Artificial intelligence-based respiratory humidification devices, control methods, equipment, media, and products.

Abstract

This application provides an artificial intelligence-based respiratory humidification device and its control method, device, medium, and product. The controller can adjust the power of the heating plate based on the first temperature of the humidification tank's inlet, the second temperature of the outlet, and the real-time flow rate of the gas flowing through the humidification tank. This adjusts the temperature and humidity of the gas output from the humidification tank, thereby more accurately and effectively controlling the temperature and humidity of the gas output by the AI-based respiratory humidification device. This allows it to adapt to various gas conditions and, in different application scenarios, more effectively reduce fluctuations in the temperature and humidity of the output gas, ensuring the stability and continuity of the output gas's temperature and humidity, and guaranteeing the expected performance.

Description

Technical Field

[0001] This application relates to respiratory medical devices, and more particularly to an artificial intelligence-based respiratory humidification device and its control method, device, medium and product. Background Technology

[0002] Home ventilators, medical ventilators, oxygen inhalers, and other AI-based humidification devices are important auxiliary medical devices in the medical field. Specifically, AI-based humidification devices include structures such as a humidification tank and a heating plate. The controller can control how the heating plate heats the humidifying liquid in the humidification tank, thereby humidifying the gas flowing through it.

[0003] In the prior art, the controller of the breathing humidification device based on artificial intelligence can specifically target the required outlet air temperature. When the outlet air temperature of the humidification tank is greater than the first target value, it indicates that the outlet air humidity is high, so the heating plate is controlled to stop heating to reduce the air humidity; when the outlet air temperature of the humidification tank is less than the second target value, it indicates that the outlet air humidity is low, so the heating plate is controlled to start heating to increase the air humidity.

[0004] However, with existing technology, the temperature and humidity of the gas output by AI-based respiratory humidification devices fluctuate significantly, affecting the patient's experience. Therefore, how to more accurately control the temperature and humidity of the gas output by AI-based respiratory humidification devices is a technical problem that needs to be solved in this field. Summary of the Invention

[0005] This application provides an artificial intelligence-based respiratory humidification device and its control method, device, medium and product, to improve the control accuracy of the temperature and humidity of the gas output by the artificial intelligence-based respiratory humidification device, reduce the fluctuation of gas temperature and humidity, and thus ensure the expected use effect of the artificial intelligence-based respiratory humidification device.

[0006] This application provides a breathing humidification device based on artificial intelligence, comprising: a humidification tank for storing water, the humidification tank further comprising an air inlet and an air outlet for gas entry and exit; a heating plate disposed at the bottom of the humidification tank for heating the water stored in the humidification tank to heat and humidify the gas flowing through the humidification tank; a first temperature detection device for detecting a real-time first temperature at the air inlet; a second temperature detection device for detecting a real-time second temperature at the air outlet; a flow rate detection device for detecting a real-time flow rate of the gas flowing through the humidification tank; and a controller for acquiring a set temperature of the gas output from the humidification tank; and determining the humidification temperature based on the set temperature. The system sets the humidity of the gas output from the humidification tank; determines the real-time first temperature and real-time flow rate based on the first temperature detection device and the flow rate detection device; determines the target temperature of the gas outlet of the humidification tank based on a second correspondence between the set humidity, the real-time first temperature, the real-time flow rate, and the target temperature; the second correspondence is obtained through machine learning based on big data; determines the real-time second temperature of the gas outlet of the humidification tank based on the second temperature detection device; and controls the power of the heating plate based on the real-time second temperature and the target temperature, so that the temperature of the gas output from the humidification tank is the target temperature and the humidity of the gas output from the humidification tank is the set humidity.

[0007] A second aspect of this application provides a control method for an artificial intelligence-based respiratory humidification device, applied to the artificial intelligence-based respiratory humidification device as described in the first aspect of this application. The control method includes: determining a real-time first temperature at the air inlet of the humidification tank, a real-time second temperature at the air outlet, and a real-time flow rate of the gas flowing through the humidification tank; determining a target temperature at the air outlet of the humidification tank based on the real-time first temperature, the real-time second temperature, and the real-time flow rate, and based on a second correspondence between a set humidity, the real-time first temperature, the real-time flow rate, and the target temperature; determining the real-time second temperature at the air outlet of the humidification tank based on a second temperature detection device; and controlling the power of the heating plate based on the real-time second temperature and the target temperature, so that the temperature of the gas output from the humidification tank is the target temperature and the humidity of the gas output from the humidification tank is the set humidity.

[0008] A third aspect of this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor, the memory storing computer-executable instructions, and the processor executing the computer-executable instructions stored in the memory to implement the method as described in the first aspect of this application.

[0009] A fourth aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method described in the first aspect of this application.

[0010] The fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect of this application.

[0011] In summary, the AI-based respiratory humidification device and its control method, equipment, medium, and product provided in this application allow the controller of the AI-based respiratory humidification device to adjust the power of the heating plate based on the first temperature of the inlet of the humidification tank, the second temperature of the outlet, and the real-time flow rate of the gas flowing through the humidification tank. This adjusts the temperature and humidity of the gas output from the humidification tank, thereby more accurately and effectively controlling the temperature and humidity of the gas output by the AI-based respiratory humidification device. Consequently, the AI-based respiratory humidification device can adapt to various gas conditions and, in different application scenarios, more effectively reduce the fluctuations in the temperature and humidity of the gas output by the AI-based respiratory humidification device, ensuring the stability and continuity of the temperature and humidity of the gas output by the AI-based respiratory humidification device, and guaranteeing the expected performance of the AI-based respiratory humidification device. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram illustrating the application scenario of this application;

[0014] Figure 2 A schematic diagram of the structure of an embodiment of the artificial intelligence-based respiratory humidification device provided in this application;

[0015] Figure 3 A schematic diagram illustrating one configuration of the flow detection device provided in this application;

[0016] Figure 4 A schematic diagram illustrating another configuration of the flow detection device provided in this application;

[0017] Figure 5 A control schematic diagram of the first temperature detection device provided in this application;

[0018] Figure 6 A control diagram of the second temperature detection device and flow detection device provided in this application;

[0019] Figure 7 A schematic diagram illustrating the test results of the flow detection device provided in this application;

[0020] Figure 8 A schematic flowchart of an embodiment of the control method for an artificial intelligence-based respiratory humidification device provided in this application;

[0021] Figure 9 A schematic diagram of humidity detection of the gas output by the AI-based respiratory humidification device provided in this application;

[0022] Figure 10 A schematic diagram of one embodiment of the mapping relationship provided in this application;

[0023] Figure 11 A schematic diagram of the preset time for the AI-based respiratory humidification device provided in this application;

[0024] Figure 12 This is a schematic diagram of the structure of an electronic device provided in this application.

