Breathing machine control method and system based on sleep behavior data

Abstract

The invention 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, and the method comprises the steps: obtaining behavior data and first operation data; wherein the behavior data comprises first behavior data used for reflecting abdominal diaphragm movement when the user sleeps and second behavior data used for reflecting respiratory movement when the user sleeps; determining an adjustment gain parameter based on the first behavior data; based on the second behavior data and the adjustment gain parameter, identifying sleep feature data used for reflecting a breathing machine tidal volume adjustment demand actually needed by the user in the sleep process from the first operation data; and after the first operation data is adjusted based on the adjustment gain parameter, second operation data is generated based on the sleep feature data and the adjusted first operation data. According to the method, when the user sleeps at night, the tidal volume of the breathing machine conforms to the sleeping habit of the user, and therefore the use experience of the breathing machine is improved.

Description

Technical Field

[0001] This application belongs to the field of ventilator technology, and in particular relates to a ventilator control method and system based on sleep behavior data. Background Technology A ventilator is a medical device that can replace, control, or alter a person's normal physiological breathing, increasing lung ventilation and improving respiratory function. Ventilators are generally divided into invasive and non-invasive ventilators. Invasive ventilators are typically used for critically ill patients who are completely unable to breathe independently. Through surgery or medical procedures, a tube (such as an endotracheal tube or tracheostomy tube) is inserted directly into the user's airway (trachea) and then connected to the ventilator for invasive ventilation to maintain the user's normal breathing activity. Non-invasive ventilators are generally used for users with relatively mild conditions who still have some ability to breathe independently. They deliver airflow to the user's airway using non-invasive methods such as a face mask (nasal mask, oronasal mask, etc.) or a nasal cannula, working in conjunction with the user's spontaneous breathing.

[0002] In related technologies, non-invasive ventilators are generally used for users with sleep disorders, such as sleep apnea, hypoventilation, and hypoxemia. Severe sleep disorders can be life-threatening during sleep. The treatment method of non-invasive ventilators typically involves setting a fixed tidal volume based on the user's physiological data while awake to provide ventilation support. The function can then automatically adjust the tidal volume according to the user's breathing airflow. However, existing automatic adjustment algorithms are designed based on averaged data from users with sleep apnea disorders, making it impossible to accurately match the tidal volume. This results in some users frequently experiencing excessively high pressure (throat discomfort) or excessively low pressure (worsened snoring) during sleep, leading to poor adaptability of the ventilator. Summary of the Invention

[0003] This application provides a ventilator control method and system based on sleep behavior data, which can improve the problem of low adaptability of ventilators.

[0004] In a first aspect, embodiments of this application provide a ventilator control method based on sleep behavior data, including: Acquire behavioral data and first operational data; wherein, the behavioral data includes first behavioral data reflecting the movement of the abdominal diaphragm during sleep and second behavioral data reflecting the breathing status of the user during sleep, and the first operational data is used to reflect the tidal volume set by the ventilator when the user is awake. Based on the first behavioral data, an adjustment gain parameter is determined; wherein, the adjustment gain parameter is used to reflect the adjustment parameter for adjusting the tidal volume of the ventilator; Based on the second behavioral data and the adjustment gain parameter, sleep characteristic data reflecting the actual tidal volume adjustment needs of the ventilator during sleep are identified from the first operating data. After adjusting the first operating data based on the adjusted gain parameter, second operating data is generated based on the sleep characteristic data and the adjusted first operating data; wherein, the second operating data is used to reflect the tidal volume set by the ventilator during the user's sleep state.

[0005] The technical solutions described in this application embodiment have at least the following technical effects: The ventilator control method based on sleep behavior data provided in this application first acquires behavioral data including first behavioral data of diaphragmatic movement during breathing when the user is asleep and not wearing a ventilator, and second behavioral data of breathing status during breathing when the user is asleep and not wearing a ventilator. It also acquires first operating data of the tidal volume set by the ventilator when the user is awake. Then, based on the first behavioral data, it determines an adjustment gain parameter to reflect the adjustment parameter for adjusting the tidal volume of the ventilator. Then, based on the second behavioral data and the adjustment gain parameter, it identifies sleep characteristic data from the first operating data to reflect the actual tidal volume adjustment needs of the user during sleep. After adjusting the first operating data by adjusting the adjustment gain parameter, it generates second operating data to reflect the tidal volume set by the ventilator when the user is asleep by combining the sleep characteristic data and the adjusted first operating data.

[0006] This method, by acquiring the user's diaphragm movement and respiratory movements, can effectively address individual differences among users. It adaptively adjusts the initial operating data of the ventilator settings, which are matched to the user's breathing behavior while awake, based on the user's abdominal diaphragm movement during sleep. Then, it further adjusts the adjusted initial operating data based on the user's respiratory movements during sleep. The resulting second operating data, obtained after these two adjustments, serves as the tidal volume setting for the ventilator during the user's nighttime sleep. This ensures that the tidal volume of the ventilator matches the user's sleep habits during nighttime sleep, thereby improving the user experience and reducing issues such as patient-ventilator asynchrony or poor user experience, ultimately enhancing the compatibility between the ventilator and the user.

[0007] In one possible implementation of the first aspect, determining the adjustment gain parameter based on the first behavioral data includes: Based on the first behavioral data, stage behavioral data is obtained; wherein, the stage behavioral data is used to reflect the user's different sleep stages and their corresponding abdominal diaphragm movement data; Based on the stage behavior data, the gain characteristic parameters of the first running data are determined.

[0008] In one possible implementation of the first aspect, obtaining the stage behavior data based on the first behavior data includes: Acquire physiological characteristic information and determine the segmentation interval of the first behavioral data based on the physiological characteristic information; wherein, the physiological characteristic information is used to reflect the user's age, weight and respiratory function rating, and the segmentation interval is used to reflect a complete cycle of abdominal diaphragm movement of the user; Based on the division interval, a diaphragm motion feature set is obtained from the first behavioral data according to the time series; wherein, the diaphragm motion feature set is a collection of multiple abdominal diaphragm motion data obtained after dividing the first behavioral data according to the division interval; Based on the diaphragm motion feature set, the first behavioral data is segmented into multiple segmented data; wherein, the segmented data is used to reflect abdominal diaphragm motion data under different sleep stages; Based on the various segmented data, stage behavior data is obtained.

[0009] In one possible implementation of the first aspect, the segmentation of the first behavioral data into multiple segmented data based on the diaphragm motion feature set includes: By comparing the i-th abdominal diaphragm motion data with the (i+1)-th abdominal diaphragm motion data in the diaphragm motion feature set, the i-th difference value is obtained; wherein, the difference value is used to reflect the difference between the average amplitudes of the abdominal diaphragm motion data; When the difference between the (i+1)th difference value and the ith difference value is greater than the difference between the ith difference value and the (i-1)th difference value, the time node between the ith diaphragm motion feature and the (i+1)th diaphragm motion feature is used as the segmentation point to obtain multiple segmentation points; the diaphragm motion feature is used to reflect the average amplitude of the abdominal diaphragm motion data corresponding to different segmentation intervals. The first action data is divided into multiple data segments based on multiple segmentation points; Based on the analysis of the diaphragm motion characteristics corresponding to multiple data segments, various segmentation data are obtained.

[0010] In one possible implementation of the first aspect, after segmenting the first action data into multiple data segments based on the multiple segmentation points, the following is included: Based on the segmentation point, extract two data segments adjacent to the segmentation point from the plurality of data segments; The transition time period is obtained by 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 in two data segments adjacent to the segmentation point.

