Atomization device and method for pediatric internal medicine respiratory system

Abstract

The invention provides an atomization device and method for a pediatric internal medicine respiratory system. The method comprises the following steps: determining respiratory characteristics when a target child uses an atomizer for atomization; classifying the breathing states of the target child according to the breathing characteristics to obtain a plurality of breathing modes, and further determining a coupling coefficient between each breathing mode and atomization particle size distribution in combination with atomization particle records in the atomization process; the inspiration flow of the target child in the current breathing mode is obtained, and the particle size prediction value of the atomized particles in the current breathing mode is determined according to the inspiration flow and all the coupling coefficients; determining the dynamic compensation amount of the particle size of the atomized particles in the current breathing mode by combining the particle size predicted value with the lung deposition rate of the atomized particles; and adjusting the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount. By the adoption of the scheme, the deposition efficiency of the atomized particles can be improved by adjusting the atomization particle size of the atomizer in a self-adaptive mode.

Description

Technical Field

[0001] This application relates to the technical field of medical devices. More specifically, this application relates to an atomization device and method for the pediatric internal medicine respiratory system. Background Art

[0002] Atomization inhalation in the pediatric internal medicine respiratory system is widely used in the management of respiratory diseases (such as asthma, bronchitis, pneumonia, etc.) due to its non-invasive nature and high efficiency in delivering drugs to the respiratory tract. Currently, the atomization devices for pediatric respiratory diseases mainly include compressed atomizers, ultrasonic atomizers, and mesh atomizers, and their core technologies mainly focus on aspects such as atomization methods, drug delivery, inhalation efficiency, and patient compliance.

[0003] Traditional atomization devices usually adopt a fixed particle size spraying method and cannot adjust atomization parameters according to the real-time breathing state of patients, resulting in low drug deposition efficiency. Some drugs cannot reach the target site sufficiently, leading to drug waste. Existing intelligent atomization devices achieve atomization regulation by simple timing control or pressure sensors to detect the breathing state of patients, but they cannot dynamically optimize the atomization particle size for different breathing stages and it is difficult to ensure the deposition efficiency of drugs in the alveoli and airways. Therefore, how to improve the deposition efficiency of atomization particles by adaptively adjusting the atomization particle size of the atomizer has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides an atomization device and method for the pediatric internal medicine respiratory system, which can improve the deposition efficiency of atomization particles by adaptively adjusting the atomization particle size of the atomizer.

[0005] In a first aspect, this application provides an atomization particle size regulation method, including: Collect the breathing signal of a target child during atomization using an atomizer, extract features from the breathing signal to obtain the breathing characteristics of the target child during atomization using the atomizer; Classify the breathing state of the target child according to the breathing characteristics to obtain multiple breathing modes of the target child during atomization, and then combine the atomization particle records during atomization to determine the coupling coefficient between each breathing mode and the atomization particle size distribution; Obtain the inhalation flow rate of the target child during atomization using the atomizer in the current breathing mode, and determine the predicted value of the atomization particle size in the current breathing mode according to the inhalation flow rate and all the coupling coefficients; Determine the dynamic compensation amount of the atomization particle size in the current breathing mode by combining the predicted value of the particle size with the pulmonary deposition rate of the atomization particles; Adjust the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount.

[0006] In some embodiments, feature extraction is performed on the respiratory signal to obtain the respiratory characteristics of the target child during atomization using the nebulizer, which specifically includes: Perform denoising processing on the respiratory signal to obtain a smooth and stable noise-free respiratory signal; Segment the noise-free respiratory signal into multiple respiratory cycles and extract the time-domain characteristics of each respiratory cycle, thereby obtaining the time-domain characteristic vector of the target child during atomization; Extract the frequency-domain characteristic vector of the target child during atomization from the noise-free respiratory signal; Perform feature fusion on the time-domain characteristic vector and the frequency-domain characteristic vector to obtain the respiratory characteristics of the target child during atomization using the nebulizer.

[0007] In some embodiments, classifying the respiratory state of the target child according to the respiratory characteristics to obtain multiple respiratory patterns of the target child during atomization specifically includes: Obtain a respiratory state dataset containing various respiratory states; Train a respiratory state classification model according to the respiratory state dataset to obtain a trained respiratory state classification model; Input the respiratory characteristics into the trained respiratory state classification model to obtain multiple respiratory patterns of the target child during atomization.

