A method and system for controlling the transfer of critically ill pregnant women based on artificial intelligence

Abstract

This invention provides an artificial intelligence-based method and system for controlling the transport of critically ill pregnant women. The method includes: acquiring the operational status characteristics of the transport vehicle; matching the operational status characteristics with the equipment monitoring status of the critically ill pregnant woman user to obtain multiple equipment delay times; constructing an equipment transport optimization model using the equipment delay times; adjusting the hyperparameters of the equipment transport optimization model using an optimization function, and iterating the model until convergence using historical data to obtain a trained equipment transport optimization model; inputting the operational status characteristics and original monitoring data into the trained equipment transport optimization model to obtain output correction information; correcting the original monitoring data based on the correction information and outputting corrected monitoring data; and then performing dual optimization using a Bayesian optimization algorithm and a whale optimization algorithm to obtain the optimal solution, thereby improving the accuracy of equipment operation and ensuring the safety of personnel transport.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to an artificial intelligence-based method for controlling the transfer of critically ill pregnant women, an artificial intelligence-based control system for the transfer of critically ill pregnant women, a computer device, and a storage medium. Background Technology

[0002] Maternal transport refers to the process of transferring pregnant or postpartum women from one medical facility to another, usually to obtain higher-level medical support or to deal with sudden complications.

[0003] For the transport of critically ill pregnant women, it is even more important to pay attention to their vital signs. Continuous monitoring of the mother's blood pressure, heart rate, blood oxygen, and fetal heart rate is necessary on the transport vehicle. Intravenous access must be maintained, and blood transfusions or fluid replacements should be administered when necessary. Prevention of vomiting or aspiration is crucial (head turned to one side, with a suction device readily available). Although the instruments have motion compensation algorithms, the operation of the monitoring instruments for critically ill pregnant women can still have some impact on the operation of the instruments, such as affecting the accuracy of the data. The safety of each critically ill pregnant woman is an urgent issue that needs to be addressed. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide an artificial intelligence-based method for controlling the transfer of critically ill pregnant women, an artificial intelligence-based control system for the transfer of critically ill pregnant women, a computer device, and a storage medium to overcome or at least partially solve the above problems.

[0005] To address the aforementioned problems, this invention discloses an artificial intelligence-based method for controlling the transfer of critically ill pregnant women, comprising:

[0006] Obtain the operational status characteristics of the transfer vehicle;

[0007] The operational status characteristics are matched with the device monitoring status of critically ill pregnant women to obtain multiple device delay times; among them, the device parameter delay times include fetal heart rate device delay time, blood oxygen device delay time, and blood pressure device delay time.

[0008] An equipment transport optimization model was constructed based on the delay times of the fetal heart rate device, the blood oxygen device, and the blood pressure device.

[0009] The hyperparameters of the equipment transfer optimization model are adjusted using an optimization function, and the model is iterated until convergence using historical data to obtain the trained equipment transfer optimization model.

[0010] The operating status characteristics of the new transfer vehicle and the original monitoring operation data are input into the trained equipment transfer optimization model to obtain the output correction information.

[0011] The original monitoring operation data is corrected based on the correction information, and the corrected monitoring operation data is output.

[0012] Preferably, the first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized;

[0013] The second constraint of the equipment transfer optimization model is that the delay time of the fetal heart rate device is less than the first preset delay threshold; the delay time of the blood oxygen device is less than the second preset delay threshold; and the delay time of the blood oxygen device is less than the third preset delay threshold.

[0014] Preferably, the step of matching the operational status characteristics with the device monitoring status of critically ill pregnant women to obtain multiple device delay times includes:

[0015] The operating status characteristics include uphill status, downhill status, emergency braking status, and speed bump status.

[0016] The change in the valley value of the signal spectrum of the device in the uphill state, downhill state, emergency braking state, and speed bump state is obtained.

[0017] Based on the changes in the valley values ​​of the signal spectrum, cluster analysis of device data was performed to obtain data on multiple abnormal device categories.

[0018] The abnormal device data is compared with a threshold to obtain specific device data, and the specific device data is converted into device delay time.

[0019] Preferably, the step of constructing an equipment transport optimization model based on the delay times of the fetal heart rate monitoring device, the blood oxygen monitoring device, and the blood pressure monitoring device includes:

[0020] We obtained fetal heart rate data at multiple times, blood pressure data at multiple times, and the probability of developing hypertension.

[0021] The fetal heart rate data, blood pressure data, probability of hypertension, and delay times of fetal heart rate equipment, blood oxygenation equipment, and blood pressure equipment were used to construct an equipment transport optimization model.