[0025] Figure label:

[0026] 1-Artificial intelligence-based respiratory humidification device; 2-Tubing; 3-Patient interface; 111-Air inlet; 112-Air outlet; 121-Hydraulic tank; 122-Heating plate; 101-First temperature detection device; 102-Second temperature detection device; 103-Flow detection device; 101-1 First thermistor; 102-1-Second thermistor; 103-1-Third thermistor; 100-Controller; 141-First constant current source; 142-Second constant current source; 143-Controllable current source; 2000-Electronic device; 2001-Processor; 2002-Memory; 2003-Communication interface. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Figure 1 This is a schematic diagram illustrating the application scenario of this application, such as... Figure 1 As shown, this application is applied in an AI-based respiratory humidification device 1. Among them, home ventilators, medical ventilators, oxygen inhalers, and other AI-based respiratory humidification devices 1 are important auxiliary medical devices in the medical field. They can be used to provide warming and humidification effects for the breathing gas provided to patients, so as to maintain the normal clearance function of the mucociliary system on the airway surface and the physiological conditions necessary for the normal contraction and diffusion characteristics of the alveolar epithelium, thereby reducing airway dryness and inflammatory symptoms.

[0030] like Figure 1 The AI-based respiratory humidification device 1 shown includes a humidification tank 121 and a heating plate 122. The humidification tank 121 stores a certain amount of water and has an air inlet 111 for gas entry and an air outlet 112 for gas output. After the humidification tank 121 is installed in the corresponding reserved space on the AI-based respiratory humidification device 1, the bottom of the humidification tank 121 is attached to the heating plate 122, allowing the heating plate 122 to heat the water stored in the humidification tank 121 through heat transfer. The air outlet 112 of the humidification tank 121 is also connected to a patient interface 3 via a tubing 2. The patient interface 3 can be either unsealed or sealed. Unsealed patient interfaces include nasal cannulas, while sealed patient interfaces include endotracheal tubes, face masks, etc. The humidification tank 111 transmits the heated and humidified gas to the patient interface 3 through the tubing 2, allowing the user of the AI-based respiratory humidification device 1 to inhale the heated and humidified gas through the patient interface 3.

[0031] In one specific implementation, the humidification tank 121 is detachably set relative to the main body of the AI-based breathing humidification device 1. When the humidification tank 121 is set in the reserved space inside the main body of the AI-based breathing humidification device 1, the controller 100 can control the heating temperature of the heating plate 122 to heat the water in the humidification tank 121, thereby heating and humidifying the gas flowing through the humidification tank 121.

[0032] In existing related technologies, the controller 100 of the artificial intelligence-based breathing humidification device 1 detects the outlet temperature of the outlet 112 by setting a temperature sensor, for example, based on the desired outlet temperature as the target, and adjusts the heating power of the heating plate 122 according to the difference between the outlet temperature and the target temperature, thereby adjusting the temperature and humidity of the gas output from the humidification tank 121.

[0033] For example, when the outlet temperature of the humidification tank 121 is greater than the first target value, it indicates that the temperature or humidity of the gas output by the humidification tank 121 is high. In this case, the controller 100 controls the heating plate 122 to stop heating or reduce the heating power to reduce the temperature or humidity of the gas output by the humidification tank 121. When the outlet temperature of the humidification tank 121 is less than the second target value, it indicates that the temperature or humidity of the gas output by the humidification tank 121 is low. In this case, the controller 100 controls the heating plate 122 to start heating or increase the heating power to increase the temperature or humidity of the gas output by the humidification tank 121.

[0034] In the aforementioned prior art, the controller 100 adjusts the humidity by controlling the heating plate 122 based on the outlet temperature of the humidification tank 121's outlet 112. This causes significant fluctuations in the temperature and humidity of the gas output from the humidification tank 121, affecting the humidification effect of the AI-based respiratory humidification device 1 and thus impacting the user experience. In some cases, the high temperature and low humidity conditions can even irritate the respiratory tract and lungs, thereby affecting the therapeutic effect of the AI-based respiratory humidification device 1.

[0035] Specifically, since the temperature and humidity of the gas output from the humidification tank 121 are not only related to the outlet temperature of the outlet 112, the controller 100's method of controlling the power of the heating plate 122 based solely on the outlet temperature of the outlet 112 cannot consider the influence of factors such as the temperature of the gas entering the humidification tank 121 and the gas flow rate in the humidification tank 121 on the temperature and humidity of the gas output from the humidification tank 121.

[0036] Therefore, how to more accurately control the temperature and humidity of the gas output by the AI-based respiratory humidification device 1 is a technical problem that needs to be solved in this field. This application provides an AI-based respiratory humidification device 1 and its control method to improve the control accuracy of the temperature and humidity of the gas output by the AI-based respiratory humidification device 1, reduce fluctuations in gas temperature and humidity, and thus ensure the expected humidification effect of the AI-based respiratory humidification device 1.

[0037] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0038] Figure 2 This is a schematic diagram of an embodiment of the artificial intelligence-based respiratory humidification device 1 provided in this application, as shown below. Figure 2 The AI-based respiratory humidification device 1 shown includes:

[0039] Humidification tank 121, combined with Figure 1 The schematic diagram shows that the humidification tank 121 can be used to store a certain amount of water, and an air inlet 111 and an air outlet 112 for gas entry and exit are provided above it.

[0040] A heating plate 122 is located at the bottom of the humidification tank 121 and is used to heat the humidification liquid stored in the humidification tank 121 to heat and humidify the gas flowing through the humidification tank 121.

[0041] The first temperature detection device 101 is used to detect the real-time first temperature at the air inlet 111 and send the real-time first temperature to the controller 100. The first temperature detection device 101 can be set upstream of the air inlet 111, for example, it can be set at the air inlet 111 of the humidification tank 121.

[0042] The second temperature detection device 102 is used to detect the real-time second temperature at the air outlet 112 and send the real-time second temperature to the controller 100. The second temperature detection device 102 can be located downstream of the air outlet 112, for example, it can be located at the air outlet 112 of the humidification tank 121.