[0011] In one possible implementation of the first aspect, the analysis based on the diaphragm motion characteristics corresponding to multiple data segments yields various segmented data, including: Multiple adjacent diaphragm motion feature groups are extracted from the diaphragm motion features corresponding to multiple data segments, and multiple feature change rates are obtained based on the multiple adjacent diaphragm motion feature groups; wherein, the adjacent diaphragm motion feature groups are used to reflect the combination of diaphragm motion features between two adjacent data segments, and the feature change rates are used to reflect the changes in diaphragm motion features between different sleep patterns; Based on the multiple characteristic change rates, the multiple data segments are divided into various segmented data.

[0012] In one possible implementation of the first aspect, the stage behavior data is obtained based on a variety of said segmented data, including: Based on various types of segmented data, the coefficients of variation corresponding to multiple data segments in each type of segmented data are obtained, and the average value of the multiple coefficients of variation is determined as the stage coefficient of variation; wherein, the coefficients of variation are used to reflect the stability of the data segments; Based on the ascending order of the stage variation coefficients corresponding to the various segmented data, multiple sleep stages corresponding to the various segmented data are obtained; wherein, the sleep stages are used to reflect the sleep structure corresponding to different physiological functional activities during user sleep; The various segmented data and the corresponding sleep stages are collectively identified as stage behavior data.

[0013] In one possible implementation of the first aspect, determining the gain characteristic parameters of the first running data based on the stage behavior data includes: The baseline diaphragmatic motion data is compared with the stage behavior data to obtain the state difference rate corresponding to different sleep stages; wherein, the baseline diaphragmatic motion data is used to reflect the diaphragmatic motion data of the user's breathing in the awake state, and the state difference rate is used to indicate the ratio between the average amplitude of the diaphragm corresponding to a single sleep stage in the stage behavior data and the average amplitude of the diaphragm in the baseline diaphragmatic motion data. The state difference rate corresponding to different sleep stages is identified as the gain characteristic parameter corresponding to different sleep stages.

[0014] In one possible implementation of the first aspect, identifying sleep characteristic data reflecting the need for adjustment during the user's sleep process from the first operational data based on the second behavioral data and the adjusted gain parameter includes: Based on the second behavioral data, a respiratory rate feature is obtained; wherein, the respiratory rate feature is used to reflect the respiratory rate of a user in one complete respiratory cycle; Multiple tidal volumes are extracted from the second behavioral data based on the respiratory rate characteristics; wherein the tidal volume is used to reflect the tidal volume of a user during a complete respiratory cycle in sleep. The adjustment gain parameter for different sleep stages is processed with the set tidal volume of the first operating data to obtain a comparative tidal volume that reflects different sleep stages; wherein, the set tidal volume is used to reflect the set value of the tidal volume of breathing when the user is awake, and the comparative tidal volume is used to indicate the product value of the set tidal volume and the adjustment gain parameter. Simultaneous comparison is performed between multiple respiratory tidal volumes and comparative tidal volumes of different sleep stages to obtain comparison results, and sleep characteristic data is obtained based on the comparison results.

[0015] In one possible implementation of the first aspect, after adjusting the first running data based on the adjustment gain parameter, generating second running data based on the sleep feature data and the adjusted first running data includes: 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 the adjustment parameter; wherein, the adjustment parameter is used to reflect the data that needs to be replaced by the set tidal volume in the first running data; Based on the first operating data and the adjustment parameters, initial operating data is obtained; wherein, the initial operating data is used to reflect the operating data after the set tidal volume that needs to be adjusted in the first operating data has been adjusted; The initial running data is smoothed and filtered based on the transition time period to obtain the second running data.

[0016] Secondly, embodiments of this application provide a ventilator control system based on sleep behavior data, comprising: An acquisition unit is used to acquire behavioral data and first operational data; wherein, the behavioral data includes first behavioral data reflecting the movement of the abdominal diaphragm during sleep and second behavioral data reflecting the breathing status of the user during sleep, and the first operational data is used to reflect the tidal volume set by the ventilator when the user is awake. The first analysis unit is used to determine the adjustment gain parameter based on the first behavioral data; wherein the adjustment gain parameter is used to reflect the adjustment parameter for adjusting the tidal volume of the ventilator; The second analysis unit is used to identify sleep characteristic data from the first operating data based on the second behavioral data and the adjustment gain parameter, which reflects the user's actual need for ventilator tidal volume adjustment during sleep. An execution unit is configured to adjust the first operating data based on the adjustment gain parameter, and then generate second operating data based on the sleep characteristic data and the adjusted first operating data; wherein the second operating data is used to reflect the tidal volume set by the ventilator during the user's sleep state.

[0017] Thirdly, embodiments of this application provide a ventilator, including a delivery mechanism, a drive mechanism, and a control device. The control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in any of the embodiments of the first aspect above.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the first aspects above.

[0019] Fifthly, embodiments of this application provide a computer program that, when run on a ventilator, causes the ventilator to perform the ventilator control method based on sleep behavior data as described in any of the first aspects.

[0020] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic flowchart of a ventilator control method based on sleep behavior data provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the implementation process of a ventilator control method based on sleep behavior data according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a ventilator control system based on sleep behavior data provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of the control device for a ventilator provided in one embodiment of this application. Detailed Implementation

[0023] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0024] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0025] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0026] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0027] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0029] In related technologies, non-invasive ventilators are generally used for users with sleep disorders, such as sleep apnea, hypoventilation, and hypoxemia. Severe sleep disorders can be life-threatening during sleep. The treatment method of non-invasive ventilators typically involves setting a fixed tidal volume based on the user's physiological data during wakefulness to provide ventilation support. The function can then automatically adjust the tidal volume according to the user's breathing airflow. However, existing automatic adjustment algorithms are designed based on averaged data from users with sleep apnea disorders. For example, even during light sleep, obese users require higher pressure to maintain the target tidal volume due to higher airway resistance, while thinner users require lower pressure. However, the machine adjusts according to a uniform standard, and the tidal volume can never be precisely matched. This results in some users frequently experiencing excessively high pressure (throat discomfort) or excessively low pressure (worsened snoring) during sleep, leading to poor adaptability of the ventilator.

[0030] To address the aforementioned issues, this application provides a ventilator control method and system based on sleep behavior data. The method acquires behavioral data including first behavioral data of diaphragmatic movement during breathing while the user is asleep and not wearing a ventilator, and second behavioral data of the user's breathing status while asleep and not wearing a ventilator. It also acquires first operational data of the tidal volume set by the ventilator when the user is awake. Using the first behavioral data, an adjustment gain parameter reflecting the adjustment parameters for the ventilator's tidal volume is determined. Then, using the second behavioral data and the adjustment gain parameter, sleep characteristic data reflecting the user's actual tidal volume adjustment needs during sleep is identified from the first operational data. The first operational data is then adjusted using the adjustment gain parameter. Finally, using the sleep characteristic data and the adjusted first operational data, second operational data reflecting the tidal volume set by the ventilator during the user's sleep state is generated.

[0031] This method, by acquiring the user's diaphragm movement and respiratory movements, can effectively address individual differences among users. It adaptively adjusts the initial operating data of the ventilator settings, which are matched to the user's breathing behavior while awake, based on the user's abdominal diaphragm movement during sleep. Then, it further adjusts the adjusted initial operating data based on the user's respiratory movements during sleep. The resulting second operating data, obtained after these two adjustments, serves as the tidal volume setting for the ventilator during the user's nighttime sleep. This ensures that the tidal volume of the ventilator matches the user's sleep habits during nighttime sleep, thereby improving the user experience and reducing issues such as patient-ventilator asynchrony or poor user experience, ultimately enhancing the compatibility between the ventilator and the user.

