A medical oxygen concentrator control method and system

Abstract

The embodiments of this specification disclose a medical oxygen concentrator control method and system, relating to the field of medical oxygen concentrator control technology. The medical oxygen concentrator is communicatively connected to a monitoring device. The method includes: obtaining oxygen output parameters of the medical oxygen concentrator during a first time period, as well as physiological parameters monitored by the monitoring device for a patient during the first time period. The oxygen output parameters include oxygen output concentration and output flow, and the physiological parameters include blood oxygen saturation, heart rate, and respiratory rate. Based on the oxygen output parameters and physiological parameters, determining the degree of match between the oxygen production effect of the medical oxygen concentrator during the first time period and the patient's physiological state; and if the degree of match does not meet a preset condition, adjusting the oxygen output parameters of the medical oxygen concentrator during a second time period. This method enables adaptive control based on the patient's physiological state, thereby improving the intelligence and adaptability of the medical oxygen concentrator and enhancing the patient's user experience.

Description

Technical Field

[0001] The present application relates to the field of medical oxygen concentrator control technology, and more specifically, to a medical oxygen concentrator control method and system. Background Art

[0002] Medical oxygen concentrators (pressure swing adsorption oxygen concentrators) use air as the raw material for oxygen production. After being filtered (to remove oil, dust, moisture, and solid impurities), the air enters the compressor for compression. The compressed, high-pressure air is cooled and then enters the adsorption tower for adsorption separation. The adsorption tower is equipped with a molecular sieve, which absorbs both nitrogen and carbon dioxide. The gas flowing out of the adsorption tower is high-purity oxygen, which can be used as medical oxygen. Part of the separated oxygen enters the gas storage tank through a one-way valve. After being reduced in pressure by a pressure reducing valve, it flows through a flow meter and a humidifier bottle for patient use. The remaining oxygen is used for backflushing and cleaning the adsorber in the desorption state.

[0003] Currently used medical oxygen concentrators typically operate with fixed oxygen production and output parameters, and cannot be flexibly adjusted according to the patient's real-time physiological state, which may result in the oxygen production effect not fully matching the patient's needs. Based on this, in order to improve the intelligence and adaptability of medical oxygen concentrators and enhance the patient's user experience, it is necessary to develop a medical oxygen concentrator control method and system that can achieve adaptive control based on the patient's physiological parameters. Summary of the Invention

[0004] To solve the above problems, one aspect of an embodiment of this specification provides a method for controlling a medical oxygen concentrator, wherein the medical oxygen concentrator is communicatively connected to a monitoring device, and the monitoring device is used to monitor the physiological parameters of a patient. The method includes:

[0005] Obtaining oxygen output parameters of the medical oxygen concentrator during a first time period, and physiological parameters monitored by a monitoring device for the patient during the first time period, wherein the oxygen output parameters include at least oxygen output concentration and output flow, and the physiological parameters include at least blood oxygen saturation, heart rate, and respiratory rate;

[0006] determining, based on the oxygen output parameter and the physiological parameter, a degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the physiological state of the patient;

[0007] If the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient does not meet the preset conditions, the oxygen output parameters of the medical oxygen concentrator in the second time period are adjusted to ensure that the patient obtains appropriate oxygen supply, wherein the second time period is an adjacent time period after the first time period.

[0008] In some embodiments, determining, based on the oxygen output parameter and the physiological parameter, the degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the physiological state of the patient includes:

[0009] inputting the physiological parameter as input data into a pre-trained oxygen output parameter prediction model for processing to obtain an oxygen output prediction parameter corresponding to the physiological parameter in the first time period;

[0010] calculating a distance between the oxygen output prediction parameter and the oxygen output parameter of the medical oxygen concentrator in the first time period, and obtaining a degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient based on the distance;

[0011] The oxygen output parameter prediction model is trained based on the following method:

[0012] Acquire a first training data set, the first training data set including a sample physiological parameter sequence of the monitoring device within a plurality of sample time periods, and label information corresponding to the sample physiological parameter sequence, the label information being used to reflect an expected oxygen output parameter corresponding to the sample physiological parameter sequence;

[0013] The sample physiological parameter feature sequence is input as input data into an initial oxygen output parameter prediction model for training, and the output result of the initial oxygen output parameter prediction model is verified and adjusted according to the label information until the output result of the initial oxygen output parameter prediction model meets the preset training requirements, thereby obtaining a trained oxygen output parameter prediction model.

[0014] In some embodiments, adjusting the oxygen output parameters of the medical oxygen concentrator in the second time period includes:

[0015] The oxygen output parameter of the medical oxygen concentrator in the first time period is adjusted based on the oxygen output prediction parameter output by the oxygen output parameter prediction model to obtain the oxygen output parameter of the medical oxygen concentrator in the second time period.

[0016] In some embodiments, determining, based on the oxygen output parameter and the physiological parameter, the degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the physiological state of the patient includes:

[0017] Inputting the oxygen output parameter and the physiological parameter as input data into a pre-trained parameter matching model for processing, thereby obtaining a degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient;

[0018] The parameter matching model is trained based on the following method:

[0019] Obtaining a second training data set, the second training data set including sample multidimensional oxygen output parameter sequences of a medical oxygen concentrator in multiple sample time periods, sample physiological parameter sequences obtained by monitoring a patient using a monitoring device in corresponding sample time periods, and matching labels corresponding to the sample multidimensional oxygen output parameter sequences and the sample physiological parameter sequences;

[0020] Performing deep feature extraction on the sample multidimensional oxygen output parameter sequence and the sample physiological parameter sequence respectively through a deep feature extraction network to obtain a sample multidimensional oxygen output parameter feature sequence and a sample physiological parameter feature sequence;

[0021] The sample multi-dimensional oxygen output parameter feature sequence and the sample physiological parameter feature sequence are input as input data into an initial parameter matching model for training, and the output result of the initial parameter matching model is verified and adjusted according to the matching label until the output result of the initial parameter matching model meets the preset training requirements, thereby obtaining a trained parameter matching model.

