Newborn intelligent full-automatic blood exchange instrument

Abstract

The application provides a new-born intelligent full-automatic blood exchange instrument, and relates to the technical field of medical devices. The device is configured to collect historical operation data, perform collaborative change characteristic analysis on parameters of the same type, and form collaborative change characteristic data of the same type of parameters; perform optimal compensation collaborative analysis according to the collaborative change characteristic data of the same type of parameters, and form corresponding collaborative compensation data of the same type; perform real-time collaborative compensation processing according to the collaborative compensation data of the same type, and form real-time collaborative data of the same type of parameters; and perform adjustment analysis on the real-time collaborative data of the same type of parameters based on collaborative accuracy, and form real-time collaborative adjustment data of the same type of parameters. The device realizes stable, reliable and intelligent operation of the blood exchange instrument through efficient and accurate collaboration between different control parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to an intelligent fully automatic blood exchange instrument for neonates. Background Art

[0002] Neonatal transfusion is a high-risk procedure, requiring stringent control of blood parameters such as pressure and flow, requiring careful operation. While intelligent transfusion machines have emerged with the advancement of science and technology, most still require human control to ensure their normal, stable, and reliable operation.

[0003] Intelligent blood exchange machines, which rely on personnel, are still subject to the influence of human factors and do not substantially reduce surgical risks. To achieve more accurate and reliable blood exchange procedures, it is necessary to analyze and process the parameters of the blood exchange machine. Considering the different energy supply devices on the blood exchange machine, their parameter control is closely linked. Ensuring their intelligent and accurate system operation is a key consideration.

[0004] Therefore, designing a newborn intelligent fully automatic blood exchange instrument to achieve stable, reliable and intelligent operation of the blood exchange instrument through efficient and accurate coordination between different control parameters is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide a newborn intelligent fully automatic blood exchange instrument, which obtains the change characteristic analysis of the coordinated regulation between the same type of parameters by collecting the historical data of the blood exchange instrument operation, and then obtains the parameter coordinated characteristic data under the current state of the blood exchange instrument. On this basis, predictive compensation analysis is carried out to determine reasonable compensation data, and real-time coordinated monitoring and adjustment are carried out while using the compensation data for real-time coordinated control, which fully and effectively ensures the efficient and intelligent coordination between the same type of parameters of the blood exchange instrument, further improves the intelligence level of the blood exchange instrument, and gets rid of the influence of errors easily generated by human operation, greatly reduces the risk of blood exchange surgery, and makes blood exchange more accurate and safe.

[0006] In the first aspect, the present invention provides a neonatal intelligent fully automatic blood exchange instrument, which is configured to: collect historical operation data, perform collaborative change characteristic analysis of parameters of the same type, and form collaborative change characteristic data of parameters of the same type; perform optimal compensation collaborative analysis based on the collaborative change characteristic data of parameters of the same type, and form corresponding collaborative compensation data of the same type; perform real-time collaborative compensation processing based on the collaborative compensation data of the same type, and form real-time collaborative data of parameters of the same type; perform adjustment analysis on the real-time collaborative data of parameters of the same type based on collaborative accuracy, and form real-time collaborative adjustment data of parameters of the same type.

[0007] In the present invention, the device acquires the change characteristic analysis of the coordinated regulation between the same type of parameters by collecting the historical data of the blood exchange instrument operation, and then obtains the parameter coordinated characteristic data under the current state of the blood exchange instrument. On this basis, predictive compensation analysis is performed to determine reasonable compensation data. While using the compensation data for real-time coordinated control, real-time coordinated monitoring and adjustment are performed, which fully and effectively guarantees the efficient and intelligent coordination between the same type of parameters of the blood exchange instrument, further improves the intelligence level of the blood exchange instrument, and gets rid of the influence of errors easily caused by human operation, greatly reduces the risk of blood exchange surgery, and makes blood exchange more accurate and safe.

[0008] As a possible implementation method, historical operation data is collected, and collaborative change characteristics analysis of parameters of the same type is performed to form collaborative change characteristic data of parameters of the same type, including: extracting the collaborative change data of parameters of the same type for each operation in time dimension order based on the historical operation data to form historical collaborative change data of parameters of the same type for a single operation; clustering and dividing the historical collaborative change data of parameters of the same type for different single operations in time dimension order to form a data set of historical collaborative change of parameters of the same type for the previous single operation and a data set of historical collaborative change of parameters of the same type for the subsequent single operation; extracting collaborative change trend characteristics of parameters of the same type based on the data set of historical collaborative change of parameters of the same type for the previous single operation to form initial collaborative change characteristic data of parameters of the same type; performing time series data matching analysis on the initial collaborative change characteristic data of parameters of the same type based on the historical collaborative change data of parameters of the same type for the subsequent single operation to form collaborative change characteristic data of parameters of the same type.

