein, the chest and abdominal position changes means that if the difference between the area of the chest and abdominal position frame at the current time and the area of the chest and abdominal position frame at the previous time is greater than the ratio of the area of the chest and abdominal position frame at the previous time , such as 0.25, it is considered that the position changes obviously, otherwise it is considered that the position change is not obvious, the area difference is Figure 5 the shadow area in the formula, and the chest and abdominal position frame refers to the union of the chest position frame and the abdominal position frame.

[0079] If the sleeping posture changes or the chest and abdominal position changes obviously are detected, the buffer variables related to the respiratory event detection are initialized, which can include the chest respiration signal buffer array, the chest respiration signal phase buffer array, the chest respiration signal amplitude buffer array, the chest respiratory cycle variability (RCV) buffer array, the abdominal respiration signal buffer array, the abdominal respiration signal phase buffer array, the abdominal respiration signal amplitude buffer array, the abdominal respiratory cycle variability RCV, and the chest and abdominal movement ratio buffer array. It means that some storage data variables related to respiratory event detection are restored to the initial state, which can ensure that the respiratory event detection system can more accurately monitor and analyze the respiratory event based on accurate initial data in the new state.

[0080] If it is detected that the sleeping posture is not changed or the chest-abdomen position is not changed significantly, the chest respiration signal and the abdominal respiration signal can be extracted. Taking the chest respiration signal as an example, the extraction process can be as follows: based on the predicted chest position, the chest region is determined, the pressure detection unit corresponding to the chest region is determined, and the pressure signals collected by all the pressure detection units corresponding to the chest region are summed to obtain a pressure mean value, which is the chest respiration signal. Similarly, the abdominal respiration signal can also be obtained based on the above method.

[0081] In step S130, based on the chest respiration signal and the abdominal respiration signal, it is determined whether the target object has a respiratory pause event.

[0082] Optionally, based on the chest respiration signal and the abdominal respiration signal, a respiratory event detection related variable can be obtained, and the related variable includes chest-abdomen signal features, chest-abdomen signal correlation features, and chest-abdomen signal time dimension features. Then, the chest-abdomen signal features, the chest-abdomen signal correlation features, and the chest-abdomen signal time dimension features can be combined to form a feature array, and the feature array can be input into a preset model for prediction to obtain a respiratory pause event detection result, which includes a respiratory pause event type and a probability of each respiratory pause event type. If the probability is greater than a preset threshold, it indicates that a respiratory pause event has occurred, and the type of the respiratory pause event can be determined, such as obstructive sleep apnea (OSA), central sleep apnea (CSA), or mixed sleep apnea. It should be noted that the preset model can be a decision tree model or other classification model. Alternatively, the occurrence of a respiratory pause event can also be determined by combining feature detection and logical judgment.

[0083] In step S140, if the target object has a respiratory pause event, based on the sleeping posture and the position information, an intervention scheme corresponding to the respiratory pause event is determined to adjust the air pressure of the corresponding air bag based on the intervention scheme.

[0084] Optionally, when it is detected that the target object has a respiratory pause event, a corresponding intervention scheme can be selected based on the current sleeping posture of the target object, and the air pressure of the air bag is adjusted to change the current sleeping posture of the target object, so as to intervene in the respiratory pause event, thereby achieving intervention in the respiratory pause event during sleep, reducing the influence of the respiratory pause on the target object as much as possible under the premise of not affecting the sleep of the target object. It should be noted that different respiratory pause events can correspond to different intervention schemes, and different intervention schemes can include different air pressure adjustment amplitudes of different air bags. If it is not detected that the target object has a respiratory pause event, the method can return to step S120, and the chest respiratory signal and the abdominal respiratory signal are extracted again based on the pressure signal collected at the current time, and then the respiratory pause event is judged to realize continuous cycle judgment of the respiratory pause event.

[0085] In the embodiment of the present application, the pressure detection unit is used to collect pressure signals in real time, and advanced algorithms are used to deeply analyze pressure data and accurately lock the sleeping posture, chest and abdominal positions of the target object. This unique design effectively avoids the interference of user sleeping position movement and frequent changes in sleeping posture on the monitoring results, and significantly improves the stability and accuracy of data acquisition compared with traditional monitoring methods. On this basis, the system can accurately identify different types of respiratory pause events through intelligent extraction and comparative analysis of chest and abdominal respiratory signals. No matter what type of sleep apnea, the system can quickly and accurately judge. When a respiratory pause event is detected, the system will automatically match the pre-set personalized intervention scheme according to the real-time sleeping posture of the user, and accurately adjust the air pressure of the corresponding air bag to minimize the interference with the user's sleep while effectively relieving the symptoms of respiratory pause and reducing the health risks of cardiovascular disease, cognitive impairment and other diseases caused by respiratory pause. This technical solution not only realizes a comfortable and convenient home monitoring experience, and gets rid of the limitations of traditional polysomnography (PSG) requiring hospitalization, complex equipment and high cost, but also breaks through the technical bottlenecks of poor comfort of portable devices and insufficient accuracy of emerging monitoring technologies, providing a more efficient and feasible solution for the monitoring and treatment of sleep apnea in an innovative way with low cost, high precision and humanization.