[0008] In some embodiments, determining the coupling coefficient between each respiratory pattern and the atomization particle size distribution in combination with the atomization particle record during the atomization process specifically includes: Obtain the atomization particle record during the atomization process; Establish an interaction mapping relationship between the respiratory pattern and the atomization particle size distribution according to the atomization particle record; For each respiratory pattern, determine the coupling coefficient between the respiratory pattern and the atomization particle size distribution through the interaction mapping relationship, thereby obtaining the coupling coefficients between each respiratory pattern and the atomization particle size distribution.

[0009] In some embodiments, determining the particle size prediction value of the atomization particles in the current respiratory pattern according to the inhalation flow rate and all the coupling coefficients specifically includes: Select the coupling coefficient that matches the current respiratory pattern from all the coupling coefficients; Determine the particle size distribution of the atomization particles in the current respiratory pattern according to the inhalation flow rate and the coupling coefficient that matches the current respiratory pattern; Based on the particle size distribution, determine the particle size prediction value of the atomization particles in the current respiratory pattern.

[0010] In some embodiments, determining the dynamic compensation amount of the atomized particle size in the current breathing mode by combining the predicted particle size value with the pulmonary deposition rate of the atomized particles specifically includes: Obtaining the target deposition rate that the desired atomized particles are to reach in the lungs; Determining the pulmonary deposition rate of the atomized particles when the target child is atomized in the current breathing mode; Determining the dynamic compensation amount of the atomized particle size in the current breathing mode according to the target deposition rate, the pulmonary deposition rate, and the predicted particle size value.

[0011] In some embodiments, adjusting the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount specifically includes: Determining the target nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount; Adjusting the actual aperture of the adjustable nozzle based on the target nozzle aperture.

[0012] In a second aspect, the present application provides an atomization device for the pediatric internal medicine respiratory system. The atomization device includes an atomization particle size regulation unit, and the atomization particle size regulation unit includes: An acquisition module, configured to acquire the breathing signal of the target child when using the atomizer for atomization, extract features from the breathing signal, and obtain the breathing characteristics of the target child when using the atomizer for atomization; A processing module, configured to classify the breathing state of the target child according to the breathing characteristics, obtain multiple breathing modes of the target child during atomization, and then determine the coupling coefficient between each breathing mode and the atomized particle size distribution in combination with the record of the atomized particles during atomization; The processing module is configured to obtain the inhalation flow rate of the target child when using the atomizer for atomization in the current breathing mode, and determine the predicted particle size value of the atomized particles in the current breathing mode according to the inhalation flow rate and all the coupling coefficients; The processing module is configured to determine the dynamic compensation amount of the atomized particle size in the current breathing mode by combining the predicted particle size value with the pulmonary deposition rate of the atomized particles; An execution module, configured to adjust the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount.

[0013] In a third aspect, the present application provides a computer device. The computer device includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned atomization particle size regulation method.

[0014] Fourthly, the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above-mentioned atomization particle size regulation method.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In the atomization device and method for pediatric internal medicine respiratory system provided by the present application, first, the breathing signal of a target child during atomization using an atomizer is collected, and feature extraction is performed on the breathing signal to obtain the breathing characteristics of the target child during atomization using the atomizer; the breathing state of the target child is classified according to the breathing characteristics to obtain multiple breathing modes of the target child during the atomization process, and then the coupling coefficient between each breathing mode and the atomization particle size distribution during the atomization process is determined in combination with the atomization particle record during the atomization process; the inhalation flow rate of the target child during atomization using the atomizer in the current breathing mode is obtained, and the particle size prediction value of the atomization particles in the current breathing mode is determined according to the inhalation flow rate and all the coupling coefficients; the dynamic compensation amount of the atomization particle size in the current breathing mode is determined by combining the particle size prediction value with the lung deposition rate of the atomization particles; the nozzle aperture of the adjustable nozzle in the atomizer is adjusted according to the dynamic compensation amount.

[0016] It can be seen that the present application adjusts the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount; firstly, determining the breathing characteristics can obtain a multi-dimensional feature vector reflecting the changes in the breathing state of the target child during the atomization process. The determination of the breathing characteristics helps to understand the breathing health status of the target child and discover potential breathing abnormalities, so as to adjust the atomization strategy in time to cope with the physiological changes of the target child; secondly, determining the coupling coefficient can obtain a coefficient coupling coefficient that measures the mutual influence intensity between the breathing mode of the target child and the change in the atomization particle size distribution. The determination of the coupling coefficient helps to dynamically optimize the atomization particle size for different breathing stages of the target child, thereby improving the deposition efficiency of the atomization particles in the alveoli and airways; finally, determining the dynamic compensation amount can obtain the dynamic adjustment range of the atomization particle size during the atomization process of the target child. The determination of the dynamic compensation amount helps to adjust the atomization particle size in the atomizer to make it more suitable for the breathing mode of the target child, so as to ensure that the drug can effectively reach the predetermined part of the lungs and improve the drug deposition efficiency; in summary, based on the above scheme, the deposition efficiency of the atomization particles can be improved by adaptively adjusting the atomization particle size of the atomizer. Description of the Drawings