[0022] In some embodiments, adjusting the oxygen output parameters of the medical oxygen concentrator in the second time period includes:

[0023] inputting the physiological parameters monitored by the monitoring device for the patient during the first time period as input data into a pre-trained oxygen output parameter prediction model for processing to obtain oxygen output prediction parameters corresponding to the physiological parameters;

[0024] adjusting the oxygen output parameter of the medical oxygen concentrator in the first time period based on the oxygen output prediction parameter to obtain the oxygen output parameter of the medical oxygen concentrator in the second time period;

[0025] The oxygen output parameter prediction model is trained based on the following method:

[0026] Acquire a first training data set, the first training data set including a sample physiological parameter sequence of the monitoring device within a plurality of sample time periods, and label information corresponding to the sample physiological parameter sequence, the label information being used to reflect an expected oxygen output parameter corresponding to the sample physiological parameter sequence;

[0027] The sample physiological parameter feature sequence is input as input data into an initial oxygen output parameter prediction model for training, and the output result of the initial oxygen output parameter prediction model is verified and adjusted according to the label information until the output result of the initial oxygen output parameter prediction model meets the preset training requirements, thereby obtaining a trained oxygen output parameter prediction model.

[0028] In some embodiments, the method further comprises:

[0029] An oxygen production parameter of the medical oxygen concentrator in the second time period is determined according to the oxygen output parameter of the medical oxygen concentrator in the second time period, and oxygen production of the medical oxygen concentrator is controlled based on the oxygen production parameter.

[0030] In some embodiments, determining the oxygen production parameters of the medical oxygen concentrator in the second time period according to the oxygen output parameters of the medical oxygen concentrator in the second time period includes:

[0031] Acquire the current oxygen storage capacity of the medical oxygen concentrator and environmental parameters of the environment in which the medical oxygen concentrator is located, wherein the environmental parameters include ambient temperature and ambient pressure;

[0032] Target oxygen production parameters are determined according to the current oxygen storage amount, ambient temperature, ambient pressure, and oxygen output parameters in the second time period, wherein the target oxygen production parameters include an operating frequency of a compressor, an operating temperature of a molecular sieve, and an operating intensity of a cooling system.

[0033] In some embodiments, determining the target oxygen production parameter according to the current oxygen storage amount, ambient temperature, ambient pressure, and the oxygen output parameter in the second time period includes:

[0034] The current oxygen storage amount, ambient temperature, ambient pressure and oxygen output parameters in the second time period are mapped using a preconfigured data mapping table to obtain the target oxygen production parameters.

[0035] In some embodiments, determining the target oxygen production parameter according to the current oxygen storage amount, ambient temperature, ambient pressure, and the oxygen output parameter in the second time period includes:

[0036] inputting the current oxygen storage amount, ambient temperature, ambient pressure, and the oxygen output parameter in the second time period as input data into a pre-trained oxygen production parameter calculation model for processing to obtain the target oxygen production parameter;

[0037] The oxygen production parameter calculation model is trained based on the following method:

[0038] Obtaining a third training data set, where each training sample in the third training data set includes oxygen storage capacity, ambient temperature, ambient pressure, oxygen output parameters, and corresponding oxygen production parameter labels;

[0039] Each training sample in the third training data set is input as input data into the initial oxygen production parameter calculation model for training, and an output result of the initial oxygen production parameter calculation model is verified and adjusted according to the oxygen production parameter label until the output result of the initial oxygen production parameter calculation model meets the preset training requirements, thereby obtaining a trained oxygen production parameter calculation model.

[0040] Another aspect of the embodiments of this specification further provides a medical oxygen concentrator control system, wherein the medical oxygen concentrator is communicatively connected to a monitoring device, wherein the monitoring device is used to monitor physiological parameters of a patient, and the system includes:

[0041] an acquisition module, configured to acquire oxygen output parameters of the medical oxygen concentrator during a first time period, and physiological parameters monitored by a monitoring device on a patient during the first time period, wherein the oxygen output parameters include at least oxygen output concentration and output flow, and the physiological parameters include at least blood oxygen saturation, heart rate, and respiratory rate;

[0042] a matching calculation module, configured to determine, based on the oxygen output parameter and the physiological parameter, a degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the physiological state of the patient;

[0043] The control module is configured to adjust the oxygen output parameters of the medical oxygen concentrator in a second time period to ensure that the patient obtains an appropriate oxygen supply when it is detected that the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient does not meet a preset condition, wherein the second time period is an adjacent time period after the first time period.

[0044] The medical oxygen concentrator control method and system provided in the embodiments of this specification may bring about at least the following beneficial effects: by adjusting the oxygen output parameters of the medical oxygen concentrator in the second time period according to the degree of matching between the oxygen output parameters of the medical oxygen concentrator in the first time period and the physiological parameters obtained by the monitoring equipment for the patient in the first time period, adaptive control can be achieved according to the patient's physiological state, thereby improving the intelligence and adaptability of the medical oxygen concentrator and improving the patient's user experience.

[0045] Additional features are described in part in the following description. They will become apparent to those skilled in the art by reviewing the following and accompanying drawings, or by following the production or operation of the examples. The features of this specification may be realized and obtained by practicing or using the various aspects of the methods, tools, and combinations described in the following detailed examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same numbers represent the same structures, wherein:

[0047] Figure 1 is an exemplary flow chart of a medical oxygen concentrator control method according to some embodiments of this specification;

[0048] Figure 2 is a schematic diagram of an exemplary application scenario of a medical oxygen concentrator control system according to some embodiments of this specification;

[0049] Figure 3 is an exemplary flow chart of a medical oxygen concentrator control method according to other embodiments of this specification;

[0050] Figure 4 is an exemplary module diagram of a medical oxygen concentrator control system according to some embodiments of this specification. DETAILED DESCRIPTION

[0051] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0052] It should be understood that the terms "system," "device," "unit," and / or "module" used in this specification are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0053] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0054] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0055] Typically, patients require oxygen after surgery to restore their bodily functions. This is because during surgery, the effects of anesthetics, pain from surgical wounds, and blood loss can temporarily weaken their respiratory function, preventing them from effectively inhaling enough oxygen to meet their body's needs. However, oxygen inhalation can help patients increase their blood oxygen saturation, accelerate their metabolism, promote wound healing, reduce postoperative complications, and thus speed up their recovery. Therefore, oxygen concentrators have broad application value in the medical field, particularly in operating rooms, intensive care units, and rehabilitation wards.