[0022] Preferably, the step of adjusting the hyperparameters of the equipment transfer optimization model using an optimization function and iterating the equipment transfer optimization model until convergence using historical data to obtain the trained equipment transfer optimization model includes:

[0023] Within the domain, determine several initial points for the Bayesian optimization algorithm;

[0024] The probability model of the equipment transfer optimization model is determined by the initial point, the probability of the optimal solution is calculated, and the next candidate data point is obtained.

[0025] The optimal solution of the equipment transfer optimization model at this point is evaluated and added to the observation dataset. When predicting the number of iterations, the equipment transfer optimization model is determined to be iterated until convergence, thus obtaining the trained equipment transfer optimization model.

[0026] Preferably, the method further includes:

[0027] The optimal solution is determined as the initial random solution. The initial parameters of the whale optimization algorithm are set, the fitness value of each solution is calculated, the current optimal whale individual and position are determined, and the whale individual performs random search, or randomly selects shrinking encirclement or spiral update method to update its position until the number of iterations is greater than a preset threshold. The second optimal solution is then output and added to the observation dataset.

[0028] This invention discloses an artificial intelligence-based transport control system for critically ill pregnant women, comprising:

[0029] The operational status feature module is used to obtain the operational status features of the transfer vehicle;

[0030] The matching module is used to match the operating status characteristics with the device monitoring status of critically ill pregnant women to obtain multiple device delay times; wherein, the device parameter delay times include fetal heart rate device delay time, blood oxygen device delay time, and blood pressure device delay time;

[0031] The module is used to construct an equipment transport optimization model based on the delay time of the fetal heart rate device, the delay time of the blood oxygen device, and the delay time of the blood pressure device.

[0032] The iterative module is used to adjust the hyperparameters of the equipment transfer optimization model using the optimization function, and to iterate the equipment transfer optimization model until convergence using historical data, thereby obtaining the trained equipment transfer optimization model.

[0033] The input module is used to input the operating status characteristics of the new transfer vehicle and the original monitoring operation data into the trained equipment transfer optimization model to obtain the output correction information.

[0034] The calibration module is used to calibrate the original monitoring operation data according to the calibration information and output the calibrated monitoring operation data.

[0035] Preferably, the first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized;

[0036] The second constraint of the equipment transfer optimization model is that the delay time of the fetal heart rate device is less than the first preset delay threshold; the delay time of the blood oxygen device is less than the second preset delay threshold; and the delay time of the blood oxygen device is less than the third preset delay threshold.

[0037] This invention also discloses a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described steps of artificial intelligence-based transfer control of critically ill pregnant women.

[0038] This invention also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described steps of artificial intelligence-based transfer control for critically ill pregnant women.

[0039] The embodiments of the present invention have the following advantages:

[0040] In this embodiment of the invention, the AI-based method for controlling the transport of critically ill pregnant women includes: acquiring the operational status characteristics of the transport vehicle; matching the operational status characteristics with the equipment monitoring status of the critically ill pregnant woman user to obtain multiple equipment delay times; wherein, the equipment parameter delay times include fetal heart rate equipment delay time, blood oxygenation equipment delay time, and blood pressure equipment delay time; constructing an equipment transport optimization model using the fetal heart rate equipment delay time, blood oxygenation equipment delay time, and blood pressure equipment delay time; adjusting the hyperparameters of the equipment transport optimization model using an optimization function, and iterating the equipment transport optimization model until convergence using historical data to obtain a trained equipment transport optimization model; inputting the new operational status characteristics of the transport vehicle and the original monitoring operation data into the trained equipment transport optimization model to obtain output correction information; correcting the original monitoring operation data according to the correction information, and outputting the corrected monitoring operation data; and then performing dual optimization using a Bayesian optimization algorithm and a whale optimization algorithm to obtain the optimal solution, thereby correcting the delay time of the critically ill pregnant woman vital sign monitoring equipment on the transport vehicle using an AI algorithm, improving the accuracy of equipment operation, and ensuring the safety of personnel transport. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1This is a flowchart illustrating the steps of an embodiment of an artificial intelligence-based method for controlling the transfer of critically ill pregnant women according to the present invention.

[0043] Figure 2 This is a structural block diagram of an embodiment of an artificial intelligence-based critical maternal transport control system according to the present invention.

[0044] Figure 3 This is an internal structural diagram of a computer device according to one embodiment. Detailed Implementation

[0045] To make the technical problems, technical solutions, and beneficial effects solved by the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0046] In this embodiment of the invention, by matching the state of the transport vehicle with the monitoring state of the equipment, an equipment transport optimization model is obtained. Then, a dual optimization solution is performed using Bayesian optimization algorithm and whale optimization algorithm to obtain a trained equipment transport optimization model. The operating status characteristics of the new transport vehicle and the original monitoring operation data are input into the trained equipment transport optimization model to obtain the output correction information. The original monitoring operation data is corrected according to the correction information, and the corrected monitoring operation data is output. The delay time of the critically ill pregnant women's vital signs monitoring equipment on the transport vehicle is corrected using artificial intelligence algorithm, which improves the accuracy of equipment operation and ensures the safety of personnel transport.