[0017] Figure 1 is an exemplary flowchart of the atomization particle size regulation method shown in some embodiments of the present application; Figure 2 is an exemplary flowchart of determining the breathing characteristics shown in some embodiments of the present application; Figure 3 It is a flowchart of operations for obtaining a breathing pattern shown in some embodiments of the present application; Figure 4 It is a schematic structural diagram of an atomization particle size regulation unit shown in some embodiments of the present application; Figure 5 It is an internal structure diagram of a computer device for implementing an atomization particle size regulation method shown in some embodiments of the present application. Detailed implementation manners

[0018] To better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0019] Refer to Figure 1 , this figure is an exemplary flowchart of an atomization particle size regulation method shown in some embodiments of the present application. The atomization particle size regulation method 100 mainly includes the following steps: In step 101, a breathing signal of a target child during atomization using an atomizer is collected, and feature extraction is performed on the breathing signal to obtain a breathing feature of the target child during atomization using the atomizer.

[0020] It should be noted that in the present application, the breathing signal refers to a physiological signal caused by respiratory movement during atomization of a target child, including information such as respiratory rate, respiratory amplitude, and respiratory rhythm; specifically, when implemented, collecting the breathing signal of a target child during atomization using an atomizer can be achieved by the following method, that is: during atomization of the target child, the airflow change during the target child's breathing can be captured by an airflow sensor (such as a high-precision MEMS airflow sensor) in the airflow channel of the atomizer and an electrical signal is output, and then the output electrical signal is used as the breathing signal of the target child during atomization using the atomizer.

[0021] In some embodiments, refer to Figure 2 , this figure is an exemplary flowchart of determining a breathing feature shown in some embodiments of the present application. In the present application, feature extraction is performed on the breathing signal to obtain the breathing feature of the target child during atomization using the atomizer, which can be achieved by the following steps: In step 1011, noise reduction processing is performed on the breathing signal to obtain a smooth and stable noise-free breathing signal; In step 1012, the noise-free breathing signal is segmented into multiple breathing cycles and the time-domain features of each breathing cycle are extracted, thereby obtaining a time-domain feature vector of the target child during atomization; In step 1013, a frequency-domain feature vector of the target child during atomization is extracted from the noise-free breathing signal; In step 1014, the time-domain feature vector and the frequency-domain feature vector are subjected to feature fusion to obtain the breathing characteristics of the target child during atomization using the atomizer.

[0022] When specifically implemented, denoising processing is performed on the breathing signal to obtain a smooth and stable noise-free breathing signal, which can be achieved in the following manner: First, an appropriate wavelet basis function (such as the Daubechies wavelet) and the decomposition level (such as 4 levels) can be selected to perform discrete wavelet transform on the breathing signal, so as to decompose it into wavelet coefficients of different frequencies. Then, inverse wavelet transform is performed on all wavelet coefficients to reconstruct a smooth and stable noise-free breathing signal; among them, the noise-free breathing signal is a pure breathing signal that eliminates environmental interference and measurement noise, and this noise-free breathing signal helps to improve the accuracy of breathing feature extraction.

[0023] When specifically implemented, the noise-free breathing signal is segmented into multiple breathing cycles and the time-domain features of each breathing cycle are extracted, and then the time-domain feature vector of the target child during atomization can be obtained in the following manner: First, an existing cycle detection method (such as zero-crossing detection) can be used to detect the noise-free breathing signal to determine the start and end points of each breathing cycle, so as to divide multiple breathing cycles. Then, for each breathing cycle, the standard deviation and root mean square value of the noise-free breathing signal within the breathing cycle are calculated, and the set of the standard deviation and the root mean square value is used as the time-domain feature of the breathing cycle. Finally, the vector composed of the time-domain features of all breathing cycles is used as the time-domain feature vector of the target child during atomization; among them, the time-domain feature vector is a numerical set describing the time-domain characteristics of the breathing signal, and this time-domain feature vector can be used to quantify the shape and changes of the signal.