[0032] The ventilator control method based on sleep behavior data provided in this application can be applied to a ventilator. In this case, the ventilator is the executing entity of the ventilator control method based on sleep behavior data provided in this application. This application does not impose any restrictions on the specific type of ventilator.

[0033] A ventilator includes a delivery mechanism, a drive mechanism, and a control unit. The drive mechanism is electrically connected to the control unit. The delivery mechanism is used to stably deliver gas to the patient's airway while efficiently expelling exhaled gas. The delivery mechanism includes a breathing mask, gas delivery tubing, and an expiratory valve. The breathing mask is used to reduce gas leakage during delivery; for example, the breathing mask can be a nasal mask or an oronasal mask. The gas delivery tubing is used to deliver gas to the breathing mask; for example, the gas delivery tubing can be a plastic connecting tube or a single plastic tube. The expiratory valve is used to prevent gas backflow; for example, the expiratory valve can be a pneumatic valve or a piston-type air pump. The drive unit is used to generate airflow; for example, the drive unit can include an electric turbine, and the output of the drive unit is connected to the gas delivery tubing of the delivery mechanism. The control unit is used to monitor and control the process of adjusting respiratory parameters and to monitor respiration in real time.

[0034] For example, the control device can be a microcontroller, a special-purpose integrated circuit, etc.

[0035] To better understand the ventilator control method based on sleep behavior data provided in the embodiments of this application, the specific implementation process of the ventilator control method based on sleep behavior data provided in the embodiments of this application will be described by way of example below.

[0036] Figure 1 and Figure 2 A schematic flowchart of a ventilator control method based on sleep behavior data provided in an embodiment of this application is shown. Please refer to [link / reference]. Figure 1 and Figure 2 Ventilator control methods based on sleep behavior data include: S100, acquire behavioral data and first operational data; wherein, the behavioral data includes first behavioral data for reflecting the movement of the abdominal diaphragm during sleep and second behavioral data for reflecting the breathing status of the user during sleep, and the first operational data is used to reflect the tidal volume set by the ventilator when the user is awake.

[0037] It can be understood that the first set of data represents the amplitude data generated by the diaphragm in the user's abdominal cavity during sleep. The second set of data represents derived data from the user's respiratory movements during sleep, such as the expiratory volume with each exhalation, the inspiratory volume with each inhalation, and the respiratory rate. Tidal volume, as a core output parameter of the ventilator, represents the volume of gas delivered to the user by the ventilator with each breath (usually in milliliters).

[0038] For example, the first set of data can be collected using a flexible pressure sensor attached to the abdomen, millimeter-wave radar, or abdominal impedance monitoring device. The second set of data can be obtained by directly acquiring and recording the respiratory airflow velocity and flow waveform using an airflow sensor integrated into the ventilator. Alternatively, the second set of data can be obtained by acquiring the pressure changes inside the breathing mask when the user wears it, using a pressure sensor. The first set of operational data refers to the tidal volume setting of the ventilator when the user is conscious and has strong voluntary respiratory control. This setting is determined by medical staff based on the user's weight when awake, underlying diseases (e.g., chronic obstructive pulmonary disease, sleep apnea syndrome), pulmonary function test results (e.g., forced vital capacity), and measured tidal volume during voluntary breathing, ensuring that the gas exchange needs of the user are met while awake.

[0039] S200, based on the data in the first row, determines the adjustment gain parameter; wherein, the adjustment gain parameter is used to reflect the adjustment parameter for adjusting the tidal volume of the ventilator.

[0040] It is understandable that the first behavioral data is the movement of the diaphragm in the user's abdominal cavity during the entire sleep process. However, there are different sleep states in the user's entire sleep process, that is, the movement data of the diaphragm controlled by the user's own brain is inconsistent in different sleep states.

[0041] For example, by analyzing the first set of data, diaphragmatic motion data of the user under different sleep stages can be obtained. Essentially, the first set of data is segmented and grouped into diaphragmatic motion data groups with the same number of data points for each sleep stage. Then, the adjustment gain parameters are determined using these diaphragmatic motion data groups corresponding to different sleep stages. Alternatively, the first set of data can be input into a learning model, which outputs the corresponding adjustment gain parameters. The training process of the learning model can use the processed first set of data and the corresponding adjustment gain parameters as the training dataset, and then input this training dataset into the learning model for training, ultimately obtaining the learning model. And so on, but not limited to these examples.

[0042] In one possible implementation, in step S200, determining the adjustment gain parameter based on the first row of data includes: S210, based on the first behavior data, stage behavior data is obtained; wherein, the stage behavior data is used to reflect the user's different sleep stages and their corresponding abdominal diaphragm movement data.

[0043] It can be understood that the first-behavioral data is the diaphragmatic motion data throughout the user's sleep process, while the stage-behavioral data, based on the first-behavioral data, marks the start and end points of different sleep stages. Different sleep stages refer to different sleep processes during the user's sleep process, divided according to the activity level of the physiological sleep state. For example, sleep stages may include deep sleep, light sleep, and REM sleep.

[0044] For example, the first behavioral data can be analyzed by first dividing it into multiple small units of diaphragmatic motion data defined according to a complete diaphragmatic motion cycle of the user. Then, by analyzing the diaphragmatic motion data within these small units, the sleep stages corresponding to each small unit can be obtained. Based on these sleep stages, the diaphragmatic motion data of the multiple small units can be classified and matched into various types of diaphragmatic motion data that reflect different sleep stages throughout the user's sleep process, finally yielding stage behavioral data. Alternatively, the activity level of brainwave signals can be acquired to determine the time periods of different sleep stages throughout the user's sleep process. Then, the first behavioral data can be divided into stage behavioral data based on the time periods corresponding to different sleep stages.

[0045] In one possible implementation, in step S210, based on the first behavior data, stage behavior data is obtained, including: S211, acquire physiological characteristic information and determine the division interval of the first behavior data based on the physiological characteristic information; wherein, the physiological characteristic information is used to reflect the user's age, weight and respiratory function rating, and the division interval is used to reflect the user's complete abdominal diaphragm movement cycle.

[0046] It is understandable that the first set of data essentially consists of continuously collected temporal signals of diaphragm movement (such as displacement and velocity curves over time). By dividing these signals into intervals and breaking them down into independent single-cycle motion units, the movement patterns of the diaphragm during each breath can be precisely analyzed (e.g., amplitude of a single movement, peak velocity). Physiological characteristic information, serving as an anchor point for individual differences, directly determines the inherent characteristics of the diaphragm movement cycle for different users. Physiological characteristic information is a set of key parameters characterizing a user's basic respiratory physiological capacity. Its three dimensions (age, weight, and respiratory function rating) directly influence the movement capacity and cycle characteristics of the abdominal diaphragm from three levels: physiological development and decline stage, physical load status, and respiratory function pathological grading, respectively.

[0047] S212, Based on the partitioning interval, obtain the diaphragm motion feature set from the first row of data according to the time series; wherein, the diaphragm motion feature set is a collection of multiple abdominal diaphragm motion data obtained after the first row of data is partitioned according to the partitioning interval.

[0048] It can be understood that the first row of data collected from the continuous time-series signal of the first row is taken as the starting point of the diaphragm movement cycle, and also as the initial point for disassembly. The starting point of the cycle is usually the moment when the diaphragm returns to its highest position at the end of expiration (i.e., the point of minimum displacement, and subsequent signals show a trend of increasing displacement). For example, if the displacement signal of the first row of data reaches its minimum value (2mm) at t=0.3 seconds, and the displacement continues to increase after t=0.3 seconds (consistent with the characteristics of the start of inspiration), then t=0.3 seconds is set as the starting point of the first cycle. At the same time, "timestamp alignment" is needed to synchronize the division interval with the data acquisition time axis. That is, if the division interval is calculated to be 4.0 seconds (i.e., the user's single diaphragm movement cycle is 4 seconds), then 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 achieve "sequential disassembly along the time axis at fixed intervals".