[0086] In an embodiment of the present application, the chest respiratory signal and the abdominal respiratory signal are extracted based on the chest position and the abdominal position, respectively, which includes:

[0087] Based on the chest position and the abdominal position, the chest region and the abdominal region are determined respectively, wherein the chest region and the abdominal region respectively constitute a first pressure matrix and a second pressure matrix composed of corresponding pressure detection units;

[0088] The first pressure mean value corresponding to the first pressure matrix is determined, and the first pressure mean value is taken as the chest respiratory signal;

[0089] determining a second pressure mean value corresponding to the second pressure matrix, and taking the second pressure mean value as the abdominal respiration signal.

[0090] Optionally, the pressure detection unit can include a plurality of units, and the plurality of units can be arranged in an array to detect the device, for example, a mattress. When a user lies on the mattress, the chest and abdominal regions of the user correspond to a pressure matrix composed of a plurality of pressure detection units. Taking the chest position as an example, the chest position output by the prediction model can include the center position coordinates of the chest position box, the height of the box, and the width of the box. Based on the center position coordinates, the height of the box, and the width of the box, the chest region can be calculated, and then all pressure detection units in the pressure matrix corresponding to the chest region are searched to obtain the pressure values collected by each pressure detection unit, and the mean value is taken as the chest respiration signal. Similarly, the abdominal respiration signal can also be obtained by the above method.

[0091] In an embodiment of the present application, based on the chest respiration signal and the abdominal respiration signal, it is determined whether the target object has a respiratory pause event, including:

[0092] Based on the chest respiration signal and the abdominal respiration signal, chest-abdominal signal features, chest-abdominal respiration correlation features, and chest-abdominal respiration time dimension features are determined.

[0093] Based on the determination of the chest-abdominal signal features, the chest-abdominal respiration correlation features, and the chest-abdominal respiration time dimension features, it is determined whether the target object has a respiratory pause event.

[0094] Optionally, based on the chest respiration signal and the abdominal respiration signal, a respiration event detection related variable can be obtained, and the related variable includes chest-abdominal signal features, chest-abdominal signal correlation features, and chest-abdominal signal time dimension features. Then, the chest-abdominal signal features, the chest-abdominal signal correlation features, and the chest-abdominal signal time dimension features can be combined to form a feature array, and the feature array can be input into a preset model for prediction to obtain a respiratory pause event detection result. The respiratory pause event detection result includes a respiratory pause event type and a probability of each respiratory pause event type. If the probability is greater than a preset threshold, it indicates that a respiratory pause event has occurred, and the type of the respiratory pause event can also be determined, such as obstructive sleep apnea (OSA), central sleep apnea (CSA), or mixed sleep apnea. It should be noted that the preset model can be a decision tree model or other classification model.

[0095] Alternatively, the occurrence of an apnea event can also be determined by a combination of feature detection and logical judgment. Exemplarily, if the phase difference between the thoracic and abdominal respiratory signals is greater than 120°, and the phase difference gradually increases; the thoracic respiratory amplitude increases by more than a preset threshold TH17, such as 2; the abdominal respiratory amplitude increases by more than a preset threshold TH17; the amplitude ratio of the thoracic to abdominal respiratory signals is greater than 2:1, and the duration is more than 10 seconds; and all the above conditions are met, it is considered that an obstructive sleep apnea (OSA) event occurs. If the thoracic respiratory amplitude suddenly decreases to less than 10% of the baseline; the abdominal respiratory amplitude suddenly decreases to less than 10% of the baseline; the chest and abdominal motion synchrony index (CSI) is less than 0.2; the thoracic and abdominal respiratory amplitudes are both less than 10% of the baseline, and the duration is more than 10 seconds; and all the above conditions are met, it is considered that a central sleep apnea (CSA) event occurs. If the thoracic and abdominal respiratory amplitudes suddenly decrease to less than 10% of the baseline, and the duration is not more than 10 seconds; and then a severe contradictory motion occurs, i.e., the phase difference between the thoracic and abdominal respiratory signals is greater than 30°, and the phase difference continuously increases, and the duration is more than 5 seconds; it is considered that a mixed sleep apnea event occurs.

[0096] In an embodiment of the present application, the determination of the thoraco-abdominal signal features, the thoraco-abdominal respiratory correlation features, and the thoraco-abdominal respiratory time dimension features based on the thoracic respiratory signal and the abdominal respiratory signal comprises:

[0097] The thoracic signal features corresponding to the thoracic respiratory signal and the abdominal signal features corresponding to the abdominal respiratory signal are extracted respectively, wherein the thoracic signal features include thoracic signal phase information and thoracic signal amplitude information, and the abdominal signal features include abdominal signal phase information and abdominal signal amplitude information;

[0098] The thoraco-abdominal respiratory correlation features are determined based on the thoracic signal phase information, the abdominal signal phase information, the thoracic signal amplitude information, and the abdominal signal amplitude information;

[0099] The thoraco-abdominal respiratory time dimension features are determined based on the thoracic signal phase information, the abdominal signal phase information, the thoracic signal amplitude information, and the abdominal signal amplitude information.