[0009] In the present invention, the big data analysis of historical operating data is mainly to determine the actual parameter synergy control of the instrument under the current state and service life. This can accurately reflect the trend of synergy parameter changes during the actual operation of the instrument. It is understandable that for the instrument, the synergy between parameters of the same type can ensure that the instrument operates normally and does not affect adjuvant treatment as long as each parameter is within the corresponding allowable range. However, the allowable range corresponding to each parameter cannot reflect the numerical synergy relationship of the instrument during operation, and therefore cannot confirm whether the parameter has the trend and risk of abnormal changes. Therefore, it is necessary to analyze the characteristics of synergy change trends to accurately grasp the synergy relationship between parameters of the same type and make timely adjustments to possible synergy anomalies. Considering that the synergy relationship has a time characteristic, after all, changes in the instrument's service life will cause the performance of the equipment and facilities that control the parameters to degrade. Therefore, it is necessary to extract the most recent data during analysis. Of course, the time span of the extracted historical data can be determined based on the actual impact of the instrument's service life on parameter control. At the same time, to ensure that the extracted feature information has a strong time factor directionality, clustering is performed, and the closest historical data is used as the basic data for directional adjustment of the initial feature data, which can further improve the accuracy and real-time performance of the result data. In addition, it should be noted that for blood exchange machines, parameters of the same type have stronger synergy. Synergistic analysis of parameters of the same type can effectively ensure that the blood exchange machine can achieve intelligent and precise parameter control. The same type of parameters here refer to the same type of control parameters of different operating devices on the blood exchange machine. For example, for pressure, this includes the pressure control parameters of arterial pumps, venous pumps, and other pumps. Of course, the same applies to parameters of the same type such as flow rate and flow velocity.

[0010] As a possible implementation method, based on the historical collaborative change data set of the same type of parameters in the previous single run, the collaborative change trend characteristics of the same type of parameters are extracted to form the initial collaborative change characteristic data of the same type of parameters, including: for different single run historical collaborative change data of the same type of parameters in the previous single run historical collaborative change data set of the same type of parameters, the first controlled similar type parameter is calibrated as the similar benchmark parameter, and the similar benchmark parameter is determined in the previous similar parameter single full change data in the entire single run process. , where m represents the number of the historical collaborative change data of the same type of parameters in the previous single run; according to the previous single full-process change data of the same type of parameters , determine the change data of other similar parameters in the whole single operation process relative to the previous similar parameters The difference between the two forms the corresponding single-time relative collaborative data of the previous similar parameters. , n represents the number of different parameters of the same type as the same benchmark parameter; for different single-run similar parameter historical collaborative change data in the previous single-run similar parameter historical collaborative change data set, the same similar parameter corresponding to the previous similar parameter single full-process relative collaborative data Clustering is performed and sorted in the order of time dimension to form a single relative collaborative sequence data set of the previous similar parameters, and the collaborative change trend analysis is performed in the following way: for the single relative collaborative sequence data set of the previous similar parameters, the adjacent single relative collaborative data of the previous similar parameters are determined. The difference of numerical integration in the whole process is linearly fitted according to the difference to form the linear change information of the relative synergistic difference of the same type of parameters; according to the linear change information of the relative synergistic difference of the same type of parameters, the previous single relative synergistic data of the same type of parameters closest to the previous single relative synergistic sequence data set in the time dimension is determined. The previous and subsequent similar parameters predict the single full-process relative coordination data ; Collect all previous similar parameters to predict the relative coordination data of a single full process , forming the initial similar parameters collaborative change characteristic data.

[0011] In the present invention, it can be understood that the extraction of the initial similar parameter collaborative change feature data using the previous clustering historical data mainly considers the influence of the change data caused by the collaborative change of similar parameters when the time factor changes. This influence can be expressed by the change trend of the cumulative deviation of the similar parameters relative to the benchmark parameters under the selected benchmark parameters. The size of the cumulative deviation is affected by the time factor and shows a regular change trend. There are various ways to analyze the trend. This application determines it through linear fitting. Of course, a higher-order prediction function can also be used to improve the accuracy of data analysis. After obtaining the characteristic data of the trend change, the difference in the future time can be predicted. Of course, this prediction can be achieved by averaging the predicted cumulative difference when forming the predicted data, that is, it is considered that the existing cumulative difference is formed by accumulating the same value per unit time during a single operation. Such averaging is conducive to the overall prediction of the average level of the control deviation level of equipment and facilities, and is representative of big data. In addition, the selection of similar benchmark parameters is based on the parameters that need to be controlled first when the instrument is running. For example, for flow control, for arterial pumps and venous pumps, the parameters of the venous pump are subject to the operation of the arterial pump, because the flow value entering the arterial pump determines the matching degree of the venous pump to the flow control. Therefore, the parameters that need to be controlled first are taken as the basis. Their data are less affected by the same type of parameters and have the outstanding advantage of active control. When conducting targeted compensation analysis later, the benchmark parameter data can be adjusted first through a relatively simple analysis, and then the data of similar parameters affected by the benchmark parameters can be obtained more quickly.

