Ventilator control method and system based on sleep behavior data

Abstract

The application is suitable for the technical field of breathing machines, and particularly relates to a breathing machine control method and system based on sleep behavior data. The method comprises the following steps: obtaining behavior data and first operation data; wherein the behavior data comprises first behavior data for reflecting the movement of the abdominal cavity diaphragm of a user during sleep and second behavior data for reflecting the breathing movement of the user during sleep; determining an adjustment gain parameter based on the first behavior data; identifying sleep feature data for reflecting the actual required breathing machine tidal volume adjustment requirement of the user during the sleep process from the first operation data based on the second behavior data and the adjustment gain parameter; and generating second operation data based on the sleep feature data and the adjusted first operation data after the adjustment of the first operation data based on the adjustment gain parameter. The method makes the tidal volume of the breathing machine in line with the sleep habits of the user during night sleep, thereby improving the use experience of the breathing machine.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of respirators, and particularly relates to a respirator control method and system based on sleep behavior data. BACKGROUND

[0002] A respirator is a medical device that can replace, control or change normal physiological respiration of a human, increase lung ventilation and improve respiratory function. Respirators are generally divided into invasive respirators and non-invasive respirators. The invasive respirator is generally used on a user in a critical condition and completely unable to breathe independently. The invasive respirator is directly inserted into the airway (trachea) of the user through surgery or medical operation, and then connected to the respirator to perform invasive ventilation to maintain normal breathing of the user. The non-invasive respirator is generally used on a user in a relatively light condition and still having a certain self-breathing ability. The non-invasive respirator is used in a non-invasive manner such as a mask (nose mask, mouth and nose mask, etc.) or a nasal catheter to deliver air flow to the respiratory tract of the user and work in cooperation with the self-breathing of the user.

[0003] In the related art, the non-invasive respirator is generally used on a user with sleep disorders, such as respiratory pause, low ventilation and low blood oxygen during sleep of the user. A user with severe sleep disorders may endanger life during sleep. The treatment method of the non-invasive respirator is generally to set a fixed tidal volume based on physiological data of the user in a wake state to achieve ventilation support, and then the tidal volume can be automatically adjusted according to the respiratory flow of the user. However, the existing automatic adjustment algorithm is designed based on the average data of the sleep-disordered user, and the tidal volume cannot be accurately matched, resulting in frequent occurrence of high pressure (throat discomfort) or low pressure (snoring aggravation) in some users during sleep, thereby reducing the adaptability of the respirator. SUMMARY

[0004] The embodiments of the present application provide a respirator control method and system based on sleep behavior data, which can improve the problem of low adaptability of the respirator.

[0005] In a first aspect, the embodiments of the present application provide a respirator control method based on sleep behavior data, comprising:

[0006] obtaining behavior data and first running data; wherein the behavior data includes first behavior data for reflecting movement of a diaphragm of a user during sleep and second behavior data for reflecting a breathing condition of the user during sleep, and the first running data is used to reflect a tidal volume of the respirator set when the user is in a wake state;

[0007] determining an adjustment gain parameter based on the first behavior data; wherein the adjustment gain parameter is used to reflect an adjustment parameter for adjusting the tidal volume of the respirator;

[0008] identify sleep feature data reflecting a user's actual need for adjustment of the ventilator tidal volume during sleep from the first operation data based on the second behavior data and the adjustment gain parameter;

[0009] generate second operation data based on the sleep feature data and the first operation data after adjustment based on the adjustment gain parameter; wherein the second operation data is used to reflect the tidal volume of the ventilator setting when the user is sleeping.

[0010] The technical solutions described above in the embodiments of the present application have at least the following technical effects:

[0011] The ventilator control method based on sleep behavior data provided in the embodiments of the present application first acquires behavior data including first behavior data of abdominal diaphragm movement of a user when breathing in a sleep state without wearing a ventilator and second behavior data of breathing conditions of the user when breathing in a sleep state without wearing a ventilator, and acquires first operation data of the tidal volume of the ventilator setting when the user is breathing in a wake state, then determines an adjustment gain parameter of an adjustment parameter for reflecting adjustment of the tidal volume of the ventilator based on the first behavior data, then identifies sleep feature data reflecting a user's actual need for adjustment of the tidal volume of the ventilator during sleep from the first operation data based on the second behavior data and the adjustment gain parameter, and then generates second operation data reflecting the tidal volume of the ventilator setting when the user is breathing in a sleep state based on the sleep feature data and the first operation data after adjustment based on the adjustment gain parameter.

[0012] The method can effectively adapt to individual differences of different users by adjusting the first operation data of the ventilator setting matching the breathing behavior of the user in a wake state based on the abdominal diaphragm movement of the user in a sleep state, and then adjusting the first operation data after adjustment based on the breathing movement of the user in a sleep state, so that the second operation data obtained after the second adjustment is used as the tidal volume of the ventilator setting when the user is sleeping at night, so that the tidal volume of the ventilator when the user is sleeping at night meets the user's sleep habits, thereby improving the use experience of the ventilator, reducing the problem of man-machine confrontation or poor use experience when using the ventilator, and improving the adaptability of the ventilator to the user.

[0013] In a possible implementation manner of the first aspect, the determining the adjustment gain parameter based on the first behavior data comprises:

[0014] obtain stage behavior data based on the first behavior data; wherein the stage behavior data is used to reflect different sleep stages of the user and corresponding diaphragm movement data;

[0015] determine a gain characteristic parameter of the first running data based on the stage behavior data.

[0016] In a possible implementation manner of the first aspect, the obtaining of the stage behavior data based on the first behavior data comprises:

[0017] obtain physiological characteristic information, and determine a division interval of the first behavior data according to the physiological characteristic information; wherein the physiological characteristic information is used to reflect age, weight and respiratory function rating of the user, and the division interval is used to reflect a complete diaphragm movement cycle of the user;

[0018] obtain a diaphragm movement feature set from the first behavior data in a time sequence based on the division interval; wherein the diaphragm movement feature set is a collection of a plurality of diaphragm movement data obtained after the first behavior data is divided according to the division interval;

[0019] divide the first behavior data into a plurality of segmentation data based on the diaphragm movement feature set; wherein the segmentation data is used to reflect diaphragm movement data in different sleep stages;

[0020] obtain stage behavior data based on a plurality of the segmentation data.

[0021] In a possible implementation manner of the first aspect, the dividing of the first behavior data into a plurality of segmentation data based on the diaphragm movement feature set comprises:

[0022] obtain an i-th difference value by comparing an i-th diaphragm movement data with an i+1-th diaphragm movement data in the diaphragm movement feature set; wherein the difference value is used to reflect a difference value between average amplitudes of the diaphragm movement data;

[0023] when a difference value between the i+1-th difference value and the i-th difference value is greater than a difference value between the i-th difference value and an i-1-th difference value, take a time node between the i-th diaphragm movement feature and the i+1-th diaphragm movement feature as a segmentation point to obtain a plurality of segmentation points; the diaphragm movement feature is used to reflect average amplitudes of the diaphragm movement data corresponding to different division intervals;

[0024] divide the first behavior data into a plurality of data segments based on the plurality of segmentation points;

[0025] analyze the diaphragm movement features corresponding to the plurality of data segments to obtain a plurality of segmentation data.

[0026] In a possible implementation manner of the first aspect, after the first behavioral data is segmented into a plurality of data segments based on the plurality of segmentation points, the method comprises:

[0027] extracting two data segments adjacent to the segmentation point from the plurality of data segments based on the segmentation point;

[0028] statistically obtaining a transition time period based on a time between a starting point amplitude of the data segment before the segmentation point and a starting point amplitude of the data segment after the segmentation point in the two data segments adjacent to the segmentation point.

[0029] In a possible implementation manner of the first aspect, the analyzing the diaphragm movement features corresponding to the plurality of data segments to obtain a plurality of segmentation data comprises:

[0030] extracting a plurality of adjacent diaphragm movement feature groups from the diaphragm movement features corresponding to the plurality of data segments, and obtaining a plurality of feature change rates based on the plurality of adjacent diaphragm movement feature groups; wherein the adjacent diaphragm movement feature group is used to reflect a combination of the diaphragm movement features between adjacent two data segments, and the feature change rate is used to reflect a change condition of the diaphragm movement features between different sleep modes;

[0031] dividing the plurality of data segments into a plurality of segmentation data based on the plurality of feature change rates.

