A cloud platform information digitization monitoring system and method based on big data

Abstract

The application discloses a cloud platform information digitization monitoring system and method based on big data, relates to the technical field of medical electronic equipment management, and realizes real-time monitoring of power supply parameters, transmission of the power supply parameters to a comparative analysis module, comprehensive analysis of the power supply parameters by the comparative analysis module to generate a power supply coefficient, comparison of the power supply coefficient with a fault threshold, analysis of whether the power supply needs to be replaced, startup of any standby power supply by a power supply switching module when the analysis result is that the power supply needs to be replaced, judgment of whether the standby power supply can support operation by a monitoring module, replacement of the standby power supply by the power supply switching module to supply power to the anesthesia machine if the standby power supply can support operation, and repetition of the above steps until a standby power supply that can support operation is found. The application can replace other power supplies in time before the input power supply fails, enables the anesthesia machine to stably operate, guarantees the anesthesia safety of patients, and reduces anesthesia risks.

Description

Technical Field

[0001] This invention relates to the field of medical electronic equipment management technology, specifically to a cloud platform information digitization monitoring system and method based on big data. Background Technology

[0002] An anesthesia machine is a medical electronic device used to deliver anesthetics and regulate the respiratory gas mixture to a patient. It is an anesthesia management device that provides safety, control, and monitoring for the patient during surgery.

[0003] The earliest anesthesia machines were manually operated, providing anesthesia by manually controlling the gas flow and breathing bag. With the advancement of science and technology and the development of theoretical knowledge, anesthesia machines have gradually evolved into automated and intelligent devices. Modern anesthesia machines are equipped with advanced electronic and computer control systems that can precisely control gas flow, concentration, and pressure, and provide multiple anesthesia modes and monitoring functions to ensure patient safety and comfort.

[0004] The existing technology has the following shortcomings:

[0005] To ensure the stable use of anesthesia machines, they are usually equipped with multiple power inputs. When the power source fails, the management system automatically switches to another power source. However, if the patient is being anesthetized at this time, the anesthesia machine may not be able to provide the correct gas concentration and flow control, increasing the patient's safety risks. Summary of the Invention

[0006] The purpose of this invention is to provide a cloud platform information digitization monitoring system and method based on big data, in order to address the shortcomings of the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a cloud platform information digital monitoring system and method based on big data, comprising a control module, an evaluation module, a monitoring module, a comparative analysis module, a power switching module, and a management module;

[0008] Control module: Used before anesthesia surgery, it controls the anesthesia machine to enter the trial operation state based on the detection instructions input by medical staff, and sends a start command to the evaluation module;

[0009] Evaluation module: During the trial operation of the anesthesia machine, various data related to the anesthesia machine are collected, and the data are analyzed through the evaluation model to determine the operating status of the anesthesia machine;

[0010] Monitoring module: Monitors power parameters in real time during anesthesia;

[0011] Comparative analysis module: After comprehensively analyzing the power parameters, it generates a power coefficient and analyzes whether the power supply needs to be replaced based on the comparison results between the power coefficient and the fault threshold.

[0012] Power switching module: When the analysis result indicates that the power supply needs to be replaced, start any backup power supply and use the monitoring module to determine whether the backup power supply can support operation. If the backup power supply can support operation, the power switching module will switch the backup power supply to power the anesthesia machine.

[0013] Management module: Creates a power set for power sources that do not support operation, and uploads the power set information to the cloud platform for storage after the anesthesia machine has finished running.

[0014] In a preferred embodiment, the construction of the evaluation model includes the following steps:

[0015] By fusing four parameters related to the health status of the anesthesia machine using principal component analysis, the first and second characteristic principal components are obtained.

[0016] The health status assessment value is obtained by weighting the first and second principal components of the feature, and the calculation expression is as follows:

[0017] pg z =w1*pc1+w2*pc2;

[0018] In the formula, pg z The values ​​represent health status assessments, with pc1 being the first principal component, pc2 being the second principal component, and w1 and w2 being the weights of the first and second principal components, respectively.

[0019] After obtaining the health status assessment value, the health status assessment value is compared with the assessment threshold to complete the construction of the assessment model.

[0020] In a preferred embodiment, the evaluation module collects gas flow rate, gas pressure, oxygen concentration, and tidal volume, performs standardization processing, and then calculates the covariance matrix among gas flow rate, gas pressure, oxygen concentration, and tidal volume. The calculation expression is as follows:

[0021]

[0022] In the formula, c(i,j) is the covariance matrix of gas flow rate and gas pressure, c(m,n) is the covariance matrix of oxygen concentration and tidal volume, and X i X represents the gas flow rate value at the i-th sample point. j X represents the gas pressure value at the j-th sample point. m X represents the oxygen concentration value at the m-th sample point. n μ represents the tidal volume value of the nth sample point.i μ j These are the sample mean values ​​for gas flow rate and gas pressure, respectively, in μ. m μ n n1 represents the sample mean of oxygen concentration and the sample mean of tidal volume, respectively; n2 represents the sample data of gas flow rate and gas pressure, respectively; and n3 represents the sample data of oxygen concentration and tidal volume, respectively.

