Automatic control method and device for breathing machine, computer equipment, readable storage medium and program product

By analyzing the ventilator's environmental sound data, using snoring events and pressure adjustment models, timely adjusting the ventilator pressure, the problems of delay and inaccurate ventilator pressure adjustment in traditional methods are solved, ensuring the effective operation of the ventilator.

CN118987423AActive Publication Date: 2024-11-22CENT SOUTH UNIV +1
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202411118151.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-22
Estimated Expiration
2044-08-15

AI Technical Summary

Technical Problem

The traditional automatic control method of ventilator cannot adjust the ventilator pressure in a timely and accurate manner, resulting in the inability to ensure the operation effect of the ventilator.

Method used

By acquiring and analyzing ambient sound monitoring data during ventilator operation, including snoring and non-snoring data, using snoring event detection models and ventilator pressure adjustment models, target snoring events characterizing precursors of respiratory abnormalities were detected and based on matching pressure Adjust the plan to control the ventilator to boost or lower the pressure.

Benefits of technology

It realizes timely and accurately adjusting the ventilator pressure when abnormal breathing precursors occur, ensuring the operating effect of the ventilator and avoiding user discomfort caused by delayed pressure adjustment or mismatch.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118987423A_ABST
    Figure CN118987423A_ABST
Patent Text Reader

Abstract

The invention relates to a breathing machine automatic control method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring environmental sound monitoring data in the running process of the breathing machine; the environmental sound monitoring data comprises snore monitoring data and non-snore monitoring data; snore event detection is conducted on the environment sound monitoring data; when a target snore event representing the abnormal breathing precursor is detected, a target pressure adjusting scheme matched with the target snore event is determined, and the breathing machine is controlled to increase the pressure according to the target pressure adjusting scheme. By the adoption of the method, when it is detected that the breathing abnormity precursor occurs, the breathing machine can be timely and accurately controlled to increase the pressure according to the corresponding target pressure adjusting scheme instead of being adjusted after breathing abnormity occurs, and therefore the pressure of the breathing machine can be timely and accurately adjusted, the running effect of the breathing machine is ensured, and the breathing efficiency is improved. And abnormal breathing of a user of the breathing machine is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a ventilator automatic control method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] A ventilator is an important medical device that can be used to assist the user to maintain normal respiratory function. In traditional technology, the target tidal volume can be set to automatically adjust the ventilator pressure in a timely manner, but this control method will cause excessive pressure when the pressure is automatically adjusted, causing discomfort to the user. In traditional technology, breathing can also be detected, and the ventilator can be controlled to adjust the pressure after abnormal breathing is detected, but this control method will cause a delay in the ventilator pressure adjustment.

[0003] Therefore, the traditional ventilator automatic control method cannot adjust the ventilator pressure in a timely and accurate manner, resulting in the inability to ensure the operating effect of the ventilator. Summary of the invention

[0004] Based on this, it is necessary to provide a ventilator automatic control method, device, computer equipment, computer readable storage medium and computer program product that can adjust the ventilator pressure both timely and accurately to ensure the operating effect of the ventilator in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for automatic control of a ventilator, comprising:

[0006] Obtain environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data;

[0007] Perform snoring event detection on environmental sound monitoring data;

[0008] When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase the pressure according to the target pressure adjustment scheme.

[0009] In one embodiment, performing snoring event detection on environmental sound monitoring data includes:

[0010] Get the snoring event detection model;

[0011] Based on the snoring event detection model, snoring events are detected on the ambient sound monitoring data.

[0012] In one embodiment, the snoring event detection model is generated by:

[0013] Obtain multiple pieces of historical ambient sound monitoring data; the historical ambient sound monitoring data carries the annotations of historical target snoring events;

[0014] Dividing the plurality of historical ambient sound monitoring data into a data set according to a first ratio to obtain a plurality of historical ambient sound monitoring data subsets;

[0015] Based on multiple historical ambient sound monitoring data subsets, the initial snoring event detection model is iteratively optimized until the first iterative optimization stop condition is reached, thereby obtaining a snoring event detection model.

[0016] In one embodiment, determining a target pressure adjustment scheme matching a target snoring event includes:

[0017] Obtain ventilator pressure adjustment model;

[0018] extracting target snoring monitoring data corresponding to the target snoring event from the environmental sound monitoring data;

[0019] The target snoring monitoring data is input into the ventilator pressure adjustment model, and the pressure adjustment scheme of the target snoring monitoring data is analyzed through the ventilator pressure adjustment model to determine the target pressure adjustment scheme that matches the target snoring event.

[0020] In one embodiment, the ventilator pressure adjustment model is generated by:

[0021] Acquire ventilator pressure adjustment data for each historical target snoring event in multiple historical environmental sound monitoring data;

[0022] For each historical target snoring event, establishing a correlation between the historical target snoring event and the ventilator pressure adjustment data of the historical target snoring event, and generating a pressure adjustment scheme group;

[0023] Dividing the data set by the plurality of pressure adjustment scheme groups according to a second ratio to obtain a plurality of pressure adjustment scheme group subsets;

[0024] Based on multiple subsets of pressure adjustment scheme groups, the initial ventilator pressure adjustment model is iteratively optimized until a second iterative optimization stop condition is reached to obtain a ventilator pressure adjustment model.

