Respiration monitoring method and system based on flexible wearable component

Abstract

The invention relates to a breath monitoring method and system based on a flexible wearable component, and the method comprises the steps: transmitting data collected by a wearable pressure sensor to an embedded upper computer, and enabling a data collection process of the upper computer to adjust the size of a window of a window watchdog according to the breath frequency; when a certain amount of data is collected, an action of feeding a dog to the window watchdog is executed; the respiration monitoring process of the upper computer adjusts the value of a prescaler of a monitoring watchdog according to the duration when the data is lower than the threshold value, and the respiration monitoring process feeds a dog to the monitoring watchdog at regular time; when the monitoring watchdog triggers advanced wakeup interruption, the monitoring watchdog sends an instruction for adjusting a data storage strategy and window adjustment to a data acquisition process, the data acquisition process adjusts a data storage mode according to the data storage strategy, and the window watchdog adjusts the size of a window according to the window adjustment instruction; the respiration monitoring process monitors respiration according to the collected data.

Description

Technical Field

[0001] The present invention relates to the field of monitoring, and in particular to a respiratory monitoring method and system based on a flexible wearable component. Background Art

[0002] Breathing is an essential function for maintaining a normal life, and the normal functioning of the respiratory function is essential for maintaining metabolic balance and organ health. Any respiratory disorder will have a serious impact on the human body. Respiratory monitoring mainly includes contact monitoring and non-contact monitoring. Contact monitoring includes respiratory airflow monitoring, thermocouple monitoring, respiratory induction volume monitoring, impedance monitoring, etc. Non-contact monitoring mainly includes infrared imaging, bio-radar, etc.

[0003] In recent years, wearable device technology has developed rapidly. Using biosensors, intelligent algorithms and wireless communication technology, people can more conveniently collect and monitor long-term and continuous health data. However, existing wearable respiratory monitoring devices still have certain limitations in accuracy and real-time performance. Especially when detecting complex physiological events such as apnea, there is still much room for improvement in the accuracy of data processing and the sensitivity of response. Apnea is a common but dangerous pathological phenomenon. If it is not effectively managed for a long time, it may lead to cardiovascular disease, metabolic abnormalities and even sudden death. Apnea is the focus of respiratory monitoring. When apnea occurs, the monitoring equipment may run away or fail to collect data, which will have a great impact and even endanger life. Summary of the invention

[0004] In order to prevent abnormality of the monitoring device during apnea, the present invention provides a respiratory monitoring method based on a flexible wearable component, the method comprising the following steps: The data collected by the wearable pressure sensor is sent to the embedded host computer. The data collection process of the host computer adjusts the window size of the window watchdog according to the breathing frequency, and feeds the window watchdog when a certain amount of data is collected. If the dog is not fed within the window period, the window watchdog sends a reset signal to the pressure sensor and reinitializes the data collection process. The respiratory monitoring process of the host computer adjusts the value of the pre-divider of the monitoring watchdog according to the duration of the data being lower than the threshold, and the respiratory monitoring process feeds the monitoring watchdog regularly; when the monitoring watchdog triggers an early wake-up interrupt, the monitoring watchdog sends instructions for adjusting the data storage strategy and window adjustment to the data acquisition process, the data acquisition process adjusts the data storage method according to the data storage strategy, and the window watchdog adjusts the window size according to the window adjustment instruction; The respiration monitoring process monitors respiration based on the collected data.

[0005] Preferably, the data acquisition process of the host computer adjusts the window size of the window watchdog according to the respiratory frequency, specifically: Calculate the relative change rate between the current respiratory rate and the average respiratory rate, and obtain the preset window size of the window watchdog; A weight is obtained according to the relative change rate, and the preset window size is weighted by using the weight to obtain the window size of the window watchdog.

[0006] Preferably, the respiratory monitoring process of the host computer adjusts the value of the prescaler of the monitoring watchdog according to the duration of the data being lower than the threshold, specifically: Set multiple time intervals, each time interval corresponds to a prescaler value; The value of the prescaler is determined according to the time interval in which the data falls below the threshold.