[0056] However, currently used medical oxygen concentrators typically operate with fixed oxygen production and output parameters, and cannot be flexibly adjusted based on the patient's real-time physiological state, which may result in the oxygen production effect not fully matching the patient's needs. Therefore, in order to improve the intelligence and adaptability of medical oxygen concentrators and enhance the patient's user experience, the embodiments of the present application provide a medical oxygen concentrator control method and system that can achieve adaptive control based on the patient's physiological parameters. The medical oxygen concentrator control method and system provided in the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0057] Figure 1 is an exemplary flow chart of a medical oxygen concentrator control method according to some embodiments of this specification. In some embodiments, the medical oxygen concentrator control method can be executed by processing logic, which can include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (instructions running on a processing device to perform hardware simulation), etc., or any combination thereof. In some embodiments, Figure 1 One or more operations in the flowchart of the medical oxygen concentrator control method shown can be implemented by a processing device. For example, the medical oxygen concentrator control method can be stored in a storage device in the form of a computer program and / or instructions and called and / or executed by the processing device.

[0058] Reference Figure 1 The medical oxygen concentrator control method provided in the embodiment of the present application may include the following steps S110 to S130:

[0059] Step S110: Obtain oxygen output parameters of the medical oxygen concentrator during a first time period, and physiological parameters monitored by the monitoring device for the patient during the first time period. In some embodiments, step S110 may be performed by the acquisition module 210 mentioned below.

[0060] In an embodiment of the present application, the medical oxygen concentrator is communicatively connected to the monitoring device, which is used to monitor the patient's physiological parameters. The medical oxygen concentrator can determine oxygen output parameters appropriate for the patient's physiological state based on the physiological parameters and supply oxygen to the patient based on the oxygen output parameters. In this embodiment of the present application, the oxygen output parameters include at least oxygen output concentration and output flow rate, and the physiological parameters include at least blood oxygen saturation, heart rate, and respiratory rate.

[0061] Reference Figure 2 In some embodiments of the present application, the monitoring device 30 can send the physiological parameters monitored by the patient to the medical oxygen concentrator 10 via the network 20. In embodiments of the present application, the network 20 may include any suitable network that can facilitate information and / or data exchange. In some embodiments, the network 20 may be any form of wired or wireless network, or any combination thereof. By way of example only, the network 20 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 20 may include at least one network access point, and the medical oxygen concentrator 10 and the monitoring device 30 may connect to the network 20 via the access point to exchange data and / or information.

[0062] Specifically, in an embodiment of the present application, the monitoring device 30 may include a blood oximeter, an electrocardiograph, a respiratory rate monitor, etc., wherein the blood oximeter can be used to monitor the patient's blood oxygen saturation in real time (for example, measuring the oxygen content in the blood through infrared spectroscopy analysis technology), the electrocardiograph can be used to monitor the patient's cardiac electrical activity to evaluate the functional state of the heart, and the respiratory rate monitor can be used to monitor the patient's respiratory rate, thereby reflecting the patient's respiratory condition.

[0063] It should be noted that blood oxygen saturation can be used to reflect the oxygen content in the patient's blood, and it can also reflect the patient's demand for oxygen. Heart rate can reflect the number of times the patient's heart beats per unit time, and it can also reflect to a certain extent the physiological reflex of the patient's body function to the current blood oxygen saturation (low blood oxygen saturation may cause an accelerated heart rate). Respiratory rate can reflect the patient's breathing intensity and frequency, which is of great significance for evaluating the patient's respiratory function and estimating the patient's oxygen demand per unit time. In an embodiment of the present application, by combining these three physiological parameters, the medical oxygen concentrator can have a more comprehensive understanding of the patient's oxygen demand, thereby performing more accurate and effective oxygen supply control.

[0064] It should also be noted that, in some embodiments, more physiological parameters can be collected from the patient through the monitoring device 30. Just as an example, in some embodiments, the physiological parameters may also include body temperature data, etc. In some embodiments, physiological parameters such as blood oxygen saturation, heart rate and respiratory rate can be further verified and analyzed through body temperature data. For example, abnormal body temperature data may indicate that the patient has an infection or inflammation, which may affect the patient's blood oxygen saturation and heart rate. By comprehensively considering body temperature data and other physiological parameters, the medical oxygen concentrator can more comprehensively assess the patient's health status, thereby adjusting the oxygen supply strategy to ensure that patients can receive the most suitable oxygen treatment under different health conditions.

[0065] In an embodiment of the present application, the oxygen output parameters of the medical oxygen concentrator 10 in a first time period and the physiological parameters obtained by the monitoring device 30 for the patient in the first time period can be obtained, and then the oxygen output parameters adapted to the physiological parameters can be determined through subsequent steps. The first time period can be understood as a time period before the current moment, for example, the past one minute, five minutes, ten minutes, or a longer / shorter time period. It should be noted that in an embodiment of the present application, by obtaining the oxygen output parameters and the patient's physiological parameters within this time period, the trend of changes in the patient's oxygen demand can be understood, which helps the medical oxygen concentrator to more accurately predict and adjust the oxygen supply in subsequent time periods to adapt to the patient's real-time needs, thereby improving the treatment effect and the patient's comfort.

[0066] In some embodiments of the present application, the oxygen output parameter and the physiological parameter can be represented in the form of a time series. For example, each data point in the time series data corresponds to a time point (the time intervals between data points can be equal or unequal), and each time point can correspond to information of multiple dimensions. For example, each time point in the oxygen output parameter sequence can correspond to an oxygen output concentration and an output flow rate (the output flow rate can be the oxygen output flow rate between two adjacent time points, which can be calculated based on the output flow rate and the interval size between two adjacent time points), and each time point in the physiological parameter sequence can correspond to a blood oxygen saturation, a heart rate, and a respiratory rate. It should be noted that in some embodiments of the present application, each of the above parameters can be an average value between two adjacent time points.