[0025] In one embodiment, the ventilator automatic control method further includes:

[0026] When it is detected that the mask of the ventilator is removed, or when it is detected that the duration of the event-free segment in the environmental sound monitoring data has reached the preset duration, the ventilator is controlled to lower the pressure;

[0027] After the ventilator is controlled to lower the pressure, if a target snoring event is detected from the latest acquired environmental sound monitoring data, the ventilator is controlled to automatically increase the pressure by executing the above ventilator automatic control method.

[0028] In a second aspect, the present application also provides a ventilator automatic control device, comprising:

[0029] A monitoring data acquisition module is used to acquire environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data;

[0030] A snoring event detection module is used to detect snoring events on environmental sound monitoring data;

[0031] The ventilator automatic control module is used to determine a target pressure adjustment scheme matching the target snoring event when a target snoring event representing a precursor of abnormal breathing is detected, and control the ventilator to increase pressure according to the target pressure adjustment scheme.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Obtain environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data;

[0034] Perform snoring event detection on environmental sound monitoring data;

[0035] When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase the pressure according to the target pressure adjustment scheme.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0037] Obtain environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data;

[0038] Perform snoring event detection on environmental sound monitoring data;

[0039] When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase the pressure according to the target pressure adjustment scheme.

[0040] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0041] Obtain environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data;

[0042] Perform snoring event detection on environmental sound monitoring data;

[0043] When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase the pressure according to the target pressure adjustment scheme.

[0044] The above-mentioned ventilator automatic control method, device, computer equipment, computer-readable storage medium and computer program product first obtain the environmental sound monitoring data during the operation of the ventilator, wherein the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data. Further, the environmental sound monitoring data is subjected to snoring event detection. When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase pressure according to the target pressure adjustment scheme. During the entire control process, it is possible to determine whether a target snoring event representing a precursor of abnormal breathing occurs by detecting the environmental sound monitoring data, and to determine a ventilator pressure adjustment scheme matching the precursor of abnormal breathing in a targeted manner, so that when the precursor of abnormal breathing is detected, the ventilator pressure can be controlled to increase pressure in a timely and accurate manner according to the corresponding ventilator pressure adjustment scheme, rather than adjusting after the abnormal breathing occurs, and the discomfort of the ventilator user will not be caused by the mismatch of the pressure adjustment scheme. Therefore, the ventilator pressure can be adjusted in a timely and accurate manner, thereby ensuring the operation effect of the ventilator. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 An application environment diagram of a ventilator automatic control method in an embodiment;

[0047] Figure 2 A schematic diagram of a flow chart of a method for automatically controlling a ventilator in one embodiment;

[0048] Figure 3 A schematic diagram of a process for implementing automatic control of a ventilator based on a snoring event detection model in one embodiment;

[0049] Figure 4A schematic diagram of a process for generating a snoring event detection model in one embodiment;

[0050] Figure 5 A schematic diagram of a process for generating a snoring event detection model in another embodiment;

[0051] Figure 6 A schematic diagram of a process for realizing automatic pressure control of a ventilator based on a ventilator pressure control model in one embodiment;

[0052] Figure 7 A schematic diagram of a process for generating a ventilator pressure adjustment model in one embodiment;

[0053] Figure 8 A schematic diagram of a flow chart for generating a ventilator pressure adjustment model in another embodiment;

[0054] Fig. 9 A schematic diagram of a process of automatically reducing the pressure of a ventilator in an embodiment, and automatically increasing the pressure according to the latest environmental sound monitoring data after reducing the pressure;

[0055] Fig.10 A comparison diagram of the control effect of a ventilator in one embodiment;

[0056] Fig.11 is a comparison diagram of ventilator control effects in another embodiment;

[0057] Fig.12 A structural block diagram of an automatic control device for a ventilator in one embodiment;

[0058] Fig.13 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] The ventilator automatic control method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the ventilator 100 is equipped with a controller 102 and an environmental sound collection device 104 connected to the controller 102. The controller 102 of the ventilator 100 can be used to receive, process and analyze data in real time, and control the operation of the ventilator 100 according to the data analysis results. A variety of control algorithms / data processing models can be integrated in the controller 102, and it can operate autonomously and intelligently. The environmental sound collection device 104 is a device or apparatus for capturing and recording snoring sounds produced by the human body during sleep, as well as other sounds around the ventilator 100. It has high sensitivity and can accurately detect and record environmental sounds, providing support for subsequent data processing and analysis of the controller 102. The environmental sound collection device 104 can be equipped with multiple microphones / sound sensors for collecting environmental sounds.

[0061] Specifically, in Figure 1 In the application environment shown, the environmental sound acquisition device 104 can transmit the environmental sound monitoring data collected in real time to the controller 102, wherein the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data. Further, the controller 102 can perform snoring event detection on the environmental sound monitoring data. When a target snoring event representing a precursor of abnormal breathing is detected, the controller 102 can determine a target pressure adjustment scheme that matches the target snoring event, and control the ventilator 100 to increase the pressure according to the target pressure adjustment scheme, so that the user of the ventilator 100 will not have abnormal breathing.

[0062] In an exemplary embodiment, Figure 2 As shown, a ventilator automatic control method is provided, and the method is applied to Figure 1 The controller 102 in FIG. 1 is taken as an example to illustrate the method, which includes the following steps 202 to 206. Among them:

[0063] Step 202, obtaining environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data.

[0064] The snoring monitoring data refers to the monitoring data containing snoring sounds, and the non-snoring monitoring data includes but is not limited to the monitoring data of various external interference sounds such as the running sound of the ventilator motor and the sound of people talking.