[0024] When specifically implemented, the frequency-domain feature vector of the target child during atomization is extracted from the noise-free breathing signal in the following manner: First, the noise-free breathing signal is subjected to Fourier transform to convert it from a time-domain signal to a frequency-domain signal. Then, the squared amplitude of the frequency-domain signal at different frequency points can be calculated and the squared amplitude is used as the spectral energy of the frequency-domain signal. Furthermore, the main frequency peak value in the frequency-domain signal is used as the breathing frequency of the target child. Finally, the vector composed of the breathing frequency and the spectral energy is used as the frequency-domain feature vector of the target child during atomization; among them, the frequency-domain feature vector is a data set reflecting the energy distribution characteristics of the breathing signal at different frequency components, and this frequency-domain feature vector helps to deeply understand the frequency characteristics of the breathing signal and provides important information for subsequent analysis.

[0025] It should be noted that in this application, the respiration feature is a multi-dimensional feature vector reflecting the changes in the respiration state of the target child during atomization. Specifically, when implementing, feature fusion of the time-domain feature vector and the frequency-domain feature vector can be performed to obtain the respiration feature of the target child when using the atomizer, which can be achieved in the following manner, that is: Finally, existing feature fusion techniques (such as principal component analysis technology) can be used to fuse the time-domain feature vector and the frequency-domain feature vector to obtain the respiration feature of the target child when using the atomizer.

[0026] In step 102, the respiration state of the target child is classified according to the respiration feature to obtain multiple respiration patterns of the target child during atomization, and then the coupling coefficient between each respiration pattern and the atomization particle size distribution during atomization is determined in combination with the atomization particle records during atomization.

[0027] In some embodiments, referring to Figure 3 , this figure is a flowchart of operations for obtaining respiration patterns according to some embodiments of the present application. In the present application, classifying the respiration state of the target child according to the respiration feature to obtain multiple respiration patterns of the target child during atomization can be achieved by the following steps: Obtain a respiration state data set containing various respiration states; Train a respiration state classification model according to the respiration state data set to obtain a trained respiration state classification model; Input the respiration feature into the trained respiration state classification model to obtain multiple respiration patterns of the target child during atomization.

[0028] Specifically, when implementing, obtaining a respiration state data set containing various respiration states can be achieved in the following manner, that is: High-precision sensors (such as MEMS airflow sensors) can be used in advance to collect respiration signals of multiple (such as 100) different users in different respiration states (such as normal respiration, tachypnea, bradypnea, and deep breathing), and the respiration signals are labeled to obtain a respiration state data set containing various respiration states; wherein, the respiration state data set refers to a signal set containing various respiration states of different users, and this respiration state data set can be used for the training and verification of the respiration state classification model, providing data support for personalized atomization.

[0029] It should be noted that in this application, the respiration state classification model is a machine learning model that automatically identifies and classifies different respiration patterns of the target child during atomization according to the input respiration feature data. The trained respiration state classification model can accurately identify the respiration state of the target child, provide data support for personalized atomization, and optimize the atomization effect.

[0030] In specific implementation, the respiratory state classification model is trained according to the respiratory state data set. The trained respiratory state classification model can be implemented in the following way, that is: an existing deep learning classification model (such as a convolutional neural network) can be loaded, and the respiratory state data set is input into the deep learning classification model for training to obtain the trained respiratory state classification model.

[0031] It should be noted that in this application, the respiratory pattern is a category of respiratory states indicating the respiratory rhythm and regularity of the target child during atomization, including: normal breathing, rapid breathing, slow breathing, and deep breathing. These respiratory patterns can provide data support for subsequent atomization particle adjustment and personalized atomization. In specific implementation, the respiratory characteristics are input into the trained respiratory state classification model to obtain multiple respiratory patterns of the target child during atomization. It can be implemented in the following way, that is: the respiratory characteristics are used as the input parameters of the trained respiratory state classification model, the respiratory state classification model is executed, and each respiratory state category output by the respiratory state classification model is respectively used as the respiratory pattern of the target child during atomization, so as to obtain multiple respiratory patterns of the target child during atomization.

[0032] In some embodiments, determining the coupling coefficient between each respiratory pattern and the atomization particle size distribution in combination with the atomization particle record during atomization can be implemented by the following steps: Obtain the atomization particle record during atomization; Establish an interaction mapping relationship between the respiratory pattern and the atomization particle size distribution according to the atomization particle record; For each respiratory pattern, determine the coupling coefficient between the respiratory pattern and the atomization particle size distribution through the interaction mapping relationship, and then obtain the coupling coefficients between each respiratory pattern and the atomization particle size distribution.

