A method and device for detecting pressure of an infusion pipeline

Abstract

The embodiment of the present invention provides a pressure detection method and device for an infusion pipeline, including: obtaining the speed and displacement of an infusion pump door when it starts and stops; calculating the vibration coefficient of the infusion pump door according to the speed and displacement; obtaining the concentration parameter of the flowing liquid in the infusion pipeline; obtaining the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door; inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into a recurrent neural network model to obtain a trained recurrent neural network model; inputting the vibration coefficient and concentration parameter of a new infusion pipeline into the trained recurrent neural network model to output the corresponding deformation pressure value; merging the deformation pressure value with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline, thereby improving the pressure detection accuracy, making the pressure prediction result more accurate, and improving the prediction accuracy, thereby improving the user's safety.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a pressure detection device for an infusion pipeline, a pressure detection method for an infusion pipeline, a computer device and a computer-readable storage medium. Background Art

[0002] During the infusion process, the infusion pump needs to detect the pressure in the infusion pipeline to prevent the pipeline from being blocked during infusion and causing harm to the patient; the pressure detected by the infusion pump actually contains two parts of force, one is the force from the pump door squeezing the pipeline to cause deformation, and the other is the pressure from the liquid in the pipeline. In the combined force formed by these two forces, the former part of the force occupies a larger proportion, and because of structural design and operation reasons, the pump door needs to be closed before the infusion pump starts working, which will apply a momentary impact to the infusion pipeline, causing a sudden deformation of the infusion pipeline. After the pump door is closed, the deformation will gradually recover over time, and the time to recover to a relatively stable state will be as long as seven or eight hours or even more. The existing infusion pipeline pressure detection technology only considers a static process, and does not consider the dynamic change process of pipeline deformation pressure during actual use, resulting in large errors in the results of pipeline pressure detection at different time points during actual use. Summary of the invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a method for detecting pressure of an infusion pipeline, an apparatus for detecting pressure of an infusion pipeline, a computer device and a computer-readable storage medium that overcome the above problems or at least partially solve the above problems.

[0004] In order to solve the above problems, an embodiment of the present invention discloses a pressure detection method for an infusion pipeline, wherein the infusion pipeline is correspondingly provided with an infusion pump door, and the method comprises:

[0005] Get the speed and displacement of the infusion pump door when it starts and stops;

[0006] Calculating the vibration coefficient of the infusion pump door according to the speed and displacement;

[0007] Obtaining concentration parameters of the flowing liquid in the infusion pipeline;

[0008] Obtaining a deformation pressure value of an infusion pipeline position corresponding to the infusion pump door;

[0009] Inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into a recurrent neural network model to obtain a trained recurrent neural network model;

[0010] Inputting new vibration coefficient and concentration parameters of the infusion pipeline into the trained recurrent neural network model, and outputting corresponding deformation pressure values;

[0011] The deformation pressure value is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

[0012] Preferably, the infusion pump door is provided with an image sensor; the acquisition of the speed and displacement of the infusion pump door when starting and stopping includes:

[0013] Acquire, by means of an image sensor, a first moving image when the infusion pump door is opened and a second moving image when the infusion pump door is stopped;

[0014] Extracting pixel change positions of two infusion pump doors through the first moving image and the second moving image;

[0015] The displacement of the infusion pump door when starting and stopping is calculated through the pixel change positions of the two infusion pump doors.

[0016] Preferably, the infusion pump door is provided with an infrared sensor; the obtaining of the speed and displacement of the infusion pump door when starting and stopping includes:

[0017] Acquire, by means of the infrared sensor, a first position of the infusion pump door when it is opened, and a second position of the infusion pump door when it is stopped;

[0018] The speed of the infusion pump door when starting and stopping is calculated according to the first position and the second position.

[0019] Preferably, the vibration coefficient of the infusion pump door is calculated according to the speed and displacement, including:

[0020] Inputting the speed into a preset function model to obtain a first vibration coefficient of the infusion pump door;

[0021] Calculating a second vibration coefficient according to the displacement and the longitudinal length of the infusion pump door;

[0022] The vibration coefficient is obtained by adding the first vibration coefficient and the second vibration coefficient in proportion.