[0065] Optionally, during the operation of the ventilator, the ambient sound collection device in the ventilator can collect the ambient sound around the ventilator in real time, such as the snoring of the ventilator user and other external sounds around the ventilator, thereby generating ambient sound monitoring data and transmitting the ambient sound monitoring data to the controller.

[0066] Step 204: Detect snoring events on the ambient sound monitoring data.

[0067] Optionally, the controller can perform real-time snoring event detection on the ambient sound monitoring data through a snoring event detection model pre-deployed on the controller, and determine whether there is a target snoring event in the ambient sound monitoring data. Among them, the snoring event detection model can be built based on a neural network model, which can learn how to detect target snoring events from complex and interfering ambient sound monitoring data. The neural network model is a computational model that simulates the structure and function of the biological nervous system. It is composed of a large number of nodes (neurons) connected to each other. Each node receives input signals from other nodes, processes these signals through activation functions, and then outputs them to the next layer of nodes. The neural network model can learn the mapping relationship between input and output by adjusting the connection weights between nodes.

[0068] Step 206 , when a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase the pressure according to the target pressure adjustment scheme.

[0069] Abnormal breathing specifically refers to: hypoventilation or apnea due to airway collapse. Snoring is caused by the vibration of the airway when a person breathes. It is closely related to human breathing and often exists before abnormal breathing occurs. Therefore, by detecting snoring, the precursors of abnormal breathing can be determined, so that the ventilator pressure can be adjusted in time before abnormal breathing occurs, to assist the user of the ventilator to maintain normal breathing and ensure the operation effect of the ventilator. The pressure adjustment plan includes but is not limited to: at which boost speed to boost the pressure, and how much proportion / pressure the ventilator needs to boost.

[0070] Optionally, when a target snoring event representing a precursor of abnormal breathing is detected from the snoring monitoring data carried by the ambient sound monitoring data, the controller can analyze the target snoring event through a ventilator pressure adjustment model pre-deployed in the controller, and determine a target pressure adjustment scheme that matches the target snoring event, thereby timely and accurately controlling the ventilator to increase pressure according to the target pressure adjustment scheme. The ventilator pressure adjustment model can be built based on a neural network model, which can learn the mapping relationship between the precursor of abnormal breathing (target snoring event) and the ventilator pressure adjustment scheme corresponding to the precursor of abnormal breathing.

[0071] In the above-mentioned automatic control method of the ventilator, the environmental sound monitoring data during the operation of the ventilator is first obtained, wherein the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data. Further, the environmental sound monitoring data is subjected to snoring event detection. When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase pressure according to the target pressure adjustment scheme. During the entire control process, it is possible to determine whether a target snoring event representing a precursor of abnormal breathing occurs by detecting the environmental sound monitoring data, and to determine a ventilator pressure adjustment scheme matching the precursor of abnormal breathing in a targeted manner, so that when the precursor of abnormal breathing is detected, the ventilator pressure can be controlled to increase pressure in a timely and accurate manner according to the corresponding ventilator pressure adjustment scheme, rather than adjusting after the abnormal breathing occurs, and the discomfort of the ventilator user will not be caused by the mismatch of the pressure adjustment scheme. Therefore, the ventilator pressure can be adjusted in a timely and accurate manner, thereby ensuring the operation effect of the ventilator.

[0072] In an exemplary embodiment, Figure 2 On the basis of Figure 3 As shown, a flow chart of realizing automatic control of a ventilator based on a snoring event detection model is provided, which mainly includes the following steps:

[0073] Step 302: Acquire a snoring event detection model.

[0074] Optionally, the controller may first obtain a snoring event detection model pre-deployed on the controller, wherein the snoring event detection model may be built based on a neural network model, and may learn how to detect target snoring events representing precursors to abnormal breathing from complex and interfering environmental sound monitoring data by pre-labeling historical environmental sound monitoring data corresponding to snoring events representing precursors to abnormal breathing. The neural networks that may be used in this embodiment include, but are not limited to, convolutional neural networks (CNN), recurrent neural networks (RNN) and their variants (such as LSTM, GRU), deep neural networks (DNN), and the like.

[0075] Step 304: Perform snoring event detection on the ambient sound monitoring data based on the snoring event detection model.

[0076] Optionally, the controller may perform snoring event detection on the ambient sound monitoring data collected in real time through a snoring event detection model to identify whether the snoring monitoring data carried by the ambient sound monitoring data has a target snoring event representing a precursor to abnormal breathing.

[0077] In this embodiment, a pre-trained snoring event detection model can be used to accurately identify in real time whether the current user of the ventilator has signs of abnormal breathing, so that when signs of abnormal breathing occur, the pressure of the ventilator can be adjusted in time to assist the user in improving breathing.

[0078] In one embodiment, Figure 4 As shown, the snoring event detection model can be generated by the following steps:

[0079] Step 402, obtaining a plurality of historical ambient sound monitoring data; the historical ambient sound monitoring data carries the annotation of the historical target snoring events.

[0080] The plurality of historical ambient sound monitoring data may be derived from multiple users and are derived from the ambient sound monitoring data generated by the multiple users at different time periods in the past. The historical target snoring event specifically refers to the snoring sound that represents the precursor of abnormal breathing carried in the historical ambient sound monitoring data.