[0012] As a possible implementation method, based on the historical collaborative change data of the same parameters in the subsequent single operation, the time series data matching analysis is performed on the initial collaborative change feature data of the same parameters to form the collaborative change feature data of the same parameters, including: the different single operation historical collaborative change data of the same parameters in the historical collaborative change data set of the same parameters in the subsequent single operation, and the subsequent single full change data of the same parameters in the entire single operation process of the same benchmark parameters. , where k represents the number of the historical collaborative change data of the same type of parameters in the subsequent single-run similar parameter historical collaborative change data set; according to the subsequent single-run similar parameter full-process change data , determine the change data of other similar parameters in the whole single operation process relative to the subsequent similar parameters The difference between the two forms the corresponding single-pass relative coordination data of the same type of parameters. ; For different single-run similar parameter historical collaborative change data in the subsequent single-run similar parameter historical collaborative change data set, the corresponding subsequent similar parameter single full-process relative collaborative data of the same similar parameter Clustering is performed and sorted in the order of time dimension to form a single relative coordination sequence data set of similar parameters in the future, and time series data matching analysis is performed in the following way: setting the prediction error limit, according to the single relative coordination sequence data set of different similar parameters in the future, the single relative coordination data of different similar parameters in the future Extract the relative collaborative data of the same type of parameters in the subsequent single process in the order of The following comparison is performed: the first extracted parameter of the same type is compared with the whole process relative synergy data , determine the relative synergy data of the same type of parameters as before for a single full trip If the prediction difference is not greater than the prediction error limit, then the linear change information of the relative synergy difference of the same type of parameters and the first extracted single full-process relative synergy data of the same type of parameters are used. , forming a single full-process relative collaborative data for similar parameters prediction If the prediction difference is greater than the prediction error limit, the first extracted parameter of the same type is obtained. Single full-process relative collaborative data of the same type of parameters as the adjacent previous one The difference of numerical integration in the whole process is used to fit and adjust the linear change information of the relative synergistic difference of similar parameters to form new linear change information of the relative synergistic difference of similar parameters, and according to the new linear change information of the relative synergistic difference of similar parameters, the relative synergistic data of the single whole process of similar parameter prediction is determined in the subsequent prediction. ; For the first extracted parameter, the relative synergy data of the same type is obtained. , and obtain the corresponding subsequent similar parameter prediction single full-process relative collaborative data in sequence Compare the corresponding data and form the corresponding subsequent similar parameters to predict the single full-process relative collaborative data and linear change information of relative synergy difference of similar parameters; until all the subsequent single relative synergy data of similar parameters in the subsequent single relative synergy sequence data set are extracted And the final formed similar parameters will be used to predict the single full-process relative synergy data The linear change information of the relative collaborative difference of the same type of parameters is determined as the collaborative change characteristic information of the same type of parameters; the collaborative change characteristic information of the same type of parameters corresponding to all the same type of parameters are collected to form the collaborative change characteristic data of the same type of parameters.

[0013] In the present invention, the formation of characteristic data of collaborative changes of similar parameters is formed by directional adjustment processing of the initial collaborative change data. This orientation comes from the influence of time factors on the initial collaborative change data. It can be understood that the trend of change of the difference between different parameters of the same type and the baseline parameters will change because the baseline parameters and similar parameters are affected by time factors during the collaborative operation process, such as the performance degradation caused by the change in the service life of equipment and facilities. The impact of this change trend has a fixed direction. Generally speaking, it is the uniform reduction in performance caused by the aging of equipment and facilities. This reduction is manifested as the inability to stably control the operating parameter values ​​at the nominal values. Therefore, the subsequent collaborative data can be used to make directional adjustments to the characteristics of performance degradation of this change trend, that is, by further adjusting the linear change information of the relative collaborative differences of similar parameters, characteristic data that can predict the current parameter values ​​is formed, and then the change of the next operating parameter data is more accurately predicted to make reasonable compensation or early warning. It should be noted that the accuracy of this prediction can be adjusted by the amount of data available. Specifically, the prediction error limit can be set according to actual needs to filter out more data to adjust the linear change information of the relative synergistic differences of similar parameters. The more available data that can be filtered out under big data, the higher the prediction accuracy of the fitted linear change information. However, excessive data can also increase the analysis burden and reduce analysis efficiency. Therefore, the prediction error limit is determined according to the actual situation. Finally, the data predicted by the linear change information is the most likely parameter value change data for the same parameter in the next instrument operation. In addition, because big data can be continuously collected and updated as the instrument is used, the resulting synergistic change characteristic data is real-time, fully considering the impact of time factors on control accuracy, so that the subsequent compensation data is more accurate and real-time.

[0014] As a possible implementation method, based on the collaborative change characteristic data of similar parameters, the best compensation collaborative analysis is performed to form the corresponding similar collaborative compensation data, including: based on the subsequent similar parameter single full-process change data in the most recent single-run similar parameter historical collaborative change data , conduct comparative analysis of the best benchmark compensation coordination to form the best benchmark compensation coordination information; based on the best benchmark compensation coordination information, combined with the collaborative change characteristic data of similar parameters, conduct the best compensation coordination analysis to form the corresponding similar collaborative compensation data.

[0015] In the present invention, the main purpose of collaborative compensation is not to perform peak-shaving and valley-filling processing on the fluctuating data of the parameters during operation, but to adjust the operating parameter values ​​of the parameters to the middle area of ​​the allowable range to avoid control abnormalities or equipment operation abnormalities that cause the parameter values ​​to suddenly change and quickly exceed the allowable value range. Although such compensation cannot achieve the stability of parameter control, it can greatly improve the reliability of operation. On the one hand, it can extend the service life of the instrument. On the other hand, it can also provide a certain amount of time for early warning and adjustment of parameter data abnormalities, fully ensuring the continuous and effective implementation of blood transfusion work.

[0016] As a possible implementation method, the single full-process change data of the same type of parameters in the most recent single run can be used to calculate the change data of the same type of parameters in the same type of parameters. , conduct comparative analysis of the best benchmark compensation coordination to form the best benchmark compensation coordination information, including: the subsequent single full-process change data of the same type of parameters in the most recent single-run historical coordinated change data of the same type of parameters , determine the average benchmark value of the same type of benchmark parameters in the entire single operation process; determine the corresponding optimal parameter average benchmark value based on the operation control allowable range of the same type of benchmark parameters; determine the difference between the average benchmark value of the same type of parameters corresponding to the same type of benchmark parameters and the average benchmark value of the optimal parameter as the optimal parameter average benchmark compensation value.