[0049] In addition, since users may experience brief fluctuations in their breathing rhythm during sleep (e.g., slight changes in breathing frequency when turning over), simply dividing the cycle into fixed intervals may result in cycle misalignment (e.g., splitting a 4-second actual cycle into 3.8-second units plus 0.2-second redundant data). Therefore, for each initially divided unit (e.g., t=4.3s~8.3s), it is necessary to extract key features of the diaphragm movement within it (e.g., the maximum displacement point, displacement change trend) to determine whether it contains a complete inhalation-exhalation process. If the unit contains a complete trend of displacement first increasing (inhalation) and then decreasing (exhalation), and the final displacement returns to a level close to the starting point, it is determined to be a valid cycle unit. Conversely, if the unit only contains an inhalation process (displacement continuously increases without a decreasing trend), the division interval needs to be fine-tuned (e.g., shortened by 0.2s), and the unit needs to be re-divided so that each unit corresponds to a complete movement cycle.

[0050] S213, based on the diaphragm motion feature set, the first row of data is segmented into multiple segmented data; among them, the segmented data is used to reflect the abdominal diaphragm motion data under different sleep stages.

[0051] It is understandable that the diaphragmatic motion data for different sleep stages are different, and the motion characteristics of the diaphragmatic motion data will also change during the process of switching sleep stages.

[0052] For example, the difference in average amplitude between two adjacent diaphragm motion data can be obtained by comparison. When the difference changes, the feature point that changes is taken as the time point of sleep state change. After traversing the diaphragm motion feature set through this step, multiple time points of sleep state change are obtained. Finally, by analyzing multiple time points and diaphragm motion features, the diaphragm motion feature set is divided into multiple segments of data.

[0053] In one possible implementation, in step S213, based on the diaphragm motion feature set, the first row data is segmented into multiple segmented data, including: S2131, compare the i-th abdominal diaphragm motion data with the (i+1)-th abdominal diaphragm motion data in the diaphragm motion feature set to obtain the i-th difference value; where the difference value is used to reflect the difference between the average amplitudes of the abdominal diaphragm motion data.

[0054] It is understandable that each data unit (the i-th and i+1-th) in the diaphragm motion feature set contains key parameters of diaphragm motion for a single breath, and the average amplitude, as the core indicator characterizing the depth of a single breath (reflecting the overall amplitude level of diaphragm motion), directly reflects the dynamic changes in the user's breathing depth during sleep (e.g., from deep breathing to shallow breathing, or the breathing depth remaining stable).

[0055] For example, the average amplitude is extracted from the i-th diaphragm motion data and the average amplitude is extracted from the (i+1)-th diaphragm motion data. Then, the i-th difference value is obtained by calculating the difference between the average amplitude of the (i+1)-th diaphragm motion data and the average amplitude of the (i+1)-th diaphragm motion data.

[0056] S2132, when the difference between the (i+1)th difference value and the ith difference value is greater than the difference between the ith difference value and the (i-1)th difference value, the time node between the ith diaphragm motion feature and the (i+1)th diaphragm motion feature is used as the segmentation point to obtain multiple segmentation points; the diaphragm motion feature is used to reflect the average amplitude of the abdominal diaphragm motion data corresponding to different segmentation intervals.

[0057] It is understandable that by analyzing whether the deterioration trend of the rate of change in respiratory depth is alleviated, the positive trend is aggravated, or the trend is reversed, the boundary between one stable trend and another can be determined. That is, the moment when the user's sleep state changes during sleep can be defined by analyzing whether the difference between the (i+1)th difference value and the ith difference value is greater than the difference between the ith difference value and the (i-1)th difference value (e.g., the user changes from light sleep to deep sleep, or from deep sleep to eye movement sleep, etc.).

[0058] For example, the difference between the (i+1)th difference value and the i-th difference value, and the difference between the i-th difference value and the (i-1)th difference value can be calculated through similar steps S2131. 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, it indicates that the i-th diaphragm motion feature and the (i+1)th diaphragm motion feature are diaphragm motion data corresponding to different sleep states of the user.

[0059] S2133, the first row of data is divided into multiple data segments based on multiple segmentation points.

[0060] It is understandable that the timeline of the first row of data is divided into intervals using the timestamp of the dividing point as the boundary marker, and each interval is a data segment.

[0061] In one possible implementation, step S2133, after dividing the first row of data into multiple data segments based on multiple segmentation points, includes: S21331, extracts two data segments adjacent to the split point from multiple data segments based on the split point.

[0062] It is understood that the segmentation point determined in step S2132 can divide the diaphragm motion feature sequence (average amplitude data sorted by time) of the user's entire sleep period into multiple continuous and independent diaphragm motion data (i.e., data segments), with each segmentation point being the time boundary between two adjacent data segments. This boundary point is the dividing point for the user's sleep mode transition. However, in the actual process of change, the switch in sleep mode may not occur at the end of a diaphragm motion cycle, i.e., the lowest or highest point of the diaphragm motion amplitude.

[0063] For example, if there is a segmentation point that separates the i-th diaphragm motion data from the (i+1)-th diaphragm motion data, then the two adjacent data segments extracted in this step are the i-th diaphragm motion data and the (i+1)-th diaphragm motion data.

[0064] 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 two data segments adjacent to the segmentation point, the transition time period is obtained by statistical analysis.

[0065] It can be understood that the starting point amplitude refers to the amplitude corresponding to the starting point of a complete abdominal diaphragm motion data. Because the two data segments adjacent to the segmentation point represent different sleep stages, the amplitudes of the data segments on either side 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 motion data being in the latter half of a complete abdominal diaphragm motion data and the time point corresponding to the starting point amplitude of the i-th diaphragm motion data. For example, if the starting point amplitude of the i-th diaphragm motion data is at the time point when the diaphragm motion data is in an upward trend (t1), and the starting point amplitude of the i-th diaphragm motion data is at the time point when the diaphragm motion data is in a downward trend (t2), and t1 and t2 represent a complete abdominal diaphragm motion cycle, and the starting point amplitude of the (i+1)-th diaphragm motion data is at the time point when the diaphragm motion data is in an upward trend (t3), and the starting point amplitude of the (i+1)-th diaphragm motion data is at the time point when the diaphragm motion data is in a downward trend (t4), then the transition time period is t3-t2, and so on.

[0066] This setup, through analysis of the transition period, provides a stable switching time for subsequent tidal volume adjustments by the ventilator. This ensures that the ventilator does not experience sudden changes in tidal volume during tidal volume switching, but rather switches tidal volume gradually according to the transition period, reducing the impact of tidal volume switching and improving the user experience.

[0067] S2134, based on the analysis of the diaphragm motion characteristics corresponding to multiple data segments, obtains a variety of segmented data.

[0068] For example, by extracting two adjacent diaphragm motion feature groups from the diaphragm motion features corresponding to multiple data segments, analyzing the changes in diaphragm motion features between the two adjacent diaphragm motion feature groups, and then defining the state transitions between adjacent data segments based on the changes, multiple data segments can be divided into various types of segmented data according to the state transitions. State transitions refer to the process of switching between a user's sleep states (e.g., light sleep → deep sleep, deep sleep → light sleep).

[0069] This setup, through the analysis of diaphragm motion data and the logical chain of difference value calculation, dynamic segmentation point determination, data segmentation, and multi-type segmented data extraction, fundamentally solves the problem of neglecting motion feature changes in traditional fixed-time segmentation, and achieves accurate transformation from "continuous time-series data" to "feature-driven structured data".