[0081] Optionally, in the process of collecting historical ambient sound monitoring data for each user, the user of the ventilator also needs to wear a polysomnography device at the same time, so that professionals with relevant knowledge can mark the historical snoring monitoring data carried by the historical ambient sound monitoring data with historical target snoring events that represent the precursors of abnormal breathing based on the physiological data monitored by the polysomnography device, and then transmit the marked historical ambient sound monitoring data to the controller, or the controller can automatically mark the historical snoring monitoring data carried by the historical ambient sound monitoring data with historical target snoring events that represent the precursors of abnormal breathing based on the physiological data monitored by the polysomnography device according to a preset program. Based on this, the controller can obtain multiple pieces of historical ambient sound monitoring data carrying the markings of historical target snoring events.

[0082] Among them, the polysomnography equipment is a professional equipment widely used in the field of sleep medicine. It records multiple physiological indicators of the monitored object during sleep by connecting multiple electrodes. For example, by connecting electrodes on the scalp, face and other parts of the body, it monitors and records physiological signals such as electroencephalogram, electrooculogram, electromyogram, etc. of the monitored object, and monitors oral and nasal airflow, blood oxygen saturation, chest and abdominal respiratory movement, etc., to comprehensively evaluate the sleep condition of the monitored object, and these signals and data are also helpful in identifying whether there are sleep disorders, such as insomnia, narcolepsy, sleep apnea, hypopnea, etc. In this embodiment, the physiological data monitored by the polysomnography equipment helps the manual / controller to determine the abnormal breathing precursors (i.e., the snoring that occurs before apnea / hypopnea) in the snoring produced by the user of the ventilator during sleep, and then assists the manual / controller to mark the historical target snoring events for the collected historical environmental sound monitoring data.

[0083] Step 404 , dividing the plurality of historical ambient sound monitoring data into data sets according to a first ratio to obtain a plurality of historical ambient sound monitoring data subsets.

[0084] Among them, the first ratio is: dividing multiple historical ambient sound monitoring data into a training set, a validation set, and a test set. In this embodiment, the ratio of dividing the data set can be flexibly configured according to the actual application scenario, including but not limited to: training set: validation set: test set = 7:1:2.

[0085] Optionally, after preprocessing the multiple historical ambient sound monitoring data, the controller may divide the data set according to the first ratio to obtain multiple historical ambient sound monitoring data subsets, that is, obtain a training set carrying multiple historical ambient sound monitoring data (as a historical ambient sound monitoring data subset), a validation set carrying multiple historical ambient sound monitoring data (as a historical ambient sound monitoring data subset), and a test set carrying multiple historical ambient sound monitoring data (as a historical ambient sound monitoring data subset). The data preprocessing includes, but is not limited to: data cleaning (noise removal, missing value filling, etc.), etc., to improve the performance of the model and the training efficiency.

[0086] Step 406 , based on the multiple historical ambient sound monitoring data subsets, the initial snoring event detection model is iteratively optimized until the first iterative optimization stop condition is reached, thereby obtaining the snoring event detection model.

[0087] Optionally, after dividing the data sets of multiple historical ambient sound monitoring data into a first ratio, the controller can input the training set into the initial snoring event detection model, calculate the output of each layer in the model, and use a pre-set loss function (such as mean square error, cross entropy, etc.) to calculate the error between the model output and the actual result, thereby calculating the gradient of the parameters of each layer in the model according to the loss function, back-propagating the gradient to the previous layer of the network, and then using the gradient descent method or other optimization algorithms to update the weights and biases of each layer of the neural network in the model, and stop the optimization when the first iteration optimization stop condition is reached. The controller can repeat the above process multiple times, and in each repetition, a different neural network model can be selected for training, thereby obtaining multiple trained models, and then using the validation set to evaluate the multiple trained models to select the best model. Finally, the controller can also perform a model performance test on the selected model based on the test set, and use the model whose test results meet expectations as the final snoring event detection model.

[0088] Based on this, Figure 5 As shown, another flowchart of generating a snoring event detection model is provided, which mainly includes the following steps:

[0089] Step 502, when the user wears a polysomnography device and a ventilator at the same time, obtaining physiological data monitored by the polysomnography device and historical environmental sound monitoring data collected by the ventilator;

[0090] Step 504, based on the physiological data monitored by the polysomnography monitoring device, annotate the historical environmental sound monitoring data collected by the ventilator with historical target snoring events that represent precursors of abnormal breathing, and obtain multiple pieces of historical environmental sound monitoring data with annotations;

[0091] Step 506, dividing the data sets of the multiple historical environmental sound monitoring data with annotations into training sets, validation sets and test sets;

[0092] Step 508, training an initial snoring event detection model based on the training set;

[0093] Step 510 , selecting the best model from the trained models based on the validation set, and using the test set to perform a model performance test on the selected best model to determine a final snoring event detection model.

[0094] For example, after the snoring event detection model is trained using the controllers of one or more ventilators, the snoring event detection model can be integrated into the controller of each ventilator, so that subsequent ventilators can process the real-time collected environmental sound monitoring data based on the snoring event detection model.

[0095] In this embodiment, the optimal snoring event detection model can be obtained through iterative training, selection, and performance testing of the model, ensuring that the ventilator can process the real-time collected environmental sound monitoring data based on the snoring event detection model integrated in the controller, so as to accurately determine whether the current user of the ventilator has signs of abnormal breathing, which is beneficial for timely and accurate adjustment of the ventilator pressure when signs of abnormal breathing occur, thereby ensuring the operating effect of the ventilator.