[0067] Step S120: Determine the degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the patient's physiological state based on the oxygen output parameter and the physiological parameter. In some embodiments, step S120 may be performed by the matching calculation module 220 described below.

[0068] In some embodiments of the present application, the physiological parameters can be input as input data into a pre-trained oxygen output parameter prediction model for processing to obtain the oxygen output prediction parameters corresponding to the physiological parameters in the first time period; then, the distance between the oxygen output prediction parameters and the oxygen output parameters of the medical oxygen concentrator in the first time period is calculated, and based on the distance, the degree of match between the oxygen production effect of the medical oxygen concentrator in the first time period and the patient's physiological state is obtained.

[0069] The oxygen output parameter prediction model can be understood as a machine learning model for predicting the oxygen output parameters required by a patient's physiological state. The machine learning model can be trained using a large amount of historical data, and after training, the machine learning model can predict the oxygen output parameters required by patients under different physiological states.

[0070] Furthermore, in embodiments of the present application, by calculating the distance (e.g., Euclidean distance, Manhattan distance, etc.) between the oxygen output prediction parameter output by the oxygen output parameter prediction model and the actual oxygen output parameter during the first time period, the degree of match between the oxygen production effect of the medical oxygen concentrator and the patient's physiological state can be quantified based on this distance (a larger distance indicates a lower degree of match, and vice versa). This allows for real-time adjustment of the medical oxygen concentrator control strategy based on this degree of match in subsequent processes, ensuring that the patient receives the most appropriate oxygen therapy. In some embodiments of the present application, the degree of match between the oxygen production effect of the medical oxygen concentrator and the patient's physiological state during the first time period can be obtained by normalizing this distance.

[0071] Specifically, in some embodiments of the present application, the oxygen output parameter prediction model can be trained based on the following method:

[0072] First, a first training dataset is obtained. The first training dataset includes sequences of sample physiological parameters of a monitoring device over multiple sample time periods, as well as label information corresponding to the sample physiological parameter sequences. The label information is used to reflect the expected oxygen output parameter corresponding to the sample physiological parameter sequences. Then, the sample physiological parameter feature sequences are used as input data into an initial oxygen output parameter prediction model for training. The output of the initial oxygen output parameter prediction model is verified and adjusted based on the label information until the output of the initial oxygen output parameter prediction model meets preset training requirements, thereby obtaining a trained oxygen output parameter prediction model.

[0073] It should be noted that in the embodiments of the present application, the oxygen output parameter prediction model may include, but is not limited to, a support vector machine model, a neural network model, a decision tree model, or a random forest model. These machine learning models have significant advantages in processing complex data relationships and can accurately predict the patient's required oxygen output parameters based on the input physiological parameter sequence. Through continuous iteration and optimization of the training process, the accuracy and robustness of the oxygen output parameter prediction model can be gradually improved, thereby providing a more reliable basis for the control of medical oxygen concentrators.

[0074] By way of example only, in some embodiments, the process of verifying and adjusting the output of the initial oxygen output parameter prediction model based on the label information can be implemented using cross-validation, gradient descent, backpropagation, or other optimization algorithms. These algorithms can effectively evaluate the performance of the prediction model and adjust model parameters based on error feedback to achieve higher prediction accuracy. In some embodiments, the preset training requirement may mean that the model's prediction error on the validation set is less than a preset threshold, or that the model's performance on the training and validation sets stabilizes and no longer improves significantly. In some embodiments, the preset training requirement may also mean reaching a preset number of iterations.

[0075] More technical details about the training of the output parameter prediction model can be regarded as prior art and will not be discussed in detail in this specification.

[0076] In step S130, if the oxygen production effect of the medical oxygen concentrator during the first time period does not match the patient's physiological condition to a predetermined level, the oxygen output parameters of the medical oxygen concentrator during the second time period are adjusted to ensure that the patient receives an appropriate oxygen supply. In some embodiments, step S130 may be performed by the control module 230 described below.

[0077] In an embodiment of the present application, the preset condition may refer to the matching degree calculated by the above steps being greater than a preset threshold value (e.g., 85%). When the degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the patient's physiological state does not meet the preset condition, it indicates that the oxygen output parameters of the current medical oxygen concentrator may not be suitable for the patient's actual needs and need to be adjusted accordingly. For example, if the matching degree is too low, it may mean that the oxygen concentration, output flow rate and other parameters output by the medical oxygen concentrator do not match the patient's current physiological state, which may cause the patient to be hypoxic or have an excess of oxygen, which may have an adverse effect on the patient's health or user experience.

[0078] In an embodiment of the present application, to enhance the intelligence and adaptability of a medical oxygen concentrator and improve the user experience of the patient, when the degree of match between the oxygen production effect of the medical oxygen concentrator and the patient's physiological state during the first time period does not meet a preset condition, the oxygen output parameters of the medical oxygen concentrator during the first time period may be adjusted based on the oxygen output prediction parameters output by the oxygen output parameter prediction model, thereby obtaining the oxygen output parameters of the medical oxygen concentrator during the second time period. Conversely, when the degree of match between the oxygen production effect of the medical oxygen concentrator during the first time period and the patient's physiological state meets the preset condition, the oxygen output parameters of the first time period may continue to be used as the oxygen output parameters of the medical oxygen concentrator during the second time period. In this embodiment of the present application, the second time period may refer to an adjacent time period following the first time period, and its length may be the same as or different from the first time period.

[0079] It will be appreciated that in the embodiments of the present application, the oxygen output prediction parameter output by the oxygen output parameter prediction model is obtained through training using a machine learning algorithm based on historical oxygen output parameters and patient physiological parameters. Specifically, the oxygen output prediction parameter can be used to indicate an oxygen output parameter suitable for use in the patient's current physiological state. Based on this, in some embodiments of the present application, the oxygen output parameter of the medical oxygen concentrator during the first time period can be adjusted based on the oxygen output prediction parameter output by the oxygen output parameter prediction model, thereby obtaining the oxygen output parameter of the medical oxygen concentrator during the second time period.