[0023] In a preferred embodiment, the eigenvalue equations for solving the covariance matrices c(i,j) of gas flow rate and gas pressure, and the covariance matrices c(m,n) of oxygen concentration and tidal volume are as follows:

[0024]

[0025] In the formula, v is the eigenvector of the gas flow rate and gas pressure covariance matrix. is the eigenvalue of the gas flow rate and gas pressure covariance matrix, and u is the eigenvector of the oxygen concentration and tidal volume covariance matrix. These are the eigenvalues ​​of the covariance matrix of oxygen concentration and tidal volume.

[0026] In a preferred embodiment, the eigenvalue equation is solved to obtain the eigenvalues ​​of gas flow rate and gas pressure. and the corresponding feature vectors v1, v2, ..., v n Characteristic values ​​of oxygen concentration and tidal volume and the corresponding feature vectors u1, u2, ..., u n ;

[0027] The eigenvectors are sorted in descending order based on the magnitude of their eigenvalues, and the largest eigenvalue and its corresponding eigenvector are selected as principal components.

[0028] Using the selected principal components, the original data is projected onto the principal component space to obtain the first and second eigencomponents.

[0029] In a preferred embodiment, the evaluation module is used during the trial run of the anesthesia machine;

[0030] The first and second characteristic principal components were obtained by fusing the collected gas flow rate, gas pressure, oxygen concentration and tidal volume using principal component analysis.

[0031] The calculated health status assessment value pg z If the health status assessment value is greater than or equal to the assessment threshold, the assessment module assesses the health status of the anesthesia machine as excellent; if the health status assessment value is less than the assessment threshold, the assessment module assesses the health status of the anesthesia machine as poor.

[0032] In a preferred embodiment, during anesthesia, the monitoring module monitors power parameters in real time, including the input power temperature dispersion index and the output voltage fluctuation amplitude. The temperature dispersion index and the output voltage fluctuation amplitude are sent to the comparison and analysis module.

[0033] In a preferred embodiment, the logic for obtaining the temperature dispersion index is as follows:

[0034] A. First, calculate the temperature dispersion of the input power supply. The calculation steps are as follows:

[0035] Collect the temperature value xi at each temperature acquisition point on the input power supply, and record the total number as N;

[0036] Calculate the average value of the temperature acquisition points, that is, sum all the temperature values ​​and divide by the total number N to get the average value μ;

[0037] For each temperature acquisition point with a value xi, calculate (xi-μ) sequentially. 2 , which represents the square of the difference between the sampling point and the average value;

[0038] All (xi-μ) 2 Summing the results, we get Σ(xi-μ). 2 , will Σ(xi-μ) 2 Divide by N to get the variance;

[0039] Taking the square root of the variance yields the temperature dispersion, lsc.

[0040] B. If the temperature dispersion lsc is less than or equal to the temperature dispersion threshold, the temperature dispersion index lsz = 0; if the temperature dispersion lsc is greater than the temperature dispersion threshold, the temperature dispersion index lsz = 1; if the temperature at any temperature acquisition point is greater than the temperature threshold, the temperature dispersion index lsz = 2.

[0041] In a preferred embodiment, the logic for obtaining the output voltage fluctuation amplitude is as follows:

[0042] A. First, obtain the voltage fluctuation value. The steps are as follows:

[0043] The stable range of the power supply output voltage is marked as V. min ~V max The voltage collected in real time is marked as V. dy ;

[0044] If V dy <V min Voltage fluctuation value V bd =|V dy -V min |;

[0045] If V dy >V max Voltage fluctuation value V bd =|V dy -V max |;

[0046] B. After obtaining the voltage fluctuation value, if the voltage fluctuation value is less than or equal to the fluctuation threshold, the output voltage fluctuation amplitude bdf = 0; if the voltage fluctuation value is greater than the fluctuation threshold, the output voltage fluctuation amplitude bdf = 1.

[0047] In a preferred embodiment, the comparative analysis module generates a power factor dy by comprehensively analyzing the temperature dispersion index and the output voltage fluctuation amplitude. x The calculation expression is: dy x =0.729*lsz+0.862*bdf, where lsz and bdf are the temperature dispersion index and the output voltage fluctuation amplitude, respectively, and 0.729 and 0.862 are the proportionality constants of the temperature dispersion index and the output voltage fluctuation amplitude, respectively.

[0048] The power factor is compared with the fault threshold. If the power factor is greater than or equal to the fault threshold, it is predicted that the power supply will not be able to be used and a backup power supply needs to be replaced. If the power factor is less than the fault threshold, it is predicted that the power supply will be able to be used and a backup power supply does not need to be replaced.

[0049] The present invention also provides a method for digital monitoring of cloud platform information based on big data, the monitoring method comprising the following steps;

[0050] Before anesthesia is required, the medical staff management system inputs the testing instructions, including specifying the testing content and parameters to be performed. The management system controls the anesthesia machine to enter the trial operation state according to the testing instructions. After receiving the testing instructions, the management system switches the anesthesia machine to the trial operation mode to prepare for relevant testing and monitoring operations.

[0051] During the trial operation of the anesthesia machine, the management system collects various data related to the anesthesia machine, analyzes the data through an evaluation model, judges the operating status of the anesthesia machine, and returns the judgment results to the medical staff.