[0096] In one possible implementation, Figure 3 On the basis of Figure 6 As shown, a flow chart of realizing automatic control of ventilator pressure based on a ventilator pressure control model is provided, which mainly includes the following steps:

[0097] Step 602: When a target snoring event representing a precursor of abnormal breathing is detected, a ventilator pressure adjustment model is obtained.

[0098] Optionally, when a target snoring event representing a precursor of abnormal breathing is detected, the controller may first obtain (call) a ventilator pressure adjustment model pre-deployed in the controller, wherein the ventilator pressure adjustment model is constructed based on a neural network, and can learn the mapping relationship between the precursor of abnormal breathing and the ventilator pressure adjustment scheme corresponding to the precursor of abnormal breathing, so as to be used to determine the target pressure adjustment scheme corresponding to the target snoring event detected in real time. The neural networks that can be used in this embodiment include, but are not limited to: convolutional neural networks (CNN), recurrent neural networks (RNN) and their variants (such as LSTM, GRU), deep neural networks (DNN, Deep Neural Networks), etc.

[0099] Step 604: extracting target snoring monitoring data corresponding to the target snoring event from the ambient sound monitoring data.

[0100] Optionally, when a target snoring event is detected from the ambient sound monitoring data (carrying snoring monitoring data and non-snoring monitoring data) collected in real time by the snoring event detection model, the controller may further extract target snoring monitoring data corresponding to the target snoring event from the ambient sound monitoring data.

[0101] Step 606, input the target snoring monitoring data into the ventilator pressure adjustment model, analyze the target snoring monitoring data through the ventilator pressure adjustment model, determine the target pressure adjustment plan that matches the target snoring event, and control the ventilator to increase the pressure according to the target pressure adjustment plan.

[0102] Optionally, the controller may input the target snoring monitoring data carrying the target snoring event into the ventilator pressure adjustment model, perform a pressure adjustment scheme analysis on the target snoring monitoring data through the ventilator pressure adjustment model, and determine a ventilator pressure adjustment scheme (target pressure adjustment scheme) that matches the respiratory abnormality precursor (target snoring event) carried by the target snoring monitoring data, thereby timely and accurately controlling the ventilator to increase pressure according to the target pressure adjustment scheme before the respiratory abnormality occurs.

[0103] It should be noted that the target pressure adjustment scheme output by the ventilator pressure adjustment model also includes a pressure increase rate that matches the target snoring event, so that the controller will not cause discomfort to the user during the pressure increase at the pressure increase rate.

[0104] In this embodiment, the trained ventilator pressure adjustment model can be used to determine in real time and accurately the ventilator pressure adjustment plan (target pressure adjustment plan) that matches the abnormal breathing precursors of the current ventilator user, so that when abnormal breathing precursors appear, the ventilator pressure can be adjusted promptly and accurately, thereby assisting the user to improve breathing before abnormal breathing occurs.

[0105] In one embodiment, Figure 7 As shown, the ventilator pressure adjustment model can be generated in the following ways:

[0106] Step 702: Acquire ventilator pressure adjustment data for each historical target snoring event in a plurality of historical ambient sound monitoring data.

[0107] Optionally, in the process of collecting each piece of historical ambient sound monitoring data for each user, the controller will also synchronously store the ventilator pressure adjustment data corresponding to each historical target snoring event in each piece of historical ambient sound monitoring data, such as the pressure increase speed, the pressure increase ratio, etc.

[0108] Step 704 : for each historical target snoring event, establish a correlation between the historical target snoring event and the ventilator pressure adjustment data of the historical target snoring event, and generate a pressure adjustment solution group.

[0109] Optionally, for each historical target snoring event, the controller will respectively establish an association between the historical target snoring event and the ventilator pressure adjustment data of the historical target snoring event, and generate a pressure adjustment scheme group, so that when the model is trained later, the neural network model can learn the mapping relationship between the precursors of abnormal breathing and the corresponding ventilator pressure adjustment schemes of the abnormal breathing precursors.

[0110] Step 706 , dividing the data set by the multiple pressure adjustment solution groups according to the second ratio to obtain multiple pressure adjustment solution group subsets.

[0111] Among them, the second ratio is: dividing multiple pressure adjustment scheme groups into a training set, a validation set, and a test set. In this embodiment, the ratio of dividing the data set can be flexibly configured according to the actual application scenario, including but not limited to training set: validation set: test set = 7:1:2.

[0112] Optionally, after performing data preprocessing on multiple pressure adjustment scheme groups, the controller may divide the data set according to the second ratio to obtain multiple pressure adjustment scheme group subsets, that is, obtain a training set carrying multiple pressure adjustment scheme groups (as a pressure adjustment scheme group subset), a validation set carrying multiple pressure adjustment scheme groups (as a pressure adjustment scheme group subset), and a test set carrying multiple pressure adjustment scheme groups (as a pressure adjustment scheme group subset). Data preprocessing includes but is not limited to: data cleaning (noise removal, missing value filling, etc.), etc., to improve the performance and training efficiency of the model.

[0113] Step 708: Based on the multiple subsets of pressure adjustment schemes, the initial ventilator pressure adjustment model is iteratively optimized until a second iterative optimization stop condition is reached to obtain a ventilator pressure adjustment model.

[0114] The second iterative optimization stop condition can be flexibly configured according to the actual application scenario, such as setting the iterative optimization to stop when the value of the loss function is less than a certain threshold.