[0100] The thoraco-abdominal signal features can include the thoracic signal features and the abdominal signal features, the thoracic signal features can include thoracic respiratory signal phase information, thoracic respiratory signal amplitude information, and thoracic respiratory cycle variability (RCV) information, and the abdominal signal features can include abdominal respiratory signal phase information, abdominal respiratory signal amplitude information, and abdominal respiratory cycle variability (RCV) information.

[0101] The chest-abdominal respiration-related features include a phase difference between a chest respiration phase and an abdominal respiration phase, a ratio of a chest respiration amplitude to an abdominal respiration amplitude, and a chest-abdominal motion synchrony index CSI. The phase difference can be obtained by subtracting a chest respiration signal phase from an abdominal respiration signal phase based on the chest-abdominal signal features. The ratio can be obtained by dividing a chest respiration amplitude by an abdominal respiration amplitude based on the chest-abdominal signal features. The chest-abdominal motion synchrony index CSI can be calculated by the following formula:

[0102] ;

[0103] wherein, is a standard deviation of the phase difference in a preset time threshold TH15 window, and the TH15 can be 10 seconds.

[0104] The chest-abdominal respiration signal time dimension features include a chest respiration signal amplitude variation feature, an abdominal respiration signal amplitude variation feature, a chest-abdominal respiration signal phase difference variation feature, and a variation feature of a ratio of a chest signal amplitude to an abdominal signal amplitude. The variation features include a ratio of a mean value of the related features from 3 seconds before a current time to the current time to a baseline value of the feature, and a difference value between the feature at the current time and the feature at a previous time. It should be noted that the baseline value can be obtained by band-pass filtering the feature, or can be obtained by calculating a mean value from TH16, for example, 6 seconds before the current time to the current time.

[0105] In an embodiment of the present application, the chest signal features corresponding to the chest respiration signal and the abdominal signal features corresponding to the abdominal respiration signal are extracted respectively, including:

[0106] The chest respiration signal and the abdominal respiration signal are analyzed respectively, and chest signal phase information and abdominal signal phase information are obtained based on the analyzed chest respiration signal and abdominal respiration signal respectively;

[0107] Based on effective peak points and effective trough points of the chest respiration signal and the abdominal respiration signal, chest respiration amplitude information and abdominal respiration signal amplitude information are determined respectively;

[0108] Based on the effective peak points of the chest respiration signal and the abdominal respiration signal, a respiration cycle variability is calculated.

[0109] Optionally, after the chest respiration signal and the abdominal respiration signal are extracted, Hilbert transform can be performed on the chest respiration signal and the abdominal respiration signal respectively to obtain the analyzed chest respiration signal and the analyzed abdominal respiration signal, and then the chest signal phase information and the abdominal signal phase information are obtained. The effective maximum value and the effective minimum value in the chest respiration signal and the abdominal respiration signal are searched, and the effective wave peak point and the effective wave trough point are determined according to the effective maximum value and the effective minimum value. The respiration amplitude is the difference between the effective wave peak point mean value and the effective wave trough point mean value within the preset window time threshold TH10.

[0110] Respiratory cycle variability (RCV) refers to the degree of change or irregularity of the respiratory cycle in time. It reflects the difference between adjacent respiratory cycles. It can be calculated by the following formula:

[0111]

[0112] is the standard deviation of the length of the continuous respiratory cycle, which refers to the time interval between the effective adjacent wave peak points, is the average value of the length of the continuous respiratory cycle. The continuous respiration refers to detecting a preset threshold TH13, such as 50 respiratory cycles or a TH14 window time length, such as 3 minutes. The respiratory cycle needs to be removed and resampled. The removal can be using a window length of 5, and if the respiratory cycle length exceeds the mean value , the removal is performed, where is the standard deviation; the resampling can be three times spline interpolation on the removed respiratory cycle array, and the interpolated data can be 10 Hz.

[0113] In an embodiment of the present application, the chest respiration signal and the abdominal respiration signal are analyzed respectively, and the chest signal phase information and the abdominal signal phase information are obtained based on the analyzed chest respiration signal and the analyzed abdominal respiration signal, which includes:

[0114] The chest respiration signal and the abdominal respiration signal are respectively subjected to band-pass filtering processing;

[0115] The filtered chest respiration signal and the filtered abdominal respiration signal are subjected to Hilbert transform to obtain the transformed chest respiration signal and the transformed abdominal respiration signal;

[0116] The chest respiration signal phase and the abdominal respiration signal phase are obtained based on the analyzed chest respiration signal and the analyzed abdominal respiration signal;

[0117] ​​The chest respiration signal phase and the abdominal respiration signal phase are phase unwrapped to obtain the chest signal phase information and the abdominal signal phase information.

[0118] Optionally, taking the chest respiration signal as an example, the chest respiration signal can be subjected to band-pass filtering processing, which can be implemented by an IIR butterworth filter, and then a preset window time TH10 is used to perform Hilbert transform on the filtered chest respiration signal to obtain an analyzed signal, which can be shown in the following formula:

[0119] ;

[0120] wherein t is the tth sampling point, j represents an imaginary number, x(t) is an input signal, represents Hilbert transform.