[0052] When it is determined that the anesthesia machine supports the anesthesia procedure, the patient is on the operating table, and the medical staff anesthetize the patient using the anesthesia machine. During the anesthesia process, the management system monitors the power parameters in real time, and generates a power coefficient after comprehensive analysis of the power parameters. Based on the comparison between the power coefficient and the fault threshold, it is analyzed whether the power supply needs to be replaced.

[0053] When the analysis results indicate that the power supply needs to be replaced, the management system first starts any backup power supply and determines whether the backup power supply can support the operation. If the backup power supply can support the operation, the management system replaces the backup power supply with the power supply for the anesthesia machine. If the backup power supply cannot support the operation, the above steps are repeated until a backup power supply that can support the operation is found.

[0054] Specifically, in order to ensure the stable operation of the anesthesia machine during power switching, in this implementation, the anesthesia machine is provided with a main power supply and a backup power supply. The main power supply is the power supply that is currently supplying power to the anesthesia machine, and the main power supply and multiple backup power supplies are connected / disconnected from the anesthesia machine through a circuit breaker.

[0055] When it is predicted that the power supply will not be able to support the use (a failure may occur in the future), the management system will start any backup power supply, but will not control the circuit breaker of the backup power supply to be energized. Then it will determine whether the backup power supply can support the operation. If the backup power supply can support the operation, the management system will simultaneously control the circuit breaker of the power supply to be disconnected and control the circuit breaker of the backup power supply to be energized.

[0056] By following the steps above, we can avoid putting the backup power supply into use without testing (if the backup power supply is put into use without testing, and if the backup power supply is already faulty, the anesthesia machine will be unusable).

[0057] The management system will not support the establishment of power sets for running power sources. Power set information includes power source location and power source number. After the anesthesia machine has finished running, the power set information will be fed back to the medical staff.

[0058] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0059] 1. During the use of the anesthesia machine, the monitoring module monitors the power parameters in real time and sends the power parameters to the comparison and analysis module. The comparison and analysis module generates a power coefficient after comprehensively analyzing the power parameters and analyzes whether the power needs to be replaced based on the comparison result of the power coefficient and the fault threshold. When the analysis result indicates that the power needs to be replaced, the power switching module first starts any backup power supply and determines whether the backup power supply can support operation through the monitoring module. If the backup power supply can support operation, the power switching module replaces the backup power supply to power the anesthesia machine. If the backup power supply cannot support operation, the above steps are repeated until a backup power supply that can support operation is found. This allows for timely replacement of other power supplies before the input power fails, enabling the anesthesia machine to operate stably, ensuring the patient's anesthesia safety, and reducing anesthesia risks.

[0060] 2. This invention uses an evaluation module to collect various data related to the anesthesia machine during trial operation. These data are then analyzed using an evaluation model to determine the operating status of the anesthesia machine. The evaluation results are returned to the control module, which then feeds the results back to medical staff. This allows for the assessment of whether the anesthesia machine is usable before the anesthesia procedure begins. If the anesthesia machine is not usable, it can be repaired or replaced with another usable anesthesia machine in a timely manner, thereby avoiding anesthesia interruption caused by anesthesia machine malfunction and ensuring the stable progress of the surgery.

[0061] 3. This invention uses an evaluation module to collect various data related to the anesthesia machine during trial operation. These data include gas flow rate, gas pressure, oxygen concentration, and tidal volume. After standardizing the gas flow rate, gas pressure, oxygen concentration, and tidal volume, the covariance matrix between these data is calculated. Then, after obtaining the health status assessment value, if the health status assessment value is greater than or equal to the assessment threshold, the evaluation module assesses the health status of the anesthesia machine as excellent; if the health status assessment value is less than the assessment threshold, the evaluation module assesses the health status of the anesthesia machine as poor. This effectively assesses the health status of the anesthesia machine before its use, with high evaluation accuracy.

[0062] 4. This invention calculates the temperature dispersion index of the input power supply and the amplitude of the output voltage fluctuation, then comprehensively analyzes and calculates the power supply coefficient based on the temperature dispersion index of the input power supply and the amplitude of the output voltage fluctuation. Finally, by comparing the power supply coefficient with the fault threshold, it predicts whether the input power supply may fail in the future, so as to replace the backup power supply in time before the input power supply fails. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0064] Figure 1 This is a system module diagram of the present invention. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] Example 1: Please refer to Figure 1 As shown in this embodiment, a cloud platform information digitization monitoring system and method based on big data includes a control module, an evaluation module, a monitoring module, a comparative analysis module, a power switching module, and a management module.

[0067] Before anesthesia is required, medical staff input test instructions into the control module. The test instructions are obtained from the anesthesia machine's big data database, including the specified test content and parameters. The control module controls the anesthesia machine to enter the trial operation state according to the test instructions. After receiving the test instructions, the control module switches the anesthesia machine to the trial operation mode, prepares to perform relevant tests and monitoring operations, and sends a start instruction to the evaluation module.

[0068] During the trial operation of the anesthesia machine, the evaluation module collects various data related to the anesthesia machine, analyzes the data through the evaluation model, judges the operating status of the anesthesia machine, and returns the judgment result to the control module, which then feeds the judgment result back to the medical staff.

[0069] When it is determined that the anesthesia machine supports the anesthesia procedure, the patient is on the operating table, and the medical staff anesthetize the patient using the anesthesia machine. During the anesthesia process, the monitoring module monitors the power parameters in real time, and the power parameters are sent to the comparison and analysis module.