[0032] In a possible implementation manner of the first aspect, the obtaining stage behavioral data based on the plurality of segmentation data comprises:

[0033] obtaining a plurality of coefficients of variation corresponding to the plurality of data segments in each segmentation data based on the plurality of segmentation data respectively, and confirming an average value of the plurality of coefficients of variation as a stage coefficient of variation; wherein the coefficient of variation is used to reflect a stability degree of the data segment;

[0034] obtaining a plurality of sleep stages corresponding to the plurality of segmentation data based on an ascending order of the stage coefficients of variation corresponding to the plurality of segmentation data; wherein the sleep stage is used to reflect a sleep structure corresponding to different physiological function activities of a user during sleep;

[0035] confirming the plurality of segmentation data and the corresponding sleep stages as stage behavioral data.

[0036] In a possible implementation manner of the first aspect, the determining the gain feature parameter of the first running data based on the stage behavioral data comprises:

[0037] The state difference rate corresponding to each of the sleep stages is obtained by comparing the benchmark diaphragm movement data with the stage behavior data, wherein the benchmark diaphragm movement data is used to reflect the diaphragm movement data of the user's breathing in a wake state, and the state difference rate is used to indicate the ratio between the average amplitude of the diaphragm generated in the stage behavior data corresponding to each of the sleep stages and the average amplitude of the diaphragm generated in the benchmark diaphragm movement data.

[0038] The state difference rate corresponding to each of the sleep stages is confirmed as a gain characteristic parameter corresponding to each of the sleep stages.

[0039] In a possible implementation manner of the first aspect, the sleep characteristic data reflecting the sleep features of the user that need to be adjusted during sleep is identified from the first running data based on the second behavior data and the adjustment gain parameter, including:

[0040] The respiration frequency feature is obtained based on the second behavior data, wherein the respiration frequency feature is used to reflect the respiration frequency of one complete respiration cycle of the user.

[0041] A plurality of respiratory tidal volumes are extracted from the second behavior data based on the respiration frequency feature, wherein the respiratory tidal volume is used to reflect the tidal volume of the user in one complete respiration cycle during sleep.

[0042] The comparison tidal volume reflecting each of the sleep stages is obtained by processing the adjustment gain parameter corresponding to each of the sleep stages and the set tidal volume of the first running data, wherein the set tidal volume is used to reflect the set value of the tidal volume of the user's breathing in a wake state, and the comparison tidal volume is used to indicate the product value of the set tidal volume and the adjustment gain parameter.

[0043] The comparison result is obtained by simultaneously comparing the plurality of respiratory tidal volumes with the comparison tidal volume corresponding to each of the sleep stages, and the sleep characteristic data is obtained based on the comparison result.

[0044] In a possible implementation manner of the first aspect, after the first running data is adjusted based on the adjustment gain parameter, the second running data is generated based on the sleep characteristic data and the adjusted first running data, including:

[0045] The adjustment parameter is obtained by processing the adjustment gain parameter corresponding to the sleep stage of the sleep characteristic data and the set tidal volume corresponding to the time point of the sleep characteristic data in the first running data, wherein the adjustment parameter is used to reflect the data that needs to replace the set tidal volume in the first running data.

[0046] processing based on the first operation data and the adjustment parameter to obtain initial operation data; wherein the initial operation data is used to reflect operation data after the set tidal volume in the first operation data that needs to be adjusted is adjusted;

[0047] performing smoothing filtering processing on the initial operation data based on the transition time period to obtain second operation data.

[0048] In a second aspect, an embodiment of the present application provides a breathing machine control system based on sleep behavior data, comprising:

[0049] an acquisition unit configured to acquire behavior data and first operation data; wherein the behavior data comprises first behavior data used to reflect movement of a user's abdominal diaphragm when sleeping and second behavior data used to reflect a user's breathing condition when sleeping, and the first operation data is used to reflect a tidal volume of a breathing machine set when a user is awake;

[0050] a first analysis unit configured to determine an adjustment gain parameter based on the first behavior data; wherein the adjustment gain parameter is used to reflect an adjustment parameter for adjusting a tidal volume of a breathing machine;

[0051] a second analysis unit configured to identify sleep feature data used to reflect a tidal volume adjustment requirement of a breathing machine actually needed by a user during sleep from the first operation data based on the second behavior data and the adjustment gain parameter;

[0052] an execution unit configured to generate second operation data based on the sleep feature data and the first operation data after adjustment based on the adjustment gain parameter; wherein the second operation data is used to reflect a tidal volume of a breathing machine set when a user is sleeping.

[0053] In a third aspect, an embodiment of the present application provides a breathing machine, comprising a delivery mechanism, a driving mechanism, and a control device, the control device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method of any of the above-mentioned first aspect when executing the computer program.

[0054] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the method of any of the above-mentioned first aspect.

[0055] In a fifth aspect, the embodiments of the present application provide a computer program, which, when running on a breathing machine, causes the breathing machine to perform the breathing machine control method based on sleep behavior data according to any one of the first aspect.

[0056] It can be understood that the beneficial effects of the second aspect to the fifth aspect described above can be referred to the related description in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0058] Figure 1 is a flowchart of a breathing machine control method based on sleep behavior data provided by an embodiment of the present application;

[0059] Figure 2 is a flowchart of an implementation process of a breathing machine control method based on sleep behavior data provided by an embodiment of the present application;

[0060] Figure 3 is a structural diagram of a breathing machine control system based on sleep behavior data provided by an embodiment of the present application;

[0061] Figure 4 is a structural diagram of a control device of a breathing machine provided by an embodiment of the present application. DETAILED DESCRIPTION

[0062] In the following description, specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, persons skilled in the art should understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary details.

[0063] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0064] It should also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items, and that the term “at least one of’ denotes one, or a combination of two or more items.

[0065] As used in the description of the application and the appended claims, the term “if’ can be interpreted to mean “when” or “upon” or “in response to determining” or “in response to detecting” depending on the context. Similarly, the phrase “if it is determined” or “if [a described condition or event] is detected” can be interpreted to mean “upon determining” or “in response to determining” or “upon [the described condition or event] being detected” or “in response to [the described condition or event] being detected,” depending on the context.

[0066] In addition, the terms “first,” “second,” “third,” etc. as used in the description of embodiments herein and throughout the claims (if any) are not used to connote any relative importance but are used differently from their meanings in the art and are mainly for the purposes of distinction among different claimed elements.

[0067] Reference throughout this specification to “one embodiment” or “an embodiment” or “some embodiments” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Thus, appearances of the phrases “in one embodiment,” “in some embodiments,” “in other embodiments,” “in additional embodiments,” and so on, in various places throughout this specification are not necessarily all referring to the same embodiment, unless otherwise specified. The terms “comprises,” “comprising,” “includes,” “including,” “has,” “having” and the like are meant to be open-ended and non-limiting.

[0068] In the related art, a non-invasive ventilator is generally used on a user with sleep disorders, such as the user having apnea, hypopnea, and hypoxemia during sleep, and a user with severe sleep disorders can endanger life during sleep. The treatment method of the non-invasive ventilator is generally to set a fixed tidal volume based on physiological data of the user in a wakeful state to realize ventilation support, and then the function of automatically adjusting the tidal volume according to the user's respiratory airflow, but the existing automatic adjustment algorithm is designed based on the average data of the sleep-disordered user, such as the same light sleep period, an obese user needs higher pressure to maintain the target tidal volume due to high airway resistance, and a weak user needs lower pressure, but the machine adjusts according to the unified standard, and the tidal volume cannot be accurately matched, resulting in that some users frequently have high pressure (throat discomfort) or low pressure (snoring is aggravated) during sleep, thereby reducing the adaptability of the ventilator.

[0069] To solve the above problems, the embodiment of the present application provides a breathing machine control method and system based on sleep behavior data. In the method, behavior data including first behavior data of diaphragm movement of a user when breathing without wearing a breathing machine in a sleep state and second behavior data of breathing condition of the user when breathing without wearing a breathing machine in a sleep state is acquired, and first running data of tidal volume of the breathing machine when the user breathes in a wake state is acquired. Then, an adjustment gain parameter of an adjustment parameter reflecting adjustment of tidal volume of the breathing machine is determined by the first behavior data. Sleep feature data reflecting actual adjustment requirement of the tidal volume of the breathing machine of the user in a sleep process is identified from the first running data by the second behavior data and the adjustment gain parameter. After the first running data is adjusted by the adjustment gain parameter, second running data reflecting the tidal volume of the breathing machine when the user breathes in a sleep state is generated by the sleep feature data and the adjusted first running data.