[0080] It should be noted that the above implementation of the matching degree calculation and oxygen output parameter adjustment is only illustrative. In some embodiments of the present application, other methods can also be used to implement the matching degree calculation process in step S120 and the oxygen output parameter adjustment process in step S130.

[0081] For example, in some embodiments, the oxygen output parameters of the medical oxygen concentrator during a first time period and the physiological parameters monitored by the monitoring device during the first time period can be input into a pre-trained parameter matching model for processing to determine the degree of match between the oxygen production effect of the medical oxygen concentrator during the first time period and the patient's physiological state. The parameter matching model can be a model built based on a machine learning or deep learning algorithm that can automatically learn and identify the complex relationships between different physiological parameters and oxygen output parameters, thereby determining the degree of match between the oxygen production effect of the medical oxygen concentrator during the first time period and the patient's physiological state.

[0082] Specifically, in the embodiment of the present application, the parameter matching model can be trained based on the following method:

[0083] First, a second training data set is obtained, which includes a sample multidimensional oxygen output parameter sequence of a medical oxygen concentrator in multiple sample time periods, a sample physiological parameter sequence obtained by monitoring a patient by a monitoring device in a corresponding sample time period, and a matching label corresponding to the sample multidimensional oxygen output parameter sequence and the sample physiological parameter sequence (the matching label can be used to reflect the degree of matching between the sample multidimensional oxygen output parameter sequence and the sample physiological parameter sequence). Then, a deep feature extraction network (such as a convolutional neural network) can be used to perform deep feature extraction on the sample multidimensional oxygen output parameter sequence and the sample physiological parameter sequence, respectively, to obtain a sample multidimensional oxygen output parameter feature sequence and a sample physiological parameter feature sequence; finally, the sample multidimensional oxygen output parameter feature sequence and the sample physiological parameter feature sequence can be used as input data to input into an initial parameter matching model for training, and the output result of the initial parameter matching model is verified and adjusted according to the matching label until the output result of the initial parameter matching model meets the preset training requirements, thereby obtaining a trained parameter matching model. For more details on the construction and training of the parameter matching model, please refer to the above-mentioned output parameter prediction model, which will not be repeated in this specification.

[0084] Furthermore, after obtaining the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient through the parameter matching model, it can be further determined whether the degree of matching meets the preset conditions. If not, it is necessary to adjust the oxygen output parameters of the medical oxygen concentrator in the second time period. If so, the oxygen output parameters of the first time period can continue to be used as the oxygen output parameters of the medical oxygen concentrator in the second time period.

[0085] Specifically, in some embodiments of the present application, when the above-mentioned parameter matching model is used to obtain the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient, and it is detected that the matching degree does not meet the preset conditions, the physiological parameters obtained by the monitoring device for the patient in the first time period can be used as input data and input into a pre-trained oxygen output parameter prediction model for processing to obtain oxygen output prediction parameters corresponding to the physiological parameters, and then the oxygen output parameters of the medical oxygen concentrator in the first time period are adjusted based on the oxygen output prediction parameters to obtain the oxygen output parameters of the medical oxygen concentrator in the second time period.

[0086] It should be noted that the oxygen output parameter prediction model involved here can be the same model as the oxygen output parameter prediction model involved above. Therefore, more technical details about the construction and training of the oxygen output parameter prediction model can be referred to above and will not be repeated here.

[0087] Furthermore, in some embodiments of the present application, after determining the oxygen output parameters of the medical oxygen concentrator in the second time period through the above steps, the oxygen production parameters of the medical oxygen concentrator in the second time period can also be determined according to the oxygen output parameters of the medical oxygen concentrator in the second time period, and the medical oxygen concentrator is controlled based on the oxygen production parameters.

[0088] Reference Figure 3 In some embodiments of the present application, the process of determining the oxygen production parameters of the medical oxygen concentrator in the second time period according to the oxygen output parameters of the medical oxygen concentrator in the second time period may include the following steps S140 to S150:

[0089] Step S140: obtaining the current oxygen storage capacity of the medical oxygen concentrator and environmental parameters of the environment in which the medical oxygen concentrator is located, wherein the environmental parameters include ambient temperature and ambient pressure.

[0090] It is understood that the oxygen production efficiency of a medical oxygen concentrator may vary in different environments due to differences in ambient temperature and ambient pressure (because the oxygen content in the air may fluctuate with changes in ambient temperature and ambient pressure). Therefore, in step S140, it is necessary to obtain these key environmental parameters and the current oxygen storage capacity of the medical oxygen concentrator to provide an accurate basis for subsequent determination of oxygen production parameters.

[0091] Specifically, in this embodiment of the present application, the medical oxygen concentrator can be equipped with a temperature sensor and an air pressure sensor for real-time monitoring of changes in the ambient temperature and air pressure of the environment in which it is located, and feeding the monitored data back to the control system. In addition, in this embodiment of the present application, the medical oxygen concentrator is also equipped with an oxygen storage capacity monitoring module for real-time detection of the oxygen storage capacity in the oxygen storage tank.

[0092] Step S150: determining target oxygen production parameters according to the current oxygen storage amount, ambient temperature, ambient pressure, and oxygen output parameters in the second time period, wherein the target oxygen production parameters include the operating frequency of the compressor, the operating temperature of the molecular sieve, and the operating intensity of the cooling system.

[0093] In this embodiment of the present application, a predetermined algorithm or model can be used to calculate target oxygen production parameters that the medical oxygen concentrator should achieve within the second time period based on the current oxygen storage capacity, ambient temperature, and ambient pressure obtained in step S140. In this embodiment of the present application, the target oxygen production parameters may include the operating frequency of the compressor, the operating temperature of the molecular sieve, and the operating intensity of the cooling system.