[0070] In one possible implementation, in step S2134, analysis is performed based on the diaphragm motion characteristics corresponding to multiple data segments to obtain various segmented data, including: S21341, extract multiple adjacent diaphragm motion feature groups from the diaphragm motion features corresponding to multiple data segments, and obtain multiple feature change rates based on the multiple adjacent diaphragm motion feature groups; wherein, the adjacent diaphragm motion feature groups are used to reflect the combination of diaphragm motion features between two adjacent data segments, and the feature change rate is used to reflect the change status of diaphragm motion features between different sleep modes.

[0071] It can be understood that the adjacent diaphragm motion feature group is the combination of two adjacent data segments in step S21331. When a user switches between different sleep stages, the changes in their diaphragm motion features are similar (e.g., switching from light sleep mode to deep sleep mode and from deep sleep mode to light sleep mode, switching from eye movement mode to light sleep mode and from light sleep mode to eye movement mode, etc.).

[0072] For example, the amplitude change in adjacent diaphragm motion feature groups is directly calculated as the feature change rate, with the amplitude size in adjacent diaphragm motion feature groups as the calculation order. That is, if the diaphragm motion feature of the first data segment in an adjacent diaphragm motion feature group is A1 and the diaphragm motion feature of the second data segment is A2, and A2 is greater than A1, then the feature change rate is A2-A1. Conversely, if A1 is greater than A2, then the feature change rate is A1-A2, and so on.

[0073] S21342 divides multiple data segments into various types of segmented data based on multiple characteristic change rates.

[0074] It is understandable that the switching between different sleep modes is bidirectional (e.g., light sleep → deep sleep, deep sleep → eye movement), but the respiratory characteristics of the same switching type (e.g., the switching between light sleep and deep sleep) have commonalities (only the direction of change is opposite, and the magnitude and trend of change are consistent), which are essentially characteristic manifestations of the same switching type.

[0075] For example, by classifying multiple data segments based on various feature change rates, we obtain multiple segmented data that are assigned to different switching types, forming an aggregation result of one type of data segment + one type of switching type. Finally, we process the aggregation result by switching type to obtain multiple segmented data.

[0076] This setup, through the basic switching logic between two sleep stages in multiple sleep stages, determines which sleep stage each data segment belongs to. It can overcome the limitations of traditional "classification based on fixed thresholds" (e.g., distinguishing patterns only by a single amplitude threshold and ignoring the transition features between patterns), and achieve a one-to-one correspondence between "data segment - rate of change - sleep mode". This allows multiple segmented data to accurately reflect the diaphragm movement characteristics of multiple typical sleep states.

[0077] S214, based on multiple segmentation data, yields stage behavior data.

[0078] It is understandable that known segmented data includes sleep stages corresponding to light sleep, deep sleep, and eye movement, while stage behavior data is data obtained by labeling the various segmented data according to the corresponding sleep stages.

[0079] For example, different sleep stages can be defined by analyzing the diaphragmatic stability of multiple segmented data. Specifically, the ratio of amplitude change rate to frequency change rate of the multiple segmented data is used as the stability level. Then, based on the characteristics of different sleep stages and the mapping relationship between the activity level and stability level of different sleep stages, the multiple segmented data are sequentially labeled with sleep stages to obtain stage-specific behavioral data. Alternatively, stage-specific behavioral data can be obtained by directly labeling the sleep stages corresponding to multiple segmented data using electroencephalogram (EEG) signals.

[0080] This setup, by dividing the first behavioral data according to the user's own physiological characteristics, and then determining different sleep stages by analyzing the divided diaphragm movement feature sets, achieves a precise upgrade from "general data processing" to "user-specific sleep data analysis" through a complete logical chain of "customized interval division - feature set extraction - sleep stage data segmentation - stage behavioral data output". This improves the compatibility of the ventilator and thus enhances the user experience.

[0081] In one possible implementation, in step S214, stage behavior data is obtained based on multiple segmentation data, including: S2141, based on various types of segmented data, obtain the coefficients of variation corresponding to multiple data segments in each segmented data, and confirm the average of multiple coefficients of variation as the stage coefficient of variation; wherein, the coefficient of variation is used to reflect the stability of the data segment.

[0082] It is understandable that the coefficient of variation can be obtained by the ratio between the amplitude change rate and the frequency change rate of a data segment. The amplitude change rate refers to the unit-time change in the average amplitude of diaphragmatic movement within a data segment, reflecting the dynamic rate of amplitude change. The frequency change rate refers to the unit-time change in respiratory rate within a data segment, reflecting the dynamic rate of respiratory rhythm change. Because different sleep stages alternate throughout a user's sleep at night, the same sleep stage may occur at different times during the entire sleep process, resulting in multiple sets of data segments for different sleep stages.

[0083] For example, the formula for calculating the amplitude change rate is Va = (Amax - Amin) ÷ T, where Amax is the maximum average amplitude within the data segment, Amin is the minimum average amplitude within the data segment, and T is the duration of the data segment (end time - start time). The formula for calculating the frequency change rate is Vb = (Fmax - Fmin) ÷ T, where Fmax is the maximum respiratory rate within the data segment, Fmin is the minimum respiratory rate within the data segment, and T is the duration of the data segment. The coefficient of variation is Va ÷ Vb.

[0084] S2142, based on the ascending order of the stage variation coefficients corresponding to multiple segmented data, multiple sleep stages corresponding to multiple segmented data are obtained; wherein, the sleep stage is used to reflect the sleep structure corresponding to different physiological functional activities during the user's sleep.

[0085] It is understandable that different sleep stages correspond to varying levels of physiological activity during sleep. Deep sleep is the stage with the calmest and lowest physiological activity. Light sleep lies between wakefulness and deep sleep, with moderate physiological activity, serving as a transitional buffer zone in the sleep cycle. Eye movement (EMG) sleep is the stage with the most active physiological activity in the sleep cycle; although called sleep, the brain state is close to wakefulness. Therefore, the stage variation coefficients of the segmented data corresponding to EMG sleep, light sleep, and deep sleep are sorted in descending order. Specifically, the sleep stage corresponding to the maximum value of the stage variation coefficients for each segmented data is identified as EMG sleep, the middle value as light sleep, and the minimum value as deep sleep.

[0086] S2143 identifies multiple segmented data and their corresponding sleep stages as stage behavioral data.

[0087] It is understandable that the various segmented data are respiratory feature datasets categorized based on sleep mode switching types (e.g., including amplitude change rate, frequency change rate, etc. of data segments), while the corresponding sleep stages are labels reflecting the user's physiological state (light sleep, deep sleep, eye movement state).

[0088] With this setup, when multiple segmented data points and sleep stages exist independently, it's impossible to directly reflect which physiological sleep scenario a particular type of respiratory characteristic data corresponds to. Subsequent adjustments to ventilator parameters need to precisely match the physiological needs of each sleep stage (e.g., eye movement monitoring requires handling drastic breathing fluctuations, while deep sleep requires maintaining smooth ventilation). Stage behavior data, as an integration of data and stages, can be directly used as input for parameter tuning strategies.

[0089] S220, based on the stage behavior data, determine the gain characteristic parameters of the first running data.

[0090] For example, the average amplitude ratio between the two types of data can be obtained by comparing the abdominal diaphragm motion data of a user's breathing while awake with the abdominal diaphragm motion data of different sleep stages in the stage behavior data, and then the ratio can be confirmed as the gain characteristic parameter.