[0017] In the present invention, the consideration of synergistic compensation is mainly to control the actual variation range of parameter data to the middle area closest to the allowable range. This can avoid abnormalities during use caused by the parameter data approaching the limit of the allowable range as the performance of the equipment and facilities deteriorates. After all, the operation of the blood exchange instrument is an operation process that requires high parameter control accuracy. Once an abnormality occurs, it will have a significant impact on the patient. Therefore, controlling the actual variation range of the parameter to the middle area of ​​the allowable range can effectively ensure the long-term stable and reliable operation of the instrument. It can also provide reasonable warning and response time when the control data is abnormal to ensure the smooth and safe operation of the blood exchange operation. It should be noted that although the service life of different equipment and facilities for parameter coordination has certain differences in the impact of their performance degradation, synergy still has an absolute advantage. That is, the synergy between similar parameters will not be uncertain or fundamentally changed due to differences in performance degradation. Therefore, compensation of different parameters of the same type should be performed simultaneously to ensure that the synergy relationship between the parameters is not significantly affected. The synchronous compensation is also considered here because the parameters of the same type are related. That is, after the parameter controlled first is changed, the parameter of the same type that is controlled later needs to be changed synchronously. For example, a blood exchanger draws blood from the artery first. If pressure control is considered here, the arterial pump's pressure control is performed first. The pressure control parameters of the arterial pump will constrain the subsequent venous pump's pressure control, as the pressure difference between the venous pump and the arterial pump cannot be too large, as this will cause large pressure differential cumulative damage to the pumps. The use of recent full-process change data to determine the average baseline value of the baseline parameter takes into account that the change in baseline parameter values ​​between adjacent runs is generally not large, and can be utilized in predictive compensation collaborative data analysis. Even if there is a large gap, it will be corrected in the real-time collaborative accuracy adjustment analysis.

[0018] As a possible implementation method, based on the optimal benchmark compensation coordination information, combined with the collaborative change characteristic data of similar parameters, the optimal compensation coordination analysis is performed to form the corresponding similar coordination compensation data, including: based on the average benchmark compensation value of the optimal parameter, the single full-process relative coordination data of the subsequent similar parameters corresponding to different similar parameters are predicted. , determine the relative synergy data of the same type of parameters in the subsequent prediction of a single full process The sum of the average benchmark compensation values ​​of the same optimal parameters forms the corresponding similar parameter prediction collaborative compensation information; the similar parameter prediction collaborative compensation information corresponding to different similar parameters is aggregated to form the similar collaborative compensation data.

[0019] In the present invention, the average benchmark compensation value of the best parameter is used to perform compensation analysis on similar parameters. The essence is to increase or decrease the parameter values ​​of the same parameters by the same value according to the benchmark compensation value, and this increase or decrease can also be directly achieved by increasing or decreasing the relative collaborative data, thereby obtaining the information after the relative collaborative data compensation. In essence, the increase or decrease of the relative collaborative data is the translation of the corresponding change curve. It should be noted here that, including similar benchmark parameters and all similar parameters, there are fluctuations in the parameter values ​​during the entire operation process, but the range of such fluctuations is small under normal circumstances. Compensating for them will usually not cause the maximum or minimum value of the fluctuation to exceed the allowable range after compensation. If there is, the parameter data before compensation has already become abnormal. After all, compensation is to move the parameter data to the optimal middle area. Such abnormal data will not be used as the basic data for the extraction of change feature data in this application, which will affect the results of the analysis or cause a waste of resources due to data screening and analysis.

[0020] As a possible implementation method, the real-time collaborative data of similar parameters is adjusted and analyzed based on collaborative accuracy to form real-time collaborative adjustment data of similar parameters, including: obtaining real-time benchmark parameter change data of similar benchmark parameters in the real-time operation period, and performing collaborative accuracy analysis in combination with the average benchmark compensation value of the best parameter to form a real-time collaborative accuracy analysis result; according to the real-time collaborative accuracy analysis result, the similar collaborative compensation data is adjusted to form real-time collaborative adjustment data of similar parameters.

[0021] In the present invention, it is understood that compensation data is the result of data analysis based on predicted data generated through big data analysis. Although it accurately reflects the trend of data changes, it may deviate from the predicted data in practice. Consequently, real-time compensation cannot control the parameter data within the optimal preset range. Therefore, it is necessary to obtain real-time data for timely analysis and adjustment to ensure accurate and effective compensation.

[0022] As a possible implementation method, real-time benchmark parameter change data of similar benchmark parameters in the real-time operation period is obtained, and collaborative accuracy analysis is performed in combination with the optimal parameter average benchmark compensation value to form a real-time collaborative accuracy analysis result, including: determining the real-time benchmark average value based on the real-time benchmark parameter change data; performing the following collaborative accuracy analysis based on the real-time benchmark average value and the optimal parameter average benchmark compensation value: if the difference between the real-time benchmark average value and the optimal parameter average benchmark compensation value is greater than the real-time collaborative accuracy limit, then the real-time benchmark average adjustment value of the real-time benchmark average value is determined based on the real-time collaborative accuracy limit; if the difference between the real-time benchmark average value and the optimal parameter average benchmark compensation value is not greater than the real-time collaborative accuracy limit, then the following judgment is performed on each similar parameter: obtaining real-time relative collaborative data of similar parameters, if the difference between the average value of the real-time relative collaborative data and the average value of the similar parameter prediction system compensation information is not greater than the predicted collaborative accuracy limit, then real-time collaborative normal information is formed; if the difference between the average value of the real-time relative collaborative data and the average value of the similar parameter prediction system compensation information is greater than the predicted collaborative accuracy limit, then the real-time collaborative adjustment value of the average value of the real-time relative collaborative data is determined based on the predicted collaborative accuracy limit.