[0070] The comparative analysis module generates a power coefficient after comprehensively analyzing the power parameters, and analyzes whether the power supply needs to be replaced based on the comparison results between the power coefficient and the fault threshold. The analysis results are then sent to the power switching module.

[0071] When the analysis results indicate that the power supply needs to be replaced, the power switching module first starts any backup power supply and uses the monitoring module to determine whether the backup power supply can support operation. If the backup power supply can support operation, the power switching module replaces the backup power supply with the power supply for the anesthesia machine. If the backup power supply cannot support operation, the above steps are repeated until a backup power supply that can support operation is found.

[0072] Specifically, in order to ensure the stable operation of the anesthesia machine during power switching, in this implementation, the anesthesia machine is provided with a main power supply and a backup power supply. The main power supply is the power supply that is currently supplying power to the anesthesia machine, and the main power supply and multiple backup power supplies are connected / disconnected from the anesthesia machine through a circuit breaker.

[0073] When it is predicted that the power supply will not be able to support the use (there may be a failure in the future), the power switching module will start any backup power supply, but will not control the circuit breaker of the backup power supply to be energized. Then the monitoring module will determine whether the backup power supply can support the operation. If the backup power supply can support the operation, the power switching module will simultaneously control the circuit breaker of the power supply to be disconnected and control the circuit breaker of the backup power supply to be energized.

[0074] By following the steps above, we can avoid putting the backup power supply into use without testing (if the backup power supply is put into use without testing, and if the backup power supply is already faulty, the anesthesia machine will be unusable).

[0075] The management module will create a power set for power supplies that are not supported for operation. The power set information includes the power supply location and power supply number. After the anesthesia machine has finished operating, the power set information will be uploaded to the cloud platform for storage. The control module will then provide feedback to medical staff that the power supply is not supported for operation.

[0076] Medical staff will send the information that the power supply is not working to the power supply maintenance personnel, who will then repair or replace the power supply.

[0077] This application uses an evaluation module to collect various data related to the anesthesia machine during trial operation. This data is then analyzed through an evaluation model to determine the operating status of the anesthesia machine. The evaluation results are returned to the control module, which then feeds back the results to medical staff. This allows for the assessment of whether the anesthesia machine is usable before the start of anesthesia surgery. If the anesthesia machine is not usable, it can be repaired or replaced with another usable anesthesia machine in a timely manner, thereby avoiding anesthesia interruption caused by anesthesia machine failure and ensuring the stable conduct of the surgery.

[0078] In this application, during the use of the anesthesia machine, the monitoring module monitors the power parameters in real time. The power parameters are sent to the comparison and analysis module, which generates a power coefficient after comprehensive analysis of the power parameters. Based on the comparison result of the power coefficient and the fault threshold, it analyzes whether the power supply needs to be replaced. When the analysis result indicates that the power supply needs to be replaced, the power switching module first starts any backup power supply and determines whether the backup power supply can support operation through the monitoring module. If the backup power supply can support operation, the power switching module switches to the backup power supply to power the anesthesia machine. If the backup power supply cannot support operation, the above steps are repeated until a backup power supply that can support operation is found. This allows for timely replacement of other power supplies before the input power supply fails, enabling the anesthesia machine to operate stably, ensuring the patient's anesthesia safety, and reducing anesthesia risks.

[0079] Example 2: During the trial operation of the anesthesia machine, the evaluation module collects various data related to the anesthesia machine, analyzes the various data through the evaluation model, judges the operating status of the anesthesia machine, and returns the judgment result to the control module, which then feeds the judgment result back to the medical staff.

[0080] The construction of the evaluation model includes the following steps:

[0081] A. By fusing the four parameters related to the health status of the anesthesia machine through principal component analysis, the first and second characteristic principal components are obtained.

[0082] B. The health status assessment value is obtained by weighting the first and second principal components. The calculation expression is as follows:

[0083] pg z =w1*pc1+w2*pc2;

[0084] In the formula, pg z The values ​​represent health status assessments, with pc1 being the first principal component, pc2 being the second principal component, and w1 and w2 being the weights of the first and second principal components, respectively.

[0085] C. After obtaining the health status assessment value, compare the health status assessment value with the assessment threshold to complete the construction of the assessment model.

[0086] During the trial run of the anesthesia machine, the evaluation module collects various data related to the anesthesia machine, including gas flow rate, gas pressure, oxygen concentration, and tidal volume.

[0087] After standardizing the gas flow rate, gas pressure, oxygen concentration, and tidal volume, the covariance matrix among these parameters is calculated using the following expression:

[0088]

[0089] In the formula, c(i,j) is the covariance matrix of gas flow rate and gas pressure, c(m,n) is the covariance matrix of oxygen concentration and tidal volume, and X i X represents the gas flow rate value at the i-th sample point. j X represents the gas pressure value at the j-th sample point. m X represents the oxygen concentration value at the m-th sample point. n μ represents the tidal volume value of the nth sample point. i μ j These are the sample mean values ​​for gas flow rate and gas pressure, respectively, in μ. m μ n n1 represents the sample mean of oxygen concentration and the sample mean of tidal volume, respectively; n2 represents the sample data of gas flow rate and gas pressure, respectively; n3 represents the sample data of oxygen concentration and tidal volume, respectively.