[0047] Reference Figure 1 The diagram illustrates a flowchart of an embodiment of an artificial intelligence-based method for controlling the transfer of critically ill pregnant women according to the present invention, which may specifically include the following steps:

[0048] Step 101: Obtain the operational status characteristics of the transfer vehicle;

[0049] The transfer control method in this embodiment of the invention can be applied to a terminal, which can be, but is not limited to, various personal computers, laptops, smartphones, tablets and portable wearable devices. This embodiment of the invention does not limit the specific type of terminal. The operating system of the terminal can include Android, Harmony OS, iOS, Windows Phone, Windows, etc. This invention does not impose too many restrictions on this. The transfer vehicle can be an ambulance.

[0050] Specifically, in the embodiments of the present invention, the operating state feature can be the change feature in the vehicle direction corresponding to the uphill state, downhill state, emergency braking state, and speed bump state. Of course, the above-mentioned operating state features are only a few examples in the embodiments of the present invention, and the embodiments of the present invention do not impose too many restrictions on them.

[0051] Step 102: Match the operating status characteristics with the equipment monitoring status of the critically ill pregnant women to obtain multiple equipment delay times; wherein, the equipment parameter delay times include the delay time of the fetal heart rate equipment, the delay time of the blood oxygen equipment, and the delay time of the blood pressure equipment.

[0052] In this embodiment of the invention, the vital signs monitoring equipment for the critically ill pregnant woman may include a fetal heart monitor, a multi-parameter monitor that monitors heart rate, respiratory rate, non-invasive blood pressure (NBP), blood oxygen saturation (SpO2), body temperature, etc., and a fetal ultrasound machine. This embodiment of the invention does not impose too many restrictions on the types of equipment.

[0053] Accordingly, the delay time of the fetal heart rate monitoring device can refer to the time information such as the calculation delay, display delay, and transmission delay of the fetal heart rate monitoring device; the delay time of the blood oxygen monitoring device can refer to the time information such as the calculation delay, display delay, and transmission delay of the blood oxygen monitoring device; and the delay time of the blood pressure monitoring device can refer to the time information such as the calculation delay, display delay, and transmission delay of the blood pressure monitoring device.

[0054] Specifically, in this embodiment of the invention, the step of matching the operating status characteristics with the device monitoring status of critically ill pregnant women to obtain multiple device delay times includes:

[0055] The operating status characteristics include uphill status, downhill status, emergency braking status, and speed bump status.

[0056] The change in the valley value of the signal spectrum of the device in the uphill state, downhill state, emergency braking state, and speed bump state is obtained.

[0057] Based on the changes in the valley values ​​of the signal spectrum, cluster analysis of device data was performed to obtain data on multiple abnormal device categories.

[0058] The abnormal device data is compared with a threshold to obtain specific device data, and the specific device data is converted into device delay time.

[0059] Specifically, in this embodiment of the invention, the change in the valley value of the signal spectrum refers to the difference between the peaks and valleys of the signal spectrum characteristic of the operating state, which can be expressed as v = {χ1,χ2,χ3,χ4,χ5,……,χ}. iWhere i = 1, 2, 3, ..., n, and n is a positive integer, the changes in the valley values ​​of the signal spectrum are subjected to cluster analysis. Cluster analysis can include various methods such as K-means algorithm, K-medoids algorithm, hierarchical clustering algorithm, and DBSCAN algorithm. This embodiment of the invention does not impose too many restrictions on the cluster analysis method, resulting in multiple types of changes in the valley values ​​of the signal spectrum, v = {v1, v2, v3, v4, v5, ..., v}. d}, where d represents the number of types, d = 1, 2, 3, ..., n, where n is a positive integer. For example, v1 can be a set of χ1, χ2, χ3. First, the changes in the valley values ​​of the signal spectrum of these multiple types can be preliminarily filtered to obtain abnormal device data. Then, by setting a threshold, specific type of device data that meets the threshold can be filtered out. The specific type of device data can then be converted into device delay time T in the following way: T = 1 / F, where F refers to the average value of the changes in the valley values ​​of the signal spectrum.

[0060] Step 103: Construct an equipment transport optimization model based on the delay time of the fetal heart rate device, the delay time of the blood oxygen device, and the delay time of the blood pressure device;

[0061] Further applied to embodiments of the present invention, after obtaining the delay time of the fetal heart rate device, the delay time of the blood oxygen device, and the delay time of the blood pressure device, an equipment transport optimization model can be constructed based on the delay time of the fetal heart rate device, the delay time of the blood oxygen device, and the delay time of the blood pressure device.