[0007] Preferably, the data collection process adjusts the data preservation mode according to the data preservation strategy, specifically: When the data acquisition receives the instruction to adjust the data storage strategy, the value of the prescaler of the monitoring watchdog is obtained. If the value of the pre-divider is less than the preset value, the data acquisition process adopts a real-time data stream preservation strategy, otherwise, the data acquisition process adopts a non-real-time data stream preservation strategy and increases the frequency of data preservation in the data acquisition process.

[0008] Preferably, the breathing monitoring process monitors breathing according to the collected data, specifically: Counting the average duration of the data between two inhalations during normal breathing being lower than the threshold, if the duration of the monitoring thread statistical data in the respiratory monitoring process being lower than the threshold is greater than the weighted value of the average, issuing a apnea warning; After the apnea warning is issued, the respiratory monitoring process obtains data from the maximum value of the last normal inspiration to the current moment and constructs a waveform, and uses a shape context algorithm to determine the type of apnea.

[0009] On the other hand, the present invention also provides a respiratory monitoring system based on a flexible wearable component, the system comprising the following modules: The data acquisition module is used to send the data collected by the wearable pressure sensor to the embedded host computer. The data acquisition process of the host computer adjusts the window size of the window watchdog according to the breathing frequency, and feeds the window watchdog when a certain amount of data is collected. If the dog is not fed within the window period, the window watchdog sends a reset signal to the pressure sensor and reinitializes the data acquisition process; The system monitoring module is used for the respiratory monitoring process of the host computer to adjust the value of the pre-divider of the monitoring watchdog according to the duration of the data being lower than the threshold, and the respiratory monitoring process feeds the monitoring watchdog regularly; when the monitoring watchdog triggers an early wake-up interrupt, the monitoring watchdog sends an instruction to adjust the data storage strategy and window adjustment to the data acquisition process, the data acquisition process adjusts the data storage mode according to the data storage strategy, and the window watchdog adjusts the window size according to the window adjustment instruction; The breathing monitoring module is used to monitor breathing based on the collected data by the breathing monitoring process.

[0010] Preferably, the data acquisition process of the host computer adjusts the window size of the window watchdog according to the respiratory frequency, specifically: Calculate the relative change rate between the current respiratory rate and the average respiratory rate, and obtain the preset window size of the window watchdog; A weight is obtained according to the relative change rate, and the preset window size is weighted by using the weight to obtain the window size of the window watchdog.

[0011] Preferably, the respiratory monitoring process of the host computer adjusts the value of the prescaler of the monitoring watchdog according to the duration of the data being lower than the threshold, specifically: Set multiple time intervals, each time interval corresponds to a prescaler value; The value of the prescaler is determined according to the time interval in which the data falls below the threshold.

[0012] Preferably, the data collection process adjusts the data preservation mode according to the data preservation strategy, specifically: When the data acquisition receives the instruction to adjust the data storage strategy, the value of the prescaler of the monitoring watchdog is obtained. If the value of the pre-divider is less than the preset value, the data acquisition process adopts a real-time data stream preservation strategy, otherwise, the data acquisition process adopts a non-real-time data stream preservation strategy and increases the frequency of data preservation in the data acquisition process.

[0013] Preferably, the breathing monitoring process monitors breathing according to the collected data, specifically: Counting the average duration of the data between two inhalations during normal breathing being lower than the threshold, if the duration of the monitoring thread statistical data in the respiratory monitoring process being lower than the threshold is greater than the weighted value of the average, issuing a apnea warning; After the apnea warning is issued, the respiratory monitoring process obtains data from the maximum value of the last normal inspiration to the current moment and constructs a waveform, and uses a shape context algorithm to determine the type of apnea.

[0014] In addition, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0015] Compared with the prior art, the present invention has the following beneficial technical effects and significant technical progress. Specifically, the window size of the window watchdog is adjusted according to the respiratory frequency, and the value of the pre-divider of the monitoring watchdog is adjusted according to the duration of the data being below the threshold. When apnea may occur, the window size and the division coefficient of the pre-divider can be reduced, the probability of data leakage caused by possible abnormalities in the data acquisition process is reduced, and the problem of the monitoring process being unable to monitor in time when apnea may occur is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of Embodiment 1; Figure 2 is the relationship between the center point and the offset in the heat map; Figure 3 Schematic diagram of the trajectory and center point matching process; Figure 4 This is a structural diagram of the second embodiment. DETAILED DESCRIPTION