[0090] After obtaining the covariance matrices c(i,j) of gas flow rate and gas pressure, and c(m,n) of oxygen concentration and tidal volume, the eigenvalue equations are solved as follows:

[0091]

[0092] In the formula, v is the eigenvector of the gas flow rate and gas pressure covariance matrix. is the eigenvalue of the gas flow rate and gas pressure covariance matrix, and u is the eigenvector of the oxygen concentration and tidal volume covariance matrix. These are the eigenvalues ​​of the oxygen concentration and tidal volume covariance matrix;

[0093] After solving the eigenvalue equations, a set of eigenvalues ​​for gas flow rate and gas pressure are obtained. and the corresponding feature vectors v1, v2, ..., v n A set of characteristic values ​​for oxygen concentration and tidal volume and the corresponding feature vectors u1, u2, ..., u n These feature vectors are unit vectors, representing the orientation of the data in the new feature space;

[0094] The eigenvectors are sorted in descending order based on the magnitude of the eigenvalues, and the largest few eigenvalues ​​and their corresponding eigenvectors are selected as principal components. Finally, the original data is projected into the principal component space using the selected principal components to obtain the first and second eigenprincipal components.

[0095] The health status assessment value is obtained by weighting the first and second principal components of the feature, and the calculation expression is as follows:

[0096] pg z =w1*pc1+w2*pc2;

[0097] In the formula, pg z The values ​​represent health status assessments, with pc1 being the first principal component, pc2 being the second principal component, and w1 and w2 being the weights of the first and second principal components, respectively.

[0098] After obtaining the health status assessment value, if the health status assessment value is greater than or equal to the assessment threshold, the assessment module assesses the health status of the anesthesia machine as excellent; if the health status assessment value is less than the assessment threshold, the assessment module assesses the health status of the anesthesia machine as poor.

[0099] In this implementation, when evaluating anesthesia machines, three samples are usually taken for each parameter, that is, the first principal component and the second principal component each have three values. After determining the weights of the first principal component and the second principal component, three health status assessment values ​​are calculated. If two health status assessment values ​​are greater than or equal to the assessment threshold, the anesthesia machine is deemed to be able to support the use of anesthesia for surgery. If two health status assessment values ​​are less than the assessment threshold, the anesthesia machine needs to be evaluated again. If all three health status assessment values ​​are less than the assessment threshold, the anesthesia machine is deemed not to support the use of anesthesia for surgery.

[0100] The steps for standardizing various types of data are as follows:

[0101] Mean removal: Calculate the mean of each parameter sample, and then subtract the mean from each parameter sample to make the mean of each parameter sample 0;

[0102] Variance scaling: Calculate the standard deviation of each parameter sample, and then divide each parameter sample after removing the mean by the standard deviation to make the variance of each parameter equal to 1, thus completing the data standardization process.

[0103] The above solutions are illustrated with examples as follows:

[0104] Assuming PC1 has a weight of 0.6 and PC2 has a weight of 0.4, and PC1 takes three values ​​of {1.5, 2.3, 3.0}, while PC2 takes three values ​​of {2.0, 1.2, -1.0}, then the calculated three health status assessment values ​​are:

[0105]

[0106] Due to pg z 1. pg z 2. pg z All three values ​​were greater than 1.5, therefore the anesthetic function was assessed as supporting the use of anesthesia for surgery.

[0107] This application utilizes an evaluation module to collect various data related to the anesthesia machine during trial operation. These data include gas flow rate, gas pressure, oxygen concentration, and tidal volume. After standardizing these data, the covariance matrix among them is calculated. Then, after obtaining a health status assessment value, if the health status assessment value is greater than or equal to the assessment threshold, the evaluation module assesses the anesthesia machine's health status as excellent; if the health status assessment value is less than the assessment threshold, the evaluation module assesses the anesthesia machine's health status as poor. This effectively assesses the health status of the anesthesia machine before its use, with high evaluation accuracy.

[0108] Example 3: When it is determined that the anesthesia machine supports the anesthesia surgery, the patient is on the operating table, and the medical staff anesthetize the patient through the anesthesia machine. During the anesthesia process, the monitoring module monitors the power parameters in real time, and the power parameters are sent to the comparison and analysis module.

[0109] The comparative analysis module generates a power coefficient after comprehensively analyzing the power parameters, and analyzes whether the power supply needs to be replaced based on the comparison results between the power coefficient and the fault threshold. The analysis results are then sent to the power switching module.

[0110] When the analysis results indicate that a power supply replacement is required, the power switching module first activates any backup power supply and then uses the monitoring module to determine whether the backup power supply can support operation. If the backup power supply can support operation, the power switching module switches the backup power supply to power the anesthesia machine. If the backup power supply cannot support operation, the above steps are repeated until a backup power supply that can support operation is found.

[0111] During anesthesia, the monitoring module monitors the power parameters in real time, including the input power temperature dispersion index and the output voltage fluctuation amplitude. The temperature dispersion index and the output voltage fluctuation amplitude are sent to the comparison and analysis module.