[0023] In the present invention, the real-time collaborative accuracy analysis is mainly to eliminate the predicted deviation that exists when the predicted compensation data is combined with the real-time data. The analysis includes the benchmark parameters and other similar parameters. It can be understood that the predicted deviation of the benchmark parameters has a greater impact, so the collaborative accuracy analysis of the benchmark parameters is first performed, and the average value and the set real-time collaborative accuracy limit are used as the basis for deviation judgment. If a deviation occurs, it is necessary to determine the difference between the average value of the real-time benchmark data that has not deviated and the average value of the real-time benchmark data. If the deviation between the benchmark parameter and the predicted compensation data is within the allowable range, the collaborative accuracy analysis of other similar parameters is performed. Therefore, even if the benchmark parameters are normal, there are differences in performance changes in the collaborative equipment and facilities. Therefore, it is necessary to continue to analyze other similar parameters when the benchmark parameters are normal. Similarly, the predicted collaborative accuracy limit is used as the judgment basis for whether a deviation occurs. The difference in the average value of the deviation is obtained and used as the basis for real-time adjustment. The limit value can be determined according to the actual situation.

[0024] As a possible implementation method, based on the results of real-time collaborative accuracy analysis, similar collaborative compensation data is adjusted to form real-time collaborative adjustment data of similar parameters, including: when the real-time benchmark average value forms a corresponding real-time benchmark average adjustment value, the real-time benchmark average value is adjusted according to the real-time benchmark average adjustment value to form benchmark real-time collaborative adjustment information; when the real-time relative collaborative data forms a real-time collaborative adjustment value, the average value of the real-time relative collaborative data is adjusted according to the real-time collaborative adjustment value to form parameter real-time collaborative adjustment information.

[0025] In the present invention, after obtaining the adjusted average, the adjustment value can be used to perform translation adjustment on the real-time data to ensure that it is in the best position, achieve high-accuracy regulation, and effectively ensure the stable and reliable operation of the blood exchange instrument.

[0026] The beneficial effects of the intelligent fully automatic blood exchange instrument for neonates provided by the present invention are as follows:

[0027] The device collects historical data of the blood exchange machine operation to obtain change characteristic analysis of coordinated regulation between parameters of the same type, and then obtains parameter coordinated characteristic data under the current state of the blood exchange machine. On this basis, predictive compensation analysis is performed to determine reasonable compensation data. While using the compensation data for real-time coordinated control, real-time coordinated monitoring and adjustment are performed. This fully and effectively ensures efficient and intelligent coordination between parameters of the same type of blood exchange machine, further improves the intelligence level of the blood exchange machine, and gets rid of the influence of errors easily caused by human operation, greatly reducing the risk of blood exchange surgery and making blood exchange more accurate and safe. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 A diagram showing the working steps of a newborn intelligent fully automatic blood exchange instrument provided by an embodiment of the present invention;

[0030] Figure 2 This is a structural diagram of an intelligent fully automatic blood exchange instrument for neonates provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] Neonatal transfusion is a high-risk procedure, requiring stringent control of blood parameters such as pressure and flow, requiring careful operation. While intelligent transfusion machines have emerged with the advancement of science and technology, most still require human control to ensure their normal, stable, and reliable operation.

[0033] Intelligent blood exchange machines, which rely on personnel, are still subject to the influence of human factors and do not substantially reduce surgical risks. To achieve more accurate and reliable blood exchange procedures, it is necessary to analyze and process the parameters of the blood exchange machine. Considering the different energy supply devices on the blood exchange machine, their parameter control is closely linked. Ensuring their intelligent and accurate system operation is a key consideration.

[0034] refer to Figure 1~Figure 2 , Figure 1 A diagram showing the working steps of a newborn intelligent fully automatic blood exchange instrument provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of an intelligent fully automatic blood exchange machine for neonates provided in an embodiment of the present invention. An embodiment of the present invention provides an intelligent fully automatic blood exchange machine for neonates, which acquires characteristic change analysis of coordinated regulation between parameters of the same type by collecting historical data of the blood exchange machine operation, and then acquires parameter coordinated characteristic data under the current state of the blood exchange machine. On this basis, predictive compensation analysis is performed to determine reasonable compensation data, and while using the compensation data for real-time coordinated control, real-time coordinated monitoring and adjustment are performed, fully and effectively ensuring efficient and intelligent coordination between parameters of the same type of blood exchange machine, further improving the intelligence level of the blood exchange machine, and getting rid of the influence of errors easily generated by human operation, greatly reducing the risk of blood exchange surgery, and making blood exchange more accurate and safe.

[0035] A newborn intelligent fully automatic blood exchange instrument is specifically configured as follows:

[0036] S1: Collect historical operation data, analyze the coordinated change characteristics of parameters of the same type, and form coordinated change characteristic data of parameters of the same type.

[0037] Collect historical operation data, perform collaborative change feature analysis on parameters of the same type, and form collaborative change feature data of parameters of the same type, including: extracting collaborative change data of parameters of the same type for each operation in time dimension order based on historical operation data, and forming historical collaborative change data of parameters of the same type for a single operation; clustering and dividing historical collaborative change data of parameters of the same type for different single operations in time dimension order, and forming a dataset of historical collaborative change of parameters of the same type for the previous single operation and a dataset of historical collaborative change of parameters of the same type for the subsequent single operation; extracting collaborative change trend features for parameters of the same type based on the dataset of historical collaborative change of parameters of the same type for the previous single operation, and forming initial collaborative change feature data of parameters of the same type; performing time series data matching analysis on the initial collaborative change feature data of parameters of the same type based on the historical collaborative change data of parameters of the same type for the subsequent single operation, and forming collaborative change feature data of parameters of the same type.