[0115] Optionally, after dividing the data set into multiple pressure adjustment scheme groups according to the second ratio, the controller can input the training set into the initial ventilator pressure adjustment model, calculate the output of each layer in the model, and use a pre-set loss function (such as mean square error, cross entropy, etc.) to calculate the error between the model output and the actual result, thereby calculating the gradient of the parameters of each layer in the model according to the loss function, back-propagating the gradient to the previous layer of the network, and then using the gradient descent method or other optimization algorithms to update the weights and biases of each layer of the neural network in the model, and stop the optimization when the second iteration optimization stop condition is reached. The controller can repeat the above process multiple times, and can select different neural network models for training in each repetition, so as to obtain multiple trained models, and then use the validation set to evaluate the multiple trained models to select the best model. Finally, the controller can also perform a model performance test on the selected best model based on the test set, and use the model with the expected test results as the final ventilator pressure adjustment model.

[0116] Based on this, Figure 8 As shown, another flow chart of generating a ventilator pressure adjustment model is provided, which mainly includes the following steps:

[0117] Step 802, collecting historical target snoring events that represent precursors to abnormal breathing and ventilator pressure adjustment data corresponding to the historical target snoring events;

[0118] Step 804, dividing the historical target snoring events and the ventilator pressure adjustment data corresponding to the historical target snoring events into a data set to obtain a training set, a validation set and a test set;

[0119] Step 806, training an initial ventilator pressure adjustment model based on the training set;

[0120] Step 808, selecting the best model from the trained models based on the validation set, and using the test set to perform a model performance test on the selected best model to determine the final ventilator pressure adjustment model.

[0121] Exemplarily, after the ventilator pressure adjustment model is obtained by training the controller of one or more ventilators, the ventilator pressure adjustment model can be integrated into the controller of each ventilator respectively, so that subsequent ventilators can determine the target pressure adjustment scheme that matches the target snoring event detected in real time based on the ventilator pressure adjustment model.

[0122] In this embodiment, the optimal ventilator pressure adjustment model can be obtained through iterative training, selection, and performance testing of the model, ensuring that the ventilator can accurately determine the pressure adjustment plan that matches the target snoring event detected in real time through the ventilator pressure adjustment model integrated in the controller, so that the ventilator pressure can be adjusted in a timely and accurate manner when the precursors of abnormal breathing occur, thereby avoiding abnormal breathing for the current user of the ventilator.

[0123] In one embodiment, if Fig. 9 As shown, the ventilator automatic control method also includes:

[0124] Step 902, when it is detected that the mask of the ventilator is removed, or it is detected that the duration of the event-free segment in the ambient sound monitoring data has reached a preset duration, the ventilator is controlled to reduce the pressure.

[0125] The event-free segment in the ambient sound monitoring data is specifically a segment of monitoring data without snoring and abnormal breathing. The duration of the event-free segment in the ambient sound monitoring data has reached the preset duration, which can indicate that the user of the ventilator may have woken up, so there is no snoring for a long time. In this case, timely blood pressure reduction can avoid discomfort to the user who wakes up / has not yet shown signs of abnormal breathing due to excessive pressure.

[0126] Optionally, during the operation of the ventilator, when the controller detects that the mask of the ventilator is removed, or detects that the duration of the event-free segment in the real-time collected ambient sound monitoring data has reached a preset duration, the controller can first control the ventilator to reduce the pressure (the pressure reduction ratio can be flexibly configured according to the actual application scenario), and after reducing the pressure, the controller can control the ventilator to maintain the pressure after the reduction and operate stably for a period of time.

[0127] Furthermore, after controlling the ventilator to lower the pressure, the server can continue to detect the latest environmental sound monitoring data collected in real time. If the target snoring event is detected from the latest environmental sound monitoring data, execute step 904 to control the ventilator to automatically increase the pressure by executing the above-mentioned ventilator automatic control method.

[0128] Optionally, during the stable operation of the ventilator after the pressure is reduced, the controller will still collect ambient sound in real time through the ambient sound collection device in the ventilator, and the controller can continue to monitor the real-time collected ambient sound monitoring data through the snoring event detection model. Once the target snoring event is detected from the latest acquired ambient sound monitoring data, the controller can determine the pressure adjustment plan in a timely and accurate manner based on the ventilator pressure adjustment model, and control the ventilator to increase the pressure according to the determined pressure adjustment plan, so as to avoid breathing abnormalities in the user of the ventilator.

[0129] For example, after the mask of the ventilator is removed, the controller can first control the ventilator to reduce the pressure by a certain proportion. Before the user puts on the mask again and enters a sleep state, the controller can continue to control the ventilator to maintain stable operation at the reduced pressure. After the user enters a sleep state, if the controller detects a target snoring event from the real-time collected ambient sound monitoring data, the controller can further control the ventilator to increase the pressure according to a target pressure adjustment plan that matches the target snoring event.

[0130] For example, taking the case where the user of the ventilator is awake at night, the controller can control the ventilator to automatically reduce the pressure based on the long-term absence of snoring. After the user falls asleep again, if the controller detects a target snoring event from the real-time collected ambient sound monitoring data, the controller can control the ventilator according to a target pressure adjustment scheme that further matches the target snoring event, that is, automatically and accurately adjust the pressure of the ventilator in a timely manner before abnormal breathing occurs.

[0131] In this embodiment, when the mask of the ventilator is removed or the user of the ventilator may be awake, the pressure can be automatically reduced to ensure the comfort of the ventilator user. The pressure of the ventilator can also be automatically adjusted according to the subsequent real-time detection of target snoring events, so that when the precursors of abnormal breathing are detected, the pressure can be increased in a timely and accurate manner to avoid hypoventilation or apnea of ​​the user due to pressure reduction.