[0043] The flow detection device 103 is used to detect the flow rate of gas flowing through the humidification tank 121 and send the real-time flow rate to the controller 100. The flow detection device 103 can be positioned upstream of the inlet 111 or downstream of the outlet 112. For example, the flow detection device 103 can be positioned at the inlet 111 of the humidification tank 121. In this case, the flow detection device 103 and the first temperature detection device 101 are located on the same side, and the flow detection device 103 can determine the real-time flow rate by combining the real-time first temperature detected by the first temperature detection device 101. Alternatively, the flow detection device 103 can be positioned at the outlet 112 of the humidification tank 121. In this case, the flow detection device 103 and the second temperature detection device 102 are located on the same side, and the flow detection device 103 can determine the real-time flow rate by combining the real-time second temperature detected by the second temperature detection device 102.

[0044] The controller 100 is used to control the heating plate 122 based on the received real-time first temperature, real-time second temperature and real-time flow rate. Specifically, it can adjust the heating power of the heating plate 122 to adjust the temperature and humidity of the gas output from the humidification tank 121.

[0045] As can be seen, in the control method executed by the AI-based respiratory humidification device 1 and controller 100 provided in this embodiment, the controller 100 can detect more parameters, including the real-time first temperature of the air inlet 111 of the humidification tank 121, the real-time second temperature of the air outlet 112, and the real-time flow rate of the humidification tank 121. Based on the real-time first temperature, the real-time second temperature, and the real-time flow rate, the controller jointly controls the heating power of the heating plate 122. This more comprehensively combines factors such as the temperature of the gas in the humidification tank 121 and the gas flow rate in the humidification tank 121, and more accurately and effectively controls the temperature and humidity of the gas output by the AI-based respiratory humidification device 1. As a result, the AI-based respiratory humidification device 1 can adapt to various gas conditions and, in different application scenarios, can more effectively reduce the fluctuations in the temperature and humidity of the gas output by the AI-based respiratory humidification device 1, ensuring the stability and continuity of the temperature and humidity of the gas output by the AI-based respiratory humidification device 1, and ensuring the expected humidification effect of the AI-based respiratory humidification device 1.

[0046] In one embodiment, the first temperature detection device 101 includes a first thermistor 101-1.

[0047] In one embodiment, the second temperature detection device 102 includes a second thermistor 102-1.

[0048] In one embodiment, the flow detection device 103 includes a third thermistor 103-1.

[0049] Figure 3 This is a schematic diagram of one configuration of the flow detection device 103 provided in this application, as shown below. Figure 3 As shown, taking the first temperature detection device 101, which includes a first thermistor 101-1, as an example, the first thermistor 101-1 is disposed around the air inlet 111 of the humidification tank 121. Taking the second temperature detection device 102, which includes a second thermistor 102-1, as an example, the second thermistor 102-1 is disposed around the air outlet 112 of the humidification tank 121. Taking the flow detection device 103, which includes a third thermistor 103-1, as an example, the third thermistor 103-1 is disposed in close contact with the air outlet 112.

[0050] Figure 4 This is a schematic diagram of another configuration of the flow detection device 103 provided in this application. Taking the flow detection device 103 including a third thermistor 103-1 as an example, the third thermistor 103-1 is disposed around the air inlet 111.

[0051] In one embodiment, the AI-based respiratory humidification device 1 further includes: a first constant current source 141. Figure 5 A control schematic diagram of the first temperature detection device provided in this application is shown below. Figure 5 As shown, a first constant current source 141 is connected to a first thermistor 101-1. A controller 100 can control the first constant current source 141 to provide a constant first current to the first thermistor 101-1, wherein the first current also prevents the first thermistor 101-1 from generating self-heating. The controller 100 detects the voltage of the first thermistor 101-1. Based on the inverse relationship between the voltage change and the resistance change of the first thermistor 101-1, the controller calculates the real-time resistance value of the first thermistor 101-1, and then determines the real-time first temperature based on the real-time resistance value by looking up a table or other methods.

[0052] In one embodiment, the AI-based respiratory humidification device 1 further includes: a second constant current source 142 and a controllable current source 143. Figure 6 The control diagram of the second temperature detection device 102 and the flow detection device 103 provided in this application is as follows: Figure 6 As shown, the second constant current source 142 is connected to the second thermistor 102-1. The controller 100 can be used to control the second constant current source 142 to provide a constant second current to the second thermistor 102-1, wherein the second current also prevents the second thermistor 102-1 from generating self-heating. The controller 100 detects the voltage of the second thermistor 102-1. Based on the inverse relationship between the voltage change and the resistance change of the second thermistor 102-1, the controller calculates the real-time resistance value of the second thermistor 102-1, and then determines the real-time second temperature based on the real-time resistance value by looking up a table or other methods.

[0053] like Figure 6 As shown, the controllable current source 143 is also connected to a third thermistor 103-1. The controller 100 can be used to control the controllable current source 143 to provide a variable third current to the third thermistor 103-1, wherein the third current can be used to keep the power of the third thermistor 103-1 constant. When the flow rate increases, the third thermistor 103-1 will lose more heat, and its real-time resistance will change. To maintain a fixed power value, the current applied to the third thermistor 103-1 will also change, so there is a non-linear relationship between the resistance of the third thermistor 103-1 and the flow rate. However, the lower the temperature of the flowing gas, the more heat will be lost from the third thermistor 103-1 at the same flow rate. Therefore, the flow rate is related to the resistance of the speed-measuring thermistor and the temperature of the temperature-measuring thermistor. The controller 100 detects the voltage of the third thermistor 103-1. Based on the inverse relationship between the voltage change and the resistance change of the third thermistor 103-1, the controller calculates the real-time resistance of the third thermistor 103-1. Then, the controller determines the real-time flow rate based on the real-time resistance of the third thermistor 103-1, the real-time resistance of the second thermistor 102-1, and the first correspondence between the flow rate and the real-time resistance.

[0054] Specifically, the first correspondence provided in this application is implemented based on artificial intelligence (AI).

[0055] In one embodiment, the first correspondence provided in this application is obtained through machine learning (ML) on big data in artificial intelligence. Machine learning is a subfield of artificial intelligence that focuses on developing algorithms and models that can automatically learn from big data and improve performance. This application does not limit the specific method of machine learning; for example, machine learning can be performed on previously acquired experience data to obtain the first correspondence. The first correspondence can specifically be in the form of a formula. The first correspondence obtained through machine learning is more accurate, making subsequent processing based on the first correspondence more effective.