[0091] This setup, by labeling the abdominal diaphragm movement data with different sleep stages, allows the originally abstract diaphragm movement data to correspond with concrete sleep stages such as "light sleep," "deep sleep," and "eye movement sleep." This quantifies the duration, duration, and cyclical alternation of each sleep stage, providing a reference scalar for subsequent adjustments to the initial operational data.

[0092] In one possible implementation, in step S220, based on the stage behavior data, the gain characteristic parameters of the first running data are determined, including: S221, Based on the comparison between the baseline abdominal diaphragm motion data and the stage behavior data, the state difference rate corresponding to different sleep stages is obtained; wherein, the baseline abdominal diaphragm motion data is used to reflect the abdominal diaphragm motion data of the user's breathing in the awake state, and the state difference rate is used to indicate the ratio between the average amplitude generated by the diaphragm corresponding to a single sleep stage in the stage behavior data and the average amplitude generated by the diaphragm in the baseline abdominal diaphragm motion data.

[0093] It is understandable that baseline diaphragmatic motion data serves as a physiological baseline for a user's respiratory function. When awake, diaphragmatic motion is controlled by the individual's conscious breathing, and the average amplitude of diaphragmatic motion is stable and can reflect an individual's basic ventilation capacity.

[0094] For example, firstly, abdominal diaphragm movement data is collected when the user is awake and at rest (e.g., sitting quietly after waking up, without physical activity, and without eating). Abnormal data points corresponding to interfering actions such as coughing and swallowing are excluded and used as the baseline abdominal diaphragm movement data. 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. 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.

[0095] S222, the state difference rate corresponding to different sleep stages is identified as the gain characteristic parameter corresponding to different sleep stages.

[0096] This is understandable, as different sleep stages correspond to different levels of physiological activity. During ventilator use, different adjustments are needed to prevent tidal surges during tidal volume adjustments, which could wake the user from sleep. In other words, different sleep stages correspond to different gain characteristic parameters.

[0097] This setup, by calculating the state difference rate (average amplitude during sleep stage ÷ baseline amplitude during wakefulness), transforms the respiratory characteristics of different sleep stages into quantified deviations from the baseline, reducing interference from individual differences in respiratory function (e.g., users with different lung capacities). Different users exhibit individual differences in their wakefulness baseline respiratory characteristics (e.g., amplitude, frequency) (e.g., user A's diaphragm amplitude during wakefulness is 2.0 mm, while user B's is 1.6 mm). Using a uniform gain (e.g., 0.8 gain for all users during deep sleep) would lead to deviations in the actual adaptation parameters for user B (user B's deep sleep amplitude is 1.2 mm, and the parameters calculated using 0.8 gain might be insufficient). However, the gain characteristic parameters determined by the individual state difference rate reflect both the common requirements of sleep stages (e.g., gain during deep sleep is generally lower than during light sleep) and individual baseline differences (e.g., user A's deep sleep gain is 0.75, while user B's is 0.78), achieving a balance between "stage commonality + individual characteristics" in parameter tuning and reducing adaptation errors caused by indiscriminate gain.

[0098] S300, based on second behavioral data and adjustment gain parameters, identifies sleep characteristic data from first operating data to reflect the user's actual need for ventilator tidal volume adjustment during sleep.

[0099] It is understandable that during the entire sleep process, the user's tidal volume fluctuates due to the relaxation of the throat, changes in sleeping posture, and changes in sleep stages. There may be events at different times in different sleep stages where the user's tidal volume is insufficient. Therefore, the CPAP machine needs to adjust for these events. However, if the user does not experience events of insufficient tidal volume at different times in different sleep stages, then the CPAP machine does not need to adjust for these events.

[0100] For example, the tidal volume corresponding to each breathing cycle in the second behavior data can be obtained by analyzing the second behavior data. Then, the adjustment gain parameters corresponding to different sleep stages at different times are processed with the set value of the tidal volume of the user's breathing in the awake state to obtain the tidal volume required by the user in different sleep stages. Then, by comparing the tidal volume corresponding to each breathing cycle of the user with the tidal volume required by the user in different sleep stages, the data that the user needs to adjust throughout the sleep process can be determined and used as sleep feature data.

[0101] In one possible implementation, in step S300, sleep characteristic data reflecting the user's actual tidal volume adjustment needs during sleep are identified from the first operating data based on the second behavioral data and the adjustment gain parameter, including: S310, based on the second line of data, obtain the respiratory rate feature; wherein, the respiratory rate feature is used to reflect the respiratory rate of a user in one complete respiratory cycle.

[0102] It is understandable that respiratory rate, as a core basic indicator of respiratory function, directly reflects the speed and stability of the respiratory rhythm (for example, the rate is slow during deep sleep and fluctuates greatly during eye movement).

[0103] For example, a complete respiratory cycle is defined as the inhalation start point → the exhalation end point. The respiratory rate can be obtained by identifying the magnitude of the airflow signal. That is, the moment when the airflow intensity increases from 0 (airflow from nothing to something) is the inhalation start point, and the moment when the airflow intensity decreases to 0 and remains stable (airflow from something to nothing) is the exhalation end point. The respiratory rate characteristics are then obtained by calculating the time difference between the inhalation start point and the exhalation end point and converting it into a cycle frequency.

[0104] S320 extracts multiple tidal volumes from the second behavior data based on respiratory rate characteristics; among them, the tidal volume is used to reflect the tidal volume of the user during a complete respiratory cycle in sleep.

[0105] It is understandable that the respiratory rate characteristics clearly define the timestamps corresponding to the start and end points of inspiration for each single respiratory cycle, and this time range serves as the precise time anchor for extracting the tidal volume of the corresponding cycle. The tidal volume can be obtained by calculating the integral of the airflow rate over time during the inspiration phase (while the flow rate during the expiration phase is reversed, and the absolute value of the integral is consistent with that during inspiration, so only the integral during inspiration needs to be calculated).

[0106] For example, a signal segment corresponding to the respiratory cycle time is extracted from the second line of data, and the tidal volume is obtained by calculating the integral value of the signal segment belonging to the inspiratory phase.

[0107] S330, based on the adjustment gain parameters of different sleep stages, processes them with the set tidal volume of the first operating data to obtain the comparative tidal volume to reflect different sleep stages; wherein, the set tidal volume is used to reflect the set value of the tidal volume of the user's breathing in the awake state, and the comparative tidal volume is used to indicate the product value of the set tidal volume and the adjustment gain parameter.

[0108] It is understandable that the initial tidal volume setting in the first set of data is the ventilation baseline value for the user in a waking state. This value is determined based on the respiratory physiological needs during wakefulness (voluntary control, activity level). However, during sleep, due to changes in respiratory center activity (e.g., deep sleep inhibition, REM fluctuations), the ventilation needs differ significantly from those in the waking state. Adjusting the gain parameter essentially involves quantifying the ventilation needs during sleep relative to the waking baseline. By multiplying the two, a comparative tidal volume is obtained, transforming the fixed setting value for the waking state into a personalized tidal volume reference value that aligns with the physiological needs of different sleep stages.

[0109] For example, if the tidal volume is set to 500 mL and the characteristic gain parameter for deep sleep is 0.75, then the contrast tidal volume corresponding to the deep sleep stage is 500 mL × 0.75 = 375 mL, which means that the ventilator needs to keep the tidal volume stable at around 375 mL during this stage.

[0110] S340 performs simultaneous comparisons of multiple respiratory tidal volumes with comparative tidal volumes of different sleep stages to obtain comparison results, and obtains sleep characteristic data based on the comparison results.