[0094] It can be understood that the operating frequency of the compressor will determine the speed and efficiency of the medical oxygen concentrator in producing oxygen. The higher the operating frequency, the faster the oxygen production speed. The operating temperature of the molecular sieve will affect its ability to adsorb and desorb oxygen (usually the adsorption capacity of the molecular sieve decreases with increasing temperature), which will also affect the speed of oxygen production. The working intensity of the cooling system (such as cooling power) can be used to adjust the temperature inside the medical oxygen concentrator, including the gas temperature, and the operating temperature of the molecular sieve. It should be pointed out that in the embodiment of the present application, by determining these oxygen production parameters and using these oxygen production parameters to control the operation of the medical oxygen concentrator, the medical oxygen concentrator can obtain corresponding oxygen production parameters according to the desired oxygen output parameters under different environmental conditions, thereby ensuring that the oxygen production effect and oxygen output of the medical oxygen concentrator can adapt to the patient's current physiological state.

[0095] Specifically, in some embodiments of the present application, the current oxygen storage capacity, ambient temperature, ambient pressure, and oxygen output parameters for the second time period can be mapped using a preconfigured data mapping table to obtain the target oxygen production parameters. For example, one or more data mapping tables can be pre-set. These data mapping tables can be derived based on historical data or experimental results and can reflect the optimal oxygen production parameter combinations corresponding to different oxygen storage capacities, ambient temperatures, ambient pressures, and oxygen output requirements. When the medical oxygen concentrator receives an oxygen production instruction to produce oxygen according to the required oxygen output parameters, the control system first obtains the current oxygen storage capacity, ambient temperature, ambient pressure, and the desired oxygen output parameters (such as oxygen output concentration and output flow rate). The control system then searches the data mapping table for the corresponding target oxygen production parameters based on this data, including the operating frequency of the compressor, the operating temperature of the molecular sieve, and the operating intensity of the cooling system. Finally, the control system controls the various components of the medical oxygen concentrator based on the target oxygen production parameters so that the oxygen production effect and oxygen output parameters are adapted to the patient's current physiological state.

[0096] In some embodiments of the present application, the current oxygen storage capacity, ambient temperature, ambient pressure, and oxygen output parameter during the second time period may be input as input data into a pre-trained oxygen production parameter calculation model for processing to obtain the target oxygen production parameter. The oxygen production parameter calculation model may be a deep learning model that is trained using a large amount of historical data and experimental results and is capable of learning the complex relationship between different input conditions (i.e., different oxygen storage capacities, ambient temperatures, ambient pressures, and different oxygen output parameter requirements) and the target oxygen production parameter.

[0097] Specifically, in some embodiments, the oxygen production parameter calculation model can be trained based on the following method:

[0098] First, a third training data set is obtained, where each training sample in the third training data set may include an oxygen storage capacity, an ambient temperature, an ambient pressure, an oxygen output parameter, and a corresponding oxygen production parameter label. Then, each training sample in the third training data set may be input as input data into an initial oxygen production parameter calculation model for training, and an output result of the initial oxygen production parameter calculation model may be verified and adjusted according to the oxygen production parameter label until the output result of the initial oxygen production parameter calculation model meets preset training requirements, thereby obtaining a trained oxygen production parameter calculation model.

[0099] In an embodiment of the present application, the oxygen production parameter label may include specific values ​​or ranges of key oxygen production parameters such as the operating frequency of the compressor, the operating temperature of the molecular sieve, and the working intensity of the cooling system that match the corresponding oxygen storage capacity, ambient temperature, ambient pressure, and oxygen output parameters. These oxygen production parameter labels can be used as supervisory information for model training to help the model learn how to accurately predict the optimal oxygen production parameters based on the input conditions, thereby improving the intelligence and adaptability of the medical oxygen concentrator. For more details on the construction and training of the oxygen production parameter calculation model, please refer to the above-mentioned oxygen output parameter prediction model, which will not be repeated here.

[0100] Figure 4 Schematic diagram of a module of a medical oxygen concentrator control system according to some embodiments of this specification. In some embodiments, Figure 4 The illustrated medical oxygen concentrator control system 200 may be implemented in software and / or hardware. For example, the control system may be configured in a processing device in the form of software and / or hardware to adjust the oxygen output parameters of the medical oxygen concentrator in a second time period based on a degree of matching between the oxygen output parameters of the medical oxygen concentrator in the first time period and the physiological parameters monitored by the monitoring device for the patient in the first time period.

[0101] Reference Figure 4 In some embodiments, the medical oxygen concentrator control system 200 may include an acquisition module 210, a matching calculation module 220, and a control module 230.

[0102] The acquisition module 210 can be used to obtain oxygen output parameters of the medical oxygen concentrator in a first time period, and physiological parameters monitored by the monitoring device for the patient in the first time period.

[0103] The matching calculation module 220 can be used to determine the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the patient's physiological state based on the oxygen output parameter and the physiological parameter.

[0104] The control module 230 can be used to adjust the oxygen output parameters of the medical oxygen concentrator in the second time period when the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the patient's physiological state does not meet the preset conditions to ensure that the patient obtains an appropriate oxygen supply.

[0105] For more details about the above modules, please refer to other places in this manual (for example Figures 1 to 3 part and its related description), which will not be repeated here.

[0106] It should be understood that Figure 4 The illustrated medical oxygen concentrator control system 200 and its modules can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented using hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic, while the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above can be implemented using computer-executable instructions and / or contained in processor control code, such as provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and their modules described herein can be implemented not only using hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips or transistors, or programmable hardware devices such as field programmable gate arrays or programmable logic devices, but can also be implemented using software executed by various types of processors, or a combination of such hardware circuits and software (e.g., firmware).

[0107] It should be noted that the above description of the medical oxygen concentrator control system 200 is provided for illustrative purposes only and is not intended to limit the scope of this specification. It is understood that those skilled in the art can, based on the description of this specification, arbitrarily combine the modules or form subsystems connected to other modules without departing from the principles of this specification. For example, Figure 4 The acquisition module 210, matching calculation module 220 and control module 230 described above can be different modules in a system, or a module can implement the functions of two or more modules. Such variations are all within the scope of protection of this specification.