[0062] Specifically, in this embodiment of the invention, the construction of the equipment transport optimization model based on the delay time of the fetal heart rate device, the delay time of the blood oxygen device, and the delay time of the blood pressure device includes:

[0063] We obtained fetal heart rate data at multiple times, blood pressure data at multiple times, and the probability of hypertension in critically ill pregnant women.

[0064] The fetal heart rate data, blood pressure data, probability of hypertension, and delay times of fetal heart rate equipment, blood oxygenation equipment, and blood pressure equipment were used to construct an equipment transport optimization model.

[0065] The objective function of the equipment transfer optimization model can be expressed as m = min{δR}. D ,κU,ρG};where, R D U represents the delay time of the fetal heart rate monitoring device, G represents the delay time of the blood oxygen monitoring device, and δ represents the correction factor corresponding to the fetal heart rate data at a certain moment. The correction factor is calculated as follows: in, Represented as a smoothing coefficient, its value ranges from 0 to 1, dt Let d represent the fetal heart rate data at time t. t-1 The fetal heart rate data at time t-1 is represented by σ, which represents the historical standard deviation of the fetal heart rate data.

[0066] κ represents the correction factor for blood pressure data at a certain moment. This correction factor is calculated as follows: κ = BP t +(β1η+β2λ+β3θ), where β1, β2, and β3 represent preset regression coefficients, which are pre-set by BP. t Let t represent the blood pressure data at time t, η represent age, λ represent the sex coefficient (where female is represented by 1 and male by 2), θ represent the pregnancy coefficient (including early pregnancy, mid pregnancy, and late pregnancy, where early pregnancy is represented by 1, mid pregnancy by 2, and late pregnancy by 3), and ρ represent the probability of developing hypertension.

[0067] The equipment transfer optimization model can be an LTSM model, which can be composed of multiple input layers, multiple convolutional layers and / or multiple pooling layers and / or multiple fully connected layers and / or multiple output layers. This embodiment of the invention does not impose too many restrictions on the type and composition of the equipment transfer optimization model.

[0068] In a preferred embodiment of the present invention, the first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized.

[0069] The second constraint of the equipment transfer optimization model is to ensure that the delay time of the fetal heart rate device is less than the first preset delay threshold; the delay time of the blood oxygen device is less than the second preset delay threshold; and the delay time of the blood oxygen device is less than the third preset delay threshold.

[0070] The first, second, and third delay preset thresholds can be any values ​​set by those skilled in the art based on actual circumstances, and the embodiments of the present invention do not impose excessive restrictions on them.

[0071] Step 104: Adjust the hyperparameters of the equipment transfer optimization model using the optimization function, and iterate the equipment transfer optimization model until convergence using historical data to obtain the trained equipment transfer optimization model.

[0072] In a further embodiment of the present invention, the historical data may include operating status characteristics, original monitoring operating data and correction information. The historical data may be divided into a training set and a test set. The training set is a dataset used to train the equipment transfer optimization model, and the test set is a dataset used to test the equipment transfer optimization model. The original monitoring operating data refers to the signal data generated by various vital sign monitoring devices.

[0073] In this embodiment of the invention, the optimization function refers to a dual optimization algorithm combining Bayesian optimization algorithm and whale optimization algorithm. The optimal solution of Bayesian optimization algorithm is used as the random initial solution of whale optimization algorithm. Random search, or random selection of shrinking encirclement or spiral update method to update the position is performed until the number of iterations is greater than a preset threshold. The second optimal solution is then output and used as a hyperparameter, which improves the model training effect.

[0074] Specifically, the step of adjusting the hyperparameters of the equipment transfer optimization model using an optimization function and iterating the model until convergence using historical data to obtain the trained equipment transfer optimization model includes:

[0075] Within the domain, determine several initial points for the Bayesian optimization algorithm;

[0076] The probability model of the equipment transfer optimization model is determined by the initial point, the probability of the optimal solution is calculated, and the next candidate data point is obtained.

[0077] The optimal solution of the equipment transfer optimization model at this point is evaluated and added to the observation dataset. When predicting the number of iterations, the equipment transfer optimization model is determined to be iterated until convergence, thus obtaining the trained equipment transfer optimization model.

[0078] In a further embodiment of the present invention, the method further includes: determining the optimal solution as an initial random solution, setting the initial parameters of the whale optimization algorithm, calculating the fitness value of each solution, determining the current optimal whale individual and position, updating the position of the whale individual by random search, or by randomly selecting shrinking encirclement or spiral update method, until the number of iterations is greater than a preset threshold, outputting the second optimal solution, and adding the second optimal solution to the observation dataset.