[0033] It should be noted that in this application, the atomization particle record refers to the data describing the particle size and concentration distribution of atomization particles during the atomization of the target child. This atomization particle record helps to understand the atomization effect of atomization particles and provides a scientific basis for optimizing the nozzle adjustment of the atomizer and improving the atomization efficiency. In specific implementation, obtaining the atomization particle record during atomization can be implemented in the following way, that is: the particle size and quantity of atomization particles during the atomization of the target child can be monitored and recorded in real time through a particle size distribution sensor (such as an electro-optical sensor) arranged in the air flow channel of the atomizer, and the scattering light change of the atomization particles is analyzed by laser particle size analysis technology and the particle size distribution of the atomization particles per second during the atomization of the target child is calculated, and then the sequence of all particle size distributions arranged in chronological order is used as the atomization particle record during atomization.

[0034] In specific implementation, the interactive mapping relationship between the breathing pattern and the atomized particle size distribution can be established according to the atomized particle record in the following way: First, the particle size distribution of the atomized particles per second in the atomized particle record can be synchronized with the breathing pattern of the target child in terms of time. Then, an existing machine learning algorithm (such as a multiple regression algorithm or a support vector machine algorithm) can be used to establish the mapping relationship between the breathing pattern and the atomized particle size distribution, and the established mapping relationship can be used as the interactive mapping relationship between the breathing pattern and the atomized particle size distribution. Among them, the interactive mapping relationship is a relationship function that quantifies the mutual influence between each breathing pattern and the change in the particle size distribution. This interactive mapping relationship helps the system to dynamically adjust the atomized particle size according to the real-time breathing state.

[0035] It should be noted that in this application, the coupling coefficient is a coefficient that measures the intensity of the mutual influence between the breathing pattern of the target child and the change in the particle size distribution of the atomized particles. The value range of this coupling coefficient is between 0 and 1. The closer the value is to 1, the greater the intensity of the mutual influence between the breathing pattern and the change in the particle size distribution of the atomized particles. The coupling coefficient reflects the change law of the atomized particle size under different breathing patterns, providing a theoretical basis for further optimizing the particle size adjustment of the atomizer. In specific implementation, the coupling coefficient between the breathing pattern and the atomized particle size distribution can be determined through the interactive mapping relationship in the following way: The breathing pattern can be input into the interactive mapping relationship, and a statistical method (such as the Pearson correlation coefficient or the regression coefficient) can be used to analyze the output result of the interactive mapping relationship to quantify the influence of the breathing pattern on the particle size distribution, and the coupling coefficient between the breathing pattern and the atomized particle size distribution can be obtained.

[0036] In step 103, the inhalation flow rate of the target child when using the atomizer for atomization in the current breathing pattern is obtained, and the predicted value of the atomized particle size in the current breathing pattern is determined according to the inhalation flow rate and all the coupling coefficients.

[0037] It should be noted that in this application, the inhalation flow rate refers to the volume of gas inhaled into the lungs per unit time during the inhalation process of the target child. In specific implementation, the inhalation flow rate of the target child when using the atomizer for atomization in the current breathing pattern can be obtained in the following way: First, the electrical signal of the target child in the current breathing pattern can be collected through an airflow sensor (such as a high-precision MEMS airflow sensor) in the airflow channel of the atomizer, and then an existing breathing phase detection algorithm (such as a peak detection algorithm based on a threshold) can be used to identify the inhalation peak in the signal and use this inhalation peak as the inhalation flow rate of the target child when using the atomizer for atomization in the current breathing pattern. Among them, the current breathing pattern refers to the category of the breathing state of the target child during the last period of time (for example: 10 seconds) when atomizing.

[0038] In some embodiments, the predicted value of the particle size of the atomized particles in the current breathing mode can be determined according to the inhalation flow rate and all the coupling coefficients by the following steps: Select the coupling coefficients that match the current breathing mode from all the coupling coefficients; Determine the particle size distribution of the atomized particles in the current breathing mode according to the inhalation flow rate and the coupling coefficients that match the current breathing mode; Based on the particle size distribution, determine the predicted value of the particle size of the atomized particles in the current breathing mode.

[0039] Specifically, when implemented, the coupling coefficients that match the current breathing mode can be selected from all the coupling coefficients in the following way, that is: the electrical signal of the target child in the current breathing mode collected can be used as the input parameter of the trained breathing state classification model, execute the breathing state classification model, use the output result of the breathing state classification model as the current breathing mode of the target child, and search among all the coupling coefficients, and use the coupling coefficient between the current breathing mode and the particle size distribution of the atomized particles as the coupling coefficient that matches the current breathing mode.