[0070] The method can effectively adapt to individual differences of different users by acquiring diaphragm movement and breathing movement of the user, and adaptively adjusting the first running data of the breathing machine set in a wake state to match the breathing behavior of the user in a sleep state. On this basis, the first running data after adjustment is adjusted again by the breathing movement of the user in a sleep state. Thus, the second running data obtained by twice adjustment is used as the tidal volume of the breathing machine when the user breathes in a sleep state at night, so that the tidal volume of the breathing machine in a sleep state at night meets the sleep habit of the user, thereby improving the use experience of the breathing machine, reducing the problem of man-machine confrontation or poor use experience when using the breathing machine, and improving the adaptation of the breathing machine to the user.

[0071] The breathing machine control method based on sleep behavior data provided by the embodiment of the present application can be applied to a breathing machine, and the breathing machine is the execution subject of the breathing machine control method based on sleep behavior data provided by the embodiment of the present application. The embodiment of the present application does not limit the specific type of the breathing machine.

[0072] The breathing machine comprises a delivery mechanism, a driving mechanism and a control device. The driving mechanism is electrically connected with the control device. The delivery mechanism is used to stably deliver gas to the respiratory tract of a patient and efficiently exhaust the exhaled gas of the patient. The delivery mechanism comprises a breathing mask, a gas delivery pipeline and an exhalation valve. The breathing mask is used to reduce the leakage of gas during delivery, for example, the breathing mask can be a nasal mask or a mouth-nose mask. The gas delivery pipeline is used to deliver gas to the breathing mask, for example, the gas delivery pipeline can be a plastic connecting pipe or a single plastic pipe. The exhalation valve is used to prevent gas backflow, for example, the exhalation valve can be a pneumatic valve or a piston air pump. The driving device is used to generate airflow, for example, the driving device can comprise an electric turbine, and the output end of the driving device is connected with the gas delivery pipeline of the delivery mechanism. The control device is used to supervise and control the adjustment of the respiratory parameters and the real-time monitoring of the breathing.

[0073] For example, the control device can be a single-chip microcomputer, a microcontroller, an application-specific integrated circuit or the like.

[0074] In order to better understand the breathing machine control method based on sleep behavior data provided by the embodiments of the present application, the specific implementation process of the breathing machine control method based on sleep behavior data provided by the embodiments of the present application is exemplarily introduced as follows.

[0075] Figure 1 And Figure 2 The breathing machine control method based on sleep behavior data provided by the embodiments of the present application is shown in the schematic flowchart, please refer to Figure 1 And Figure 2 The breathing machine control method based on sleep behavior data comprises the following steps.

[0076] S100, obtain behavior data and first running data; wherein the behavior data comprises first behavior data for reflecting the movement of the diaphragm of the abdominal cavity of the user in the sleep state and second behavior data for reflecting the breathing condition of the user in the sleep state, and the first running data is used to reflect the tidal volume of the breathing machine set in the breathing state of the user in the wake state.

[0077] It can be understood that the first behavior data is the amplitude data generated by the diaphragm of the abdominal cavity of the user in the sleep state. The second behavior data is derived data of the breathing movement of the user in the sleep state, for example, the exhalation volume of each exhalation, the inhalation volume of each inhalation and the frequency of breathing and the like. The tidal volume, as the core output parameter of the breathing machine, represents the gas volume (usually in milliliter) delivered by the breathing machine to the user in each breathing.

[0078] Exemplarily, the first behavior data can be collected by a flexible pressure sensor attached to the abdomen, a millimeter wave radar or an abdominal impedance monitoring device. The second behavior data can be directly obtained and recorded by an airflow sensor integrated in the breathing machine as the respiratory airflow velocity and flow waveform, and can also be obtained by an air pressure sensor to obtain the air pressure change inside the breathing mask when the user wears the breathing mask. The first operation data is the tidal volume setting value of the breathing machine when the user is conscious and has strong self-control ability of breathing. The setting value is determined by medical staff based on the user's weight, underlying diseases (for example, chronic obstructive pulmonary disease, sleep apnea syndrome), lung function test results (for example, forced vital capacity) and self-breathing tidal volume measured value when the user is conscious, and can meet the gas exchange demand of the user in the conscious state.

[0079] In S200, an adjustment gain parameter is determined based on the first behavior data, wherein the adjustment gain parameter is used to reflect an adjustment parameter for adjusting the tidal volume of the breathing machine.

[0080] It can be understood that the first behavior data is the diaphragm movement of the user in the whole sleep process, but in the whole sleep process of the user, there are different sleep states, that is, the diaphragm movement data controlled by the user's own brain is inconsistent in different sleep states.

[0081] Exemplarily, the diaphragm movement data of the user in different sleep stages can be obtained by analyzing the first behavior data. The essence is to divide and summarize the first behavior data into the same number of diaphragm movement data groups in different sleep stages according to different sleep stages, and then determine the adjustment gain parameter through the diaphragm movement data groups corresponding to different sleep stages. The first behavior data can also be input into a learning model, and the learning model outputs the corresponding adjustment gain parameter. The training process of the learning model can be performed by using the data processed from the first behavior data and the corresponding adjustment gain parameter as the training data set of the learning model, and then inputting the training data set of the learning model into the learning model for training and learning, and finally obtaining the learning model. And the like, but not limited thereto.

[0082] In a possible implementation, in S200, the adjustment gain parameter is determined based on the first behavior data, comprising:

[0083] In S210, stage behavior data is obtained based on the first behavior data, wherein the stage behavior data is used to reflect the diaphragm movement data corresponding to different sleep stages of the user.

[0084] It can be understood that the first behavior data is diaphragm movement data of the user in the entire sleep process, and the stage behavior data is diaphragm movement data in which starting points and ending points of different sleep stages are marked on the basis of the first behavior data. Different sleep stages refer to different sleep processes in the sleep process of the user according to the activity level of physiological sleep states, for example, the sleep stages can include deep sleep, light sleep, rapid eye movement sleep, etc.

[0085] Exemplarily, the first behavior data can be divided into a plurality of small units of diaphragm movement data defined by the user in a complete diaphragm movement cycle by analyzing the first behavior data, the sleep stages corresponding to the plurality of small units are obtained by analyzing the diaphragm movement data in the plurality of small units, and the diaphragm movement data of the plurality of small units is classified and matched into a plurality of diaphragm movement data capable of reflecting different sleep stages of the user in the entire sleep process according to the sleep stages, and finally the stage behavior data is obtained. The time period of different sleep stages of the user in the entire sleep process can also be determined by obtaining the activity level of the brain wave signal, and the first behavior data is divided into the stage behavior data by the time period corresponding to the different sleep stages.

[0086] In a possible implementation, in step S210, the stage behavior data is obtained based on the first behavior data, including:

[0087] S211, obtaining physiological characteristic information, and determining a division interval of the first behavior data according to the physiological characteristic information; wherein the physiological characteristic information is used to reflect the age, weight and respiratory function rating of the user, and the division interval is used to reflect a complete diaphragm movement cycle of the user.

[0088] It can be understood that the first behavior data is essentially a continuous diaphragm movement time sequence signal (such as a displacement, speed change curve over time), which is divided into an independent single cycle movement unit by the division interval, and the movement law of the diaphragm in each breath (for example, single movement amplitude, speed peak value) can be accurately analyzed. The physiological characteristic information as an individual difference anchor point directly determines the inherent characteristics of the diaphragm movement cycle of different users. The physiological characteristic information is a key parameter set representing the physiological basic ability of the user, and the three dimensions (age, weight, respiratory function rating) directly affect the movement ability and cycle characteristics of the diaphragm from three aspects of physiological development and recession stage, body load state, and respiratory function pathological classification.

[0089] S212, obtaining a diaphragm movement feature set from the first behavior data in time sequence based on the division interval; wherein the diaphragm movement feature set is a collection of a plurality of diaphragm movement data obtained after the first behavior data is divided according to the division interval.