[0079] Specifically, Bayesian optimization is a directed acyclic graph where nodes represent random variables in different experiments, and paths between nodes represent causal relationships between multiple variables. It effectively measures the relationships between nodes in the network. Because hyperparameters are interconnected, Bayesian networks can be used to determine if the model can achieve optimal training results. However, training speed can slow down when dealing with complex models. Further optimization using the whale optimization algorithm can improve the model's convergence speed and global and local search capabilities, thereby achieving both effective and fast model training.

[0080] Step 105: Input the operating status characteristics of the new transfer vehicle and the original monitoring operation data into the trained equipment transfer optimization model to obtain the output correction information;

[0081] In a further embodiment of the present invention, after obtaining the trained equipment transfer optimization model, the operating status characteristics of the new transfer vehicle and the original monitoring operation data can be input into the trained equipment transfer optimization model to obtain the output correction information.

[0082] Step 106: Correct the original monitoring operation data according to the correction information, and output the corrected monitoring operation data.

[0083] Specifically, the correction information is compared with the original monitoring data of the vital signs monitoring equipment to output the corrected monitoring data, which is the filtered and accurate data, avoiding data errors and ensuring the safety of personnel transfer.

[0084] In this embodiment of the invention, the AI-based method for controlling the transport of critically ill pregnant women includes: acquiring the operational status characteristics of the transport vehicle; matching the operational status characteristics with the equipment monitoring status of the critically ill pregnant woman user to obtain multiple equipment delay times; wherein, the equipment parameter delay times include fetal heart rate equipment delay time, blood oxygenation equipment delay time, and blood pressure equipment delay time; constructing an equipment transport optimization model using the fetal heart rate equipment delay time, blood oxygenation equipment delay time, and blood pressure equipment delay time; adjusting the hyperparameters of the equipment transport optimization model using an optimization function, and iterating the equipment transport optimization model until convergence using historical data to obtain a trained equipment transport optimization model; inputting the new operational status characteristics of the transport vehicle and the original monitoring operation data into the trained equipment transport optimization model to obtain output correction information; correcting the original monitoring operation data according to the correction information, and outputting the corrected monitoring operation data; and then performing dual optimization using a Bayesian optimization algorithm and a whale optimization algorithm to obtain the optimal solution, thereby correcting the delay time of the critically ill pregnant woman vital sign monitoring equipment on the transport vehicle using an AI algorithm, improving the accuracy of equipment operation, and ensuring the safety of personnel transport.

[0085] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0086] Reference Figure 2 The diagram illustrates a structural block diagram of an embodiment of an artificial intelligence-based critical maternal transport control system according to the present invention, which may specifically include the following modules:

[0087] The operation status feature module 301 is used to acquire the operation status features of the transfer vehicle;

[0088] The matching module 302 is used to match the operating status characteristics with the device monitoring status of the critically ill pregnant women to obtain multiple device delay times; wherein, the device parameter delay times include fetal heart rate device delay time, blood oxygen device delay time, and blood pressure device delay time.

[0089] Module 303 is used to construct an equipment transport optimization model based on the delay time of the fetal heart rate device, the delay time of the blood oxygen device, and the delay time of the blood pressure device.

[0090] The iteration module 304 is used to adjust the hyperparameters of the equipment transfer optimization model using the optimization function, and to iterate the equipment transfer optimization model until convergence using historical data to obtain the trained equipment transfer optimization model.

[0091] The input module 305 is used to input the operating status characteristics of the new transfer vehicle and the original monitoring operation data into the trained equipment transfer optimization model to obtain the output correction information.

[0092] The correction module 306 is used to correct the original monitoring operation data according to the correction information and output the corrected monitoring operation data.

[0093] Preferably, the first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized;

[0094] The second constraint of the equipment transfer optimization model is that the delay time of the fetal heart rate device is less than the first preset delay threshold; the delay time of the blood oxygen device is less than the second preset delay threshold; and the delay time of the blood oxygen device is less than the third preset delay threshold.

[0095] Preferably, the matching module includes:

[0096] The operating status characteristics include uphill status, downhill status, emergency braking status, and speed bump status.

[0097] The first acquisition submodule is used to acquire the change in the signal spectrum valley value of the device in the uphill state, downhill state, emergency braking state, and speed bump state.

[0098] The clustering analysis submodule is used to perform device data clustering analysis based on the change in the valley value of the signal spectrum, and obtain multiple abnormal device data.

[0099] The threshold comparison submodule is used to perform threshold comparison on the abnormal device data to obtain specific device data, and convert the specific device data into device delay time.

[0100] Preferably, the building module includes:

[0101] The second acquisition submodule is used to acquire fetal heart rate data at multiple times, blood pressure data at multiple times, and the probability of hypertension.