[0017] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Example 1 See also Figure 1 The present invention provides a respiratory monitoring method based on a flexible wearable component, the method comprising the following steps: Step 1: Send the data collected by the wearable pressure sensor to the embedded host computer. The data collection process of the host computer adjusts the window size of the window watchdog according to the breathing frequency, and feeds the window watchdog when a certain amount of data is collected. If the dog is not fed within the window period, the window watchdog sends a reset signal to the pressure sensor and reinitializes the data collection process; The wearable respiratory monitoring device of the present invention includes two parts, the first part is a wearable component, and the second part is an embedded host computer; the wearable component includes a pressure sensor and a single-chip microcomputer, and the single-chip microcomputer is used to send the data of the pressure sensor to the host computer, see Figure 2 The wearable component is a pair of shorts or a belt with a pressure sensor, and the pressure sensor is preferably a flexible pressure sensor. In a more specific embodiment, the pressure sensor is a piezoelectric film pressure sensor.

[0020] The pressure sensor can sense the pressure changes in the chest cavity or airway. These changes fluctuate with the breathing cycle (inhalation and exhalation). The pressure sensor will continuously transmit pressure data to the microcontroller through its hardware interface (such as I2C or SPI). The microcontroller will further send the pressure data to the embedded host computer via wired or wireless means.

[0021] The window watchdog is used to detect whether the data acquisition process of the host computer is running normally. Since the wearable component and the embedded host computer are easily affected by the communication environment during communication, the present invention uses a window watchdog for the acquisition process. If the process feeds the dog before the window, the watchdog will determine that the operation is invalid and regard it as a system abnormality. If the data acquisition process does not perform the "feed the dog" operation within the specified time, the window watchdog will think that the data acquisition process is stuck and take measures such as reset. The window watchdog means that within a certain time window, the data acquisition process must perform the dog feeding operation.

[0022] In most cases, especially in obstructive sleep apnea (OSA), the respiratory rate tends to gradually decrease before apnea occurs. This phenomenon is mainly due to the gradual occurrence of airway obstruction, which makes breathing more and more difficult until it stops completely, i.e. apnea; in addition, when the respiratory rate is abnormally high, it is also necessary to strengthen monitoring. When the respiratory rate is abnormal, in order to prevent the failure to collect data due to abnormal data collection process, in an optional embodiment, the data collection process of the host computer adjusts the window size of the window watchdog according to the respiratory frequency, specifically: Calculate the relative change rate between the current respiratory rate and the average respiratory rate, and obtain the preset window size of the window watchdog; A weight is obtained according to the relative change rate, and the preset window size is weighted by using the weight to obtain the window size of the window watchdog.

[0023] The relative rate of change is calculated as |current respiratory rate-average respiratory rate| / average respiratory rate. For example, if the current respiratory rate is 10 and the average respiratory rate is 15, the relative rate of change is 0.33. In one embodiment, in the weight obtained according to the relative rate of change, the specific calculation method of the weight is 1 / (1+k×relative rate of change), where k is the adjustment coefficient. Assuming k=2, the weight is 0.6. The weight is used to weight the preset window size, that is, the product of the preset window size and the weight is used as the window size of the window watchdog. Assuming the preset window is 2s, the calculated window size of the window watchdog is 1.2s. The window becomes smaller, and the timing of feeding the dog in the data acquisition process is more stringent. If the dog is not fed within the window, it is very likely that an abnormality has occurred. A reset signal is sent to the pressure sensor faster, and the data acquisition process is reinitialized, which can reduce the loss of collected data. In another embodiment, if the window watchdog is fed in advance, a reset operation will also be triggered.

[0024] When the window watchdog triggers a reset, the data acquisition thread will be reinitialized, and in another embodiment, the wearable component reset will also be triggered.

[0025] Step 2: The respiratory monitoring process of the host computer adjusts the value of the prescaler of the monitoring watchdog according to the duration of the data being lower than the threshold, and the respiratory monitoring process feeds the monitoring watchdog regularly; when the monitoring watchdog triggers an early wake-up interrupt, the monitoring watchdog sends an instruction to adjust the data storage strategy and window adjustment to the data acquisition process, the data acquisition process adjusts the data storage mode according to the data storage strategy, and the window watchdog adjusts the window size according to the window adjustment instruction; The prescaler is a part of the watchdog timer, which is used to control the counting speed of the watchdog timer. The prescaler is an important parameter of the prescaler, and the division coefficient is WTGTB, which determines the time interval of the counter decreasing by one. When the collected data is lower than the threshold for a long time, apnea may occur. At this time, the prescaler division coefficient is continuously reduced to speed up the counting speed and reduce the missed detection of apnea caused by possible abnormalities in the monitoring process.