[0132] In a specific application scenario, such as Fig.10 As shown, a comparison diagram of the ventilator control effect of the ventilator automatic control method of the present invention and the traditional ventilator automatic control method is provided through the respiratory event sequence without intervention, the respiratory event sequence under the traditional ventilator automatic control method, and the respiratory event sequence under the ventilator automatic control method of the present invention, wherein:

[0133] Taking the traditional ventilator automatic control method of "detecting breathing and controlling the ventilator to perform pressure compensation after abnormal breathing is detected" as an example, compared with no intervention, under the traditional ventilator automatic control method, although abnormal breathing can be improved, the traditional ventilator automatic control method has a pressure increase delay, and it is necessary to increase the pressure after abnormal breathing is detected. The ventilator automatic control method of the present invention, on the one hand, can reduce the pressure in time after detecting a long event-free segment to avoid the user feeling uncomfortable due to excessive pressure after waking up. On the other hand, it can detect the current user of the ventilator in real time by real-time detection of the collected environmental sound monitoring data, and timely and accurately detect whether there are signs of abnormal breathing in the current user of the ventilator, so that when the signs of abnormal breathing occur, the ventilator can be controlled to increase the pressure in time and accurately according to the corresponding target pressure adjustment plan, which can avoid the pressure adjustment delay of the ventilator and effectively improve the user's breathing condition.

[0134] In a specific application scenario, such as Fig.11 As shown, a comparison diagram of the ventilator control effect between the ventilator automatic control method of the present invention and the traditional ventilator automatic control method is further provided, wherein: compared with the case without intervention, under the traditional ventilator automatic control method, although the abnormal breathing can be improved, the traditional ventilator automatic control method has a boost delay. The ventilator automatic control method of the present invention can detect whether the current user of the ventilator has abnormal breathing precursors in a timely and accurate manner by real-time detection of the collected environmental sound monitoring data, so that when abnormal breathing precursors occur, the ventilator boost can be controlled in a timely and accurate manner according to the corresponding target pressure adjustment scheme, avoiding the ventilator's pressure adjustment delay, and effectively improving the user's breathing condition and avoiding abnormal breathing in the user.

[0135] It should be noted that the above-mentioned embodiments, when reducing or increasing the pressure, will follow the principle of avoiding / minimizing human-machine confrontation, and reduce or increase the pressure at a speed acceptable to the user to ensure the comfort of the ventilator user. The specific speed of reducing or increasing the pressure can be determined based on past ventilator test data.

[0136] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0137] Based on the same inventive concept, the embodiment of the present application also provides a ventilator automatic control device for implementing the ventilator automatic control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more ventilator automatic control device embodiments provided below can refer to the limitations of the ventilator automatic control method above, and will not be repeated here.

[0138] In an exemplary embodiment, Fig.12 As shown, a ventilator automatic control device is provided, including: a monitoring data acquisition module 1202, a snoring event detection module 1204 and a ventilator automatic control module 1206, wherein:

[0139] A monitoring data acquisition module is used to acquire environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data;

[0140] A snoring event detection module is used to detect snoring events on environmental sound monitoring data;

[0141] The ventilator automatic control module is used to determine a target pressure adjustment scheme matching the target snoring event when a target snoring event representing a precursor of abnormal breathing is detected, and control the ventilator to increase pressure according to the target pressure adjustment scheme.

[0142] The above-mentioned automatic control device for the ventilator first obtains the environmental sound monitoring data during the operation of the ventilator, wherein the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data. Furthermore, the environmental sound monitoring data is subjected to snoring event detection. When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase pressure according to the target pressure adjustment scheme. During the entire control process, it is possible to determine whether a target snoring event representing a precursor of abnormal breathing occurs by detecting the environmental sound monitoring data, and to determine a ventilator pressure adjustment scheme matching the precursor of abnormal breathing in a targeted manner, so that when the precursor of abnormal breathing is detected, the ventilator pressure can be controlled to increase pressure in a timely and accurate manner according to the corresponding ventilator pressure adjustment scheme, rather than adjusting after the abnormal breathing occurs, and the discomfort of the ventilator user will not be caused by the mismatch of the pressure adjustment scheme. Therefore, the ventilator pressure can be adjusted in a timely and accurate manner, thereby ensuring the operation effect of the ventilator.

[0143] In one embodiment, the snoring event detection module includes: a snoring event detection model acquisition unit, used to acquire a snoring event detection model; and a snoring event detection unit, used to perform snoring event detection on the ambient sound monitoring data based on the snoring event detection model.

[0144] In one of the embodiments, the ventilator automatic control device also includes a snoring event detection model generation module, which is used to obtain multiple historical ambient sound monitoring data; the historical ambient sound monitoring data carries the annotation of the historical target snoring event; the multiple historical ambient sound monitoring data are divided into data sets according to a first ratio to obtain multiple historical ambient sound monitoring data subsets; based on the multiple historical ambient sound monitoring data subsets, the initial snoring event detection model is iteratively optimized until the first iterative optimization stop condition is reached to obtain the snoring event detection model.

[0145] In one of the embodiments, the ventilator automatic control module includes: a ventilator pressure adjustment model acquisition unit, used to acquire the ventilator pressure adjustment model; a target snoring monitoring data extraction unit, used to extract target snoring monitoring data corresponding to the target snoring event from the ambient sound monitoring data; a target pressure adjustment scheme determination unit, used to input the target snoring monitoring data into the ventilator pressure adjustment model, perform pressure adjustment scheme analysis on the target snoring monitoring data through the ventilator pressure adjustment model, and determine the target pressure adjustment scheme that matches the target snoring event.