[0112] The logic for obtaining the temperature dispersion index is as follows:

[0113] 1) First, calculate the temperature dispersion of the input power supply. The calculation steps are as follows:

[0114] Collect the temperature value xi at each temperature acquisition point on the input power supply, and record the total number as N;

[0115] Calculate the average value of the temperature acquisition points, that is, sum all the temperature values ​​and divide by the total number N to obtain the average value μ;

[0116] For each temperature acquisition point with a value xi, calculate (xi-μ) sequentially. 2 , which represents the square of the difference between the sampling point and the average value;

[0117] All (xi-μ) 2 Summing the results, we get Σ(xi-μ). 2 , will Σ(xi-μ) 2 Divide by N to get the variance;

[0118] Taking the square root of the variance yields the temperature dispersion, lsc.

[0119] 2) The larger the temperature dispersion lsc, the wider the range of the input power supply temperature data and the greater the difference between temperature values; the smaller the temperature dispersion lsc, the narrower the range of the temperature data and the smaller the difference between temperature values.

[0120] Therefore, if the temperature dispersion lsc is less than or equal to the temperature dispersion threshold, the temperature dispersion index lsz = 0; if the temperature dispersion lsc is greater than the temperature dispersion threshold, the temperature dispersion index lsz = 1; if the temperature at any temperature acquisition point is greater than the temperature threshold, the temperature dispersion index lsz = 2.

[0121] The logic for obtaining the output voltage fluctuation amplitude is as follows:

[0122] 1) First, obtain the voltage fluctuation value. The steps are as follows:

[0123] The stable range of the power supply output voltage is marked as V. min ~V max The voltage collected in real time is marked as V. dy ;

[0124] If V dy <V min Voltage fluctuation value V bd =|V dy -V min |;

[0125] If V dy >V max Voltage fluctuation value V bd =|V dy -V max |;

[0126] 2) After obtaining the voltage fluctuation value, if the voltage fluctuation value is less than or equal to the fluctuation threshold, the output voltage fluctuation amplitude bdf = 0; if the voltage fluctuation value is greater than the fluctuation threshold, the output voltage fluctuation amplitude bdf = 1.

[0127] The comparative analysis module generates power coefficients after comprehensively analyzing power parameters, following these steps:

[0128] The comparative analysis module generates the power factor dy by comprehensively analyzing the temperature dispersion index and the output voltage fluctuation amplitude. x The calculation expression is: dy x =0.729*lsz+0.862*bdf, where lsz and bdf are the temperature dispersion index and the output voltage fluctuation amplitude, respectively, and 0.729 and 0.862 are the proportionality constants of the temperature dispersion index and the output voltage fluctuation amplitude, respectively.

[0129] After obtaining the power factor, compare the power factor with the fault threshold. If the power factor is greater than or equal to the fault threshold, it is predicted that the power supply will not be supported and the backup power supply needs to be replaced. If the power factor is less than the fault threshold, it is predicted that the power supply will be supported and the backup power supply does not need to be replaced.

[0130] Specifically, in this application, the fault threshold is determined as follows:

[0131] When the temperature dispersion index lsz = 1 or the output voltage fluctuation amplitude bdf = 1, it indicates that there are unstable factors in the input power supply. In order to predict the possible failure of the power supply in advance, this application takes the fault threshold value as 0.729.

[0132] This application calculates the input power supply temperature dispersion index and the output voltage fluctuation amplitude, then comprehensively analyzes and calculates the power supply coefficient based on the input power supply temperature dispersion index and the output voltage fluctuation amplitude, and finally predicts whether the input power supply may fail in the future by comparing the power supply coefficient with the fault threshold, so as to replace the backup power supply in time before the input power supply fails.

[0133] When the analysis results indicate that the power supply needs to be replaced, the power switching module first starts any backup power supply and then uses the monitoring module to determine whether the backup power supply can support the operation.

[0134] Since the temperature change is not obvious when the backup power supply is started, the monitoring module mainly monitors the voltage fluctuation value of the backup power supply to determine whether the backup power supply is fault-free and can be used. In addition, after the backup power supply is put into use, the monitoring module also obtains the power factor of the backup power supply in real time to predict whether the backup power supply may fail in the future.

[0135] Specifically, if multiple backup power supplies are deemed unusable by the monitoring module during the use of the anesthesia machine, the unusable backup power supplies enter the isolation zone. The backup power supplies in the isolation zone will not be selected during the next power switch, thereby improving the power switching efficiency of the power switching module.

[0136] Example 4: This example describes a cloud platform information digitization monitoring system method based on big data. The monitoring system method includes the following steps;

[0137] Before anesthesia is required, the medical staff management system inputs the testing instructions, including specifying the testing content and parameters to be performed. The management system controls the anesthesia machine to enter the trial operation state according to the testing instructions. After receiving the testing instructions, the management system switches the anesthesia machine to the trial operation mode to prepare for relevant testing and monitoring operations.

[0138] During the trial operation of the anesthesia machine, the management system collects various data related to the anesthesia machine, analyzes the data through an evaluation model, judges the operating status of the anesthesia machine, and returns the judgment results to the medical staff.

[0139] When it is determined that the anesthesia machine supports the anesthesia procedure, the patient is on the operating table, and the medical staff anesthetize the patient using the anesthesia machine. During the anesthesia process, the management system monitors the power parameters in real time, and generates a power coefficient after comprehensive analysis of the power parameters. Based on the comparison between the power coefficient and the fault threshold, it is analyzed whether the power supply needs to be replaced.