[0040] Specifically, when implemented, the particle size distribution of the atomized particles in the current breathing mode can be determined according to the inhalation flow rate and the coupling coefficients that match the current breathing mode in the following way, that is: an existing atomized particle prediction model (such as the atomization model in Fluent software) can be loaded, input the nozzle type of the atomizer and the liquid used for atomization, and use the inhalation flow rate and the coupling coefficients that match the current breathing mode as the input parameters of the atomized particle prediction model, execute the atomized particle prediction model, and use the prediction result output by the atomized particle prediction model as the particle size distribution of the atomized particles in the current breathing mode; wherein, the particle size distribution is the relative content of the atomized particles in different particle size ranges.

[0041] It should be noted that in this application, the atomized particle prediction model is a mathematical model used to simulate and predict the particle size distribution of the atomized particles formed during the atomization process of the liquid. This atomized particle prediction model is based on the principle of computational fluid dynamics and considers factors such as nozzle design, inhalation flow rate, breathing mode, and liquid properties to predict the size and distribution of the atomized particles.

[0042] It should be noted that in this application, the predicted particle size value is the average particle size of the atomized particles in the atomizer estimated under the current breathing mode. This predicted particle size value helps to adjust the nozzle aperture of the atomizer to achieve the best atomization effect. Specifically, when implemented, the predicted particle size value of the atomized particles under the current breathing mode can be determined based on the particle size distribution in the following way: for each particle size range in the particle size distribution, the average particle size within the particle size range can be multiplied by the relative content of the atomized particles within the particle size range to obtain the content value of the particle size range. Through the above steps, the content values of each particle size range in the particle size distribution can be obtained, and then the average value of the content values of all particle size ranges can be used as the predicted particle size value of the atomized particles under the current breathing mode.

[0043] In step 104, the dynamic compensation amount of the atomized particle size under the current breathing mode is determined by combining the predicted particle size value with the pulmonary deposition rate of the atomized particles.

[0044] In some embodiments, the dynamic compensation amount of the atomized particle size under the current breathing mode can be determined by combining the predicted particle size value with the pulmonary deposition rate of the atomized particles through the following steps: Obtain the target deposition rate that the desired atomized particles are expected to reach in the lungs; Determine the pulmonary deposition rate of the atomized particles when the target child undergoes atomization under the current breathing mode; Determine the dynamic compensation amount of the atomized particle size under the current breathing mode according to the target deposition rate, the pulmonary deposition rate, and the predicted particle size value.

[0045] It should be noted that in this application, the target deposition rate refers to the proportion of the desired atomized particles that can successfully deposit in the target lung region. Specifically, when implemented, the target deposition rate can be preset according to the specific treatment plan of the target child and the doctor's experience judgment. In other embodiments, other methods can also be used to obtain the target deposition rate that the desired atomized particles are expected to reach in the lungs, which is not specifically limited here.

[0046] In specific implementation, the pulmonary deposition rate of aerosol particles during nebulization of a target child in the current breathing mode can be achieved in the following manner: First, obtain the pulmonary anatomical structure data of the target child (i.e., the airway diameter, length, and branching angle of the target child). Then, an existing computational fluid dynamics simulation software can be used to take the pulmonary anatomical structure data and the particle size distribution of the aerosol particles as the input parameters of the computational fluid dynamics simulation software, run the computational fluid dynamics simulation software to simulate the movement trajectory of the aerosol particles in the respiratory tract of the target child, and then through computational fluid dynamics analysis, calculate the deposition amount of the aerosol particles in different pulmonary regions of the target child and output the pulmonary deposition rate of the aerosol particles during nebulization of the target child; wherein, the pulmonary deposition rate refers to the deposition ratio of the inhaled aerosol particles in the lungs during nebulization of the target child. The determination of this pulmonary deposition rate helps to evaluate the utilization rate of the nebulized drug by the lungs, thereby optimizing the nebulization effect.

[0047] It should be noted that in this application, the dynamic compensation amount refers to the dynamic adjustment amount of the particle size of the aerosol particles during the nebulization of the target child. This dynamic compensation amount helps to adjust the particle size of the aerosol particles in the nebulizer to make it more suitable for the breathing mode of the target child, thereby ensuring that the drug can effectively reach the predetermined part of the lungs and improving the drug deposition rate; in specific implementation, determining the dynamic compensation amount of the particle size of the aerosol particles in the current breathing mode according to the target deposition rate, the pulmonary deposition rate, and the particle size prediction value can be achieved in the following manner: A particle size compensation model of the aerosol particles (such as a quadratic residual compensation droplet size model) can be loaded, take the pulmonary deposition rate, the target deposition rate, and the particle size prediction value as the input parameters of the particle size compensation model, execute the particle size compensation model, and take the compensation interval in the output result of the particle size compensation model as the dynamic compensation amount of the particle size of the aerosol particles in the current breathing mode.