[0056] In another embodiment, the first correspondence provided in this application can also be obtained by fitting large datasets. The first correspondence obtained through fitting requires less computational power and can be used in scenarios with limited computing power and high efficiency requirements.

[0057] For example, in one embodiment, the first correspondence includes:

[0058] Flow=P1+P2*X+P3*X^2+P4*X^3+P5*Y+P6*Y^2+P7*Y^3;

[0059] Where Flow represents flow rate, in the case of... Figure 5 and Figure 6 In the example shown, X is the real-time resistance of the second thermistor 102-1, Y is the real-time resistance of the third thermistor 103-1, and P1, P2, P3, P4, P5, P6 and P7 are coefficients that can be obtained through experiments. This application does not limit the value of the coefficients.

[0060] It is understandable that, such as Figure 5 and Figure 6 In the example shown, the flow detection device 103 is used as the third thermistor 103-1 and is set at the air outlet 112 of the humidification tank 121 as an example. In another possible embodiment, when the flow detection device 103 is used as the third thermistor 103-1 and is set at the air inlet 111 of the humidification tank 121, when the controller 100 performs the corresponding calculation according to the first correspondence above, X in the first correspondence is the real-time resistance value of the first thermistor 101-1.

[0061] Figure 7 This is a schematic diagram illustrating the test results of the flow detection device 103 provided in this application, as shown below. Figure 7 As shown, during testing, gas can be supplied to the AI-based respiratory humidification device 1 according to the measured flow rate, and based on... Figure 6 The flow detection device 103 shown detects the real-time flow rate of the gas and obtains the detected flow rate. It can be seen that, through experiments, the detected flow rate obtained by the method of determining the real-time flow rate through the first correspondence relationship is relatively close to the test flow rate provided during the test, so that the flow rate calculated by the flow detection device 103 provided in this application has high accuracy and effectiveness.

[0062] In summary, the artificial intelligence-based respiratory humidification device 1 provided in this embodiment is equipped with the following features: Figure 5 and Figure 6 The first temperature detection device 101 and the second temperature detection device 102 shown are both implemented using thermistors, which have a relatively simple structure, making temperature detection simpler and more effective, and greatly reducing the amount of computation required by the controller 100. At the same time, the flow detection device 103 can effectively obtain the flow rate of the gas flowing through the humidification tank 121 by combining the real-time resistance value of the second thermistor 102-1 detected by the second temperature detection device 102. Thus, gas flow rate can be detected based on thermistors without the need for a dedicated flow meter. Furthermore, while obtaining the flow rate, the required structural and computational complexity is reduced, which is more conducive to the application and promotion of the artificial intelligence-based respiratory humidification device 1 provided in this application.

[0063] Furthermore, in this embodiment, the flow rate is indirectly determined by setting a temperature detection device, rather than directly using a flow sensor. This is because the structure of a flow sensor, under high humidity conditions in the pipeline 2, can affect the accuracy of the detection data, and the flow sensor is easily damaged by moisture. Therefore, the AI-based humidification device 1 provided in this application determines the flow rate through a temperature detection device without using a flow sensor. This allows for accurate flow rate detection under any humidity conditions, ensuring the validity and accuracy of the measurement results, effectively preventing moisture damage to the device, and extending the lifespan of the AI-based humidification device 1.

[0064] More specifically, the humidity of the gas output by the AI-based breathing humidification device 1 includes at least two parts: the first part is the humidity of the air entering the humidification tank 121, and the second part is the humidity of the humidifying liquid evaporating inside the humidification tank 121. The first part is related to the environment and is an uncontrollable variable, but the humidity of the second part can be controlled based on the humidity of the first part. The factors affecting the humidity of the second part of the AI-based breathing humidification device 1 include one or more of the following: liquid temperature, liquid surface area, flow rate above the liquid, gas temperature above the liquid, gas humidity above the liquid, and liquid volume.

[0065] In practical applications, the humidification tank 121 of the AI-based respiratory humidification device 1 has automatic water filling and stopping functions, so the liquid surface area and liquid volume of each humidification tank 121 are approximately the same. The flow rate, gas temperature, and gas humidity of the gas entering the AI-based respiratory humidification device 1 can all be detected by sensors. The heating plate 122 heats the bottom of the humidification tank 121, so the temperature of the heating plate 122 is directly proportional to the water temperature, and the temperature of the heating plate 122 is also reflected in the difference between the inlet and outlet air temperatures of the humidification tank 121. In summary, the humidification output of the AI-based respiratory humidification device 1 is related to the inlet air temperature, inlet relative humidity, gas flow rate, target temperature at the patient interface, and target humidity at the patient interface, thus requiring comprehensive analysis.

[0066] The second correspondence provided in this application is specifically obtained through machine learning based on big data. However, this application does not limit the specific machine learning method. For example, the first correspondence can be obtained by using artificial intelligence (AI) to perform machine learning on the previously acquired experience data.

[0067] In one specific embodiment, the operator can collect parameters such as the inlet air temperature, inlet air humidity, and gas flow rate of the AI-based respiratory humidification device 1, and derive a second correspondence using the AI ​​machine learning RIDGE model. This second correspondence can specifically be in the form of a formula.

[0068] For example, the second correspondence is represented by the following formula:

[0069] Z=W1+W2*T1+W3*T1^2+W5*H1+W6*H1^2+W7*H1^3+W8*H2+W9*H2^2+W10*H2^3+W11*Flow +W11*Flow^2;

[0070] Wherein, T1 is the real-time first temperature, H1 is the estimated humidity at the air inlet of air inlet 111, Flow is the real-time flow rate, H2 is the set humidity, Z is the target temperature, and W1, W2, W3, W4, W5, W6, W7, W8, W9, W10, and W11 are coefficients that can be obtained through model training. This application does not limit the values ​​of the coefficients. The estimated humidity at air inlet 111 can be set according to the application scenario.

[0071] Figure 8 This is a flowchart illustrating an embodiment of the control method for an AI-based respiratory humidification device 1 provided in this application. Based on the aforementioned second correspondence, this application also provides a control method for an AI-based respiratory humidification device 1, which can be applied to... Figure 2 In the AI-based respiratory humidification device 1 shown, the operation is performed by the controller 100. Specifically, as... Figure 8 The control methods shown include:

[0072] S101: Controller 100 obtains the set temperature of the gas output from humidification tank 121.

[0073] In one embodiment, the controller 100 can obtain the set temperature set by the user of the AI-based breathing humidification device 1 through an interactive device such as a display interface; or, the controller 100 can connect to the Internet through a communication device to obtain the set temperature sent by other devices via the Internet.