[0026] In an optional embodiment, the respiratory monitoring process of the host computer adjusts the value of the prescaler of the monitoring watchdog according to the duration of the data being lower than the threshold, specifically: Set multiple time intervals, each time interval corresponds to a prescaler value; The value of the prescaler is determined according to the time interval in which the data falls below the threshold.

[0027] For example, two time intervals [t1, t2) and [t2, t3] are set, where the value of the pre-divider corresponding to the first time interval, that is, the division coefficient, is f1, and the value of the pre-divider corresponding to the second time interval, that is, the division coefficient, is f2, where t3>t2>t1, f1>f2, when the duration is in the first time interval, the division coefficient f1 is used, and when the duration is in the second time interval, the division coefficient f2 is used.

[0028] The respiratory monitoring process feeds the monitoring watchdog regularly. When the monitoring watchdog triggers an early wake-up interrupt, the monitoring watchdog sends instructions to the data acquisition process to adjust the data storage strategy and window adjustment, and adjusts the data storage strategy of the data acquisition process. In a specific embodiment, the data acquisition process adjusts the data storage method according to the data storage strategy, specifically: When the data acquisition receives the instruction to adjust the data storage strategy, the value of the prescaler of the monitoring watchdog is obtained. If the value of the pre-divider is less than the preset value, the data acquisition process adopts a real-time data stream preservation strategy, otherwise, the data acquisition process adopts a non-real-time data stream preservation strategy and increases the frequency of data preservation in the data acquisition process.

[0029] The data acquisition process determines the current system status by obtaining the prescaler value of the monitoring watchdog. The prescaler value of the watchdog determines the counting frequency of the watchdog timer. The smaller the prescaler value, the faster the watchdog timer counts, and the system needs to execute tasks more frequently, which often reflects that the system is in a more urgent state.

[0030] Determine the relationship between the pre-divider value and the preset value. If the pre-divider value is less than the preset value, it means that the possibility of apnea is greater, and as the pre-divider value, i.e., the frequency division coefficient, decreases, the possibility of apnea increases, and the data acquisition process will enable the real-time data stream saving strategy, that is, save immediately after each data acquisition. This is to ensure that in the case of apnea, all data can be saved in time without losing any key information. If the pre-divider value is greater than or equal to the preset value, the system believes that it may be apnea, but the possibility is not as great as described above. At this time, the data acquisition process can use a non-real-time data stream saving strategy, that is, save the data in batches to the storage device. At the same time, in order to ensure that the data will not lag for a long time, the system will increase the frequency of data saving to ensure that the data saving frequency is fast enough, but it does not need to be saved in real time to save system resources. For example, the collected data was originally saved to the disk every 2s. After increasing the frequency of data saving in the data acquisition process, the collected data is saved to the disk every 1s. The window watchdog adjusts the window size according to the window adjustment instruction, specifically, the window size is reduced by a preset ratio, for example, reduced to 90% of the original.

[0031] If the reset signal of the monitoring watchdog is further triggered after the early wake-up interrupt is triggered, the embedded host computer is reset.

[0032] Step 3: Respiration monitoring process The respiration is monitored based on the collected data.

[0033] During normal operation, the respiratory monitoring process will monitor breathing based on the collected data, and calculate the average duration of the time when the data between two inhalations during normal breathing is lower than the threshold. If the duration of the statistical data of the monitoring thread in the respiratory monitoring process being lower than the threshold is greater than the weighted value of the average value, a apnea warning will be issued.

[0034] Under normal breathing conditions, the respiratory monitoring process will count the time period when the data between two breaths is below the threshold and calculate the average value of this time period. Below the threshold here may mean that the respiratory data drops below a certain set level. In normal breathing, as exhalation and inhalation proceed, the pressure corresponding to the last breath is the largest. The time period when the data between two consecutive breaths is below the threshold is also the time period when the data between the two corresponding pressure maximums is below the threshold. Figure 3 If the continuous time that the data is below the threshold is greater than the weighted value of the average value, it is considered that apnea has occurred, wherein the weighted value of the average value is specifically weighted for the average value, and the weight is a value greater than 1.