[0102] A submodule is constructed to build an equipment transport optimization model based on the fetal heart rate data, blood pressure data, probability of hypertension, and delay times of the fetal heart rate device, blood oxygen device, and blood pressure device.

[0103] Preferably, the iteration module includes:

[0104] The determination submodule is used to determine several initial points for the Bayesian optimization algorithm within the defined domain;

[0105] The calculation submodule is used to determine the probability model of the equipment transfer optimization model through the initial point, calculate the probability of the optimal solution, and obtain the next candidate data point;

[0106] A submodule is added to evaluate the optimal solution of the equipment transfer optimization model at this point and add the optimal solution to the observation dataset; when predicting the number of iterations, the equipment transfer optimization model is determined to be iterated until convergence, and the trained equipment transfer optimization model is obtained.

[0107] Preferably, the system further includes:

[0108] The output module is used to determine that the optimal solution is the initial random solution, set the initial parameters of the whale optimization algorithm, calculate the fitness value of each solution, determine the current optimal whale individual and position, and update the position of the whale individual by random search, or by randomly selecting shrinking encirclement or spiral update method until the number of iterations is greater than a preset threshold, output the second optimal solution, and add the second optimal solution to the observation dataset.

[0109] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0110] Specific limitations regarding the AI-based critical maternal transport control system can be found in the above section on the limitations of AI-based critical maternal transport control methods, and will not be repeated here. Each module in the aforementioned AI-based critical maternal transport control system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, allowing the processor to call and execute the corresponding operations of each module.

[0111] The artificial intelligence-based critical maternal transport control system provided above can be used to execute the artificial intelligence-based critical maternal transport control method provided in any of the above embodiments, and has the corresponding functions and beneficial effects.

[0112] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements an artificial intelligence-based method for controlling the transfer of critically ill pregnant women. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0113] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0115] Obtain the operational status characteristics of the transfer vehicle;

[0116] The operational status characteristics are matched with the device monitoring status of critically ill pregnant women to obtain multiple device delay times; among them, the device parameter delay times include fetal heart rate device delay time, blood oxygen device delay time, and blood pressure device delay time.

[0117] An equipment transport optimization model was constructed based on the delay times of the fetal heart rate device, the blood oxygen device, and the blood pressure device.

[0118] The hyperparameters of the equipment transfer optimization model are adjusted using an optimization function, and the model is iterated until convergence using historical data to obtain the trained equipment transfer optimization model.

[0119] The operating status characteristics of the new transfer vehicle and the original monitoring operation data are input into the trained equipment transfer optimization model to obtain the output correction information.

[0120] The original monitoring operation data is corrected based on the correction information, and the corrected monitoring operation data is output.

[0121] Preferably, the first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized;

[0122] The second constraint of the equipment transfer optimization model is that the delay time of the fetal heart rate device is less than the first preset delay threshold; the delay time of the blood oxygen device is less than the second preset delay threshold; and the delay time of the blood oxygen device is less than the third preset delay threshold.

[0123] Preferably, the step of matching the operational status characteristics with the device monitoring status of critically ill pregnant women to obtain multiple device delay times includes:

[0124] The operating status characteristics include uphill status, downhill status, emergency braking status, and speed bump status.

[0125] The change in the valley value of the signal spectrum of the device in the uphill state, downhill state, emergency braking state, and speed bump state is obtained.

[0126] Based on the changes in the valley values ​​of the signal spectrum, cluster analysis of device data was performed to obtain data on multiple abnormal device categories.

[0127] The abnormal device data is compared with a threshold to obtain specific device data, and the specific device data is converted into device delay time.

[0128] Preferably, the step of constructing an equipment transport optimization model based on the delay times of the fetal heart rate monitoring device, the blood oxygen monitoring device, and the blood pressure monitoring device includes:

[0129] We obtained fetal heart rate data at multiple times, blood pressure data at multiple times, and the probability of developing hypertension.

[0130] The fetal heart rate data, blood pressure data, probability of hypertension, and delay times of fetal heart rate equipment, blood oxygenation equipment, and blood pressure equipment were used to construct an equipment transport optimization model.

[0131] Preferably, the step of adjusting the hyperparameters of the equipment transfer optimization model using an optimization function and iterating the equipment transfer optimization model until convergence using historical data to obtain the trained equipment transfer optimization model includes:

[0132] Within the domain, determine several initial points for the Bayesian optimization algorithm;

[0133] The probability model of the equipment transfer optimization model is determined by the initial point, the probability of the optimal solution is calculated, and the next candidate data point is obtained.

[0134] The optimal solution of the equipment transfer optimization model at this point is evaluated and added to the observation dataset. When predicting the number of iterations, the equipment transfer optimization model is determined to be iterated until convergence, thus obtaining the trained equipment transfer optimization model.