[0023] Preferably, the recurrent neural network model comprises an input layer, a hidden layer, an activation layer and an output layer; the vibration coefficient, the concentration parameter and the corresponding deformation pressure value are input into the recurrent neural network model to obtain a trained recurrent neural network model, comprising:

[0024] Inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into the input layer of the recurrent neural network model to obtain a first eigenvector; inputting the first eigenvector into the hidden layer to obtain a second eigenvector;

[0025] The activation layer is set according to the vibration coefficient, and the activation function corresponding to the activation layer is f=α / (γ+e -x ), where α represents the vibration coefficient, γ represents the number of categories, x represents the input of the function, and the second eigenvector is input to the set activation layer to obtain the third eigenvector;

[0026] The third eigenvector is input into the output layer, the weight and bias of the recurrent neural network model are adjusted, and the training of the recurrent neural network model is completed until the model converges to obtain the trained recurrent neural network model.

[0027] Preferably, the infusion pump door, the infusion pipeline and the pressure sensor are arranged in sequence; the deformation pressure value is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline, including:

[0028] Obtain the basic pressure value of the infusion pipeline on the pressure sensor;

[0029] The basic pressure value and the deformation pressure value of the infusion pipeline are added to obtain the total pressure value of the infusion pipeline.

[0030] The embodiment of the present invention discloses a pressure detection device for an infusion pipeline, wherein the infusion pipeline is correspondingly provided with an infusion pump door, and the device comprises:

[0031] The first acquisition module is used to acquire the speed and displacement of the infusion pump door when it starts and stops;

[0032] A vibration coefficient calculation module, used to calculate the vibration coefficient of the infusion pump door according to the speed and displacement;

[0033] A second acquisition module, used to acquire the concentration parameter of the flowing liquid in the infusion pipeline;

[0034] A deformation pressure value module, used to obtain the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door;

[0035] A training module, used for inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into a recurrent neural network model to obtain a trained recurrent neural network model;

[0036] An output module, used to input the new vibration coefficient and concentration parameters of the infusion pipeline into the trained recurrent neural network model, and output the corresponding deformation pressure value;

[0037] The merging module is used to merge the deformation pressure value with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

[0038] Preferably, the infusion pump door is provided with an image sensor; the first acquisition module comprises:

[0039] A first acquisition submodule, used to acquire, through an image sensor, a first moving image when the infusion pump door is opened and a second moving image when the infusion pump door is stopped;

[0040] An extraction submodule, used for extracting pixel change positions of two infusion pump gates through the first moving image and the second moving image;

[0041] The first calculation submodule is used to calculate the displacement of the infusion pump door when starting and stopping according to the pixel change position of the two infusion pump doors.

[0042] An embodiment of the present invention discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned infusion pipeline pressure detection method when executing the computer program.

[0043] An embodiment of the present invention discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned pressure detection method for an infusion pipeline are implemented.

[0044] The embodiments of the present invention include the following advantages:

[0045] In an embodiment of the present invention, the pressure detection method of the infusion pipeline includes: obtaining the speed and displacement of the infusion pump door when it starts and stops; calculating the vibration coefficient of the infusion pump door according to the speed and displacement; obtaining the concentration parameter of the flowing liquid in the infusion pipeline; obtaining the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door; inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into a recurrent neural network model to obtain a trained recurrent neural network model; inputting the vibration coefficient and concentration parameter of the new infusion pipeline into the trained recurrent neural network model to output the corresponding deformation pressure value; merging the deformation pressure value with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline, which not only considers the errors caused by different deformation characteristics of different infusion pipelines, but also considers the errors caused by the infusion pipeline changing over time, and also considers the errors caused each time the infusion pump door is opened or closed, which can significantly reduce the errors caused by these errors in the pressure sensor measuring the liquid pressure in the infusion pipeline, improve the pressure detection accuracy, make the pressure prediction result more accurate, improve the prediction accuracy, and thus improve the user's use safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 is a schematic diagram of an embodiment of a method for detecting pressure of an infusion pipeline according to an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram of an infusion pump door and an infusion pipeline arranged relative to each other according to an embodiment of the present invention;

[0049] Figure 3 is a schematic diagram of an image sensor and an infrared sensor arranged on both sides of an infusion pipeline according to an embodiment of the present invention;

[0050] Figure 4 is a schematic diagram of a pressure detection device for an infusion pipeline according to an embodiment of the present invention;

[0051] Figure 5 The diagram is a diagram of the internal structure of a computer device according to an embodiment. DETAILED DESCRIPTION

[0052] In order to make the technical problems, technical solutions and beneficial effects solved by the embodiments of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] In a core concept of an embodiment of the present invention, based on the basic pressure value of the infusion pipeline on the pressure sensor, the vibration coefficient is calculated by the speed and displacement of the infusion pump door when it starts and stops, and then the concentration parameters of the flowing liquid and the vibration coefficient, the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door and other historical measurement data are further used to train the recurrent neural network model to obtain the predicted deformation pressure value, and then the two are combined to obtain the total pressure value, without the need for cumbersome measurement process, thereby improving the pressure detection accuracy, making the pressure prediction result more accurate, and improving the prediction accuracy.