[0121] Phase calculation is performed on the analyzed signal, which can be shown in the following formula:

[0122] ;

[0123] wherein arctan represents inverse tangent calculation.

[0124] Then, phase unwrapping is performed on the obtained phase to eliminate the 2π jump of the inverse tangent function, which can be shown as follows:

[0125] Starting from the first sampling point, an initial unwrapped phase is set as

[0126] ;

[0127] For each subsequent point i, the phase difference between adjacent points is calculated as

[0128] ;

[0129] If , it is indicated that there is a downward jump, and the compensation is , that is,

[0130] ;

[0131] If , it is indicated that there is an upward jump, and the compensation is , that is,

[0132] ;

[0133] Otherwise, the original value is kept.

[0134] The compensated cumulative integer multiple k is recorded to ensure the continuity of subsequent points.

[0135] Finally, phase smoothing is performed, which can be done using a moving average or low-pass filtering, to obtain the phase information of the chest signal. Similarly, the phase information of the abdominal signal can also be obtained in the same way.

[0136] In one embodiment of this application, determining the amplitude information of the chest respiratory signal and the amplitude information of the abdominal respiratory signal based on the effective peak points and effective trough points of the chest respiratory signal and the abdominal respiratory signal respectively includes:

[0137] The minimum and maximum points of the chest respiratory signal and the abdominal respiratory signal are detected respectively to obtain the effective maximum and minimum points of the chest respiratory signal and the effective maximum and minimum points of the abdominal respiratory signal.

[0138] Based on the effective maximum and minimum points of the chest respiratory signal and the effective maximum and minimum points of the abdominal respiratory signal, the effective peak and effective trough points of the chest respiratory signal and the effective peak and effective trough points of the abdominal respiratory signal are determined respectively.

[0139] Based on the effective peak and trough points of the chest respiratory signal and the effective peak and trough points of the abdominal respiratory signal, the amplitude information of the chest respiratory signal and the amplitude information of the abdominal respiratory signal are obtained respectively.

[0140] Optionally, such as Figure 6 The diagram illustrates the detection of effective peaks and troughs in a respiratory signal. For minimum point detection, if a minimum point is detected, and the corresponding minimum value is less than a preset threshold TH11-1, and the time interval between this minimum point and the previous effective minimum point is greater than a preset threshold TH12 (e.g., 2 seconds), then this minimum point is considered an effective minimum. In this case, the minimum point flag is set to a preset value (e.g., 1), and the cached effective minimum points and the preset threshold TH11 are updated. Similarly, for maximum point detection, if a maximum point is detected, and the corresponding maximum value is greater than a preset threshold TH11-2, and the minimum point flag is 1, then this point is considered a candidate peak point. The maximum value cache array and the preset threshold TH11-2 are updated, and the minimum point flag is set to 0. If the minimum point flag is 0, and a candidate peak point exists, and the maximum point is greater than the candidate peak point, then the candidate peak point is updated, i.e., this point is considered a candidate peak point. If a valid minimum value is detected, the minimum value flag is 0, and a candidate peak point exists, then the candidate peak point is taken as a valid peak point, the candidate peak points are cleared, and the minimum value flag is set to 1, and the minimum value cache array and TH11-1 are updated. When detecting valid trough points, the respiratory signal can be inverted.

[0141] It should be noted that if no valid peak point is detected within a preset window time threshold TH10, such as 20 seconds, the breathing amplitude is considered to be 0.

[0142] It should be noted that TH11-1 is strongly related to sensor characteristics, and the initial TH11-1 is obtained by statistically collecting matrix pressure sensor data of different people distributed on the bed without obvious body movement scenes, extracting the current collected breathing signal, extracting the minimum value of the breathing signal, and then obtaining the upper quartile of the minimum value. TH11-1 can be the upper quartile multiplied by a certain coefficient, for example, 0.5. The subsequent TH11-1 is updated by the minimum value cache array. TH11-2 is strongly related to sensor characteristics, and can be obtained by collecting matrix pressure sensor data of different people distributed on the bed without obvious body movement scenes, extracting the current collected breathing signal, extracting the maximum value of the breathing signal, and then obtaining the lower quartile of the maximum value. TH11-2 can be the lower quartile multiplied by a certain coefficient, for example, 0.5. The subsequent TH11-2 is updated by the maximum value cache array.

[0143] In an embodiment of the present application, the position information includes a body inclination of the target object, and the intervention scheme corresponding to the apnea event is determined based on the sleep posture and the position information, including:

[0144] Based on the position information, the contact state between the target object and each air bag is determined;

[0145] Based on the body inclination of the target object, each air bag is classified to obtain the type corresponding to each air bag;

[0146] Based on the sleep posture, the contact state, and the type corresponding to each air bag, the intervention scheme corresponding to the apnea event is determined.