[0135] Preferably, the method further includes:

[0136] The optimal solution is determined as the initial random solution. The initial parameters of the whale optimization algorithm are set, the fitness value of each solution is calculated, the current optimal whale individual and position are determined, and the whale individual performs random search, or randomly selects shrinking encirclement or spiral update method to update its position until the number of iterations is greater than a preset threshold. The second optimal solution is then output and added to the observation dataset.

[0137] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0138] Obtain the operational status characteristics of the transfer vehicle;

[0139] The operational status characteristics are matched with the device monitoring status of critically ill pregnant women to obtain multiple device delay times; among them, the device parameter delay times include fetal heart rate device delay time, blood oxygen device delay time, and blood pressure device delay time.

[0140] An equipment transport optimization model was constructed based on the delay times of the fetal heart rate device, the blood oxygen device, and the blood pressure device.

[0141] The hyperparameters of the equipment transfer optimization model are adjusted using an optimization function, and the model is iterated until convergence using historical data to obtain the trained equipment transfer optimization model.

[0142] The operating status characteristics of the new transfer vehicle and the original monitoring operation data are input into the trained equipment transfer optimization model to obtain the output correction information.

[0143] The original monitoring operation data is corrected based on the correction information, and the corrected monitoring operation data is output.

[0144] Preferably, the first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized;

[0145] The second constraint of the equipment transfer optimization model is that the delay time of the fetal heart rate device is less than the first preset delay threshold; the delay time of the blood oxygen device is less than the second preset delay threshold; and the delay time of the blood oxygen device is less than the third preset delay threshold.

[0146] Preferably, the step of matching the operational status characteristics with the device monitoring status of critically ill pregnant women to obtain multiple device delay times includes:

[0147] The operating status characteristics include uphill status, downhill status, emergency braking status, and speed bump status.

[0148] The change in the valley value of the signal spectrum of the device in the uphill state, downhill state, emergency braking state, and speed bump state is obtained.

[0149] Based on the changes in the valley values ​​of the signal spectrum, cluster analysis of device data was performed to obtain data on multiple abnormal device categories.

[0150] The abnormal device data is compared with a threshold to obtain specific device data, and the specific device data is converted into device delay time.

[0151] Preferably, the step of constructing an equipment transport optimization model based on the delay times of the fetal heart rate monitoring device, the blood oxygen monitoring device, and the blood pressure monitoring device includes:

[0152] We obtained fetal heart rate data at multiple times, blood pressure data at multiple times, and the probability of developing hypertension.

[0153] The fetal heart rate data, blood pressure data, probability of hypertension, and delay times of fetal heart rate equipment, blood oxygenation equipment, and blood pressure equipment were used to construct an equipment transport optimization model.

[0154] Preferably, the step of adjusting the hyperparameters of the equipment transfer optimization model using an optimization function and iterating the equipment transfer optimization model until convergence using historical data to obtain the trained equipment transfer optimization model includes:

[0155] Within the domain, determine several initial points for the Bayesian optimization algorithm;

[0156] The probability model of the equipment transfer optimization model is determined by the initial point, the probability of the optimal solution is calculated, and the next candidate data point is obtained.

[0157] The optimal solution of the equipment transfer optimization model at this point is evaluated and added to the observation dataset. When predicting the number of iterations, the equipment transfer optimization model is determined to be iterated until convergence, thus obtaining the trained equipment transfer optimization model.

[0158] Preferably, the method further includes:

[0159] The optimal solution is determined as the initial random solution. The initial parameters of the whale optimization algorithm are set, the fitness value of each solution is calculated, the current optimal whale individual and position are determined, and the whale individual performs random search, or randomly selects shrinking encirclement or spiral update method to update its position until the number of iterations is greater than a preset threshold. The second optimal solution is then output and added to the observation dataset.

[0160] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0161] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0162] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products 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 code.

[0163] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of apparatus, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0164] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction methods implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0165] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0166] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0167] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or terminal device that includes said element.