[0048] In step 105, the nozzle aperture of the adjustable nozzle in the nebulizer is adjusted according to the dynamic compensation amount.

[0049] In some embodiments, adjusting the nozzle aperture of the adjustable nozzle in the nebulizer according to the dynamic compensation amount can be achieved by the following steps: Determine the target nozzle aperture of the adjustable nozzle in the nebulizer according to the dynamic compensation amount; Adjust the actual aperture of the adjustable nozzle based on the target nozzle aperture.

[0050] In specific implementation, the target nozzle aperture of the adjustable nozzle in the nebulizer can be determined according to the dynamic compensation amount by the following method: the density of the atomized liquid and the gas flow rate of the current nozzle of the nebulizer can be obtained, and then the dynamic compensation amount, the density and the gas flow rate are used as input parameters to be input into an existing particle size-aperture conversion function (such as an empirical formula of particle size and nozzle aperture) for calculation, and the calculation result is used as the target nozzle aperture of the adjustable nozzle in the nebulizer; wherein, the target nozzle aperture is the ideal nozzle aperture size that ensures the particle size distribution of the atomized particles conforms to the breathing characteristics of the target child and the expected treatment effect.

[0051] In specific implementation, the actual aperture of the adjustable nozzle can be adjusted based on the target nozzle aperture by the following method: the target nozzle aperture can be transmitted to the adjustable nozzle (such as a MEMS variable nozzle) in the nebulizer. After receiving the control signal, the adjustable nozzle adjusts the actual aperture of the nozzle to the target nozzle aperture, and monitors the adjustment process through a feedback sensor (such as a displacement sensor) to ensure that the nozzle aperture accurately matches the required particle size distribution.

[0052] In addition, on the other hand of the present application, in some embodiments, the present application provides an atomization device for the pediatric internal medicine respiratory system. The atomization device includes an atomization particle size regulation unit. Refer to Figure 4 , this figure is a schematic structural diagram of the atomization particle size regulation unit shown according to some embodiments of the present application. The atomization particle size regulation unit 400 includes: a collection module 401, a processing module 402, and an execution module 403, which are described as follows: The collection module 401. In the present application, the collection module 401 is mainly used to collect the breathing signal of the target child when using the nebulizer for atomization, extract the characteristics of the breathing signal, and obtain the breathing characteristics of the target child when using the nebulizer for atomization. The processing module 402. In the present application, the processing module 402 is mainly used to classify the breathing state of the target child according to the breathing characteristics, obtain multiple breathing modes of the target child during the atomization process, and then combine the atomized particle records during the atomization process to determine the coupling coefficient between each breathing mode and the atomized particle size distribution. It should be noted that in the present application, the processing module 402 is further used to obtain the inhalation flow rate of the target child when using the nebulizer for atomization in the current breathing mode, and determine the particle size prediction value of the atomized particles in the current breathing mode according to the inhalation flow rate and all the coupling coefficients. In addition, it should be noted that in the present application, the processing module 402 is further used to determine the dynamic compensation amount of the atomized particle size in the current breathing mode by combining the particle size prediction value with the pulmonary deposition rate of the atomized particles. Execution module 403. In this application, the execution module 403 is mainly used to adjust the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount.

[0053] Each module in the above atomization device for pediatric internal medicine respiratory system can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of 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.

[0054] In addition, in one embodiment, this application provides a computer device, which can be a server, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. 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 atomization particle size regulation method data. The network 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, it implements an atomization particle size regulation method.

[0055] Those skilled in the art can understand that Figure 5 the structure shown in

[0056] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0057] In one embodiment, there is also provided a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above embodiment of the atomization particle size regulation method.

[0058] In one embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-described embodiment of the atomization particle size regulation method.

[0059] Those of ordinary skill in the art can understand that all or part of the processes in the above-described embodiment methods can be completed by instructing relevant hardware through a computer program. 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 above-described embodiments of the various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0060] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered to be within the scope described in this specification.

[0061] The above-described embodiments merely represent several implementation manners of this application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of the patent of this application should be subject to the appended claims.