[0054] Reference Figure 1 , shows a schematic diagram of an embodiment of a pressure detection method for an infusion pipeline according to an embodiment of the present invention, wherein the infusion pipeline is provided with an infusion pump door, and specifically may include the following steps:

[0055] Step S101, obtaining the speed and displacement of the infusion pump door when starting and stopping;

[0056] In the embodiment of the present invention, the pressure detection method of the infusion pipeline can be applied to a medical infusion device, and the operating system running on the medical infusion device may include Android, Harmony OS, IOS, Windows Phone, Windows, etc., and the present invention does not impose too many restrictions on this;

[0057] Furthermore, the medical infusion device may also be provided with an infusion pump door, referring to Figure 2 , shows a schematic diagram of an infusion pump door 13 and an infusion pipeline 12 arranged relative to each other in an embodiment of the present invention; the infusion pipeline and the infusion pump door are arranged relative to each other, and the infusion pump door is used to open or close the infusion pipeline, and 11 represents a pressure sensor.

[0058] In another embodiment, the medical infusion device may be provided with a variety of sensors, such as image sensors, infrared sensors, pressure sensors, etc., and the embodiment of the present invention does not impose excessive restrictions on this.

[0059] The image sensor and infrared sensor are set at positions such as Figure 3 As shown, the image sensor 14 and the infrared sensor 15 can be arranged on both sides of the infusion pipeline, not in the same straight line as the pressure sensor, to avoid obstruction.

[0060] In a specific example of an embodiment of the present invention, the infusion pump door is provided with an image sensor; the speed and displacement of the infusion pump door when starting and stopping are obtained, including: obtaining a first moving image of the infusion pump door when it is opened and a second moving image of the infusion pump door when it is stopped through the image sensor; extracting the pixel change positions of the two infusion pump doors through the first moving image and the second moving image; and calculating the displacement of the infusion pump door when starting and stopping through the pixel change positions of the two infusion pump doors.

[0061] The degree of change of the infusion pump door is determined by image recognition. Specifically, a first moving image when the infusion pump door is started and a second moving image when the infusion pump door is closed are obtained; the positions of the two infusion pump doors in the first moving image and the second moving image are pixel-extracted to obtain the pixel change positions of the two, that is, the distance between the two can be obtained, and the distance when the infusion pump door is opened and closed. In another preferred embodiment, the infusion pump door is provided with an infrared sensor; the speed and displacement of the infusion pump door when it is started and stopped are obtained, including:

[0062] Acquire, by means of the infrared sensor, a first position of the infusion pump door when it is opened, and a second position of the infusion pump door when it is stopped;

[0063] The speed of the infusion pump door when starting and stopping is calculated according to the first position and the second position.

[0064] Further applied to the embodiment of the present invention, an infrared sensor can also be used to measure the infusion pump door

[0065] The speed at start and stop measures the impact of impact force on the pressure value. Specifically, the infrared sensor can measure the first position and the second position of the infusion pump door when it starts and stops. According to the distance between the first position and the second position and the time to pass the distance, the speed of the infusion pump door when it starts and stops can be calculated.

[0066] In a preferred embodiment, the infrared sensor replaces the image sensor to obtain the displacement of the infusion pump door when it starts and stops, thereby realizing the reuse of sensor functions and reducing costs.

[0067] Step S102, calculating the vibration coefficient of the infusion pump door according to the speed and displacement;

[0068] After obtaining the speed and displacement, the vibration coefficient of the infusion pump door can be calculated based on the two data.

[0069] Specifically applied to the embodiment of the present invention, the vibration coefficient of the infusion pump door is calculated based on the speed and displacement, including: converting the speed according to a preset formula to obtain a first vibration coefficient of the infusion pump door; calculating the second vibration coefficient based on the displacement and the longitudinal length of the infusion pump door; and obtaining the vibration coefficient by adding the first vibration coefficient and the second vibration coefficient in proportion.

[0070] Specifically, the preset formula is p1=nv; wherein p is the first vibration coefficient of the infusion pump door; n is the conversion coefficient, which can be an empirical value; v represents the speed;

[0071] Furthermore, the ratio of the displacement to the longitudinal length of the infusion pump door is determined as the second vibration coefficient, that is, p2=s / l; wherein p2 represents the second vibration coefficient of the infusion pump door; s is the displacement; v represents the longitudinal length of the infusion pump door; and the vibration coefficient is obtained based on the first vibration coefficient and the second vibration coefficient.