[0168] The foregoing has provided a detailed description of an artificial intelligence-based method for controlling the transfer of critically ill pregnant women, an artificial intelligence-based control system for the transfer of critically ill pregnant women, a computer device, and a storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for controlling the transfer of critically ill pregnant women based on artificial intelligence, characterized in that, include: Obtain the operational status characteristics of the transfer vehicle; The operational status characteristics are matched with the device monitoring status of critically ill pregnant women to obtain multiple device delay times; among them, the device delay times include fetal heart rate device delay time, blood oxygen device delay time, and blood pressure device delay time. An equipment transport optimization model was constructed based on the delay times of the fetal heart rate device, the blood oxygen device, and the blood pressure device. The hyperparameters of the equipment transfer optimization model are adjusted using an optimization function, and the model is iterated until convergence using historical data to obtain the trained equipment transfer optimization model. The operating status characteristics of the new transfer vehicle and the original monitoring operation data are input into the trained equipment transfer optimization model to obtain the output correction information. Correct the original monitoring operation data according to the correction information, and output the corrected monitoring operation data; The first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized. The second constraint of the equipment transfer optimization model is that the delay time of the fetal heart rate monitoring equipment is less than the first preset delay threshold; the delay time of the blood oxygen monitoring equipment is less than the second preset delay threshold; and the delay time of the blood oxygen monitoring equipment is less than the third preset delay threshold. The construction of the equipment transport optimization model based on the delay times of the fetal heart rate monitoring device, the blood oxygen monitoring device, and the blood pressure monitoring device includes: We obtained fetal heart rate data at multiple times, blood pressure data at multiple times, and the probability of developing hypertension. The fetal heart rate data, blood pressure data, probability of hypertension, and delay times of fetal heart rate equipment, blood oxygenation equipment, and blood pressure equipment were used to construct an equipment transport optimization model.

2. The method according to claim 1, characterized in that, The process of matching the operational status characteristics with the device monitoring status of critically ill pregnant women to obtain multiple device delay times includes: The operating status characteristics include uphill status, downhill status, emergency braking status, and speed bump status. The change in the valley value of the signal spectrum of the device in the uphill state, downhill state, emergency braking state, and speed bump state is obtained. Based on the changes in the valley values ​​of the signal spectrum, cluster analysis of device data was performed to obtain data on multiple abnormal device categories. The abnormal device data is compared with a threshold to obtain specific device data, and the specific device data is converted into device delay time.

3. The method according to claim 1, characterized in that, The process of adjusting the hyperparameters of the equipment transfer optimization model using an optimization function and iterating the model until convergence using historical data to obtain the trained equipment transfer optimization model includes: Within the domain, determine several initial points for the Bayesian optimization algorithm; The probability model of the equipment transfer optimization model is determined by the initial point, the probability of the optimal solution is calculated, and the next candidate data point is obtained. The optimal solution of the equipment transfer optimization model at this point is evaluated and added to the observation dataset. When predicting the number of iterations, the equipment transfer optimization model is determined to be iterated until convergence, thus obtaining the trained equipment transfer optimization model.

4. The method according to claim 3, characterized in that, The method further includes: The optimal solution is determined as the initial random solution. The initial parameters of the whale optimization algorithm are set, the fitness value of each solution is calculated, the current optimal whale individual and position are determined, and the whale individual performs random search, or randomly selects shrinking encirclement or spiral update method to update its position until the number of iterations is greater than a preset threshold. The second optimal solution is then output and added to the observation dataset.

5. A critically ill pregnant woman transport control system based on artificial intelligence, characterized in that, include: The operational status feature module is used to obtain the operational status features of the transfer vehicle; The matching module is used to match the operating status characteristics with the device monitoring status of critically ill pregnant women to obtain multiple device delay times; wherein, the device delay times include fetal heart rate device delay time, blood oxygen device delay time, and blood pressure device delay time; The module is used to construct an equipment transport optimization model based on the delay time of the fetal heart rate device, the delay time of the blood oxygen device, and the delay time of the blood pressure device. The iterative module is used to adjust the hyperparameters of the equipment transfer optimization model using the optimization function, and to iterate the equipment transfer optimization model until convergence using historical data, thereby obtaining the trained equipment transfer optimization model. The input module is used to input the operating status characteristics of the new transfer vehicle and the original monitoring operation data into the trained equipment transfer optimization model to obtain the output correction information. The calibration module is used to calibrate the original monitoring operation data according to the calibration information and output the calibrated monitoring operation data. The first constraint of the equipment transfer optimization model is that the sum of the delay time of the fetal heart rate equipment, the delay time of the blood oxygenation equipment, and the delay time of the blood pressure equipment is minimized. The second constraint of the equipment transfer optimization model is that the delay time of the fetal heart rate monitoring equipment is less than the first preset delay threshold; the delay time of the blood oxygen monitoring equipment is less than the second preset delay threshold; and the delay time of the blood oxygen monitoring equipment is less than the third preset delay threshold. The building module includes: The second acquisition submodule is used to acquire fetal heart rate data at multiple times, blood pressure data at multiple times, and the probability of hypertension. A submodule is constructed to build an equipment transport optimization model based on the fetal heart rate data, blood pressure data, probability of hypertension, and delay times of the fetal heart rate device, blood oxygen device, and blood pressure device.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the artificial intelligence-based transfer control method for critically ill pregnant women as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the artificial intelligence-based transfer control method for critically ill pregnant women as described in any one of claims 1 to 4.

Images