[0038] Big data analysis of historical operating data primarily identifies the actual coordinated control of instrument parameters under the current state and service life. This accurately reflects the trends in coordinated parameter changes during actual instrument operation. It is understood that for an instrument, as long as the coordinated control of parameters of the same type is within the corresponding allowable range, the instrument can function normally without affecting adjuvant therapy. However, the allowable range of each parameter does not reflect the numerical coordinated relationship during instrument operation and, therefore, cannot confirm the trend or risk of abnormal parameter changes. Therefore, it is necessary to analyze the characteristics of coordinated change trends to accurately understand the coordinated relationship between parameters of the same type and make timely adjustments to potential coordinated anomalies. Considering the temporal nature of coordinated relationships, as instrument lifespan changes can cause performance degradation in the equipment and facilities that control the parameters, the analysis requires extracting recent data. The time span of the extracted historical data can be determined based on the actual impact of the instrument's service life on parameter control. Furthermore, to ensure that the extracted feature information has a strong temporal directional component, clustering is performed, and the closest historical data is used as the basis for initial feature data directional adjustments, which can further improve the accuracy and real-time performance of the resulting data. In addition, it should be noted that for blood exchange machines, parameters of the same type have stronger synergy. Synergistic analysis of parameters of the same type can effectively ensure that the blood exchange machine can achieve intelligent and precise parameter control. The same type of parameters here refer to the same type of control parameters of different operating devices on the blood exchange machine. For example, for pressure, this includes the pressure control parameters of arterial pumps, venous pumps, and other pumps. Of course, the same applies to parameters of the same type such as flow rate and flow velocity.

[0039] According to the previous single-run similar parameter historical collaborative change data set, the collaborative change trend feature extraction for the similar parameters is performed to form the initial similar parameter collaborative change feature data, including: for different single-run similar parameter historical collaborative change data in the previous single-run similar parameter historical collaborative change data set, the first controlled similar parameter is calibrated as the similar benchmark parameter, and the similar benchmark parameter is determined in the previous similar parameter single full-process change data during the entire single run. , where m represents the number of the historical collaborative change data of the same type of parameters in the previous single run; according to the previous single full-process change data of the same type of parameters , determine the change data of other similar parameters in the whole single operation process relative to the previous similar parameters The difference between the two forms the corresponding single-time relative collaborative data of the previous similar parameters. , n represents the number of different parameters of the same type as the same benchmark parameter; for different single-run similar parameter historical collaborative change data in the previous single-run similar parameter historical collaborative change data set, the same similar parameter corresponding to the previous similar parameter single full-process relative collaborative data Clustering is performed and sorted in the order of time dimension to form a single relative collaborative sequence data set of the previous similar parameters, and the collaborative change trend analysis is performed in the following way: for the single relative collaborative sequence data set of the previous similar parameters, the adjacent single relative collaborative data of the previous similar parameters are determined. The difference of numerical integration in the whole process is linearly fitted according to the difference to form the linear change information of the relative synergistic difference of the same type of parameters; according to the linear change information of the relative synergistic difference of the same type of parameters, the previous single relative synergistic data of the same type of parameters closest to the previous single relative synergistic sequence data set in the time dimension is determined. The previous and subsequent similar parameters predict the single full-process relative coordination data ; Collect all previous similar parameters to predict the relative coordination data of a single full process , forming the initial similar parameters collaborative change characteristic data.

[0040] It is understandable that the extraction of the initial similar parameter collaborative change feature data using the previous clustering historical data mainly considers the impact of the collaborative change of similar parameters on the change data caused by the change of time factors. This impact can be expressed by the change trend of the cumulative deviation of similar parameters relative to the benchmark parameters under the selected benchmark parameters. The size of the cumulative deviation is affected by the time factor and shows a regular change trend. There are various ways to analyze the trend. This application determines it through linear fitting. Of course, a higher-order prediction function can also be used to improve the accuracy of data analysis. After obtaining the characteristic data of the trend change, the difference in time can be predicted. Of course, this prediction can be achieved by averaging the predicted cumulative difference when forming the predicted data, that is, it is considered that the existing cumulative difference is formed by the accumulation of the same value per unit time during a single operation. Such averaging is conducive to the overall prediction of the average level of the control deviation level of equipment and facilities, and is representative of big data. In addition, the selection of similar benchmark parameters is based on the parameters that need to be controlled first when the instrument is running. For example, for flow control, for arterial pumps and venous pumps, the parameters of the venous pump are subject to the operation of the arterial pump, because the flow value entering the arterial pump determines the matching degree of the venous pump to the flow control. Therefore, the parameters that need to be controlled first are taken as the basis. Their data are less affected by the same type of parameters and have the outstanding advantage of active control. When conducting targeted compensation analysis later, the benchmark parameter data can be adjusted first through a relatively simple analysis, and then the data of similar parameters affected by the benchmark parameters can be obtained more quickly.