[0072] For example, the ratio can be 40% or 60%, then p1*40%+ p2*60%=Pz; wherein Pz refers to the vibration coefficient, which takes into account the deformation factor of the infusion pump door and provides diverse data for the training of the recurrent neural network model.

[0073] Step S103, obtaining the concentration parameter of the flowing liquid in the infusion pipeline;

[0074] Step S104, obtaining the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door;

[0075] Furthermore, the concentration parameters of the flowing liquid in the infusion pipeline can also be obtained. For example, if the flowing liquid is a drug solution of a certain concentration, the concentration of the flowing liquid can be collected. In addition, the deformation pressure value of the corresponding position of the infusion pipeline can also be obtained. The deformation pressure value can be a sample value measured by a higher-precision pressure sensor, measured under different concentration parameters and vibration coefficient conditions. Step S105: Input the vibration coefficient, concentration parameter and corresponding deformation pressure value into the recurrent neural network model to obtain a trained recurrent neural network model;

[0076] In actual application to the embodiment of the present invention, the vibration coefficient, concentration parameter and corresponding deformation pressure value can be composed of sample data, and the sample data can be input into the recurrent neural network model to obtain a trained recurrent neural network model.

[0077] In another preferred embodiment, the recurrent neural network model includes an input layer, a hidden layer, an activation layer and an output layer; the vibration coefficient, the concentration parameter and the corresponding deformation pressure value are input into the recurrent neural network model to obtain a trained recurrent neural network model, including:

[0078] Inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into the input layer of the recurrent neural network model to obtain a first eigenvector; inputting the first eigenvector into the hidden layer to obtain a second eigenvector;

[0079] The activation layer is set according to the vibration coefficient, and the second eigenvector is input into the set activation layer to obtain the third eigenvector; the third eigenvector is input into the output layer, the weight and bias of the recurrent neural network model are adjusted, and the reciprocating iteration is performed until the model converges, thereby completing the training of the recurrent neural network model and obtaining the trained recurrent neural network model.

[0080] In the embodiment of the present invention, the recurrent neural network model may also include other structures, and the embodiment of the present invention does not impose too many restrictions on this.

[0081] The activation function corresponding to the activation layer is f=α / (γ+e -x ) ; wherein α represents the vibration coefficient, γ represents the number of categories; x represents the input of the function, the second eigenvector is input to the reset activation layer to obtain the third eigenvector, and then the third eigenvector is input to the output layer, the weights and bias of the recurrent neural network model are adjusted, and the iteration is repeated until the model converges to complete the training of the recurrent neural network model. The soft saturation of the model is improved by setting the vibration coefficient, and the training efficiency of the model is improved.

[0082] Step S106, inputting the new vibration coefficient and concentration parameters of the infusion pipeline into the trained recurrent neural network model, and outputting the corresponding deformation pressure value;

[0083] In the embodiment of the present invention, the new vibration coefficient of the infusion pipeline during operation and the concentration parameter of the liquid in the infusion pipeline can be detected, and both are input into the trained recurrent neural network model to obtain the output deformation pressure value, which refers to the pressure generated by the pipeline deformation on the infusion pipeline. Step S107, the deformation pressure value is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

[0084] Furthermore, the basic pressure value of the infusion pipeline can be obtained and combined with the deformation pressure value to obtain the total pressure value of the infusion pipeline, wherein the basic pressure value of the infusion pipeline is the pressure generated on the infusion pipeline when the flowing liquid in the infusion pipeline flows smoothly.

[0085] In a preferred embodiment of the embodiments of the present invention; the deformation pressure value and the basic pressure value of the infusion pipeline are combined to obtain the total pressure value of the infusion pipeline, including: obtaining the basic pressure value of the infusion pipeline on the pressure sensor; adding the basic pressure value of the infusion pipeline to the deformation pressure value to obtain the total pressure value of the infusion pipeline.

[0086] In the embodiment of the present invention, the total pressure value of the infusion pipeline is F 合 , the basic pressure value F of the infusion line on the pressure sensor 液 , the deformation pressure value is F 管 . F 管 It is a function that changes with the time t after the infusion pump door is closed, denoted as F 管 = f(t), so

[0087] F 合 =F 液 +F 管 , that is, F 合 =F 液 +f(t); The f(t) corresponding to different infusion pipelines is different, but the overall change trend is similar, which can be calibrated by fitting through actual measured values. The technical solution of the embodiment of the present invention is to predict the f(t) through a recurrent neural network model, which takes into account the pipeline deformation factor, so that the pressure prediction result is more accurate and the prediction accuracy is improved.