[0111] It is understandable that multiple tidal volumes (reflecting the actual ventilation volume of a single breath during sleep) are dynamic feedbacks of the user's true physiological state, while the comparative tidal volume for different sleep stages (reflecting the ideal ventilation target for that stage) serves as a theoretical baseline. Simultaneous comparison of these two metrics can accurately verify whether the actual ventilation volume matches the target requirement for the current sleep stage. The comparison results include two outcomes: satisfied and unsatisfied. Specifically, if the tidal volume is less than the corresponding comparative tidal volume, the comparison result is unsatisfied; otherwise, the comparison result is satisfied.

[0112] This setup analyzes the user's breathing data to obtain the actual tidal volume during sleep. Then, by adjusting the gain parameters and processing the data against the set tidal volume, the required tidal volume during sleep is obtained. Finally, the actual tidal volume is compared with the required tidal volume, and the timing of a second adjustment is determined based on the comparison results. The second adjustment is made based on the user's breathing behavior, improving the adaptability of the ventilator.

[0113] S400, after adjusting the first operating data based on the adjustment gain parameter, generates second operating data based on sleep characteristic data and the adjusted first operating data; wherein, the second operating data is used to reflect the tidal volume set by the ventilator in the user's sleep state.

[0114] It is understandable that after adjusting the gain parameters to adjust the first operating data, the ideal tidal volume setting data for the user throughout the entire sleep stage is obtained (for example, tidal volume A between 2 am and 3 am, and tidal volume B between 3 am and 4 am). Then, the first operating data after the first adjustment is adjusted a second time using sleep characteristic data, thereby obtaining the timing tidal volume setting data that can adapt to the user throughout the entire sleep stage (for example, between 2:45 am and 2:47 am, the user's spontaneous breathing tidal volume meets the tidal volume required for sleep due to changes in sleep posture, meaning the ventilator does not need to output according to the ideal tidal volume). In one possible implementation, in step S400, after adjusting the first running data based on the adjustment gain parameter, second running data is generated based on the sleep feature data and the adjusted first running data, including: S410, 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 are processed to obtain the adjustment parameter; wherein, the adjustment parameter is used to reflect the data that needs to be replaced by the set tidal volume in the first running data.

[0115] It is understandable that the core processing logic for adjusting parameters is the adjustment gain parameter corresponding to the sleep stage multiplied by the set tidal volume corresponding to the time of the first running data.

[0116] For example, first establish two sets of associations: "sleep characteristic data time point → corresponding sleep stage → adjustment of gain parameter in this stage" and "sleep characteristic data time point → set tidal volume at the time corresponding to the first running data", so that the input parameters are fully aligned in the time dimension and the sleep stage dimension.

[0117] S420, based on the first operating data and adjustment parameters, the initial operating data is obtained; wherein, the initial operating data is used to reflect the operating data after the set tidal volume that needs to be adjusted in the first operating data is completed.

[0118] It is understandable that the parameters in the first set of running data are related (for example, the tidal volume, inspiratory time, and airway pressure need to be matched, and the inspiratory time needs to be shortened synchronously when the tidal volume decreases in order to maintain the respiratory rate), which means that the tidal volume needs to be replaced and the related parameters need to be adjusted synchronously.

[0119] S430 performs smoothing filtering on the initial running data based on the transition time period to obtain the second running data.

[0120] It is understandable that in the initial operating data, there are significant differences in parameters (such as tidal volume and airway pressure) at different sleep stages (e.g., 450mL in light sleep → 375mL in deep sleep, with a sudden drop in tidal volume of 75mL). If the parameters are changed directly at the stage switching time (transition period), it will cause a sudden change in the airflow and pressure output by the ventilator. From a physiological point of view, users may experience shortness of breath, chest tightness, or even wake up due to the sudden change in ventilation or pressure, which will disrupt the continuity of sleep and result in poor user performance.

[0121] This setup ensures that all parameters in the initial operating data are compatible with each other, reducing system conflicts caused by local adjustments and guaranteeing stable operation of the ventilator. If only the tidal volume setting is replaced without adjusting the associated parameters, it can easily lead to abnormal ventilator operation (for example, if the tidal volume drops to 375mL but the inspiratory time remains at 1.5 seconds when the patient is awake, it may cause excessively high airflow and user discomfort).

[0122] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0123] Corresponding to the ventilator control method based on sleep behavior data described in the above embodiments, this application also provides 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 A structural block diagram of a ventilator control system based on sleep behavior data provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0124] Reference Figure 3 The ventilator control system based on sleep behavior data includes: The acquisition unit is used to acquire behavioral data and first operational data; wherein, the behavioral data includes first behavioral data reflecting the movement of the abdominal diaphragm during sleep and second behavioral data reflecting the breathing status of the user during sleep, and the first operational data is used to reflect the tidal volume set by the ventilator when the user is awake.

[0125] The first analysis unit is used to determine the adjustment gain parameter based on the first row of data; wherein the adjustment gain parameter is used to reflect the adjustment parameter for adjusting the tidal volume of the ventilator.

[0126] The second analysis unit is used to identify sleep characteristic data from the first operating data based on the second behavioral data and the adjusted gain parameters. This sleep characteristic data reflects the actual tidal volume adjustment needs of the user during sleep.

[0127] The execution unit is used to adjust the first operating data based on the adjustment gain parameter, and then generate second operating data based on sleep characteristic data and the adjusted first operating data; wherein the second operating data is used to reflect the tidal volume set by the ventilator in the user's sleep state.

[0128] It should be noted that the information interaction and execution process between the above systems / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be 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 into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0130] This application also provides a ventilator, which includes a delivery mechanism, a drive mechanism, and a control device, and the ventilator is electrically connected to the control device. Figure 4 This is a schematic diagram of the structure of the control device 4 provided in one embodiment of this application. Figure 4 As shown, the control device 4 in this embodiment includes: at least one processor 40 ( Figure 4Only one is shown in the image), at least one memory 41 ( Figure 4 (Only one is shown in the image) and a computer program 42 stored in the at least one memory 41 and executable on the at least one processor 40. When the processor 40 executes the computer program 42, it causes the control device 4 to implement the steps in any of the above embodiments of the ventilator control method based on sleep behavior data, or causes the control device 4 to implement the functions of each module / unit in the above embodiments of the system.

[0131] For example, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 42 in the control device 4.

[0132] The control device 4 can be a microcontroller, application-specific integrated circuit, etc. The control device 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of control device 4 and does not constitute a limitation on control device 4. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0133] The processor 40 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0134] In some embodiments, the memory 41 may be an internal storage unit of the control device 4, such as a hard disk or memory of the control device 4. In other embodiments, the memory 41 may be an external storage device of the control device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the control device 4. Furthermore, the memory 41 may include both internal storage units and external storage devices of the control device 4. The memory 41 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0135] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0136] This application provides a computer program product that, when run on a ventilator, enables the ventilator to perform the steps described in any of the above method embodiments.

[0137] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a ventilator, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0138] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0139] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0140] In the embodiments provided in this application, it should be understood that the disclosed sleep behavior data-based ventilator control system can be implemented in other ways. For example, the sleep behavior data-based ventilator control system embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be indirect couplings or communication connections through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0141] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0142] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A ventilator control method based on sleep behavior data, characterized in that, include: Acquire behavioral data and first operational data; wherein, the behavioral data includes first behavioral data reflecting the movement of the abdominal diaphragm during sleep and second behavioral data reflecting the breathing status of the user during sleep, and the first operational data is used to reflect the tidal volume set by the ventilator when the user is awake. Based on the first behavioral data, an adjustment gain parameter is determined; wherein, the adjustment gain parameter is used to reflect the adjustment parameter for adjusting the tidal volume of the ventilator; Based on the second behavioral data and the adjustment gain parameter, sleep characteristic data reflecting the actual tidal volume adjustment needs of the ventilator during sleep are identified from the first operating data. After adjusting the first operating data based on the adjusted gain parameter, second operating data is generated based on the sleep characteristic data and the adjusted first operating data; wherein, the second operating data is used to reflect the tidal volume set by the ventilator during the user's sleep state.