[0074] S102: The controller 100 determines the set humidity of the gas output by the humidification tank 121 in order to achieve the set temperature based on the set temperature determined in S101.

[0075] For example, when the set temperature is 37°C, the determined output humidity of 90%RH is equivalent to 39.57 mg / L. That is, when the set humidity of the gas output by the humidifier 121 is 90%RH, the gas output by the humidifier 121 can reach the set temperature of 37°C.

[0076] In one embodiment, the controller 100 can determine the set humidity and other information corresponding to the set temperature by looking up a table.

[0077] S103: The controller 100 determines the real-time first temperature of the air inlet 111 of the humidification tank 121 based on the first temperature detection device 101, and determines the real-time flow rate of the humidification tank 121 based on the flow detection device 103. For specific detection methods, refer to... Figures 3-6 The embodiments shown will not be described in detail again.

[0078] S104: The controller 100 inputs the set humidity, real-time first temperature, and real-time flow rate into the second correspondence relationship, and then determines the target temperature Z of the air outlet 112 of the humidification tank 121 according to the second correspondence relationship.

[0079] S105: The controller 100 determines the real-time second temperature of the humidification tank 121 based on the second temperature detection device 102. For specific detection methods, please refer to [reference needed]. Figures 3-6 The embodiments shown will not be described in detail again.

[0080] S106: The controller 100 controls the heating power of the heating plate 122 according to the real-time second temperature determined in S105 and the target temperature Z determined in S104, so that the temperature of the gas output from the humidification tank 121 is the target temperature and the humidity of the gas output from the humidification tank 121 is the set humidity determined in S101.

[0081] In one embodiment, the controller 100 may specifically employ an incremental PID model to perform PID heating control on the heating plate 122, wherein the variable PID derivative time PID.TimeDiff = 0.02, the variable PID integral time PID.TimeInte = 486, and the proportional coefficient PID.uKP_Coe = 0.6. The control duty cycle of the heating plate 122 can then be calculated based on the difference between the real-time second temperature and the set temperature, ensuring that the temperature of the gas output from the humidification tank 121 is the target temperature.

[0082] Understandably, controller 100 will repeatedly execute S105 and S106 until the temperature of the gas output from humidification tank 121 reaches the target temperature and the humidity reaches the set humidity. For example, assuming the target temperature is 35°C, if controller 100 detects a real-time second temperature of 30°C through S105, it can raise the temperature of the gas output from humidification tank 121 by controlling heating plate 122 to turn on heating or increasing the power of heating plate 122. After a preset time, controller 100 will again detect the real-time second temperature through S105. If the absolute value of the difference between the real-time second temperature and the target temperature is less than the preset value of 1°C, it will maintain the power of heating plate 122 to maintain the temperature of the gas output from humidification tank 121 at the target temperature and the humidity at the set humidity. For example, if the controller 100 detects a real-time second temperature of 37°C in S105, the controller 100 will reduce the temperature of the gas output from the humidification tank 121 by reducing the power of the heating plate 122 or stopping the heating plate 122. After a preset time, the controller 100 will detect the real-time second temperature again in S105. If the absolute value of the difference between the real-time second temperature and the target temperature is less than the preset value of 1°C, the controller will maintain the power of the heating plate 122, etc., so as to maintain the temperature of the gas output from the humidification tank 121 at the target temperature and the humidity at the set humidity.

[0083] In one embodiment, the controller 100 can store the correspondence between different temperature differences and power. For example, when the difference between the real-time second temperature and the target temperature is in the range of 1-5℃, the controller 100 controls the heating plate 122 to heat according to power A; when the difference between the real-time second temperature and the target temperature is in the range of 5-10℃, the controller 100 controls the heating plate 122 to heat according to power B, where power B is greater than power A, and so on, thereby achieving more precise, rapid and effective control, so that the temperature of the gas output from the humidification tank 121 reaches the target temperature faster, and the humidity of the gas output from the humidification tank 121 reaches the set humidity determined in S101 faster, thereby improving the use effect of the artificial intelligence-based respiratory humidification device 1.

[0084] Figure 9 This is a schematic diagram illustrating the humidity detection of the gas output by the AI-based respiratory humidification device 1 provided in this application, as shown below. Figure 9 As shown, when using as Figure 8When the control method shown controls the gas output by the AI-based breathing humidification device 1, it can be seen that the pipeline humidity of the gas output by the AI-based breathing humidification device 1 can be maintained between the upper and lower humidity limits throughout the entire time range, and the pipeline temperature can also be maintained between the upper and lower temperature limits throughout the entire time range. Moreover, the pipeline humidity and pipeline temperature are relatively stable. Therefore, the control method provided in this embodiment can achieve more precise and effective control over the temperature and humidity of the gas output by the AI-based breathing humidification device 1.

[0085] Furthermore, the above embodiments illustrate a specific control method by which the controller 100 controls the heating power of the heating plate 122 according to the set temperature. In addition to passively obtaining the set temperature input by the user through the interactive device, the controller 100 can also autonomously determine the set temperature according to different scenarios and conditions of the AI-based humidification device 1, thereby enabling the AI-based humidification device 1 to perform more intelligent applications, improving the automation level of the AI-based humidification device 1, and thus improving the user experience of the AI-based humidification device 1.

[0086] Specifically, in one embodiment, the controller 100 can acquire usage information of the AI-based respiratory humidification device 1 and determine the set temperature corresponding to the usage information from a mapping relationship. For example, Figure 10 A schematic diagram of one embodiment of the mapping relationship provided in this application is shown below. Figure 10 The mapping relationships shown include: the correspondence between usage information a and set temperature a, the correspondence between usage information b and set temperature b, ..., the correspondence between usage information N and set temperature N. Therefore, when the controller 100 can obtain the usage information of the AI-based respiratory humidification device 1, it can... Figure 10 In the mapping relationship shown, the set temperature corresponding to the current usage information is determined, and then... Figure 8 The method shown is used for subsequent control.

[0087] In one embodiment, the mapping relationship can be obtained by inputting historical usage information of the AI-based respiratory humidification device 1 into a machine learning model for training.

[0088] In one embodiment, the usage information of the AI-based respiratory humidification device 1 includes one or more of the following: the usage scenario, usage location, usage time, age of the user, or type of disease of the user.

[0089] For example, the usage information of the AI-based respiratory humidification device 1 includes:

[0090] The application scenarios for AI-based respiratory humidification devices include: ICU, wards, emergency rooms, homes, and medical institutions.