[0035] And after issuing a warning of apnea, the respiratory monitoring process obtains data from the maximum value of the last normal inspiration to the current moment and constructs a waveform, and uses a shape context algorithm to determine the type of apnea.

[0036] There are several types of apnea, including obstructive sleep apnea (OSA), central sleep apnea (CSA), etc. The waveforms of these apneas are different. In order to identify the specific type of apnea, the waveform is constructed using the collected data from the maximum value of the last normal inhalation to the current moment, and the shape context algorithm is used to determine the specific type of apnea.

[0037] Example 2 The present invention also provides a respiratory monitoring system based on a flexible wearable component, the system comprising the following modules: The data acquisition module is used to send the data collected by the wearable pressure sensor to the embedded host computer. The data acquisition process of the host computer adjusts the window size of the window watchdog according to the breathing frequency, and feeds the window watchdog when a certain amount of data is collected. If the dog is not fed within the window period, the window watchdog sends a reset signal to the pressure sensor and reinitializes the data acquisition process; The system monitoring module is used for the respiratory monitoring process of the host computer to adjust the value of the pre-divider of the monitoring watchdog according to the duration of the data being lower than the threshold, and the respiratory monitoring process feeds the monitoring watchdog regularly; when the monitoring watchdog triggers an early wake-up interrupt, the monitoring watchdog sends an instruction to adjust the data storage strategy and window adjustment to the data acquisition process, the data acquisition process adjusts the data storage mode according to the data storage strategy, and the window watchdog adjusts the window size according to the window adjustment instruction; The breathing monitoring module is used to monitor breathing based on the collected data by the breathing monitoring process.

[0038] Preferably, the data acquisition process of the host computer adjusts the window size of the window watchdog according to the respiratory frequency, specifically: Calculate the relative change rate between the current respiratory rate and the average respiratory rate, and obtain the preset window size of the window watchdog; A weight is obtained according to the relative change rate, and the preset window size is weighted by using the weight to obtain the window size of the window watchdog.

[0039] Preferably, the respiratory monitoring process of the host computer adjusts the value of the prescaler of the monitoring watchdog according to the duration of the data being lower than the threshold, specifically: Set multiple time intervals, each time interval corresponds to a prescaler value; The value of the prescaler is determined according to the time interval in which the data falls below the threshold.

[0040] Preferably, the data collection process adjusts the data preservation mode according to the data preservation strategy, specifically: When the data acquisition receives the instruction to adjust the data storage strategy, the value of the prescaler of the monitoring watchdog is obtained. If the value of the pre-divider is less than the preset value, the data acquisition process adopts a real-time data stream preservation strategy, otherwise, the data acquisition process adopts a non-real-time data stream preservation strategy and increases the frequency of data preservation in the data acquisition process.

[0041] Preferably, the breathing monitoring process monitors breathing according to the collected data, specifically: Counting the average duration of the data between two inhalations during normal breathing being lower than the threshold, if the duration of the monitoring thread statistical data in the respiratory monitoring process being lower than the threshold is greater than the weighted value of the average, issuing a apnea warning; After the apnea warning is issued, the respiratory monitoring process obtains data from the maximum value of the last normal inspiration to the current moment and constructs a waveform, and uses a shape context algorithm to determine the type of apnea.

[0042] Example 3 The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in Example 1 is implemented.

[0043] Through the description of the above implementation methods, technicians in this field can clearly understand that each implementation method can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it, and other embodiments may also be used. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A respiratory monitoring method based on a flexible wearable component, characterized in that: The method comprises the following steps: The data collected by the wearable pressure sensor is sent to the embedded host computer. The data collection process of the host computer adjusts the window size of the window watchdog according to the breathing frequency, and feeds the window watchdog when a certain amount of data is collected. If the dog is not fed within the window period, the window watchdog sends a reset signal to the pressure sensor and reinitializes the data collection process. The respiratory monitoring process of the host computer adjusts the value of the pre-divider of the monitoring watchdog according to the duration of the data being lower than the threshold, and the respiratory monitoring process feeds the monitoring watchdog regularly; when the monitoring watchdog triggers an early wake-up interrupt, the monitoring watchdog sends instructions for adjusting the data storage strategy and window adjustment to the data acquisition process, the data acquisition process adjusts the data storage method according to the data storage strategy, and the window watchdog adjusts the window size according to the window adjustment instruction; The respiration monitoring process monitors respiration based on the collected data.