[0041] According to the historical collaborative change data of similar parameters in the subsequent single operation, the time series data matching analysis is performed on the initial collaborative change feature data of similar parameters to form the collaborative change feature data of similar parameters, including: the subsequent single full-process change data of similar benchmark parameters in the entire single operation process determined by the different single-operation similar parameter historical collaborative change data in the subsequent single-operation similar parameter historical collaborative change data set. , where k represents the number of the historical collaborative change data of the same type of parameters in the subsequent single-run similar parameter historical collaborative change data set; according to the subsequent single-run similar parameter full-process change data , determine the change data of other similar parameters in the whole single operation process relative to the subsequent similar parameters The difference between the two forms the corresponding single-pass relative coordination data of the same type of parameters. ; For different single-run similar parameter historical collaborative change data in the subsequent single-run similar parameter historical collaborative change data set, the corresponding subsequent similar parameter single full-process relative collaborative data of the same similar parameter Clustering is performed and sorted in the order of time dimension to form a single relative coordination sequence data set of similar parameters in the future, and time series data matching analysis is performed in the following way: setting the prediction error limit, according to the single relative coordination sequence data set of different similar parameters in the future, the single relative coordination data of different similar parameters in the future Extract the relative collaborative data of the same type of parameters in the subsequent single process in the order of The following comparison is performed: the first extracted parameter of the same type is compared with the whole process relative synergy data , determine the relative synergy data of the same type of parameters as before for a single full trip If the prediction difference is not greater than the prediction error limit, then the linear change information of the relative synergy difference of the same type of parameters and the first extracted single full-process relative synergy data of the same type of parameters are used. , forming a single full-process relative collaborative data for similar parameters prediction If the prediction difference is greater than the prediction error limit, the first extracted parameter of the same type is obtained. Single full-process relative collaborative data of the same type of parameters as the adjacent previous one The difference of numerical integration in the whole process is used to fit and adjust the linear change information of the relative synergistic difference of similar parameters to form new linear change information of the relative synergistic difference of similar parameters, and according to the new linear change information of the relative synergistic difference of similar parameters, the relative synergistic data of the single whole process of similar parameter prediction is determined in the subsequent prediction. ; For the first extracted parameter, the relative synergy data of the same type is obtained. , and obtain the corresponding subsequent similar parameter prediction single full-process relative collaborative data in sequence Compare the corresponding data and form the corresponding subsequent similar parameters to predict the single full-process relative collaborative data and linear change information of relative synergy difference of similar parameters; until all the subsequent single relative synergy data of similar parameters in the subsequent single relative synergy sequence data set are extracted And the final formed similar parameters will be used to predict the single full-process relative synergy data The linear change information of the relative collaborative difference of the same type of parameters is determined as the collaborative change characteristic information of the same type of parameters; the collaborative change characteristic information of the same type of parameters corresponding to all the same type of parameters are collected to form the collaborative change characteristic data of the same type of parameters.

[0042] The formation of characteristic data of collaborative changes of similar parameters is formed by making targeted adjustments to the initial collaborative change data. This orientation comes from the influence of time factors on the initial collaborative change data. It can be understood that the trend of change in the difference between different parameters of the same type and the baseline parameters will change because the baseline parameters and similar parameters are affected by time factors during the collaborative operation process, such as the performance degradation caused by the change in the service life of equipment and facilities. The impact of this change trend has a fixed direction. Overall, it is the uniform reduction in performance caused by the aging of equipment and facilities. This reduction is manifested as the inability to stably control the operating parameter values ​​at the nominal values. Therefore, the subsequent collaborative data can be used to make targeted adjustments to the characteristics of performance degradation of this change trend, that is, by further adjusting the linear change information of the relative collaborative differences of similar parameters, characteristic data that can be used to predict the current parameter values ​​is formed, and then the changes in the next operating parameter data can be more accurately predicted to make reasonable compensation or early warning. It should be noted that the accuracy of this prediction can be adjusted by the amount of data available. Specifically, the prediction error limit can be set according to actual needs to filter out more data to adjust the linear change information of the relative synergistic differences of similar parameters. The more available data that can be filtered out under big data, the higher the prediction accuracy of the fitted linear change information. However, excessive data can also increase the analysis burden and reduce analysis efficiency. Therefore, the prediction error limit is determined according to the actual situation. Finally, the data predicted by the linear change information is the most likely parameter value change data for the same parameter in the next instrument operation. In addition, because big data can be continuously collected and updated as the instrument is used, the resulting synergistic change characteristic data is real-time, fully considering the impact of time factors on control accuracy, so that the subsequent compensation data is more accurate and real-time.

[0043] S2: Based on the collaborative change characteristic data of similar parameters, optimal compensation collaborative analysis is performed to form corresponding similar collaborative compensation data.

[0044] According to the collaborative change characteristic data of similar parameters, the optimal compensation collaborative analysis is carried out to form the corresponding similar collaborative compensation data, including: the subsequent similar parameter single full-process change data in the most recent single-run similar parameter historical collaborative change data , conduct comparative analysis of the best benchmark compensation coordination to form the best benchmark compensation coordination information; based on the best benchmark compensation coordination information, combined with the collaborative change characteristic data of similar parameters, conduct the best compensation coordination analysis to form the corresponding similar collaborative compensation data.

[0045] The main purpose of collaborative compensation is not to smooth out the fluctuating data of parameters during operation, but to adjust the operating parameter values ​​of the parameters to the middle area of ​​the allowable range to avoid abnormal control or abnormal equipment operation, which causes the parameter values ​​to suddenly change and quickly exceed the allowable value range. Although such compensation cannot achieve the stability of parameter control, it can greatly improve the reliability of operation. On the one hand, it can extend the service life of the instrument. On the other hand, it can also provide a certain amount of time for early warning and adjustment of parameter data abnormalities, fully ensuring the continuous and effective implementation of blood transfusion work.

[0046] Based on the most recent single-run similar parameter historical collaborative change data, the subsequent similar parameter single full-process change data , conduct comparative analysis of the best benchmark compensation coordination to form the best benchmark compensation coordination information, including: the subsequent single full-process change data of the same type of parameters in the most recent single-run historical coordinated change data of the same type of parameters , determine the average benchmark value of the same type of benchmark parameters in the entire single operation process; determine the corresponding optimal parameter average benchmark value based on the operation control allowable range of the same type of benchmark parameters; determine the difference between the average benchmark value of the same type of parameters corresponding to the same type of benchmark parameters and the average benchmark value of the optimal parameter as the optimal parameter average benchmark compensation value.