[0140] When the analysis results indicate that the power supply needs to be replaced, the management system first starts any backup power supply and determines whether the backup power supply can support the operation. If the backup power supply can support the operation, the management system replaces the backup power supply with the power supply for the anesthesia machine. If the backup power supply cannot support the operation, the above steps are repeated until a backup power supply that can support the operation is found.

[0141] Specifically, in order to ensure the stable operation of the anesthesia machine during power switching, in this implementation, the anesthesia machine is provided with a main power supply and a backup power supply. The main power supply is the power supply that is currently supplying power to the anesthesia machine, and the main power supply and multiple backup power supplies are connected / disconnected from the anesthesia machine through a circuit breaker.

[0142] When it is predicted that the power supply will not be able to support the use (a failure may occur in the future), the management system will start any backup power supply, but will not control the circuit breaker of the backup power supply to be energized. Then it will determine whether the backup power supply can support the operation. If the backup power supply can support the operation, the management system will simultaneously control the circuit breaker of the power supply to be disconnected and control the circuit breaker of the backup power supply to be energized.

[0143] By following the steps above, we can avoid putting the backup power supply into use without testing (if the backup power supply is put into use without testing, and if the backup power supply is already faulty, the anesthesia machine will be unusable).

[0144] The management system will not support the establishment of power sets for running power sources. Power set information includes power source location and power source number. After the anesthesia machine has finished running, the power set information will be fed back to the medical staff.

[0145] During the trial operation of the anesthesia machine, this application collects various data related to the anesthesia machine, analyzes these data through an evaluation model, determines the operating status of the anesthesia machine, and feeds back the results to medical staff. This allows for an assessment of whether the anesthesia machine can be used before the start of the anesthesia procedure. If the anesthesia machine is not usable, it can be repaired or replaced with another usable anesthesia machine in a timely manner, thereby avoiding anesthesia interruption caused by anesthesia machine failure and ensuring the stable conduct of the surgery.

[0146] This application monitors power parameters in real time during the use of the anesthesia machine, generates a power coefficient after comprehensive analysis of the power parameters, and analyzes whether the power supply needs to be replaced based on the comparison result of the power coefficient and the fault threshold. When the analysis result indicates that the power supply needs to be replaced, any backup power supply is first started, and it is determined whether the backup power supply can support operation. If the backup power supply can support operation, the backup power supply is used to power the anesthesia machine. If the backup power supply cannot support operation, the above steps are repeated until a backup power supply that can support operation is found. In this way, other power supplies can be replaced in time before the input power supply fails, so that the anesthesia machine can operate stably, ensuring the patient's anesthesia safety and reducing the risk of anesthesia.

[0147] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0148] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0149] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A cloud platform information digitization monitoring system based on big data, characterized in that: It includes a control module, an evaluation module, a monitoring module, a comparative analysis module, a power switching module, and a management module; Control module: Used before anesthesia surgery, it controls the anesthesia machine to enter the trial operation state based on the detection instructions input by medical staff, and sends a start command to the evaluation module; Evaluation module: During the trial operation of the anesthesia machine, various data related to the anesthesia machine are collected, and the data are analyzed through an evaluation model to determine the operating status of the anesthesia machine; The construction of the evaluation model includes the following steps: By fusing four parameters related to the health status of the anesthesia machine using principal component analysis, the first and second characteristic principal components are obtained. The health status assessment value is obtained by weighting the first and second principal components. After obtaining the health status assessment value, the health status assessment value is compared with the assessment threshold to complete the construction of the assessment model; Monitoring module: Monitors power parameters in real time during anesthesia; Comparative analysis module: After comprehensively analyzing the power parameters, it generates a power coefficient and analyzes whether the power supply needs to be replaced based on the comparison results between the power coefficient and the fault threshold. Power switching module: When the analysis result indicates that the power supply needs to be replaced, start any backup power supply and use the monitoring module to determine whether the backup power supply can support operation. If the backup power supply can support operation, the power switching module will switch the backup power supply to power the anesthesia machine. Management module: Creates a power set for power supplies that do not support operation, and uploads the power set information to the cloud platform for storage after the anesthesia machine has finished running; The health status assessment value is obtained by weighting the first and second principal components of the feature, and the calculation expression is as follows: In the formula, This is a health status assessment value. As the first characteristic principal component, It is the second principal component. , These are the weights of the first and second principal components, respectively. The comparative analysis module generates a power factor by comprehensively analyzing the temperature dispersion index and the output voltage fluctuation amplitude. The calculation expression is: In the formula, , These represent the temperature dispersion index and the output voltage fluctuation amplitude, respectively, with 0.729 and 0.862 being the proportionality constants for the temperature dispersion index and the output voltage fluctuation amplitude, respectively. The power factor is compared with the fault threshold. If the power factor is greater than or equal to the fault threshold, it is predicted that the power supply will not be able to be used and a backup power supply needs to be replaced. If the power factor is less than the fault threshold, it is predicted that the power supply will be able to be used and a backup power supply does not need to be replaced.