[0108] In summary, the beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) In the medical oxygen concentrator control method and system provided in some embodiments of this specification, by adjusting the oxygen output parameters of the medical oxygen concentrator in the second time period according to the matching degree between the oxygen output parameters of the medical oxygen concentrator in the first time period and the physiological parameters obtained by the monitoring equipment for the patient in the first time period, adaptive control can be achieved according to the patient's physiological state, thereby improving the intelligence and adaptive ability of the medical oxygen concentrator and improving the patient's user experience; (2) In the medical oxygen concentrator control method and system provided in some embodiments of this specification, by comprehensively analyzing the blood oxygen saturation The three physiological parameters of temperature, heart rate and respiratory rate can enable the medical oxygen concentrator to more comprehensively understand the patient's oxygen demand status, thereby performing more accurate and effective oxygen supply control; (3) In the medical oxygen concentrator control method and system provided in some embodiments of this specification, by determining the operating frequency of the compressor, the operating temperature of the molecular sieve and the working intensity of the cooling system according to the current oxygen storage capacity, ambient temperature, ambient pressure and the required oxygen output parameters, the medical oxygen concentrator can obtain corresponding oxygen production parameters according to the expected oxygen output parameters under different environmental conditions, thereby ensuring that the oxygen production effect and oxygen output of the medical oxygen concentrator can adapt to the patient's current physiological state.

[0109] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0110] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0111] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0112] In addition, it will be understood by those skilled in the art that various aspects of this specification may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0113] A computer storage medium may include a propagated data signal embodying the computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, or any suitable combination thereof. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium that can be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transfer the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of these.

[0114] The computer program code required for the operation of the various parts of this specification can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages. The program code can be run entirely on the user's computer, or as a separate software package on the user's computer, or partly on the user's computer and partly on a remote computer, or entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0115] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some embodiments of the invention that are currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing processing device or mobile device.

[0116] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0117] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0118] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A medical oxygen concentrator control method, characterized in that: The medical oxygen concentrator is communicatively connected to a monitoring device, the monitoring device being used to monitor physiological parameters of a patient, and the method comprising: Obtaining oxygen output parameters of the medical oxygen concentrator during a first time period, and physiological parameters monitored by a monitoring device for the patient during the first time period, wherein the oxygen output parameters include at least oxygen output concentration and output flow, and the physiological parameters include at least blood oxygen saturation, heart rate, and respiratory rate; determining, based on the oxygen output parameter and the physiological parameter, a degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the physiological state of the patient; If the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient does not meet a preset condition, adjusting the oxygen output parameters of the medical oxygen concentrator in a second time period to ensure that the patient obtains an appropriate oxygen supply, wherein the second time period is an adjacent time period after the first time period; Determining, based on the oxygen output parameter and the physiological parameter, a degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient includes: Inputting the oxygen output parameter and the physiological parameter as input data into a pre-trained parameter matching model for processing, thereby obtaining a degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient; The parameter matching model is trained based on the following method: Obtaining a second training data set, the second training data set including sample multidimensional oxygen output parameter sequences of a medical oxygen concentrator in multiple sample time periods, sample physiological parameter sequences obtained by monitoring a patient using a monitoring device in corresponding sample time periods, and matching labels corresponding to the sample multidimensional oxygen output parameter sequences and the sample physiological parameter sequences; Performing deep feature extraction on the sample multidimensional oxygen output parameter sequence and the sample physiological parameter sequence respectively through a deep feature extraction network to obtain a sample multidimensional oxygen output parameter feature sequence and a sample physiological parameter feature sequence; Inputting the sample multi-dimensional oxygen output parameter feature sequence and the sample physiological parameter feature sequence as input data into an initial parameter matching model for training, and verifying and adjusting the output result of the initial parameter matching model according to the matching label until the output result of the initial parameter matching model meets the preset training requirements, thereby obtaining a trained parameter matching model; The adjusting the oxygen output parameter of the medical oxygen concentrator in the second time period includes: inputting the physiological parameters monitored by the monitoring device for the patient during the first time period as input data into a pre-trained oxygen output parameter prediction model for processing to obtain oxygen output prediction parameters corresponding to the physiological parameters; adjusting the oxygen output parameter of the medical oxygen concentrator in the first time period based on the oxygen output prediction parameter to obtain the oxygen output parameter of the medical oxygen concentrator in the second time period; The oxygen output parameter prediction model is trained based on the following method: Acquire a first training data set, the first training data set including a sample physiological parameter sequence of the monitoring device within a plurality of sample time periods, and label information corresponding to the sample physiological parameter sequence, the label information being used to reflect an expected oxygen output parameter corresponding to the sample physiological parameter sequence; The sample physiological parameter feature sequence is input as input data into an initial oxygen output parameter prediction model for training, and the output result of the initial oxygen output parameter prediction model is verified and adjusted according to the label information until the output result of the initial oxygen output parameter prediction model meets the preset training requirements, thereby obtaining a trained oxygen output parameter prediction model.

2. The medical oxygen concentrator control method according to claim 1, wherein: Determining, based on the oxygen output parameter and the physiological parameter, a degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient includes: inputting the physiological parameter as input data into a pre-trained oxygen output parameter prediction model for processing to obtain an oxygen output prediction parameter corresponding to the physiological parameter in the first time period; calculating a distance between the oxygen output prediction parameter and the oxygen output parameter of the medical oxygen concentrator in the first time period, and obtaining a degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient based on the distance; The oxygen output parameter prediction model is trained based on the following method: Acquire a first training data set, the first training data set including a sample physiological parameter sequence of the monitoring device within a plurality of sample time periods, and label information corresponding to the sample physiological parameter sequence, the label information being used to reflect an expected oxygen output parameter corresponding to the sample physiological parameter sequence; The sample physiological parameter feature sequence is input as input data into an initial oxygen output parameter prediction model for training, and the output result of the initial oxygen output parameter prediction model is verified and adjusted according to the label information until the output result of the initial oxygen output parameter prediction model meets the preset training requirements, thereby obtaining a trained oxygen output parameter prediction model.