[0147] Optionally, if it is detected that the target object has an apnea event, and the duration of the apnea event exceeds a preset threshold TH18, such as 10 seconds, the contact state between the target object and each contact air bag can be obtained. The contact state can be obtained by a user box composed of a user center horizontal coordinate , a user center vertical coordinate , a user box height , a user box width , and a user body inclination angle . Specifically, taking Figure 7 as an example, S11-S17 are the positions of the array pressure sensor and each air bag, the box shown by S41 is the user box, the dashed arrow shown by S42 is the vertical upward direction, the arrow shown by S43 is the direction from the user's feet to the head, and the angle between S42 and S43 is If the user box overlaps with the position box of a single air bag by an area greater than a preset threshold TH19, such as 0.1, it is considered that the user has contacted the air bag, and the contact state of the air bag is set to 1, otherwise the contact state is set to 0; if If the sleep posture is in 0°-45° or 315°-360°, it is considered that the user sleeps longitudinally with the head upward, and the air bags from top to bottom are set to categories 1, 2 and 3 respectively, Figure 7 If the sleep posture is in 0°-45° or 315°-360°, it is considered that the user sleeps longitudinally with the head upward, and the air bags from top to bottom are set to categories 1, 2 and 3 respectively, If the sleep posture is in 45°-135°, it is considered that the user sleeps transversely with the head to the left, and the air bags from left to right are set to categories 1 and 2, Figure 7 If the sleep posture is in 45°-135°, it is considered that the user sleeps transversely with the head to the left, and the air bags from left to right are set to categories 1 and 2, If the sleep posture is in 135°-225°, it is considered that the user sleeps longitudinally with the head downward, Figure 7 If the sleep posture is in 135°-225°, it is considered that the user sleeps longitudinally with the head downward, If the sleep posture is in 225°-315°, it is considered that the user sleeps transversely with the head to the right, Figure 7 If the sleep posture is in 225°-315°, it is considered that the user sleeps transversely with the head to the right,

[0148] Then, the sleep posture, the contact state of each air bag, and the type of each air bag are combined into a feature array, which is used to determine an intervention scheme corresponding to the apnea event through the feature array.

[0149] In an embodiment of the present application, the determination of the intervention scheme corresponding to the apnea event based on the sleep posture, the contact state, and the type of each air bag includes:

[0150] If the sleep posture is supine or prone, it is determined based on the contact state whether there are multiple contact air bags of the same type in contact with the target object;

[0151] If there are multiple contact air bags of the same type, a distribution mode corresponding to the multiple contact air bags of the same type is determined, and the air pressure of the contact air bags is adjusted based on the distribution mode;

[0152] If there are no multiple contact air bags of the same type, the air pressure of air bags of different types is adjusted respectively.

[0153] Optionally, based on the predicted target object sleeping posture, it is determined whether the target object is in a supine state or a prone state, and if so, it is determined whether multiple same type airbags are contacted. The same type of contact airbag refers to airbags belonging to the same category after classification based on the body inclination of the target object, such as category 1, category 2, or category 3. If multiple same type contact airbags exist, the distribution mode corresponding to the multiple same type contact airbags is determined, such as horizontal distribution or vertical distribution. If it is horizontal distribution, the air pressure of the right side airbag contacted by all target objects is increased, the air pressure of the left side airbag contacted by all target objects is decreased, and a certain difference between the air pressures of the two sides is maintained. If the multiple contacted airbags are longitudinally distributed, the air pressure of the upper side airbag contacted by all target objects is increased, the air pressure of the lower side airbag contacted by all target objects is decreased, and the user can be changed from supine to lateral recumbency.

[0154] If it is detected that the target object is in a lateral recumbency state, other sleeping posture, or there is no multiple same type contact airbag, the air pressure of each category airbag can be adjusted correspondingly, for example, the air pressure of category 1 airbag > the air pressure of category 2 airbag > the air pressure of category 3 airbag, so that the target object forms a C shape to adjust the breathing mode.

[0155] In an embodiment of the present application, after adjusting the air pressure of the corresponding airbag based on the intervention scheme, the method further comprises:

[0156] detecting whether the chest and abdominal breathing related feature changes;

[0157] If the chest and abdominal breathing related feature changes, it is determined whether the change of the chest and abdominal breathing related feature meets a preset intervention condition;

[0158] If the preset intervention condition is not met, the adjustment amplitude of the corresponding airbag is increased;

[0159] If the preset intervention condition is met, the current air pressure of the corresponding airbag is restored to the air pressure before the intervention.

[0160] The chest and abdominal breathing related feature includes the phase difference between the chest breathing phase and the abdominal breathing phase, the ratio of the chest breathing amplitude to the abdominal breathing amplitude, and the chest and abdominal motion synchronization index CSI.

[0161] If the respiratory phase difference gradually decreases and is less than a preset threshold TH20, such as 120 degrees; the chest / abdominal respiratory amplitude ratio is within a preset range; the chest-abdominal movement synchrony index is greater than a preset threshold TH21, such as 0.2; if the above requirements cannot be met simultaneously within a duration threshold TH22, if the airbag air pressure is in an adjustable state, the intervention scheme adjustment range, which refers to the size of the air pressure difference of different airbags, can be increased. If the above requirements are met simultaneously within the duration threshold TH22, the airbag air pressure distribution before intervention can be restored, which refers to the average of each airbag air pressure in a preset window time TH23 before the respiratory abnormality event is identified by S25.