2. The ventilator control method based on sleep behavior data as described in claim 1, characterized in that, The step of determining the adjustment gain parameter based on the first behavioral data includes: Based on the first behavioral data, stage behavioral data is obtained; wherein, the stage behavioral data is used to reflect the user's different sleep stages and their corresponding abdominal diaphragm movement data; Based on the stage behavior data, the gain characteristic parameters of the first running data are determined.

3. The ventilator control method based on sleep behavior data as described in claim 2, characterized in that, The process of obtaining stage behavior data based on the first behavior data includes: Acquire physiological characteristic information and determine the segmentation interval of the first behavioral data based on the physiological characteristic information; wherein, the physiological characteristic information is used to reflect the user's age, weight and respiratory function rating, and the segmentation interval is used to reflect a complete cycle of abdominal diaphragm movement of the user; Based on the division interval, a diaphragm motion feature set is obtained from the first behavioral data according to the time series; wherein, the diaphragm motion feature set is a collection of multiple abdominal diaphragm motion data obtained after dividing the first behavioral data according to the division interval; Based on the diaphragm motion feature set, the first behavioral data is segmented into multiple segmented data; wherein, the segmented data is used to reflect abdominal diaphragm motion data under different sleep stages; Based on the various segmented data, stage behavior data is obtained.

4. The ventilator control method based on sleep behavior data as described in claim 3, characterized in that, Based on the diaphragm motion feature set, the first behavioral data is segmented into multiple segmented data, including: By comparing the i-th abdominal diaphragm motion data with the (i+1)-th abdominal diaphragm motion data in the diaphragm motion feature set, the i-th difference value is obtained; wherein, the difference value is used to reflect the difference between the average amplitudes of the abdominal diaphragm motion data; When the difference between the (i+1)th difference value and the ith difference value is greater than the difference between the ith difference value and the (i-1)th difference value, the time node between the ith diaphragm motion feature and the (i+1)th diaphragm motion feature is used as the segmentation point to obtain multiple segmentation points; the diaphragm motion feature is used to reflect the average amplitude of the abdominal diaphragm motion data corresponding to different segmentation intervals. The first action data is divided into multiple data segments based on multiple segmentation points; Based on the analysis of the diaphragm motion characteristics corresponding to multiple data segments, various segmentation data are obtained.

5. The ventilator control method based on sleep behavior data as described in claim 4, characterized in that, After segmenting the first action data into multiple data segments based on the multiple segmentation points, the process includes: Based on the segmentation point, extract two data segments adjacent to the segmentation point from the plurality of data segments; The transition time period is obtained by 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 in two data segments adjacent to the segmentation point.

6. The ventilator control method based on sleep behavior data as described in claim 4, characterized in that, The analysis based on the diaphragm motion characteristics corresponding to multiple data segments yields various segmented data, including: Multiple adjacent diaphragm motion feature groups are extracted from the diaphragm motion features corresponding to multiple data segments, and multiple feature change rates are obtained based on the multiple adjacent diaphragm motion feature groups; wherein, the adjacent diaphragm motion feature groups are used to reflect the combination of diaphragm motion features between two adjacent data segments, and the feature change rates are used to reflect the changes in diaphragm motion features between different sleep patterns; Based on the multiple characteristic change rates, the multiple data segments are divided into various types of segmented data.

7. The ventilator control method based on sleep behavior data as described in claim 5, characterized in that, The stage behavior data obtained based on the various segmented data includes: Based on various types of segmented data, the coefficients of variation corresponding to multiple data segments in each type of segmented data are obtained, and the average value of the multiple coefficients of variation is determined as the stage coefficient of variation; wherein, the coefficients of variation are used to reflect the stability of the data segments; Based on the ascending order of the stage variation coefficients corresponding to the various segmented data, multiple sleep stages corresponding to the various segmented data are obtained; wherein, the sleep stages are used to reflect the sleep structure corresponding to different physiological functional activities during user sleep; The various segmented data and the corresponding sleep stages are collectively identified as stage behavior data.

8. The ventilator control method based on sleep behavior data as described in claim 7, characterized in that, The step of determining the gain characteristic parameters of the first running data based on the stage behavior data includes: The baseline diaphragmatic motion data is compared with the stage behavior data to obtain the state difference rate corresponding to different sleep stages; wherein, the baseline diaphragmatic motion data is used to reflect the diaphragmatic motion data of the user's breathing in the awake state, and the state difference rate is used to indicate the ratio between the average amplitude of the diaphragm corresponding to a single sleep stage in the stage behavior data and the average amplitude of the diaphragm in the baseline diaphragmatic motion data. The state difference rate corresponding to different sleep stages is identified as the gain characteristic parameter corresponding to different sleep stages; And / or, the step of identifying sleep characteristic data from the first operational data, based on the second behavioral data and the adjusted gain parameter, to reflect sleep characteristics that need adjustment during the user's sleep process, includes: Based on the second behavioral data, a respiratory rate feature is obtained; wherein, the respiratory rate feature is used to reflect the respiratory rate of a user in one complete respiratory cycle; Multiple tidal volumes are extracted from the second behavioral data based on the respiratory rate characteristics; wherein the tidal volume is used to reflect the tidal volume of a user during a complete respiratory cycle in sleep. The adjustment gain parameter for different sleep stages is processed with the set tidal volume of the first operating data to obtain a comparative tidal volume that reflects different sleep stages; wherein, the set tidal volume is used to reflect the set value of the tidal volume of breathing when the user is awake, and the comparative tidal volume is used to indicate the product value of the set tidal volume and the adjustment gain parameter. Simultaneous domain comparison is performed between multiple respiratory tidal volumes and comparative tidal volumes of different sleep stages to obtain comparison results, and sleep characteristic data is obtained based on the comparison results.

9. The ventilator control method based on sleep behavior data as described in claim 8, characterized in that, After adjusting the first operating data based on the adjusted gain parameter, generating second operating data based on the sleep feature data and the adjusted first operating data includes: 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 the adjustment parameter; wherein, the adjustment parameter is used to reflect the data that needs to be replaced by the set tidal volume in the first running data; Based on the first operating data and the adjustment parameters, initial operating data is obtained; wherein, the initial operating data is used to reflect the operating data after the set tidal volume that needs to be adjusted in the first operating data has been adjusted; The initial running data is smoothed and filtered based on the transition time period to obtain the second running data.

10. A ventilator control system based on sleep behavior data, characterized in that, include: An acquisition unit is used to acquire behavioral data and first operational data; wherein, the behavioral data includes first behavioral data reflecting the movement of the abdominal diaphragm during sleep and second behavioral data reflecting the breathing status of the user during sleep, and the first operational data is used to reflect the tidal volume set by the ventilator when the user is awake. The first analysis unit is used to determine the adjustment gain parameter based on the first behavioral data; wherein the adjustment gain parameter is used to reflect the adjustment parameter for adjusting the tidal volume of the ventilator; The second analysis unit is used to identify sleep characteristic data from the first operating data based on the second behavioral data and the adjustment gain parameter, which reflects the user's actual need for ventilator tidal volume adjustment during sleep. An execution unit is configured to adjust the first operating data based on the adjustment gain parameter, and then generate second operating data based on the sleep characteristic data and the adjusted first operating data; wherein the second operating data is used to reflect the tidal volume set by the ventilator during the user's sleep state.

Images