[0091] The application locations of the AI-based respiratory humidification device 1 include: climate data and latitude and longitude data of the country and city where it is used.

[0092] The usage time of the AI-based respiratory humidification device 1 includes: season, time of day, etc.

[0093] The age range of users of the AI-based respiratory humidification device 1 includes adults and children.

[0094] The types of diseases experienced by users of the AI-based respiratory humidification device 1 include: normal individuals, obstructive pulmonary disease, restrictive pulmonary disease, and respiratory failure.

[0095] The ventilation types for users of the AI-based respiratory humidification device 1 include: invasive ventilation, non-invasive ventilation, and nasal ventilation.

[0096] The ambient temperature range for the AI-based respiratory humidification device 1 is 18℃-35℃.

[0097] The ambient humidity range of the AI-based respiratory humidification device 1 includes: 10%RH-95%RH.

[0098] The flow rate of the AI-based respiratory humidification device 1 includes: 0.5 LPM-120 LPM.

[0099] The temperature range of the AI-based respiratory humidification device 1 is 18℃-50℃.

[0100] The interface temperature setting range for the AI-based respiratory humidification device 1 is 27℃-40℃.

[0101] The interface setting humidity range for the AI-based respiratory humidification device 1 is 18mg / L-51mg / L.

[0102] Based on the above examples, in a specific instance, for example, when controller 100 determines that the current disease type of the AI-based respiratory humidification device 1 is a normal person, then according to... Figure 10 The mapping relationship shown determines that the set temperature is 37℃, which corresponds to a normal person; when the controller 100 determines that the current disease type of the AI-based respiratory humidification device 1 is respiratory failure, then according to... Figure 10 The mapping relationship shown determines that the set temperature is 40℃.

[0103] For example, when controller 100 determines that the current user's age corresponds to an adult, it can then proceed according to, for example... Figure 10The mapping relationship shown determines the corresponding set temperature to 37°C, which is the temperature set by the user through the interactive device; when the controller 100 determines that the current user's age corresponds to a child, it can then proceed according to... Figure 10 The mapping relationship shown determines that the set temperature for adults is the product of the temperature set by the user through the interactive device and the weight value. The weight value can be 0.6, etc., so the set temperature is determined to be 37℃*0.6.

[0104] For example, when controller 100 determines the current location and season, and determines that the current air humidity is high, it can then... Figure 10 The mapping relationship shown determines that the corresponding set temperature is the product of the temperature 37°C set by the user through the interactive device and a weight value, where the weight value can be 0.8, etc.; when the controller 100 determines the current usage location and season, and determines that the current air humidity is low, it can therefore, according to, for example... Figure 10 The mapping relationship shown determines that the corresponding set temperature is the product of the temperature of 37°C set by the user through the interactive device and the weight value, which can be 1.2, etc.

[0105] In one specific implementation, the usage information of the AI-based respiratory humidification device 1 is obtained; wherein, the usage information includes one or more of the following: real-time flow rate, set temperature, set humidity level, set mode, usage scenario, usage location, usage time, age of the user, or type of disease of the user.

[0106] By acquiring real-time flow rate, set temperature, set humidity level, and set mode of the AI-based respiratory humidification device 1, the expected output humidification level of the device can be calculated. For example, if the non-invasive mode is set, the temperature is set to 34℃, and the humidity level is 0, the expected output humidification level can be calculated to be 27.26 mg / L.

[0107] The system can assess regional differences and predict current environmental conditions by analyzing the usage scenarios, locations, and times of the AI-based respiratory humidification device 1. This allows for superior improvement in the device's performance across different regions, such as north and south. For example, if the usage scenario is in a hospital ICU in Zhejiang, China, and the usage time is in July (summer), the expected ambient temperature is 26°C and the ambient humidity is 60%RH.

[0108] The AI-based respiratory humidification device 1 can compensate for the user's age or disease type by adjusting the output humidity. Too low humidity may cause nasal bleeding and ciliary dysfunction, while too high humidity may increase the risk of mucosal edema and bacterial growth. For example, young users with acute respiratory distress syndrome / chronic obstructive pulmonary disease / pulmonary fibrosis / interstitial lung disease / cardiogenic pulmonary edema require 70%RH-80%RH. Elderly users, especially those on postoperative mechanical ventilation, require humidity above 95%RH. Middle-aged users with bronchial asthma / allergic asthma / chronic obstructive pulmonary disease (COPD) with type II respiratory failure require 50%RH-70%RH.

[0109] The target temperature corresponding to the usage information of the AI-based respiratory humidification device 1 is determined from the big data mapping relationship; the target outlet temperature is the set temperature. The big data mapping relationship includes multiple usage information items and the correspondence between each usage information item of the AI-based respiratory humidification device 1 and the temperature. This big data mapping relationship is constructed by extracting the feature independent variables and feature dependent variables of the historical usage information of the AI-based respiratory humidification device 1, forming a data set, and constructing a data polynomial. Using the Ridge Regression approach in machine learning, the dpotrf and dpotri functions of the LAPACK library are used to perform Cholesky decomposition and inverse calculation. Regularization is achieved through weighted summation of the identity matrix. Automated computation and fitting are then performed to determine the optimal polynomial and parameters.

[0110] It is understood that the artificial intelligence-based respiratory humidification device 1 provided in this application can perform actions such as... Figure 8 The steps S101-S104 shown determine the target temperature of the air outlet 112 of the humidification tank 121. Alternatively, the AI-based breathing humidification device 1 can also determine the target temperature of the air outlet 112 of the humidification tank 121 from a big data mapping relationship based on the usage information of the AI-based breathing humidification device 1 obtained in the above embodiments, and then perform the operation based on the determined target temperature. Figure 8 The subsequent steps in the process. Alternatively, the AI-based humidification device 1 can also simultaneously possess the above two capabilities for determining the target temperature, allowing the user of the AI-based humidification device 1 to select and configure the method for determining the target temperature, thereby improving the flexibility of the AI-based humidification device 1 in application.

[0111] In one embodiment, the controller 100 can acquire usage information through a communication module, which can be a short-range wireless communication module such as a Bluetooth module or a Wi-Fi module. The controller 100 connects to electronic devices in the scene where the AI-based humidification device 1 is located via the communication module. Once the electronic devices determine the current user's usage information, they can send this information to the AI-based humidification device 1. The AI-based humidification device 1 then receives the usage information through the communication module. At this point, without any user intervention, the AI-based humidification device 1 can determine the usage information and perform subsequent control based on it.