[0090] It can be understood that, from the continuous time sequence signal of the first behavior data, the first collected first behavior data is taken as the starting point of the diaphragm movement cycle and also as the initial point of the disassembly. The cycle starting point is usually the time when the diaphragm is reset to the highest position at the end of expiration (i.e. the displacement minimum point, and the subsequent signal shows a trend of increasing displacement). For example, if the displacement signal of the first behavior data has a minimum value (2 mm) at t=0.3 seconds, and the displacement continues to increase after t=0.3 seconds (consistent with the start of inspiration), t=0.3 seconds is set as the starting point of the first cycle. Exemplarily, if the displacement signal of the first behavior data has a minimum value (2 mm) at t=0.3 seconds, and the displacement continues to increase after t=0.3 seconds (consistent with the start of inspiration), t=0.3 seconds is set as the starting point of the first cycle. At the same time, the division interval needs to be synchronized with the data acquisition time axis through "time stamp alignment", i.e. if the division interval is calculated as 4.0 seconds (i.e. the user's single diaphragm movement cycle is 4 seconds), the time range of the first cycle is t=0.3s~4.3s, the second cycle is t=4.3s~8.3s, and so on, to realize "fixed interval disassembly along the time axis in sequence".

[0091] In addition, since the user may have a short-term breathing rhythm fluctuation (e.g. slight change in breathing frequency when turning over) during sleep, only disassembling according to a fixed division interval may cause cycle misalignment (e.g. splitting a 4s actual cycle into a 3.8s unit + 0.2s redundant data), so the key features (e.g. displacement maximum point, displacement trend) of the internal diaphragm movement of each preliminary disassembled unit (e.g. t=4.3s~8.3s) need to be extracted to determine whether it contains a complete inspiration-expiration process. If there is a complete trend of increasing displacement (inspiration) and then decreasing displacement (expiration) in the unit, and the end displacement returns to a level close to the starting point, it is determined as a valid cycle unit. Otherwise, if there is only an inspiration process (continuous increase in displacement without a decreasing trend) in the unit, the division interval needs to be adjusted slightly (e.g. shortened by 0.2s) to re-disassemble the unit so that each unit corresponds to a complete movement cycle.

[0092] S213, based on the diaphragm movement feature set, the first behavior data is segmented into multiple segmented data; wherein the segmented data is used to reflect the abdominal diaphragm movement data in different sleep stages.

[0093] It can be understood that the abdominal diaphragm movement data corresponding to different sleep stages is different, and during the process of switching sleep stages, the movement features of the abdominal diaphragm movement data will also change.

[0094] Exemplarily, the difference between the average amplitudes of two adjacent diaphragm movement data can be obtained by comparison, and when the difference changes, the changed feature point is taken as the time point of sleep state change. After traversing the diaphragm movement feature set through this step, multiple time points of sleep state change are obtained. Finally, through multiple time points and analysis of the diaphragm movement feature, the diaphragm movement feature set is divided into multiple segmentation data.

[0095] In a possible implementation, in step S213, the first behavior data is divided into multiple segmentation data based on the diaphragm movement feature set, including:

[0096] S2131, comparing the ith abdominal diaphragm movement data and the ith+1 abdominal diaphragm movement data in the diaphragm movement feature set to obtain the ith difference value; wherein the difference value is used to reflect the difference between the average amplitudes of the abdominal diaphragm movement data.

[0097] It can be understood that each data unit (ith, ith+1) in the diaphragm movement feature set contains the diaphragm movement key parameter of a single breath, and the average amplitude as a core index representing the depth of a single breath (reflecting the overall amplitude level of diaphragm movement) directly reflects the dynamic change of the user's breathing depth in sleep (for example, from deep breathing to shallow breathing, or the breathing depth remains stable).

[0098] Exemplarily, the average amplitude of the ith diaphragm movement data is extracted, and the average amplitude of the ith+1 diaphragm movement data is extracted, and then the difference between the average amplitude of the ith+1 diaphragm movement data and the average amplitude of the ith+1 diaphragm movement data is calculated to obtain the ith difference value.

[0099] S2132, when the difference between the ith+1 difference value and the ith difference value is greater than the difference between the ith difference value and the ith-1 difference value, the time node between the ith diaphragm movement feature and the ith+1 diaphragm movement feature is taken as a segmentation point, and multiple segmentation points are obtained; the diaphragm movement feature is used to reflect the average amplitude of the abdominal diaphragm movement data corresponding to different division intervals.

[0100] It can be understood that by analyzing the deterioration trend alleviation, positive trend intensification or trend reversal of the breathing depth change rate, the demarcation of the respiratory state from one stable trend to another stable trend can be known, that is, by analyzing the difference between the ith+1 difference value and the ith difference value is greater than the difference between the ith difference value and the ith-1 difference value, the time when the sleep state of the user changes during sleep can be determined (for example, the user switches from light sleep stage to deep sleep stage, the user switches from deep sleep stage to eye movement stage, etc.).

[0101] Exemplarily, the difference between the i+1th difference value and the ith difference value and the difference between the ith difference value and the i-1th difference value can be calculated through similar steps S2131, and when the difference between the i+1th difference value and the ith difference value is greater than the difference between the ith difference value and the i-1th difference value, it means that the ith diaphragm movement feature and the i+1th diaphragm movement feature are corresponding to the diaphragm movement data of the sleep state of the user.

[0102] S2133, segmenting the first behavior data into a plurality of data segments based on the plurality of segmentation points.

[0103] It can be understood that the segmentation point timestamp is taken as a boundary identifier, and intervals are divided on the time axis of the first behavior data, and each interval is a data segment.

[0104] In a possible implementation, after the first behavior data is segmented into a plurality of data segments based on the plurality of segmentation points in step S2133, the method comprises:

[0105] S21331, extracting two data segments adjacent to the segmentation point from the plurality of data segments based on the segmentation point.

[0106] It can be understood that the segmentation point determined through step S2132 can split the diaphragm movement feature sequence (average amplitude data sorted by time) of the entire sleep period of the user into a plurality of continuous and independent diaphragm movement data (i.e., data segments), and each segmentation point is a time boundary of two adjacent data segments. The boundary point is the boundary point of the sleep mode transition of the user. However, in the actual change process, the switching of the sleep mode can not be at the end point of the abdominal diaphragm movement cycle, that is, the minimum point or the maximum point of the amplitude of the abdominal diaphragm movement.

[0107] Exemplarily, if there is a segmentation point that segments the ith diaphragm movement data and the i+1th diaphragm movement data, the two adjacent data segments extracted through this step are the ith diaphragm movement data and the i+1th diaphragm movement data.

[0108] S21332, based on the time between the starting point amplitude of the data segment before the segmentation point and the starting point amplitude of the data segment after the segmentation point in the two data segments adjacent to the segmentation point, a transition time period is obtained.

[0109] It can be understood that the starting point amplitude refers to the amplitude corresponding to the starting point of a complete abdominal diaphragm movement data. Because the two data segments adjacent to the segmentation point are in different sleep stages, the amplitudes of the data segments on both sides of the segmentation point are different. The transition time period is the difference between the time point corresponding to the starting point amplitude of the i-th diaphragm movement data in the latter half of a complete abdominal diaphragm movement data and the time point corresponding to the starting point amplitude of the i-th diaphragm movement data, wherein, for example, if the starting point amplitude of the i-th diaphragm movement data is at a time point t1 when the diaphragm movement data is in an upward trend, the starting point amplitude of the i-th diaphragm movement data is at a time point t2 when the diaphragm movement data is in a downward trend, and t1 and t2 are a complete abdominal diaphragm movement cycle, the starting point amplitude of the i+1-th diaphragm movement data is at a time point t3 when the diaphragm movement data is in an upward trend, and the starting point amplitude of the i+1-th diaphragm movement data is at a time point t4 when the diaphragm movement data is in a downward trend, then the transition time period is t3-t2, and so on.

[0110] In this way, by analyzing the transition time period, a stable switching time is provided for subsequent ventilator tidal volume adjustment, so that the ventilator does not suddenly change the tidal volume when switching the tidal volume, but gradually switches the tidal volume according to the transition time period, reduces the impact of tidal volume switching, and improves the user experience.