[0162] In the embodiments of the present application, the pressure detection unit collects pressure signals in real time, and advanced algorithms are used to deeply analyze pressure data and accurately lock the sleeping posture, chest and abdominal position of the target object. This unique design effectively avoids the interference of user sleeping position movement and frequent changes in sleeping posture on the monitoring results, significantly improving the stability and accuracy of data collection compared with traditional monitoring methods. On this basis, the system can accurately identify different types of apnea events through intelligent extraction and comparative analysis of chest and abdominal respiratory signals. Regardless of the type of sleep apnea, rapid and accurate judgment can be achieved. When detecting the occurrence of an apnea event, the system will automatically match the pre-set personalized intervention scheme according to the user's real-time sleeping posture, and accurately adjust the air pressure of the corresponding airbag to effectively alleviate the symptoms of apnea and reduce the health risks of cardiovascular diseases, cognitive impairment and other diseases caused by apnea, while minimizing the interference with the user's sleep. This technical solution not only realizes a comfortable and convenient home monitoring experience, and eliminates the limitations of traditional polysomnography (PSG) requiring hospitalization, complex equipment and high cost, but also breaks through the technical bottlenecks of poor comfort of portable devices and insufficient accuracy of emerging monitoring technologies, providing a more efficient and feasible solution for the monitoring and treatment of sleep apnea in a low-cost, high-precision and user-friendly manner.

[0163] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0164] In an embodiment, a respiratory apnea event intervention device is provided, which corresponds to the respiratory apnea event intervention method in the above embodiments. As shown in the figure, the respiratory apnea event intervention device includes a prediction unit 10, a chest-abdominal signal extraction unit 20, a respiratory apnea event determination unit 30, and a respiratory apnea intervention unit 40. The functions of each module are described in detail as follows: Figure 8

[0165] ​The prediction unit 10 is configured to acquire the pressure signal collected by the pressure detection unit, and predict the sleeping posture and the position information of the target object based on the pressure signal, wherein the position information comprises a chest position and an abdomen position.

[0166] The thoraco-abdominal signal extraction unit 20 is configured to extract a chest respiration signal and an abdomen respiration signal based on the chest position and the abdomen position respectively.

[0167] The apnea event determination unit 30 is configured to determine whether the target object has an apnea event based on the chest respiration signal and the abdomen respiration signal.

[0168] The apnea intervention unit 40 is configured to, if the target object has an apnea event, determine an intervention scheme corresponding to the apnea event based on the sleeping posture and the position information, and adjust the air pressure of the corresponding air bag based on the intervention scheme.

[0169] In an embodiment of the present application, the apnea event determination unit 30 is further configured to:

[0170] determine a thoraco-abdominal signal feature, a thoraco-abdominal respiration correlation feature, and a thoraco-abdominal respiration time dimension feature based on the chest respiration signal and the abdomen respiration signal;

[0171] determine whether the target object has an apnea event based on the determined thoraco-abdominal signal feature, thoraco-abdominal respiration correlation feature, and thoraco-abdominal respiration time dimension feature.

[0172] In an embodiment of the present application, the device further comprises an intervention scheme adjustment unit configured to:

[0173] detect whether the thoraco-abdominal respiration correlation feature changes;

[0174] if the thoraco-abdominal respiration correlation feature changes, determine whether the change of the thoraco-abdominal respiration correlation feature meets a preset intervention condition;

[0175] if the preset intervention condition is not met, increase the adjustment amplitude of the corresponding air bag;

[0176] if the preset intervention condition is met, restore the current air pressure of the corresponding air bag to the air pressure before the intervention.

[0177] In an embodiment of the present application, the apnea event determination unit 30 is further configured to:

[0178] extract chest signal features corresponding to the chest respiratory signal and abdominal signal features corresponding to the abdominal respiratory signal, wherein the chest signal features include chest signal phase information and chest signal amplitude information, and the abdominal signal features include abdominal signal phase information and abdominal signal amplitude information;

[0179] determine the chest-abdominal respiratory correlation features based on the chest signal phase information, abdominal signal phase information, chest signal amplitude information, and abdominal signal amplitude information;

[0180] determine the chest-abdominal respiratory signal time dimension features based on the chest signal phase information, abdominal signal phase information, chest signal amplitude information, and abdominal signal amplitude information.

[0181] In an embodiment of the present application, the apnea event determination unit 30 is further configured to:

[0182] analyze the chest respiratory signal and abdominal respiratory signal respectively, and obtain chest signal phase information and abdominal signal phase information based on the analyzed chest respiratory signal and abdominal respiratory signal;

[0183] determine chest respiratory amplitude information and abdominal respiratory signal amplitude information based on effective peak points and effective trough points of the chest respiratory signal and abdominal respiratory signal respectively;

[0184] calculate respiratory cycle variability based on effective peak points of the chest respiratory signal and abdominal respiratory signal.

[0185] In an embodiment of the present application, the apnea event determination unit 30 is further configured to:

[0186] perform band-pass filtering processing on the chest respiratory signal and abdominal respiratory signal respectively;

[0187] perform Hilbert transform on the filtered chest respiratory signal and abdominal respiratory signal to obtain transformed chest respiratory signal and abdominal respiratory signal;

[0188] obtain chest respiratory signal phase and abdominal respiratory signal phase based on the analyzed chest respiratory signal and abdominal respiratory signal;

[0189] perform phase unwrapping on the chest respiratory signal phase and abdominal respiratory signal phase to obtain the chest signal phase information and abdominal signal phase information.