[0088] It should be noted that the above-mentioned recurrent neural network model is only an example of an embodiment of the present invention. Pressure prediction can also be performed through other types of models, and the embodiment of the present invention does not impose too many restrictions on this.

[0089] In an embodiment of the present invention, the pressure detection method of the infusion pipeline includes: obtaining the speed and displacement of the infusion pump door when it starts and stops; calculating the vibration coefficient of the infusion pump door according to the speed and displacement; obtaining the concentration parameter of the flowing liquid in the infusion pipeline; obtaining the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door; inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into a recurrent neural network model to obtain a trained recurrent neural network model; inputting the vibration coefficient and concentration parameter of the new infusion pipeline into the trained recurrent neural network model to output the corresponding deformation pressure value; merging the deformation pressure value with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline, which not only considers the errors caused by different deformation characteristics of different infusion pipelines, but also considers the errors caused by the infusion pipeline changing over time, and also considers the errors caused each time the infusion pump door is opened or closed, which can significantly reduce the errors caused by these errors in the pressure sensor measuring the liquid pressure in the infusion pipeline, improve the pressure detection accuracy, make the pressure prediction result more accurate, improve the prediction accuracy, and thus improve the user's use safety. It should be noted that, for the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that this embodiment is not limited by the order of the actions described, because according to this embodiment, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by this embodiment.

[0090] Reference Figure 4 , shows a structural block diagram of an embodiment of a pressure detection device for an infusion pipeline of this embodiment, wherein the infusion pipeline is provided with an infusion pump door correspondingly, and specifically may include the following modules:

[0091] The first acquisition module 301 is used to acquire the speed and displacement of the infusion pump door when it starts and stops;

[0092] A vibration coefficient calculation module 302, used to calculate the vibration coefficient of the infusion pump door according to the speed and displacement;

[0093] A second acquisition module 303 is used to acquire the concentration parameter of the flowing liquid in the infusion pipeline;

[0094] A deformation pressure value module 304 is used to obtain the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door;

[0095] The training module 305 is used to input the vibration coefficient, concentration parameter and corresponding deformation pressure value into the recurrent neural network model to obtain a trained recurrent neural network model; the output module 306 is used to input the new vibration coefficient and concentration parameter of the infusion pipeline into the trained recurrent neural network model to output the corresponding deformation pressure value;

[0096] The merging module 307 is used to merge the deformation pressure value with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

[0097] Preferably, the infusion pump door is provided with an image sensor; the first acquisition module comprises:

[0098] A first acquisition submodule, used to acquire, through an image sensor, a first moving image when the infusion pump door is opened and a second moving image when the infusion pump door is stopped;

[0099] An extraction submodule, used for extracting pixel change positions of two infusion pump gates through the first moving image and the second moving image;

[0100] The first calculation submodule is used to calculate the displacement of the infusion pump door when starting and stopping according to the pixel change position of the two infusion pump doors.

[0101] Preferably, the infusion pump door is provided with an infrared sensor; the first acquisition module comprises:

[0102] A second acquisition submodule, used for acquiring, through the infrared sensor, a first position of the infusion pump door when it is opened, and a second position of the infusion pump door when it is stopped;

[0103] The second calculation submodule is used to calculate the speed of the infusion pump door when starting and stopping according to the first position and the second position. Preferably, the vibration coefficient calculation module includes:

[0104] A first vibration coefficient calculation submodule, used for inputting the speed into a preset function model to obtain a first vibration coefficient of the infusion pump door;

[0105] A second vibration coefficient calculation submodule, used for calculating a second vibration coefficient according to the displacement and the longitudinal length of the infusion pump door;

[0106] The addition calculation submodule is used to perform addition calculation according to a proportion on the first vibration coefficient and the second vibration coefficient to obtain a vibration coefficient.

[0107] Preferably, the recurrent neural network model includes an input layer, a hidden layer, an activation layer and an output layer; the training module includes:

[0108] A first input submodule is used to input the vibration coefficient, concentration parameter and corresponding deformation pressure value into the input layer of the recurrent neural network model to obtain a first eigenvector; and input the first eigenvector into the hidden layer to obtain a second eigenvector;

[0109] The third feature vector acquisition submodule is used to set the activation layer according to the vibration coefficient. The activation function corresponding to the activation layer is f=α / (γ+e -x ) ; wherein α represents the vibration coefficient, γ represents the number of categories; x represents the input of the function, and the second eigenvector is input to the set activation layer to obtain the third eigenvector; a training submodule is used to input the third eigenvector to the output layer, adjust the weights and biases of the recurrent neural network model, iterate back and forth until the model converges, complete the training of the recurrent neural network model, and obtain the trained recurrent neural network model.