2. The method according to claim 1, characterized in that The data acquisition process of the host computer adjusts the window size of the window watchdog according to the respiratory frequency, specifically: Calculate the relative change rate between the current respiratory rate and the average respiratory rate, and obtain the preset window size of the window watchdog; A weight is obtained according to the relative change rate, and the preset window size is weighted by using the weight to obtain the window size of the window watchdog.

3. The method according to claim 1, characterized in that The respiratory monitoring process of the host computer adjusts the value of the prescaler of the monitoring watchdog according to the duration of the data being lower than the threshold, specifically: Set multiple time intervals, each time interval corresponds to a prescaler value; The value of the prescaler is determined according to the time interval in which the data falls below the threshold.

4. The method according to claim 1, characterized in that The data collection process adjusts the data storage method according to the data storage strategy, specifically: When the data acquisition receives the instruction to adjust the data storage strategy, the value of the prescaler of the monitoring watchdog is obtained. If the value of the pre-divider is less than the preset value, the data acquisition process adopts a real-time data stream preservation strategy, otherwise, the data acquisition process adopts a non-real-time data stream preservation strategy and increases the frequency of data preservation in the data acquisition process.

5. The method according to claim 1, characterized in that The breathing monitoring process monitors breathing according to the collected data, specifically: Counting the average duration of the data between two inhalations during normal breathing being lower than the threshold, if the duration of the monitoring thread statistical data in the respiratory monitoring process being lower than the threshold is greater than the weighted value of the average, issuing a apnea warning; After the apnea warning is issued, the respiratory monitoring process obtains data from the maximum value of the last normal inspiration to the current moment and constructs a waveform, and uses a shape context algorithm to determine the type of apnea.

6. A respiratory monitoring system based on a flexible wearable component, characterized in that: The system includes the following modules: The data acquisition module is used to send the data collected by the wearable pressure sensor to the embedded host computer. The data acquisition process of the host computer adjusts the window size of the window watchdog according to the breathing frequency, and feeds the window watchdog when a certain amount of data is collected. If the dog is not fed within the window period, the window watchdog sends a reset signal to the pressure sensor and reinitializes the data acquisition process; The system monitoring module is used for the respiratory monitoring process of the host computer to adjust the value of the pre-divider of the monitoring watchdog according to the duration of the data being lower than the threshold, and the respiratory monitoring process feeds the monitoring watchdog regularly; when the monitoring watchdog triggers an early wake-up interrupt, the monitoring watchdog sends an instruction to adjust the data storage strategy and window adjustment to the data acquisition process, the data acquisition process adjusts the data storage mode according to the data storage strategy, and the window watchdog adjusts the window size according to the window adjustment instruction; The breathing monitoring module is used to monitor breathing based on the collected data by the breathing monitoring process.

7. The system according to claim 6, characterized in that The data acquisition process of the host computer adjusts the window size of the window watchdog according to the respiratory frequency, specifically: Calculate the relative change rate between the current respiratory rate and the average respiratory rate, and obtain the preset window size of the window watchdog; A weight is obtained according to the relative change rate, and the preset window size is weighted by using the weight to obtain the window size of the window watchdog.

8. The system according to claim 6, characterized in that The respiratory monitoring process of the host computer adjusts the value of the prescaler of the monitoring watchdog according to the duration of the data being lower than the threshold, specifically: Set multiple time intervals, each time interval corresponds to a prescaler value; The value of the prescaler is determined according to the time interval in which the data falls below the threshold.

9. The system according to claim 6, characterized in that The data collection process adjusts the data storage method according to the data storage strategy, specifically: When the data acquisition receives the instruction to adjust the data storage strategy, the value of the prescaler of the monitoring watchdog is obtained. If the value of the pre-divider is less than the preset value, the data acquisition process adopts a real-time data stream preservation strategy, otherwise, the data acquisition process adopts a non-real-time data stream preservation strategy and increases the frequency of data preservation in the data acquisition process.

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

Images