[0112] For example, the controller 100 can be connected to the control system of the hospital where the AI-based respiratory humidification device 1 is located via a communication module. Once the doctor or nurse has determined the user information of the AI-based respiratory humidification device 1, the AI-based respiratory humidification device 1 can receive the user information sent by the control system, so that the AI-based respiratory humidification device 1 can provide more suitable humidified gas to the user without the user having to input relevant information.

[0113] Furthermore, after the AI-based humidification device 1 starts working, the controller 100 also needs to control the heating plate 122 to preheat it. After the heating plate 122 preheats with a certain preheating power, the humidification tank 121 is heated according to the set humidity and temperature. In other words, for a period of time after the AI-based humidification device 1 starts working, the output gas cannot immediately meet the requirements of the set humidity and temperature.

[0114] Figure 11 The diagram below shows the preset time of the AI-based respiratory humidification device 1 provided in this application. It is assumed that the AI-based respiratory humidification device 1 starts working at time t0. During the time interval T from time t0 to time t1, the controller 100 controls the heating plate 122 to preheat. However, the AI-based respiratory humidification device 1 can only output gas with the set humidity after time t1. This results in the AI-based respiratory humidification device 1 not being very effective and affecting the humidification effect under some special needs.

[0115] Therefore, in the AI-based respiratory humidification device 1 provided in this application, the controller 100 can determine in advance the preset time t0 when the AI-based respiratory humidification device 1 needs to start working, and control the heating plate 122 to preheat with preheating power at time t2 before the preset time t0, so that after the preheating time period T, the gas with the set humidity can be output at the preset time t0 when it needs to start working.

[0116] For example, the controller 100 can connect to the control system of the hospital where the AI-based humidification device 1 is located via a communication module. When a doctor or nurse determines a preset time (10:00 AM) when the AI-based humidification device 1 needs to start operating, the control system can send this preset time to the corresponding AI-based humidification device 1, allowing it to begin preheating the heating plate 122 at 9:50 AM, before the preset time. When the user starts using the AI-based humidification device 1 at the preset time of 10:00 AM, the device can directly output gas with the set humidity. It can be seen that in this process, the AI-based humidification device 1 can place the preheating process before starting operation, eliminating the need for waiting for the user. This greatly improves the efficiency of the AI-based humidification device 1, ensuring the humidification effect for users who continue humidifying, and enabling the AI-based humidification device 1 to be applied in more emergency scenarios.

[0117] In one embodiment, the AI-based respiratory humidification device 1 provided in this application further includes a fan, which can be used to adjust the flow rate of the gas output from the humidification tank 121. The controller 100 is also used to control the fan to rotate at a preset speed upon receiving a stop command, so that the flow rate of the gas output from the humidification tank 121 is the preset flow rate, thereby drying the pipeline 2 connected to the humidification tank 121, preventing bacteria growth from residual liquid in the pipeline 2, and achieving self-cleaning of the humidification tank 121, pipeline 2, and mask, further enriching the functionality and intelligence of the AI-based respiratory humidification device 1.

[0118] In the above embodiments, the controller 100 of the artificial intelligence-based respiratory humidification device 1 provided in this application can also monitor the rate of change of the real-time first temperature and / or the real-time second temperature, and when the rate of change of one or more of the real-time first temperature and / or the real-time second temperature is greater than a preset value, adjust the power of the heating plate 122 in a timely manner to reduce the rate of change of the first temperature and the second temperature.

[0119] When the rate of change of one or more of the real-time first temperature and / or real-time second temperature is greater than a preset value, it indicates that the humidity or temperature of the output gas may soon exceed the set humidity. The control method provided in this embodiment can adjust the humidity and temperature of the output gas in advance before the output gas changes abnormally, preventing the situation where the humidity and temperature cannot be effectively adjusted due to the large rate of change, and further ensuring the stability of the temperature and humidity of the gas output by the artificial intelligence-based breathing humidification device 1.

[0120] In one embodiment, the controller 100 of the AI-based respiratory humidification device 1 provided in this application can also record historical abnormal data, determine the next abnormal period of the AI-based respiratory humidification device 1 based on the historical abnormal data, and adjust the power of the heating plate 122 in a timely manner during the next abnormal period to adjust the temperature and humidity of the gas output by the humidification tank 121.

[0121] For example, if the humidity of the gas output from the ward where the AI-based respiratory humidification device 1 is used is low every night, the controller 100 can determine, based on historical abnormal data, that the AI-based respiratory humidification device 1 needs to increase temperature and humidity when used at night. Therefore, when the AI-based respiratory humidification device 1 is used again at night, the controller 100 can increase the power of the heating plate 122 to more effectively adjust the temperature and humidity of the gas output from the humidification tank 121, thereby more effectively ensuring the stability of the temperature and humidity of the gas output from the humidification tank 121 throughout the entire time period.

[0122] In the foregoing embodiments of this application, the artificial intelligence-based respiratory humidification device 1 and its control method provided by the embodiments of this application have been described. To realize the various functions in the control method provided by the embodiments of this application, the controller 100, as the execution subject, can be implemented through hardware structures and / or software modules, for example, in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0123] It should be understood that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, a processing module can be a separate processing element, or it can be integrated into a chip within the above device. Alternatively, it can be stored as program code in the memory of the above device, and its functions can be called and executed by a processing element of the device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0124] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to implement a system-on-a-chip (SOC).

[0125] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0126] For example, Figure 12 A schematic diagram of the structure of an electronic device provided in this application, such as... Figure 12 The device shown can be used to execute the control method of the AI-based respiratory humidification device 1 provided in any embodiment of this application. In one embodiment, such as Figure 12The illustrated electronic device 2000 includes one or more processors 2001 and a memory 2002. The memory 2002 stores computer-executable instructions, and the processor 2001 can execute the computer-executable instructions stored in the memory 2002. When the computer-executable instructions are executed by the processor 2001, the processor 2001 implements the control method of the artificial intelligence-based respiratory humidification device 1 as described in any of the foregoing embodiments of this application.

[0127] In one embodiment, such as Figure 12 The electronic device 2000 shown also includes a communication interface 2003, through which the processor 2001 can communicate with other devices, such as obtaining a first temperature, a second temperature, and flow rate through the communication interface 2003.

[0128] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0129] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0130] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0131] This application also provides a chip for executing instructions, the chip being used to execute the control method of the artificial intelligence-based respiratory humidification device 1 provided in any of the foregoing embodiments of this application.