[0110] Preferably, the infusion pump door, the infusion pipeline and the pressure sensor are arranged in sequence; the merging module includes:

[0111] The third acquisition submodule is used to obtain the basic pressure value of the infusion pipeline on the pressure sensor;

[0112] The addition submodule is used to add the basic pressure value and the deformation pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline. Each module in the pressure detection device of the infusion pipeline can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0113] The pressure detection device for the infusion pipeline provided above can be used to execute the pressure detection method for the infusion pipeline provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0114] In one embodiment, a computer device is provided, wherein the computer device includes a medical infusion device, and its internal structure diagram can be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a pressure detection device method for an infusion pipeline is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc. Those skilled in the art can understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the above embodiment are implemented:

[0116] Get the speed and displacement of the infusion pump door when it starts and stops;

[0117] Calculating the vibration coefficient of the infusion pump door according to the speed and displacement;

[0118] Obtaining concentration parameters of the flowing liquid in the infusion pipeline;

[0119] Obtaining a deformation pressure value of an infusion pipeline position corresponding to the infusion pump door;

[0120] Input the vibration coefficient, concentration parameter and corresponding deformation pressure value into the recurrent neural network model to obtain a trained recurrent neural network model; input the new vibration coefficient and concentration parameter of the infusion pipeline into the trained recurrent neural network model to output the corresponding deformation pressure value;

[0121] The deformation pressure value is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

[0122] Preferably, the infusion pump door is provided with an image sensor; the acquisition of the speed and displacement of the infusion pump door when starting and stopping includes:

[0123] Acquire, by means of an image sensor, a first moving image when the infusion pump door is opened and a second moving image when the infusion pump door is stopped;

[0124] Extracting pixel change positions of two infusion pump doors through the first moving image and the second moving image;

[0125] The displacement of the infusion pump door when starting and stopping is calculated through the pixel change positions of the two infusion pump doors.

[0126] Preferably, the infusion pump door is provided with an infrared sensor; the obtaining of the speed and displacement of the infusion pump door when starting and stopping includes:

[0127] The infrared sensor is used to obtain a first position of the infusion pump door when it is opened and a second position of the infusion pump door when it is stopped; and the speed of the infusion pump door when it is started and stopped is calculated based on the first position and the second position.

[0128] Preferably, the vibration coefficient of the infusion pump door is calculated according to the speed and displacement, including:

[0129] Inputting the speed into a preset function model to obtain a first vibration coefficient of the infusion pump door;

[0130] Calculating a second vibration coefficient according to the displacement and the longitudinal length of the infusion pump door;

[0131] The vibration coefficient is obtained by adding the first vibration coefficient and the second vibration coefficient in proportion. Preferably, the recurrent neural network model includes an input layer, a hidden layer, an activation layer and an output layer; the vibration coefficient, the concentration parameter and the corresponding deformation pressure value are input into the recurrent neural network model to obtain a trained recurrent neural network model, including:

[0132] Inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into the input layer of the recurrent neural network model to obtain a first eigenvector; inputting the first eigenvector into the hidden layer to obtain a second eigenvector;

[0133] The activation layer is set according to the vibration coefficient, and the activation function corresponding to the activation layer is f=α / (γ+e -x ), where α represents the vibration coefficient, γ represents the number of categories, x represents the input of the function, and the second eigenvector is input to the set activation layer to obtain the third eigenvector;

[0134] The third eigenvector is input into the output layer, the weight and bias of the recurrent neural network model are adjusted, and the training of the recurrent neural network model is completed until the model converges to obtain the trained recurrent neural network model.

[0135] Preferably, the infusion pump door, the infusion pipeline and the pressure sensor are arranged in sequence; the deformation pressure value is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline, including:

[0136] Obtain the basic pressure value of the infusion pipeline on the pressure sensor;

[0137] The basic pressure value of the infusion pipeline is added to the deformation pressure value to obtain the total pressure value of the infusion pipeline. In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above embodiment are implemented:

[0138] Get the speed and displacement of the infusion pump door when it starts and stops;

[0139] Calculating the vibration coefficient of the infusion pump door according to the speed and displacement;

[0140] Obtaining concentration parameters of the flowing liquid in the infusion pipeline;

[0141] Obtaining a deformation pressure value of an infusion pipeline position corresponding to the infusion pump door;