[0111] In S2134, the diaphragm movement characteristics corresponding to the plurality of data segments are analyzed to obtain a plurality of segmented data.

[0112] For example, adjacent two diaphragm movement characteristic groups can be extracted from the diaphragm movement characteristics corresponding to the plurality of data segments, and the change condition of the diaphragm movement characteristics between the adjacent two diaphragm movement characteristic groups is analyzed, and then the state switching between adjacent data segments in the plurality of data segments is defined according to the change condition, so as to divide the plurality of data segments into a plurality of segmented data according to the state switching. The state switching refers to the switching process of the sleep state of the user (for example, light sleep→deep sleep, deep sleep→light sleep).

[0113] In this way, by analyzing the diaphragm movement data, the logic chain of difference value calculation-dynamic segmentation point determination-data segmentation-multiple type segmented data extraction is realized, which solves the problem of ignoring the change of movement characteristics in the traditional fixed time segmentation, and realizes the accurate conversion from "continuous time sequence data" to "feature-driven structured data".

[0114] In one possible implementation, in step S2134, the diaphragm movement characteristics corresponding to the plurality of data segments are analyzed to obtain a plurality of segmented data, including:

[0115] S21341, a plurality of adjacent diaphragm movement feature groups are extracted from the diaphragm movement features corresponding to the plurality of data segments, and a plurality of feature change rates are obtained based on the plurality of adjacent diaphragm movement feature groups; wherein the adjacent diaphragm movement feature group is used to reflect the combination of diaphragm movement features between adjacent two data segments, and the feature change rate is used to reflect the change condition of diaphragm movement features between different sleep modes.

[0116] It can be understood that the adjacent diaphragm movement feature group is the combination of the two adjacent data segments in step S21331. When the user switches between different sleep stages, the change condition of the diaphragm movement features is similar (for example, shallow sleep mode switches to deep sleep mode, deep sleep mode switches to shallow sleep mode, eye movement mode switches to shallow sleep mode, and shallow sleep mode switches to eye movement mode, etc.).

[0117] Exemplarily, the amplitude change in the adjacent diaphragm movement feature group is directly calculated as the feature change rate in the calculation sequence of the amplitude size in the adjacent diaphragm movement feature group, that is, if the diaphragm movement feature of the first data segment in the adjacent diaphragm movement feature group is A1, the diaphragm movement feature of the second data segment is A2, and A2 is greater than A1, then the feature change rate is A2-A1, otherwise if A1 is greater than A2, then the feature change rate is A1-A2, and so on.

[0118] S21342, based on the plurality of feature change rates, the plurality of data segments are divided into a plurality of segmented data.

[0119] It can be understood that different sleep mode switching exists in bidirectionality (for example, shallow sleep→deep sleep, deep sleep→eye movement), but the respiratory feature change rule of the same switching type (for example, switching between shallow sleep and deep sleep) has commonality (only the change direction is opposite, the change amplitude and trend feature are consistent), and the essence belongs to the feature of the same switching type.

[0120] Exemplarily, by classifying the plurality of data segments based on the plurality of feature change rates, all data segments are classified into a plurality of segmented data corresponding to the switching type, forming an aggregation result of one type of data segment+one type of switching type, and finally the aggregation result is processed through the switching type to obtain a plurality of segmented data.

[0121] In this way, through the basic switching logic of the sleep stage switching between two sleep stages in a plurality of sleep stages, it can be determined which sleep stage in a plurality of sleep stages the plurality of data segments respectively belong to, which can get rid of the limitation of the traditional “classification based on fixed threshold” (for example, only a single amplitude threshold is used to distinguish the mode, and the transition feature between modes is ignored), realizes the one-to-one correspondence of “data segment-change rate-sleep mode”, and makes the plurality of segmented data accurately reflect the diaphragm movement features of a plurality of typical sleep states.

[0122] S214, obtain stage behavior data based on the plurality of segmentation data.

[0123] It can be understood that the plurality of segmentation data corresponds to sleep stages of light sleep, deep sleep and eye movement, and the stage behavior data is obtained by marking the plurality of segmentation data corresponding to the sleep stages.

[0124] Exemplarily, different sleep stages can be defined by respectively analyzing the diaphragm stability of the plurality of segmentation data, i.e., by analyzing the ratio of the amplitude change rate to the frequency change rate of the plurality of segmentation data as the stability, and then by the characteristics of different sleep stages, the plurality of segmentation data is marked with sleep stage labels in sequence according to the mapping relationship between the activity level and the stability of different sleep stages, so as to obtain the stage behavior data. The sleep stages corresponding to the plurality of segmentation data can also be directly marked with labels by the brain wave signal, so as to obtain the stage behavior data.

[0125] In this way, by dividing the first behavior data according to the physiological characteristics of the user himself, and then determining the diaphragm movement characteristics set after the division according to different sleep stages, the complete logical chain of "customized interval division-feature set extraction-sleep stage data segmentation-stage behavior data output" is realized, which realizes the accurate upgrade from "general data processing" to "user-specific sleep data analysis", improves the adaptation degree of the breathing machine, and thus improves the user experience.

[0126] In one possible implementation, in step S214, the stage behavior data is obtained based on the plurality of segmentation data, including:

[0127] S2141, respectively based on the plurality of segmentation data, obtain the coefficient of variation corresponding to a plurality of data segments in each segmentation data, and confirm the average value of the plurality of coefficients of variation as the stage coefficient of variation; wherein the coefficient of variation is used to reflect the stability of the data segment.

[0128] It can be understood that the coefficient of variation can be obtained by the ratio between the amplitude change rate and the frequency change rate of the data segment. The amplitude change rate refers to the unit time change amplitude of the average amplitude of the diaphragm movement in the data segment, which reflects the dynamic change speed of the amplitude. The frequency change rate refers to the unit time change amplitude of the breathing frequency in the data segment, which reflects the dynamic change speed of the breathing rhythm. Because different sleep stages appear alternately in the whole sleep process of the user at night, the same sleep stage of the user appears at different times in the whole sleep process, so that there are multiple data segments for different sleep stages.

[0129] Exemplarily, a calculation formula of the amplitude variation rate is Va=(Amax-Amin)÷T, where Amax is the maximum average amplitude in the data segment, Amin is the minimum average amplitude in the data segment, and T is the duration of the data segment (end time-start time). A calculation formula of the frequency variation rate is Vb=(Fmax-Fmin)÷T, where Fmax is the maximum respiratory frequency in the data segment, Fmin is the minimum respiratory frequency in the data segment, and T is the duration of the data segment. The coefficient of variation is Va÷Vb.

[0130] S2142, based on an ascending order of the coefficients of variation of the stages corresponding to the plurality of segmented data, a plurality of sleep stages corresponding to the plurality of segmented data is obtained; wherein the sleep stages are used to reflect sleep structures corresponding to different physiological function activities of the user during sleep.

[0131] It can be understood that, during sleep, the physiological activities corresponding to different sleep stages have different activities. The deep sleep stage is the stage with the most gentle physiological activity and the lowest activity in sleep. The light sleep stage is between wakefulness and deep sleep, and the physiological activity is moderate, which is a transition buffer zone of the sleep cycle. The eye movement stage is the stage with the most active physiological activity in the sleep cycle, and although it is called sleep, the brain state is close to wakefulness. That is, the coefficients of variation of the segmented data corresponding to the eye movement sleep state, the light sleep state and the deep sleep state are sorted in descending order. That is, the sleep stage corresponding to the maximum value in the coefficient of variation of the segmented data corresponding to each of the plurality of segmented data is confirmed as the eye movement sleep state, the sleep stage corresponding to the intermediate value is confirmed as the light sleep state, and the sleep stage corresponding to the minimum value is confirmed as the deep sleep state.

[0132] S2143, the plurality of segmented data and the corresponding sleep stages are collectively confirmed as stage behavior data.

[0133] It can be understood that the plurality of segmented data is a set of respiratory feature data classified based on sleep mode switching types (for example, containing the amplitude variation rate, the frequency variation rate, etc. of the data segment), and the corresponding sleep stage is a label reflecting the physiological state of the user (light sleep, deep sleep, eye movement state).