3. The medical oxygen concentrator control method according to claim 2, wherein: The adjusting the oxygen output parameter of the medical oxygen concentrator in the second time period includes: The oxygen output parameter of the medical oxygen concentrator in the first time period is adjusted based on the oxygen output prediction parameter output by the oxygen output parameter prediction model to obtain the oxygen output parameter of the medical oxygen concentrator in the second time period.

4. The medical oxygen concentrator control method according to any one of claims 1 to 3, characterized in that: The method further comprises: An oxygen production parameter of the medical oxygen concentrator in the second time period is determined according to the oxygen output parameter of the medical oxygen concentrator in the second time period, and oxygen production of the medical oxygen concentrator is controlled based on the oxygen production parameter.

5. The medical oxygen concentrator control method according to claim 4, wherein: The determining the oxygen production parameters of the medical oxygen concentrator in the second time period according to the oxygen output parameters of the medical oxygen concentrator in the second time period includes: Acquire the current oxygen storage capacity of the medical oxygen concentrator and environmental parameters of the environment in which the medical oxygen concentrator is located, wherein the environmental parameters include ambient temperature and ambient pressure; Target oxygen production parameters are determined according to the current oxygen storage amount, ambient temperature, ambient pressure, and oxygen output parameters in the second time period, wherein the target oxygen production parameters include an operating frequency of a compressor, an operating temperature of a molecular sieve, and an operating intensity of a cooling system.

6. The medical oxygen concentrator control method according to claim 5, characterized in that: The determining the target oxygen production parameter according to the current oxygen storage amount, ambient temperature, ambient pressure, and the oxygen output parameter in the second time period includes: The current oxygen storage amount, ambient temperature, ambient pressure and oxygen output parameters in the second time period are mapped using a preconfigured data mapping table to obtain the target oxygen production parameters.

7. The medical oxygen concentrator control method according to claim 5, wherein: The determining the target oxygen production parameter according to the current oxygen storage amount, ambient temperature, ambient pressure, and the oxygen output parameter in the second time period includes: inputting the current oxygen storage amount, ambient temperature, ambient pressure, and the oxygen output parameter in the second time period as input data into a pre-trained oxygen production parameter calculation model for processing to obtain the target oxygen production parameter; The oxygen production parameter calculation model is trained based on the following method: Obtaining a third training data set, where each training sample in the third training data set includes oxygen storage capacity, ambient temperature, ambient pressure, oxygen output parameters, and corresponding oxygen production parameter labels; Each training sample in the third training data set is input as input data into the initial oxygen production parameter calculation model for training, and an output result of the initial oxygen production parameter calculation model is verified and adjusted according to the oxygen production parameter label until the output result of the initial oxygen production parameter calculation model meets the preset training requirements, thereby obtaining a trained oxygen production parameter calculation model.

8. A medical oxygen concentrator control system, characterized in that: The medical oxygen concentrator is in communication with a monitoring device, which is used to monitor the patient's physiological parameters. The system includes: an acquisition module, configured to acquire oxygen output parameters of the medical oxygen concentrator during a first time period, and physiological parameters monitored by a monitoring device on a patient during the first time period, wherein the oxygen output parameters include at least oxygen output concentration and output flow, and the physiological parameters include at least blood oxygen saturation, heart rate, and respiratory rate; a matching calculation module, configured to determine, based on the oxygen output parameter and the physiological parameter, a degree of matching between the oxygen production effect of the medical oxygen concentrator during the first time period and the physiological state of the patient; a control module configured to, upon detecting that the degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient does not satisfy a preset condition, adjust the oxygen output parameters of the medical oxygen concentrator in a second time period to ensure that the patient obtains an appropriate oxygen supply, wherein the second time period is an adjacent time period after the first time period; The matching calculation module is specifically used for: Inputting the oxygen output parameter and the physiological parameter as input data into a pre-trained parameter matching model for processing, thereby obtaining a degree of matching between the oxygen production effect of the medical oxygen concentrator in the first time period and the physiological state of the patient; The parameter matching model is trained based on the following method: Obtaining a second training data set, the second training data set including sample multidimensional oxygen output parameter sequences of a medical oxygen concentrator in multiple sample time periods, sample physiological parameter sequences obtained by monitoring a patient using a monitoring device in corresponding sample time periods, and matching labels corresponding to the sample multidimensional oxygen output parameter sequences and the sample physiological parameter sequences; Performing deep feature extraction on the sample multidimensional oxygen output parameter sequence and the sample physiological parameter sequence respectively through a deep feature extraction network to obtain a sample multidimensional oxygen output parameter feature sequence and a sample physiological parameter feature sequence; Inputting the sample multi-dimensional oxygen output parameter feature sequence and the sample physiological parameter feature sequence as input data into an initial parameter matching model for training, and verifying and adjusting the output result of the initial parameter matching model according to the matching label until the output result of the initial parameter matching model meets the preset training requirements, thereby obtaining a trained parameter matching model; The control module is specifically used for: inputting the physiological parameters monitored by the monitoring device for the patient during the first time period as input data into a pre-trained oxygen output parameter prediction model for processing to obtain oxygen output prediction parameters corresponding to the physiological parameters; adjusting the oxygen output parameter of the medical oxygen concentrator in the first time period based on the oxygen output prediction parameter to obtain the oxygen output parameter of the medical oxygen concentrator in the second time period; The oxygen output parameter prediction model is trained based on the following method: Acquire a first training data set, the first training data set including a sample physiological parameter sequence of the monitoring device within a plurality of sample time periods, and label information corresponding to the sample physiological parameter sequence, the label information being used to reflect an expected oxygen output parameter corresponding to the sample physiological parameter sequence; The sample physiological parameter feature sequence is input as input data into an initial oxygen output parameter prediction model for training, and the output result of the initial oxygen output parameter prediction model is verified and adjusted according to the label information until the output result of the initial oxygen output parameter prediction model meets the preset training requirements, thereby obtaining a trained oxygen output parameter prediction model.

Images