[0142] Inputting the vibration coefficient, concentration parameter and corresponding deformation pressure value into a recurrent neural network model to obtain a trained recurrent neural network model;

[0143] The new vibration coefficient and concentration parameters of the infusion pipeline are input into the trained recurrent neural network model, and the corresponding deformation pressure value is output; the deformation pressure value is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

[0144] Preferably, the infusion pump door is provided with an image sensor; the acquisition of the speed and displacement of the infusion pump door when starting and stopping includes:

[0145] Acquire, by means of an image sensor, a first moving image when the infusion pump door is opened and a second moving image when the infusion pump door is stopped;

[0146] Extracting pixel change positions of two infusion pump doors through the first moving image and the second moving image;

[0147] The displacement of the infusion pump door when starting and stopping is calculated through the pixel change positions of the two infusion pump doors.

[0148] Preferably, the infusion pump door is provided with an infrared sensor; the obtaining of the speed and displacement of the infusion pump door when starting and stopping includes:

[0149] The infrared sensor is used to obtain a first position of the infusion pump door when it is opened and a second position of the infusion pump door when it is stopped; and the speed of the infusion pump door when it is started and stopped is calculated based on the first position and the second position.

[0150] Preferably, the vibration coefficient of the infusion pump door is calculated according to the speed and displacement, including:

[0151] Inputting the speed into a preset function model to obtain a first vibration coefficient of the infusion pump door;

[0152] Calculating a second vibration coefficient according to the displacement and the longitudinal length of the infusion pump door;

[0153] The vibration coefficient is obtained by adding the first vibration coefficient and the second vibration coefficient in proportion.

[0154] Preferably, the recurrent neural network model comprises an input layer, a hidden layer, an activation layer and an output layer; the vibration coefficient, the concentration parameter and the corresponding deformation pressure value are input into the recurrent neural network model to obtain a trained recurrent neural network model, comprising:

[0155] The vibration coefficient, concentration parameter and corresponding deformation pressure value are input into the input layer of the recurrent neural network model to obtain the first eigenvector; the first eigenvector is input into the hidden layer to obtain the second eigenvector; the activation layer is set according to the vibration coefficient, and the activation function corresponding to the activation layer is f=α / (γ+e -x ) ; where α represents the vibration coefficient, γ represents the number of categories; x represents the input of the function, and the second eigenvector is input to the set activation layer to obtain the third eigenvector;

[0156] The third eigenvector is input into the output layer, the weight and bias of the recurrent neural network model are adjusted, and the training of the recurrent neural network model is completed until the model converges to obtain the trained recurrent neural network model.

[0157] Preferably, the infusion pump door, the infusion pipeline and the pressure sensor are arranged in sequence; the deformation pressure value is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline, including:

[0158] Obtain the basic pressure value of the infusion pipeline on the pressure sensor;

[0159] The basic pressure value of the infusion pipeline is added to the deformation pressure value to obtain the total pressure value of the infusion pipeline. Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can be referred to each other.

[0160] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0161] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing terminal device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0163] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention. Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements. The above is a detailed introduction to a pressure detection method for an infusion pipeline, a pressure detection device for an infusion pipeline, a computer device and a computer-readable storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for detecting pressure of an infusion pipeline, characterized in that: The infusion pipeline is correspondingly provided with an infusion pump door, and the method comprises: Get the speed and displacement of the infusion pump door when it starts and stops; Calculating the vibration coefficient of the infusion pump door according to the speed and displacement; Obtaining concentration parameters of the flowing liquid in the infusion pipeline; The deformation pressure value of the infusion line position corresponding to the infusion pump door is obtained; the deformation pressure value is a sample value measured by a higher-precision pressure sensor under different concentration parameters and vibration coefficient conditions; Inputting the vibration coefficient, the concentration parameter and the corresponding deformation pressure value measured by the pressure sensor into the recurrent neural network model to obtain a trained recurrent neural network model; Inputting new vibration coefficient and concentration parameters of the infusion pipeline into the trained recurrent neural network model, and outputting corresponding deformation pressure values; The deformation pressure value corresponding to the new vibration system and concentration parameters of the infusion pipeline output by the recurrent neural network is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

2. The pressure detection method of the infusion pipeline according to claim 1, characterized in that: The infusion pump door is provided with an image sensor; the speed and displacement of the infusion pump door when starting and stopping are obtained, including: Acquire, by means of an image sensor, a first moving image when the infusion pump door is opened and a second moving image when the infusion pump door is stopped; Extracting pixel change positions of two infusion pump doors through the first moving image and the second moving image; The displacement of the infusion pump door when starting and stopping is calculated through the pixel change positions of the two infusion pump doors.