[0132] This application also provides a computer program product, including a computer program that, when executed, implements the control method of the artificial intelligence-based respiratory humidification device 1 provided in any of the foregoing embodiments of this application.

[0133] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, can be used to implement the control method of the artificial intelligence-based respiratory humidification device 1 provided in any of the foregoing embodiments of this application.

[0134] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0135] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0136] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0138] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0139] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0140] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0141] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A respiratory humidification device based on artificial intelligence, characterized in that, include: A humidification tank for storing water, the humidification tank is also provided with an air inlet and an air outlet for gas entry and exit; A heating plate, located at the bottom of the humidification tank, is used to heat the water stored in the humidification tank in order to heat and humidify the gas flowing through the humidification tank. A first temperature detection device is used to detect the real-time first temperature at the air inlet; The second temperature detection device is used to detect the real-time second temperature at the air outlet. A flow detection device is used to detect the real-time flow rate of the gas flowing through the humidification tank; Controller, used for: Obtain the set temperature of the gas output from the humidification tank; The set humidity of the gas output from the humidification tank is determined based on the set temperature. The real-time first temperature and the real-time flow rate are determined based on the first temperature detection device and the flow rate detection device. The target temperature of the humidification tank outlet is determined based on the set humidity, the real-time first temperature, the real-time flow rate, and the second correspondence with the target temperature; the second correspondence is obtained through machine learning based on big data. The real-time second temperature at the outlet of the humidification tank is determined according to the second temperature detection device. Based on the real-time second temperature and the target temperature, the power of the heating plate is controlled so that the temperature of the gas output from the humidification tank is the target temperature and the humidity of the gas output from the humidification tank is the set humidity.

2. The device according to claim 1, characterized in that, Also includes: First constant current source, second constant current source, and controllable current source; The first temperature detection device includes: a first thermistor, and the controller is further configured to control a first constant current source to provide a first current to the first thermistor, and determine the first temperature based on the real-time resistance value of the first thermistor; The second temperature detection device includes a second thermistor. The controller is further configured to control a second constant current source to provide a second current to the second thermistor and determine the second temperature based on the real-time resistance value of the second thermistor. The flow detection device includes a third thermistor. The controller is further configured to control the controllable current source to provide a variable current to the third thermistor, so that the power of the third thermistor remains constant, and to determine the flow rate of the gas flowing through the humidification tank based on the real-time resistance value of the third thermistor, the real-time resistance value of the first thermistor, and the first correspondence between the flow rate, or to determine the flow rate of the gas flowing through the humidification tank based on the real-time resistance value of the third thermistor, the real-time resistance value of the second thermistor, and the first correspondence between the flow rate.

3. The device according to claim 1, characterized in that, The controller is also configured to: The usage information of the AI-based respiratory humidification device is obtained; wherein, the usage information includes one or more of the following: real-time flow rate, set temperature, set humidity level, set mode, usage scenario, usage location, usage time, and the user's age or disease type; the obtained set temperature, set humidity level, and set mode of the AI-based respiratory humidification device are used to determine the expected humidification output of the AI-based respiratory humidification device; the obtained usage scenario, usage location, and usage time of the AI-based respiratory humidification device are used to predict the current environmental conditions; and the obtained age or disease type of the user of the AI-based respiratory humidification device is used to perform humidity compensation on the expected humidification output of the AI-based respiratory humidification device. The target temperature corresponding to the usage information of the AI-based respiratory humidification device is determined from the big data mapping relationship. The big data mapping relationship includes multiple usage information and the correspondence between each AI-based respiratory humidification device usage information and temperature. The mapping relationship is obtained by extracting the feature independent variables and feature dependent variables of the historical usage information of the AI-based respiratory humidification device, forming a data set, and constructing a data polynomial.

4. The device according to claim 1, characterized in that, The controller is also configured to: A preset time for the start of operation of the AI-based respiratory humidification device is determined, and the heating plate is preheated before the preset time to ensure that the humidity of the gas output from the humidification tank is the set humidity when the AI-based respiratory humidification device starts operating at the preset time.

5. The device according to claim 1, characterized in that, The controller is also configured to: When the rate of change of the first temperature and / or the second temperature is greater than a preset value, the power of the heating plate is adjusted to reduce the rate of change of the first temperature and / or the second temperature. And / or, when the next abnormal time period of the AI-based respiratory humidification device is determined based on historical abnormal data of the AI-based respiratory humidification device, and during the next abnormal time period, the power of the heating plate is adjusted to adjust the temperature and humidity of the gas output from the humidification tank.

6. The device according to claim 2, characterized in that, The first correspondence includes: Flow = P1 + P2*X + P3*X^2 + P4*X^3 + P5*Y + P6*Y^2 + P7*Y^3, where Flow is the flow rate, X is the real-time resistance of the first thermistor or the real-time resistance of the second thermistor, Y is the real-time resistance of the third thermistor, and P1, P2, P3, P4, P5, P6 and P7 are coefficients. The second correspondence includes: Z = W1 + W2*T1 + W3*T1^2 + W5*H1 + W6*H1^2 + W7*H1^3 + W8*H2 + W9*H2^2 + W10*H2^3 + W11*Flow + W11*Flow^2, where T1 is the real-time first temperature, H1 is the estimated humidity at the air inlet, Flow is the real-time flow rate, H2 is the set humidity, Z is the target temperature, and W1, W2, W3, W4, W5, W6, W7, W8, W9, W10, and W11 are coefficients.

7. A control method for a respiratory humidification device based on artificial intelligence, characterized in that, The control method, applied to the AI-based respiratory humidification device as described in any one of claims 1-6, comprises: Obtain the set temperature of the gas output from the humidification tank; The set humidity of the gas output from the humidification tank is determined based on the set temperature. The real-time first temperature and the real-time flow rate are determined based on the first temperature detection device and the flow rate detection device. The target temperature of the humidification tank outlet is determined based on the set humidity, the real-time first temperature, the real-time flow rate, and the second correspondence with the target temperature. The real-time second temperature at the outlet of the humidification tank is determined according to the second temperature detection device. Based on the real-time second temperature and the target temperature, the power of the heating plate is controlled so that the temperature of the gas output from the humidification tank is the target temperature and the humidity of the gas output from the humidification tank is the set humidity.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor, the memory storing computer-executable instructions, the processor executing the computer-executable instructions stored in the memory to implement the method of claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in claim 7.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method as described in claim 7.

Images