[0134] In this way, when the plurality of segmented data and the sleep stage exist independently, it cannot directly reflect which physiological sleep scenario a certain type of respiratory feature data corresponds to. Subsequent adjustment of the breathing machine parameters needs to accurately match the physiological needs of the sleep stage (for example, the eye movement state needs to cope with the severe fluctuation of breathing, and the deep sleep needs to maintain gentle ventilation). The stage behavior data, as an integrated body of data and stage, can be directly used as an input basis for parameter adjustment strategies.

[0135] S220, based on the stage behavior data, a gain characteristic parameter of the first running data is determined.

[0136] Exemplarily, the abdominal diaphragm movement data of the user in the wake state can be used for comparison with the abdominal diaphragm movement data in different sleep stages in the stage behavior data, and then the average amplitude ratio between the two kinds of data is obtained, and the ratio is confirmed as the gain characteristic parameter.

[0137] In this way, by labeling the abdominal diaphragm movement data in different sleep stages, the abstract diaphragm movement data can be corresponded to the specific sleep stages of "light sleep, deep sleep and REM sleep", and then the length proportion, continuous length and periodic alternation rule of each sleep stage are quantified, which provides a reference scalar for subsequent adjustment of the first running data.

[0138] In a possible implementation, in step S220, based on the stage behavior data, the gain characteristic parameter of the first running data is determined, including:

[0139] S221, the baseline abdominal diaphragm movement data is compared with the stage behavior data respectively to obtain the state difference rate corresponding to different sleep stages; wherein the baseline abdominal diaphragm movement data is used to reflect the abdominal diaphragm movement data of the user in the wake state, and the state difference rate is used to indicate the ratio between the average amplitude of the diaphragm generated in the stage behavior data of a single sleep stage and the average amplitude of the diaphragm generated in the baseline abdominal diaphragm movement data.

[0140] It can be understood that the baseline abdominal diaphragm movement data is the physiological baseline of the user's respiratory function, and the abdominal diaphragm movement in the wake state is controlled by the autonomous consciousness of the human body, and the average amplitude of the diaphragm movement is stable and can reflect the individual basic ventilation capacity.

[0141] Exemplarily, the abdominal diaphragm movement data of the user in the wake and resting state (for example, sitting still after getting up in the morning, without physical activity, without eating) is collected first, the abnormal data points corresponding to interference actions such as coughing and swallowing are excluded, and the baseline abdominal diaphragm movement data is obtained, and then the average amplitude of the diaphragm movement data corresponding to a single sleep stage (i.e. the segmented data in the stage behavior data) is calculated, and finally the average amplitude of the diaphragm movement data corresponding to a single sleep stage and the average amplitude of the baseline abdominal diaphragm movement data are used as the state difference rate.

[0142] S222, the state difference rate corresponding to different sleep stages is confirmed as the gain characteristic parameter corresponding to different sleep stages.

[0143] It can be understood that because the activities of different sleep stages are different, different corresponding adjustments need to be made during the use of the breathing machine by the user, so that the user does not have tidal impact when the breathing machine adjusts the tidal volume, so that the user wakes up from the sleep process. That is, different sleep stages correspond to another gain characteristic parameter.

[0144] In this way, by calculating the state difference rate (sleep stage average amplitude ÷ wake-up reference amplitude), the breathing characteristics of different sleep stages can be converted into quantitative deviation values relative to the reference, reducing the interference of individual breathing function differences (such as different lung capacities of users). There are individual differences in the wake-up reference breathing characteristics (e.g., amplitude, frequency) of different users (e.g., the abdominal diaphragm amplitude of user A when waking up is 2.0 mm, and the abdominal diaphragm amplitude of user B when waking up is 1.6 mm). If a unified gain (e.g., 0.8 gain for all users in deep sleep) is used, it will cause the actual adaptive parameter deviation of user B (user B's deep sleep amplitude is 1.2 mm, and the parameter calculated by 0.8 gain may be insufficient). The gain characteristic parameter determined by the individual state difference rate not only reflects the common needs of sleep stages (e.g., the deep sleep gain is generally lower than the light sleep gain), but also incorporates individual reference differences (e.g., the deep sleep gain of user A is 0.75, and the deep sleep gain of user B is 0.78). It realizes the balance of "stage commonality + individual characteristics" in parameter adjustment, and reduces the adaptive error caused by non-differential gain.

[0145] S300, identifying sleep characteristic data for reflecting the actual need of the user in the sleep process from the first running data based on the second behavior data and the adjustment gain parameter.

[0146] It can be understood that the tidal volume of the user's breathing fluctuates throughout the sleep process due to the relaxation of the throat, changes in sleep posture, and changes in sleep stages. There may be events of insufficient tidal volume of the user himself at different times in different sleep stages. Therefore, the ventilator needs to adjust this event, and the ventilator does not need to adjust the event when the user does not have an insufficient tidal volume at different times in different sleep stages.

[0147] Exemplarily, the tidal volume corresponding to each breathing cycle in the second behavior data can be obtained by analyzing the second behavior data. The set value of the tidal volume of the user's breathing in the wake-up state is processed by the adjustment gain parameter in different sleep stages corresponding to different times to obtain the required tidal volume of the user in different sleep stages. The comparison result after comparing the tidal volume corresponding to each breathing cycle of the user with the required tidal volume of the user in different sleep stages is obtained. The data required for adjustment of the user in the entire sleep process is determined as the sleep characteristic data.

[0148] In a possible implementation, in step S300, the sleep characteristic data for reflecting the actual need of the user in the sleep process from the first running data based on the second behavior data and the adjustment gain parameter, comprises:

[0149] S310, obtain a breathing frequency feature based on the second behavior data; wherein the breathing frequency feature is used to reflect a breathing frequency of a complete breathing cycle of the user.

[0150] It can be understood that the breathing frequency, as a core basic indicator of respiratory function, directly reflects the speed and stability of respiratory rhythm (for example, the frequency is slow during deep sleep, and the frequency fluctuates greatly during eye movement state).

[0151] Exemplarily, a complete breathing cycle is an inspiration starting point to an expiration ending point. The breathing frequency can be obtained by identifying the size of the airflow signal, that is, the time when the airflow intensity starts to rise from 0 (airflow from nothing to something) is the inspiration starting point, and the time when the airflow intensity drops to 0 and maintains stable (airflow from something to nothing) is the expiration ending point. After calculating the time difference between the inspiration starting point and the expiration ending point, the breathing frequency feature is obtained by converting the cycle frequency.

[0152] S320, extract a plurality of tidal volumes of respiration from the second behavior data based on the breathing frequency feature; wherein the tidal volume of respiration is used to reflect the tidal volume of the user in a complete breathing cycle during sleep.

[0153] It can be understood that the breathing frequency feature has determined the time stamp corresponding to the inspiration starting point and the expiration ending point of each single breathing cycle, and the time range is the accurate time anchor point for extracting the corresponding cycle tidal volume. The tidal volume of respiration can be obtained by calculating the integral of the airflow flow in the inspiration stage with respect to time (and the airflow flow in the expiration stage is in the opposite direction, the integral value is taken as an absolute value after the inspiration stage, so only the integral of the inspiration stage needs to be calculated).

[0154] Exemplarily, the signal segment in the corresponding range of the breathing cycle time is extracted from the second behavior data, and then the integral value of the inspiration stage in the signal segment is calculated to obtain the tidal volume of respiration.

[0155] S330, based on the adjustment gain parameters of different sleep stages, respectively process the set tidal volume of the first running data to obtain comparative tidal volumes for reflecting different sleep stages; wherein the set tidal volume is used to reflect the set value of the tidal volume of the user in a wakeful state, and the comparative tidal volume is used to indicate the product value of the set tidal volume and the adjustment gain parameter.

[0156] It can be understood that the set tidal volume of the first running data is a ventilation reference value of the user in a conscious state, which is determined based on the respiratory physiological demand in the conscious state (autonomous conscious regulation, active state), and the ventilation demand in the sleep stage is significantly different from that in the conscious state due to changes in respiratory center activity (for example, inhibition in deep sleep, fluctuations in REM period). The essence of adjusting the gain parameter is a quantitative coefficient of the ventilation demand in the sleep stage relative to the conscious reference, and the comparative tidal volume is obtained by multiplying the two, which can convert the fixed set value in the conscious state into a personalized tidal volume reference value that fits the physiological demand of different sleep stages.