[0146] In one of the embodiments, the ventilator automatic control device also includes a ventilator pressure adjustment model generation module, which is used to obtain ventilator pressure adjustment data for each historical target snoring event in multiple historical environmental sound monitoring data; for each historical target snoring event, establish an association between the historical target snoring event and the ventilator pressure adjustment data of the historical target snoring event, and generate a pressure adjustment scheme group; divide the multiple pressure adjustment scheme groups into data sets according to a second ratio to obtain multiple pressure adjustment scheme group subsets; based on the multiple pressure adjustment scheme group subsets, perform model iterative optimization on the initial ventilator pressure adjustment model until the second iterative optimization stop condition is reached to obtain the ventilator pressure adjustment model.

[0147] In one of the embodiments, the ventilator automatic control device also includes: a pressure reduction module, which is used to control the ventilator to reduce the pressure when it is detected that the mask of the ventilator is removed, or when it is detected that the duration of the event-free segment in the environmental sound monitoring data has reached a preset duration; after controlling the ventilator to reduce the pressure, if a target snoring event is detected from the latest acquired environmental sound monitoring data, the ventilator is controlled to automatically increase the pressure by executing the above-mentioned ventilator automatic control method.

[0148] Each module in the above-mentioned ventilator automatic control device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0149] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.13 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store ventilator automatic control data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a ventilator automatic control method is implemented.

[0150] Those skilled in the art will understand that Fig.13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0151] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0152] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0153] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0154] It should be noted that the user information (including but not limited to user personal information, information about the ventilator used by the user) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0155] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0156] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0157] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for automatically controlling a ventilator, It is characterized in that The method comprises: Acquire environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data; Performing snoring event detection on the environmental sound monitoring data; When a target snoring event representing a precursor of abnormal breathing is detected, a target pressure adjustment scheme matching the target snoring event is determined, and the ventilator is controlled to increase the pressure according to the target pressure adjustment scheme.

2. The method according to claim 1, It is characterized in that The performing snoring event detection on the environmental sound monitoring data includes: Get the snoring event detection model; Based on the snoring event detection model, snoring event detection is performed on the environmental sound monitoring data.

3. The method according to claim 2, It is characterized in that The snoring event detection model is generated in the following way: Acquire multiple pieces of historical ambient sound monitoring data; the historical ambient sound monitoring data carry annotations of historical target snoring events; Dividing the plurality of historical ambient sound monitoring data into data sets according to a first ratio to obtain a plurality of historical ambient sound monitoring data subsets; Based on the multiple historical ambient sound monitoring data subsets, the initial snoring event detection model is iteratively optimized until a first iterative optimization stop condition is reached, thereby obtaining a snoring event detection model.

4. The method according to claim 1, It is characterized in that The determining of a target pressure adjustment scheme matching the target snoring event comprises: Obtain ventilator pressure adjustment model; Extracting target snoring monitoring data corresponding to the target snoring event from the environmental sound monitoring data; The target snoring monitoring data is input into the ventilator pressure adjustment model, and the ventilator pressure adjustment model is used to perform pressure adjustment scheme analysis on the target snoring monitoring data to determine a target pressure adjustment scheme that matches the target snoring event.

5. The method according to claim 4, It is characterized in that The ventilator pressure adjustment model is generated in the following manner: Acquire ventilator pressure adjustment data for each historical target snoring event in multiple historical environmental sound monitoring data; For each of the historical target snoring events, establishing an association between the historical target snoring event and the ventilator pressure adjustment data of the historical target snoring event, and generating a pressure adjustment scheme group; Dividing the plurality of pressure adjustment scheme groups into data sets according to a second ratio to obtain a plurality of pressure adjustment scheme group subsets; Based on the multiple subsets of pressure adjustment scheme groups, the initial ventilator pressure adjustment model is iteratively optimized until a second iterative optimization stop condition is reached to obtain a ventilator pressure adjustment model.

6. The method according to claim 1, It is characterized in that The method further comprises: When it is detected that the mask of the ventilator is removed, or when it is detected that the duration of the event-free segment in the environmental sound monitoring data has reached a preset duration, the ventilator is controlled to reduce the pressure; After controlling the ventilator to reduce pressure, if a target snoring event is detected from the latest acquired environmental sound monitoring data, the ventilator is controlled to automatically increase pressure by executing the method of any one of claims 1 to 5.

7. A ventilator automatic control device, It is characterized in that The device comprises: A monitoring data acquisition module, used to acquire environmental sound monitoring data during the operation of the ventilator; the environmental sound monitoring data includes snoring monitoring data and non-snoring monitoring data; A snoring event detection module, used for performing snoring event detection on the environmental sound monitoring data; The ventilator automatic control module is used to determine a target pressure adjustment scheme matching the target snoring event when a target snoring event representing a precursor of abnormal breathing is detected, and control the ventilator to increase pressure according to the target pressure adjustment scheme.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Apnea detector and system

    CN101917903A

  • Method and system for determining categories of sleep-related breathing events

    CN104688239A

  • Sleep quality improving method and pillow

    CN110687835A

  • Sleep monitoring system based on snore recognition

    CN112971731A

  • Sleep apnea treatment apparatus and method

    CN113168902A