[0190] In an embodiment of the present application, the position information includes body inclination of the target object, and the apnea intervention unit 40 is further configured to:

[0191] determine a contact state between the target object and each air bag based on the position information;

[0192] classify each air bag based on a body inclination of the target object to obtain a corresponding type of each air bag;

[0193] determine an intervention scheme corresponding to the apnea event based on the sleeping posture, the contact state, and the corresponding type of each air bag.

[0194] In an embodiment of the present application, the apnea intervention unit 40 is further configured to:

[0195] if the sleeping posture is supine or prone, determine whether there are multiple contact air bags of the same type in contact with the target object based on the contact state;

[0196] if there are multiple contact air bags of the same type, determine a distribution mode corresponding to the multiple contact air bags of the same type, and adjust the air pressure of the contact air bags based on the distribution mode;

[0197] if there are no multiple contact air bags of the same type, adjust the air pressure of air bags of different types respectively.

[0198] In an embodiment of the present application, the chest and abdomen signal extraction unit 20 is further configured to:

[0199] determine a chest region and an abdomen region based on the chest position and the abdomen position, wherein the chest region and the abdomen region respectively form a first pressure matrix and a second pressure matrix by corresponding pressure detection units;

[0200] determine a first pressure average corresponding to the first pressure matrix, and take the first pressure average as a chest respiration signal;

[0201] determine a second pressure average corresponding to the second pressure matrix, and take the second pressure average as an abdomen respiration signal.

[0202] In the embodiments of the present application, a pressure detection unit is used to collect pressure signals in real time, advanced algorithms are used to deeply analyze the pressure data, and the sleep posture, chest and abdominal positions of the target object are accurately locked. This unique design effectively avoids the interference of user sleep position movement and frequent changes in sleep posture on the monitoring results, significantly improving the stability and accuracy of data collection compared with traditional monitoring methods. On this basis, the system can accurately identify different types of apnea events through intelligent extraction and comparative analysis of chest and abdominal respiratory signals. Regardless of the type of sleep apnea, rapid and accurate judgment can be achieved. When an apnea event is detected, the system will automatically match the pre-set personalized intervention scheme according to the user's real-time sleep posture, accurately adjust the air pressure of the corresponding air bag, minimize the interference with the user's sleep, effectively relieve the symptoms of apnea, and reduce the health risks of cardiovascular diseases, cognitive impairment and other diseases caused by apnea. This technical solution not only realizes a comfortable and convenient home monitoring experience, and gets rid of the limitations of traditional polysomnography (PSG) requiring hospitalization, complex equipment and high cost, but also breaks through the technical bottlenecks of poor comfort of portable devices and insufficient accuracy of emerging monitoring technologies, providing a more efficient and feasible solution for the monitoring and treatment of sleep apnea in a low-cost, high-precision and user-friendly manner.

[0203] The specific limitations of the intervention device for the apnea event can be referred to the limitations of the intervention method for the apnea event in the above, which will not be repeated here. Each module in the intervention device for the apnea event can be realized by software, hardware and their combination in whole or in part. Each module can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to each module by the processor.

[0204] In one embodiment, a computer device, which can be a terminal device, has an internal structure as shown in Figure 9 The computer device includes a processor, a memory and a network interface connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer readable instructions. The network interface of the computer device is used to communicate with external terminals through network connection. The computer readable instructions are executed by the processor to implement an intervention method for an apnea event. The readable storage medium provided in the embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0205] In the embodiments of the present application, a computer device is provided, which comprises a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, and the processor implements the steps of the intervention method for apnea event as described above when executing the computer readable instructions.

[0206] In the embodiments of the present application, a readable storage medium is provided, which stores computer readable instructions, and the computer readable instructions implement the steps of the intervention method for apnea event as described above when executed by a processor.

[0207] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by computer readable instructions instructing related hardware, and the computer readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium, and when executed, can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0208] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0209] The above examples are only used to illustrate the technical solutions of the present application, but not limit the same; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent ones; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An intervention device for sleep apnea events, characterized in that, An application in a respiratory intervention device, the device comprising multiple pressure detection units and an airbag, the device including: The prediction unit is used to acquire the pressure signal collected by the pressure detection unit, and based on the pressure signal, predict the sleeping posture and position information of the target object, including the position information of the chest, abdomen and body tilt. The chest and abdomen signal extraction unit is used to extract chest respiratory signals and abdominal respiratory signals based on the chest position and the abdomen position, respectively. An apnea event determination unit is used to acquire the phase difference, chest / abdominal respiratory amplitude, and synchronicity index of the chest and abdominal respiratory signals based on the chest and abdominal respiratory signals to determine whether the target subject has experienced an apnea event. Specifically, if the phase difference of the chest and abdominal respiratory signals is greater than 120° and gradually increases; the chest respiratory amplitude increases beyond a preset threshold; the abdominal respiratory amplitude increases beyond a preset threshold; and the chest / abdominal respiratory signal amplitude ratio is greater than 2:1 and lasts for more than 10 seconds, an obstructive apnea event is indicated. If the chest respiratory amplitude suddenly decreases to below 10% of the baseline; the abdominal respiratory amplitude suddenly decreases to below 10% of the baseline; the chest / abdominal movement synchronicity index is less than 0.2; and both chest and abdominal respiratory amplitudes are below 10% of the baseline and last for more than 10 seconds, a central apnea event is indicated. If first the chest and abdominal respiratory amplitude suddenly decreases to below 10% of the baseline and lasts for no more than 10 seconds, followed by violent contradictory movements (i.e., the phase difference of the chest and abdominal respiratory signals is greater than 30° and continues to increase, lasting for more than 5 seconds), a mixed apnea event is considered to have occurred. An apnea intervention unit is used to determine the contact state between the target object and each airbag based on the location information if the target object experiences an apnea event; classify each airbag based on the target object's body tilt to obtain the corresponding type of each airbag; and determine an intervention plan corresponding to the apnea event based on the sleeping posture, contact state, and corresponding type of each airbag, so as to adjust the air pressure of the corresponding airbag based on the intervention plan.