Claims

1. A method for regulating atomization particle size, which is used to regulate the particle size of an atomization device for the pediatric internal medicine respiratory system, and is characterized in that, It includes the following steps: Collect the breathing signal of the target child during atomization using an atomizer, extract features from the breathing signal, and obtain the breathing characteristics of the target child during atomization using the atomizer; Classify the breathing state of the target child according to the breathing characteristics to obtain multiple breathing patterns of the target child during atomization, and then combine the atomization particle records during atomization to determine the coupling coefficient between each breathing pattern and the atomization particle size distribution; Obtain the inhalation flow rate of the target child during atomization using the atomizer in the current breathing pattern, and determine the predicted particle size value of the atomization particles in the current breathing pattern according to the inhalation flow rate and all the coupling coefficients; Determine the dynamic compensation amount of the atomization particle size in the current breathing pattern by combining the predicted particle size value with the lung deposition rate of the atomization particles; Adjust the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount.

2. The method according to claim 1, wherein The specific steps of extracting features from the breathing signal to obtain the breathing characteristics of the target child during atomization using the atomizer include: Denoise the breathing signal to obtain a smooth and stable noise-free breathing signal; Segment the noise-free breathing signal into multiple breathing cycles and extract the time-domain features of each breathing cycle, and then obtain the time-domain feature vector of the target child during atomization; Extract the frequency-domain feature vector of the target child during atomization from the noise-free breathing signal; Fuse the time-domain feature vector and the frequency-domain feature vector to obtain the breathing characteristics of the target child during atomization using the atomizer.

3. The method according to claim 1, characterized in that The specific steps of classifying the breathing state of the target child according to the breathing characteristics to obtain multiple breathing patterns of the target child during atomization include: Obtain a breathing state data set containing multiple breathing states; Train a breathing state classification model according to the breathing state data set to obtain a trained breathing state classification model; Input the breathing characteristics into the trained breathing state classification model to obtain multiple breathing patterns of the target child during atomization.

4. The method according to claim 1, wherein The specific steps of combining the atomization particle records during atomization to determine the coupling coefficient between each breathing pattern and the atomization particle size distribution include: Obtain the atomization particle records during atomization; Establish an interaction mapping relationship between the breathing pattern and the atomization particle size distribution according to the atomization particle records; For each breathing pattern, determine the coupling coefficient between the breathing pattern and the atomization particle size distribution through the interaction mapping relationship, and then obtain the coupling coefficient between each breathing pattern and the atomization particle size distribution.

5. The method according to claim 1, characterized in that, The specific steps of determining the predicted particle size value of the atomization particles in the current breathing pattern according to the inhalation flow rate and all the coupling coefficients include: Select the coupling coefficient that matches the current breathing pattern from all the coupling coefficients; Determine the atomization particle size distribution in the current breathing pattern according to the inhalation flow rate and the coupling coefficient that matches the current breathing pattern; Determine the predicted particle size value of the atomization particles in the current breathing pattern based on the particle size distribution.

6. The method according to claim 1, wherein The specific steps of determining the dynamic compensation amount of the atomization particle size in the current breathing pattern by combining the predicted particle size value with the lung deposition rate of the atomization particles include: Obtain the target deposition rate that the desired atomized particles are to reach in the lungs; Determine the lung deposition rate of the atomized particles when the target child is undergoing atomization in the current breathing mode; Determine the dynamic compensation amount of the atomized particle size in the current breathing mode according to the target deposition rate, the lung deposition rate, and the predicted particle size value; 7. The method according to claim 1, characterized in that, Adjusting the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount specifically includes: Determine the target nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount; Adjust the actual aperture of the adjustable nozzle based on the target nozzle aperture.

8. An atomizing device for the pediatric internal medicine respiratory system, the atomizing device comprising an atomization particle size regulation unit, characterized in that, The atomized particle size control unit includes: An acquisition module, configured to acquire the breathing signal of the target child when using the atomizer for atomization, extract features from the breathing signal, and obtain the breathing characteristics of the target child when using the atomizer for atomization; A processing module, configured to classify the breathing state of the target child according to the breathing characteristics, obtain multiple breathing modes of the target child during atomization, and then determine the coupling coefficient between each breathing mode and the atomized particle size distribution in combination with the record of the atomized particles during atomization; The processing module is configured to obtain the inhalation flow rate of the target child when using the atomizer for atomization in the current breathing mode, and determine the predicted particle size value of the atomized particles in the current breathing mode according to the inhalation flow rate and all the coupling coefficients; The processing module is configured to determine the dynamic compensation amount of the atomized particle size in the current breathing mode by combining the predicted particle size value with the lung deposition rate of the atomized particles; An execution module, configured to adjust the nozzle aperture of the adjustable nozzle in the atomizer according to the dynamic compensation amount.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the atomized particle size control method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the atomized particle size control method according to any one of claims 1 to 7 are implemented.

Images