[0157] For example, if the set tidal volume is 500 mL and the characteristic gain parameter of deep sleep is 0.75, the comparative tidal volume corresponding to the deep sleep stage is = 500 mL x 0.75 = 375 mL, which means that the ventilator needs to stabilize the tidal volume at about 375 mL in this stage.

[0158] S340, based on the simultaneous domain comparison of the plurality of respiratory tidal volumes and the comparative tidal volumes of different sleep stages, an comparison result is obtained, and based on the comparison result, sleep characteristic data is obtained.

[0159] It can be understood that the plurality of respiratory tidal volumes (reflecting the actual ventilation volume of the user's real-time single breath in sleep) is a dynamic feedback of the real physiological state, and the comparative tidal volume of different sleep stages (reflecting the ideal ventilation target of the stage) is a theoretical demand reference. The simultaneous domain comparison of the two can accurately verify whether the actual ventilation volume matches the target demand of the current sleep stage. The comparison result includes two comparison results of satisfaction and dissatisfaction, wherein the comparison result is not satisfied when the respiratory tidal volume is less than the corresponding comparative tidal volume, otherwise the comparison result is satisfied.

[0160] In this way, by analyzing the user's own respiratory data, the actual tidal volume of the user during sleep is obtained, and then the required tidal volume of the user during sleep is obtained by adjusting the gain parameter and the set tidal volume. Finally, by comparing the actual tidal volume with the required tidal volume, the timing of the secondary adjustment is defined according to the comparison result, and the secondary adjustment is performed on the basis of the ventilator running parameter after the first adjustment according to the user's own respiratory behavior, thereby improving the use adaptability of the ventilator.

[0161] S400, after adjusting the first running data based on the adjustment gain parameter, generating second running data based on the sleep characteristic data and the adjusted first running data; wherein the second running data is used to reflect the tidal volume set by the ventilator in the user's sleep state.

[0162] It can be understood that, after adjusting the gain parameter to adjust the first running data, the ideal tidal volume setting data of the user in the whole sleep stage is obtained (for example, the tidal volume from 2 o'clock at night to 3 o'clock at night is A, and the tidal volume from 3 o'clock at night to 4 o'clock at night is B), and then the first adjusted running data is adjusted again through the sleep feature data, so that the timing tidal volume setting data that can adapt to the whole sleep stage of the user is obtained (for example, from 2:45 to 2:47 at night, because the user changes the sleep posture, the tidal volume of the user's own spontaneous breathing meets the tidal volume required for sleep, that is, the ventilator does not need to output according to the ideal tidal volume)

[0163] In a possible implementation, in step S400, after adjusting the gain parameter to adjust the first running data, the second running data is generated based on the sleep feature data and the adjusted first running data, including:

[0164] S410, the adjustment gain parameter corresponding to the sleep stage of the sleep feature data and the set tidal volume corresponding to the time point of the sleep feature data in the first running data are processed to obtain an adjustment parameter; wherein the adjustment parameter is used to reflect the data that needs to replace the set tidal volume in the first running data.

[0165] It can be understood that the core processing logic of the adjustment parameter is the adjustment gain parameter corresponding to the sleep stage x the set tidal volume corresponding to the time of the first running data.

[0166] Exemplarily, two groups of associations of “sleep feature data time point→corresponding sleep stage→adjustment gain parameter of the stage” and “sleep feature data time point→set tidal volume of the first running data corresponding time” are established, so that the input parameters are completely aligned in the time dimension and the sleep stage dimension.

[0167] S420, the first running data and the adjustment parameter are processed to obtain initial running data; wherein the initial running data is used to reflect the running data after the adjustment of the set tidal volume that needs to be adjusted in the first running data is completed.

[0168] It can be understood that the parameters in the first running data have correlation (for example, the set tidal volume needs to be matched with the inspiration time and the airway pressure, and when the tidal volume is reduced, the inspiration time needs to be shortened synchronously to maintain the breathing frequency), that is, the tidal volume needs to be replaced, and the associated parameters also need to be adjusted synchronously.

[0169] S430, the initial running data is smoothed and filtered based on the transition time period to obtain the second running data.

[0170] It can be understood that in the initial running data, the parameters of different sleep stages (for example, tidal volume, airway pressure) have significant differences (such as shallow sleep 450 mL→deep sleep 375 mL, tidal volume drops 75 mL), and if the parameter jump is directly performed at the stage switching time (transition period), it will cause the sudden change of the air flow and pressure output by the ventilator. From the physiological level, the user may have shortness of breath, chest tightness, even wake up, which destroys the continuity of sleep, and thus the user's use experience is poor.

[0171] In this way, all parameters in the initial running data are adapted to each other, reducing system conflicts caused by local adjustment and ensuring stable operation of the ventilator. If only the set tidal volume is replaced without adjusting the associated parameters, it is easy to cause abnormal operation of the ventilator (for example, the tidal volume is reduced to 375 mL, but the inspiration time is still 1.5 seconds as in the awake state, which may cause the air flow rate to be too high and the user to be uncomfortable).

[0172] It should be understood that the size of the serial number of each step in the above embodiment 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.

[0173] Corresponding to the ventilator control method based on sleep behavior data described in the above embodiment, the embodiments of the present application also provide a ventilator control system based on sleep behavior data. Each module of the ventilator control system based on sleep behavior data can implement each step of the ventilator control method based on sleep behavior data. Figure 3 The structure block diagram of the ventilator control system based on sleep behavior data provided by the embodiments of the present application is shown, and only the parts related to the embodiments of the present application are shown for ease of illustration.

[0174] Referring to Figure 3 The ventilator control system based on sleep behavior data includes:

[0175] The acquisition unit is configured to acquire behavior data and first running data. The behavior data includes first behavior data for reflecting the movement of the diaphragm of the user when sleeping and second behavior data for reflecting the breathing condition of the user when sleeping. The first running data is used to reflect the tidal volume of the ventilator set when the user is in a wake state.

[0176] The first analysis unit is configured to determine an adjustment gain parameter based on the first behavior data. The adjustment gain parameter is used to reflect an adjustment parameter for adjusting the tidal volume of the ventilator.

[0177] The second analysis unit is configured to identify sleep feature data for reflecting the adjustment requirement of the tidal volume of the ventilator actually required by the user in the sleep process from the first running data based on the second behavior data and the adjustment gain parameter.

[0178] The execution unit is configured to generate second running data based on the sleep feature data and the adjusted first running data after adjusting the first running data based on the adjustment gain parameter; wherein the second running data is used to reflect the tidal volume of the ventilator setting in the user sleep state.

[0179] It should be noted that the information interaction, execution process and the like between the above systems / units are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought by the same can be referred to the method embodiments part, which will not be repeated here.

[0180] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0181] The present application also provides a ventilator, which comprises a delivery mechanism, a driving mechanism and a control device, wherein the ventilator is electrically connected with the control device. Figure 4 The control device 4 provided by an embodiment of the present application is shown in a structural schematic diagram. As shown in the figure, the control device 4 of the embodiment comprises at least one processor 40 (only one is shown in the figure), at least one memory 41 (only one is shown in the figure) and a computer program 42 stored in the at least one memory 41 and executable on the at least one processor 40. Figure 4 When the processor 40 executes the computer program 42, the control device 4 implements the steps in any of the above-mentioned various ventilator control methods based on sleep behavior data embodiments, or the control device 4 implements the functions of the modules / units in the above-mentioned system embodiments. Figure 4 Figure 4

[0182] ​​Exemplarily, the computer program 42 can be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to accomplish the present application. The one or more modules / units can be a series of computer program instruction segments capable of accomplishing specific functions, which are used to describe the execution process of the computer program 42 in the control device 4.

[0183] The control device 4 can be a single-chip microcomputer, a microcontroller, an application specific integrated circuit, etc. The control device 4 can include, but is not limited to, the processor 40 and the memory 41. Those skilled in the art can understand that the control device 4 can include more or less components, or combine some components, or different components, such as input / output devices, network access devices, buses, etc. Figure 4 The control device 4 is only an example and does not constitute a limitation on the control device 4, and can include more or less components than those shown in the figure, or combine some components, or different components, such as input / output devices, network access devices, buses, etc.