2. The intervention device for sleep apnea events as described in claim 1, characterized in that, The apnea event determination unit is further configured to: Based on the chest and abdominal respiratory signals, chest and abdominal signal characteristics, chest and abdominal respiratory correlation characteristics, and chest and abdominal respiratory time dimension characteristics are determined. Based on the determined chest and abdominal signal characteristics, chest and abdominal respiratory correlation characteristics, and chest and abdominal respiratory signal time dimension characteristics, it is determined whether the target object has experienced a sleep apnea event.

3. The intervention device for sleep apnea events as described in claim 2, characterized in that, The apnea event determination unit is further configured to: Chest signal features corresponding to the chest breathing signal and abdominal signal features corresponding to the abdominal breathing signal are extracted respectively. The chest signal features include chest signal phase information and chest signal amplitude information, and the abdominal signal features include abdominal signal phase information and abdominal signal amplitude information. Based on the chest signal phase information, abdominal signal phase information, chest signal amplitude information, and abdominal signal amplitude information, the chest and abdominal respiratory correlation characteristics are determined. Based on the chest signal phase information, abdominal signal phase information, chest signal amplitude information, and abdominal signal amplitude information, the temporal dimension characteristics of the chest and abdominal respiratory signals are determined.

4. The intervention device for sleep apnea events as described in claim 3, characterized in that, The apnea event determination unit is further configured to: The chest respiratory signal and the abdominal respiratory signal are analyzed separately, and the chest signal phase information and the abdominal signal phase information are obtained based on the analyzed chest respiratory signal and abdominal respiratory signal, respectively. Based on the effective peak points and effective trough points of the chest respiratory signal and the abdominal respiratory signal, the amplitude information of the chest respiratory signal and the amplitude information of the abdominal respiratory signal are determined respectively. The respiratory cycle variability is calculated based on the effective peak points of the chest and abdominal respiratory signals.

5. The intervention device for sleep apnea events as described in claim 4, characterized in that, The apnea event determination unit is further configured to: The chest respiratory signal and the abdominal respiratory signal were respectively subjected to bandpass filtering. Hilbert transform is performed on the filtered chest and abdominal respiratory signals to obtain the transformed chest and abdominal respiratory signals. Based on the parsed chest and abdominal respiratory signals, the phases of the chest and abdominal respiratory signals are obtained. Phase unwinding is performed on the chest respiratory signal phase and the abdominal respiratory signal phase to obtain the chest signal phase information and the abdominal signal phase information.

6. The intervention device for sleep apnea events as described in claim 1, characterized in that, The sleep apnea intervention unit is also used for: If the sleeping position is supine or prone, based on the contact state, determine whether there are multiple contact airbags of the same type that have a contact relationship with the target object; If there are multiple contact airbags of the same type, determine the distribution pattern of the multiple contact airbags of the same type, and adjust the air pressure of the contact airbags accordingly based on the distribution pattern; If there are not multiple contact airbags of the same type, adjust the air pressure of each type of airbag accordingly.

7. The intervention device for sleep apnea events as described in any one of claims 1-6, characterized in that, The device further includes an intervention program adjustment unit for: Detect whether there are changes in chest and abdominal respiratory characteristics; If the chest and abdominal respiratory correlation characteristics change, determine whether the change in the chest and abdominal respiratory correlation characteristics meets the preset intervention conditions. If the preset intervention conditions are not met, the adjustment range of the corresponding airbag will be increased; If the preset intervention conditions are met, the current air pressure of the corresponding airbag will be restored to the air pressure before the intervention.

8. The intervention device for sleep apnea events as described in any one of claims 1-6, characterized in that, The chest and abdominal signal extraction unit is also used for: Based on the chest and abdomen positions, the regions where the chest and abdomen are located are determined respectively, wherein the regions where the chest and abdomen are located are respectively composed of a first pressure matrix and a second pressure matrix by corresponding pressure detection units; Determine the first average pressure value corresponding to the first pressure matrix, and use the first average pressure value as the chest breathing signal; Determine the second average pressure value corresponding to the second pressure matrix, and use the second average pressure value as the abdominal breathing signal.

Images