3. The pressure detection method of the infusion pipeline according to claim 1, characterized in that: The infusion pump door is provided with an infrared sensor; the speed and displacement of the infusion pump door when starting and stopping are obtained, including: Acquire, by means of the infrared sensor, a first position of the infusion pump door when it is opened, and a second position of the infusion pump door when it is stopped; The speed of the infusion pump door when starting and stopping is calculated according to the first position and the second position.

4. The pressure detection method of the infusion pipeline according to claim 1, characterized in that: The step of calculating the vibration coefficient of the infusion pump door according to the speed and displacement includes: Inputting the speed into a preset function model to obtain a first vibration coefficient of the infusion pump door; Calculating a second vibration coefficient according to the displacement and the longitudinal length of the infusion pump door; The vibration coefficient is obtained by adding the first vibration coefficient and the second vibration coefficient in proportion.

5. The pressure detection method of the infusion pipeline according to claim 1, characterized in that: The recurrent neural network model includes an input layer, a hidden layer, an activation layer and an output layer; the vibration coefficient, the concentration parameter and the corresponding deformation pressure value measured by the pressure sensor are input into the recurrent neural network model to obtain a trained recurrent neural network model, including: Input the vibration coefficient, concentration parameter and the corresponding deformation pressure value measured by the pressure sensor into the input layer of the recurrent neural network model to obtain a first eigenvector; input the first eigenvector into the hidden layer to obtain a second eigenvector; The activation layer is set according to the vibration coefficient, and the activation function corresponding to the activation layer is f=α / (γ+e -x ) ; where α represents the vibration coefficient, γ represents the number of categories; x represents the input of the function, and the second eigenvector is input to the set activation layer to obtain the third eigenvector; The third eigenvector is input into the output layer, the weight and bias of the recurrent neural network model are adjusted, and the training of the recurrent neural network model is completed until the model converges to obtain the trained recurrent neural network model.

6. The pressure detection method of the infusion pipeline according to claim 1, characterized in that: The infusion pump door, the infusion pipeline and the pressure sensor are arranged in sequence; the deformation pressure value corresponding to the new vibration system and concentration parameter of the infusion pipeline output by the recurrent neural network is combined with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline, including: Obtain the basic pressure value of the infusion pipeline on the pressure sensor; The basic pressure value of the infusion pipeline is added to the deformation pressure value corresponding to the new vibration system and concentration parameters of the infusion pipeline output by the recurrent neural network to obtain the total pressure value of the infusion pipeline.

7. A pressure detection device for an infusion pipeline, characterized in that: The infusion pipeline is correspondingly provided with an infusion pump door, and the device comprises: The first acquisition module is used to acquire the speed and displacement of the infusion pump door when it starts and stops; A vibration coefficient calculation module, used to calculate the vibration coefficient of the infusion pump door according to the speed and displacement; A second acquisition module, used to acquire the concentration parameter of the flowing liquid in the infusion pipeline; A deformation pressure value module is used to obtain the deformation pressure value of the infusion pipeline position corresponding to the infusion pump door; the deformation pressure value is a sample value measured by a higher-precision pressure sensor under different concentration parameters and vibration coefficient conditions; A training module, used for inputting the vibration coefficient, the concentration parameter and the corresponding deformation pressure value measured by the pressure sensor into the recurrent neural network model to obtain a trained recurrent neural network model; An output module, used to input the new vibration coefficient and concentration parameters of the infusion pipeline into the trained recurrent neural network model, and output the corresponding deformation pressure value; The merging module is used to merge the deformation pressure value corresponding to the new vibration system and concentration parameters of the infusion pipeline output by the recurrent neural network with the basic pressure value of the infusion pipeline to obtain the total pressure value of the infusion pipeline.

8. The pressure detection device for an infusion pipeline according to claim 7, characterized in that: The infusion pump door is provided with an image sensor; the first acquisition module comprises: A first acquisition submodule, used to acquire, through an image sensor, a first moving image when the infusion pump door is opened and a second moving image when the infusion pump door is stopped; An extraction submodule, used to extract pixel change positions of two infusion pump doors through the first moving image and the second moving image; The first calculation submodule is used to calculate the displacement of the infusion pump door when starting and stopping according to the pixel change position of the two infusion pump doors.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for detecting pressure of an infusion pipeline according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting pressure of an infusion pipeline according to any one of claims 1 to 6 are implemented.

Images