2. The cloud platform information digital monitoring system based on big data according to claim 1, characterized in that: The evaluation module collects gas flow rate, gas pressure, oxygen concentration, and tidal volume, performs standardization processing, and then calculates the covariance matrix among gas flow rate, gas pressure, oxygen concentration, and tidal volume. The calculation expression is as follows: ； In the formula, Let the covariance matrix be the gas flow rate and gas pressure. Let be the covariance matrix of oxygen concentration and tidal volume. This represents the gas flow rate value at the i-th sample point. This represents the gas pressure value at the j-th sample point. This represents the oxygen concentration value at the m-th sample point. This represents the tidal volume value of the nth sample point. , These are the sample mean values ​​for gas flow rate and gas pressure, respectively. , These represent the sample mean of oxygen concentration and the sample mean of tidal volume, respectively. For sample data of gas flow rate and gas pressure, For sample data on oxygen concentration and tidal volume.

3. The cloud platform information digitization monitoring system based on big data according to claim 2, characterized in that: The covariance matrix of the gas flow rate and gas pressure And the covariance matrix of oxygen concentration and tidal volume The eigenvalue equations are solved as follows: ； In the formula, v is the eigenvector of the gas flow rate and gas pressure covariance matrix. These are the eigenvalues ​​of the gas flow rate and gas pressure covariance matrix. It is the eigenvector of the covariance matrix of oxygen concentration and tidal volume. These are the eigenvalues ​​of the covariance matrix of oxygen concentration and tidal volume.

4. The cloud platform information digitization monitoring system based on big data according to claim 3, characterized in that: The eigenvalue equation is solved to obtain the eigenvalues ​​of gas flow rate and gas pressure. and the corresponding feature vector Characteristic values ​​of oxygen concentration and tidal volume and the corresponding feature vector ; The eigenvectors are sorted in descending order based on the magnitude of their eigenvalues, and the largest eigenvalue and its corresponding eigenvector are selected as principal components. Using the selected principal components, the original data is projected onto the principal component space to obtain the first and second eigencomponents.

5. The cloud platform information digitization monitoring system based on big data according to claim 4, characterized in that: The evaluation module is used during the trial operation of the anesthesia machine; The first and second characteristic principal components were obtained by fusing the collected gas flow rate, gas pressure, oxygen concentration and tidal volume using principal component analysis. Calculate the health status assessment value If the health status assessment value is greater than or equal to the assessment threshold, the assessment module assesses the health status of the anesthesia machine as excellent; if the health status assessment value is less than the assessment threshold, the assessment module assesses the health status of the anesthesia machine as poor.

6. The cloud platform information digitization monitoring system based on big data according to claim 1, characterized in that: During anesthesia, the monitoring module monitors power parameters in real time, including the input power temperature dispersion index and the output voltage fluctuation amplitude. The temperature dispersion index and the output voltage fluctuation amplitude are sent to the comparison and analysis module.

7. The cloud platform information digital monitoring system based on big data according to claim 6, characterized in that: The logic for obtaining the temperature dispersion index is as follows: A. First, calculate the temperature dispersion of the input power supply. The calculation steps are as follows: Collect the temperature value xi at each temperature acquisition point on the input power supply, and record the total number as N; Calculate the average value of the temperature acquisition points, that is, sum all the temperature values ​​and divide by the total number N to get the average value μ; For each temperature acquisition point with a value xi, calculate (xi-μ) sequentially. 2 , which represents the square of the difference between the sampling point and the average value; All (xi-μ) 2 Summing the results, we get Σ(xi-μ). 2 , will Σ(xi-μ) 2 Divide by N to get the variance; Taking the square root of the variance yields the temperature dispersion, lsc. B. If the temperature dispersion lsc is less than or equal to the temperature dispersion threshold, the temperature dispersion index lsz = 0; if the temperature dispersion lsc is greater than the temperature dispersion threshold, the temperature dispersion index lsz = 1; if the temperature at any temperature acquisition point is greater than the temperature threshold, the temperature dispersion index lsz = 2.

8. The cloud platform information digital monitoring system based on big data according to claim 7, characterized in that: The logic for obtaining the output voltage fluctuation amplitude is as follows: A. First, obtain the voltage fluctuation value. The steps are as follows: The stable range of the power supply output voltage is marked as V. min ~V max The real-time collected voltage is marked as V. dy ; If V dy <V min Voltage fluctuation value ; If V dy >V max Voltage fluctuation value ; B. After obtaining the voltage fluctuation value, if the voltage fluctuation value is less than or equal to the fluctuation threshold, the output voltage fluctuation amplitude bdf=0; if the voltage fluctuation value is greater than the fluctuation threshold, the output voltage fluctuation amplitude bdf=1.

9. A method for digital monitoring of cloud platform information based on big data, implemented by the monitoring system described in any one of claims 1-8, characterized in that: The monitoring method includes the following steps: Before anesthesia, the control unit initiates a trial run of the anesthesia machine based on the monitoring commands input by medical staff. During the trial run, the data acquisition unit collects various data related to the anesthesia machine and analyzes this data using an evaluation model to determine the machine's operating status. During anesthesia, power parameters are monitored in real time. The processing unit then analyzes these parameters to generate a power coefficient and compares it with a fault threshold to determine if a power supply replacement is necessary. If the analysis indicates a power supply replacement is required, any backup power supply is activated, and its operational capability is assessed. If the backup power supply is capable of supporting the operation, it powers the anesthesia machine.

Images