[0184] The processor 40 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0185] The memory 41 can be an internal storage unit of the control device 4 in some embodiments, such as a hard disk or a memory of the control device 4. The memory 41 can also be an external storage device of the control device 4 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 41 can include both the internal storage unit and the external storage device of the control device 4. The memory 41 is used to store an operating system, application programs, a boot loader, data, and other programs, such as program codes of the computer program, etc. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0186] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in any of the above method embodiments.

[0187] The embodiment of the present application provides a computer program product. When the computer program product is run on a breathing machine, the breathing machine implements the steps in any of the above method embodiments.

[0188] The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. According to such understanding, the embodiment of the present application can implement all or part of the above processes through a computer program to instruct related hardware to complete, and the computer program can be stored in a computer readable storage medium. The computer program is executed by a processor to implement the steps in each of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the breathing machine, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal and a software distribution medium. For example, a U disk, a mobile hard disk, a magnetic disk or an optical disk.

[0189] In the above embodiments, the description of each embodiment has its own focus. The parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0190] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0191] In the embodiments provided by the present application, it should be understood that the disclosed breathing machine control system based on sleep behavior data can be implemented in other manners. For example, the embodiments of the breathing machine control system based on sleep behavior data described above are merely specific embodiments and are not intended to limit the present application. For example, the division of the modules or units is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the display or discussion of the coupling or direct coupling or communication connection between the modules can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0192] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0193] The above-described embodiments are merely used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent technical features; and these modifications or replacements do not make 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. A ventilator control system based on sleep behavior data, characterized by, Comprise: An acquisition unit is configured to acquire behavior data and first operation data, wherein the behavior data comprises first behavior data for reflecting diaphragm movement of a user during sleep and second behavior data for reflecting breathing condition of the user during sleep, and the first operation data is for reflecting tidal volume of a ventilator set by the user during wakefulness; A first analysis unit is configured to determine an adjustment gain parameter based on the first behavior data, wherein the adjustment gain parameter is for reflecting an adjustment parameter for adjusting the tidal volume of the ventilator; A second analysis unit is configured to identify sleep feature data for reflecting adjustment requirement of the tidal volume of the ventilator actually needed by the user during sleep from the first operation data based on the second behavior data and the adjustment gain parameter; An execution unit is configured to generate second operation data based on the sleep feature data and the first operation data adjusted based on the adjustment gain parameter, wherein the second operation data is for reflecting the tidal volume of the ventilator set by the user during sleep; The first analysis unit is specifically configured to: Obtain stage behavior data based on the first behavior data, wherein the stage behavior data is for reflecting different sleep stages of the user and corresponding diaphragm movement data thereof; Determine a gain feature parameter of the first operation data based on the stage behavior data; The determination of the gain feature parameter of the first operation data based on the stage behavior data comprises: Obtain state difference rates corresponding to different sleep stages by comparing reference diaphragm movement data with the stage behavior data respectively, wherein the reference diaphragm movement data is for reflecting diaphragm movement data of the user during breathing in a wakeful state, and the state difference rate is for indicating a ratio between an average amplitude of a diaphragm corresponding to a single sleep stage in the stage behavior data and an average amplitude of a diaphragm in the reference diaphragm movement data; Confirm the state difference rates corresponding to different sleep stages as the gain feature parameters corresponding to different sleep stages.

2. The sleep behavior data-based ventilator control system of claim 1, wherein, The obtaining of the stage behavior data based on the first behavior data comprises: Obtain physiological feature information, and determine a division interval of the first behavior data according to the physiological feature information, wherein the physiological feature information is for reflecting age, weight and respiratory function rating of the user, and the division interval is for reflecting a complete movement period of the diaphragm of the user; Obtain a diaphragm movement feature set from the first behavior data in a time sequence based on the division interval, wherein the diaphragm movement feature set is a collection of multiple diaphragm movement data obtained by dividing the first behavior data according to the division interval; Divide the first behavior data into multiple division data based on the diaphragm movement feature set, wherein the division data is for reflecting diaphragm movement data in different sleep stages; Obtain stage behavior data based on the multiple division data.

3. The sleep behavior data-based ventilator control system of claim 2, wherein, The dividing of the first behavior data into multiple division data based on the diaphragm movement feature set comprises: comparing the i-th diaphragm movement data in the diaphragm movement feature set with the i+1-th diaphragm movement data, to obtain an i-th difference value, wherein the difference value is used to reflect the difference between the average amplitudes of the diaphragm movement data; when the difference between the i+1-th difference value and the i-th difference value is greater than the difference between the i-th difference value and the i-1-th difference value, the time node between the i-th diaphragm movement feature and the i+1-th diaphragm movement feature is taken as a segmentation point, and a plurality of segmentation points are obtained; the diaphragm movement feature is used to reflect the average amplitude of the diaphragm movement data corresponding to different division intervals; segmenting the first behavior data into a plurality of data segments based on the plurality of segmentation points; analyzing the diaphragm movement features corresponding to the plurality of data segments to obtain a plurality of segmentation data.

4. The sleep behavior data-based ventilator control system of claim 3, wherein, After the first behavior data is segmented into a plurality of data segments based on the plurality of segmentation points, the following steps are included: extracting two data segments adjacent to the segmentation point from the plurality of data segments based on the segmentation point; statistically analyzing the time between the starting point amplitude of the data segment before the segmentation point and the starting point amplitude of the data segment after the segmentation point based on the two data segments adjacent to the segmentation point, to obtain a transition time period.

5. The sleep behavior data-based ventilator control system of claim 3, wherein, The analysis of the diaphragm movement features corresponding to the plurality of data segments to obtain a plurality of segmentation data includes: extracting a plurality of adjacent diaphragm movement feature groups from the diaphragm movement features corresponding to the plurality of data segments, and obtaining a plurality of feature change rates based on the plurality of adjacent diaphragm movement feature groups; wherein the adjacent diaphragm movement feature group is used to reflect the combination of the diaphragm movement features between the two adjacent data segments, and the feature change rate is used to reflect the change condition of the diaphragm movement features between different sleep modes; dividing the plurality of data segments into a plurality of segmentation data based on the plurality of feature change rates.

6. The sleep behavior data-based ventilator control system of claim 4, wherein, The stage behavior data is obtained based on the plurality of segmentation data, including: obtaining the coefficient of variation corresponding to the plurality of data segments in each segmentation data based on the plurality of segmentation data respectively, and confirming the average value of the plurality of coefficients of variation as a stage coefficient of variation; wherein the coefficient of variation is used to reflect the stability of the data segment; obtaining a plurality of sleep stages corresponding to a plurality of segmentation data based on the ascending order of the stage coefficients of variation corresponding to a plurality of segmentation data; wherein the sleep stage is used to reflect the sleep structure corresponding to different physiological function activities of the user during sleep; confirming the plurality of segmentation data and the corresponding sleep stages as stage behavior data.

7. The sleep behavior data-based ventilator control system of claim 6, wherein, The second analysis unit is specifically used for: obtaining a breathing frequency feature based on the second behavior data; wherein the breathing frequency feature is used to reflect the breathing frequency of a complete breathing cycle of the user; extracting a plurality of tidal volumes from the second behavior data based on the breathing frequency feature; wherein the tidal volume is used to reflect the tidal volume of the user during sleep after a complete breathing cycle. The adjustment gain parameter corresponding to the sleep stage of the sleep feature data is processed with the set tidal volume corresponding to the time point of the sleep feature data in the first running data to obtain an adjustment parameter, wherein the adjustment parameter is used to reflect data that needs to be replaced in the set tidal volume in the first running data. The plurality of respiratory tidal volumes are simultaneously compared with the comparative tidal volume of different sleep stages based on the plurality of respiratory tidal volumes and the comparative tidal volume of different sleep stages to obtain a comparison result, and sleep feature data is obtained based on the comparison result.

8. The sleep behavior data-based ventilator control system of claim 7, wherein, The execution unit is specifically configured to: The adjustment gain parameter corresponding to the sleep stage of the sleep feature data is processed with the set tidal volume corresponding to the time point of the sleep feature data in the first running data to obtain an adjustment parameter, wherein the adjustment parameter is used to reflect data that needs to be replaced in the set tidal volume in the first running data. The initial running data is obtained by processing the first running data and the adjustment parameter, wherein the initial running data is used to reflect the running data after the adjustment of the set tidal volume that needs to be adjusted in the first running data is completed. The initial running data is smoothed and filtered based on the transition time period to obtain second running data.

Images