[0047] The key consideration for synergistic compensation is to control the actual range of parameter data within the middle of the allowable range. This prevents abnormalities during use, as parameter data approaches the limit of the allowable range as equipment performance deteriorates. After all, blood exchange instrument operation requires high parameter control accuracy; any abnormality can have a significant impact on patients. Therefore, controlling the actual range of parameter variation within the middle of the allowable range effectively ensures the long-term stable and reliable operation of the instrument. It also provides reasonable early warning and response time when control data anomalies occur, ensuring the smooth and safe conduct of blood exchange operations. It should be noted that although the performance degradation of different equipment and facilities involved in parameter coordination varies with their service life, synergy is still dominant. This means that differences in performance degradation will not cause the synergy between similar parameters to be uncertain or fundamentally altered. Therefore, compensation for different parameters of the same type should be performed simultaneously to ensure that the synergy between the parameters is not significantly affected. Synergistic compensation is also considered here because parameters of the same type are correlated. That is, changes in the first-controlled parameter require synchronous changes in the later-controlled parameter of the same type. For example, a blood exchanger draws blood from the artery first. If pressure control is considered here, the arterial pump's pressure control is performed first. The pressure control parameters of the arterial pump will constrain the subsequent venous pump's pressure control, as the pressure difference between the venous pump and the arterial pump cannot be too large, as this will cause large pressure differential cumulative damage to the pumps. The use of recent full-process change data to determine the average baseline value of the baseline parameter takes into account that the change in baseline parameter values ​​between adjacent runs is generally not large, and can be utilized in predictive compensation collaborative data analysis. Even if there is a large gap, it will be corrected in the real-time collaborative accuracy adjustment analysis.

[0048] Based on the best benchmark compensation coordination information, combined with the coordinated change characteristic data of similar parameters, the best compensation coordination analysis is carried out to form the corresponding similar coordination compensation data, including: based on the average benchmark compensation value of the best parameters, the single full-process relative coordination data of the subsequent similar parameters corresponding to different similar parameters are predicted. , determine the relative synergy data of the same type of parameters in the subsequent prediction of a single full process The sum of the average benchmark compensation values ​​of the same optimal parameters forms the corresponding similar parameter prediction collaborative compensation information; the similar parameter prediction collaborative compensation information corresponding to different similar parameters is aggregated to form the similar collaborative compensation data.

[0049] The use of the average benchmark compensation value of the best parameter to perform compensation analysis on similar parameters is essentially to increase or decrease the parameter values ​​of the same parameters by the same amount according to the benchmark compensation value, and this increase or decrease can also be achieved directly by increasing or decreasing the relative collaborative data, thereby obtaining the information after the relative collaborative data compensation. In essence, the increase or decrease of the relative collaborative data is the translation of the corresponding change curve. It should be noted here that, including similar benchmark parameters and all similar parameters, there are fluctuations in the parameter values ​​during the entire operation process, but this fluctuation is normally within a small range, and compensation for it will usually not cause the maximum or minimum value of the fluctuation to exceed the allowable range after compensation. If there is, then the parameter data before compensation has already become abnormal. After all, compensation is to move the parameter data to the optimal middle area. Such abnormal data will not be used as the basic data for the extraction of change feature data in this application, which will affect the results of the analysis or cause a waste of resources due to data screening and analysis.

[0050] S3: Perform real-time collaborative compensation processing based on similar collaborative compensation data to form real-time collaborative data of similar parameters.

[0051] After obtaining the compensation data, direct compensation can be performed during real-time collaborative control. The real-time collaborative data obtained after compensation is the parameter data of the current actual operation process.

[0052] S4: Perform adjustment analysis on the real-time collaborative data of similar parameters based on collaborative accuracy to form real-time collaborative adjustment data of similar parameters.

[0053] Perform adjustment analysis on the real-time collaborative data of similar parameters based on collaborative accuracy to form real-time collaborative adjustment data of similar parameters, including: obtaining real-time benchmark parameter change data of similar benchmark parameters in the real-time operation period, and performing collaborative accuracy analysis in combination with the average benchmark compensation value of the best parameter to form real-time collaborative accuracy analysis results; according to the real-time collaborative accuracy analysis results, adjust the similar collaborative compensation data to form real-time collaborative adjustment data of similar parameters.

[0054] It's understandable that compensation data is the result of analyzing predicted data generated through big data analysis. While accurate in predicting data trends, actual deviations from the predicted data can occur, making real-time compensation incapable of keeping parameter data within the optimal preset range. Therefore, real-time data acquisition, timely analysis, and adjustments are necessary to ensure accurate and effective compensation.

[0055] Real-time benchmark parameter change data of similar benchmark parameters in the real-time operation period are obtained, and collaborative accuracy analysis is performed in combination with the optimal parameter average benchmark compensation value to form a real-time collaborative accuracy analysis result, including: determining the real-time benchmark average value based on the real-time benchmark parameter change data; performing the following collaborative accuracy analysis based on the real-time benchmark average value and the optimal parameter average benchmark compensation value: if the difference between the real-time benchmark average value and the optimal parameter average benchmark compensation value is greater than the real-time collaborative accuracy limit, then the real-time benchmark average adjustment value of the real-time benchmark average value is determined based on the real-time collaborative accuracy limit; if the difference between the real-time benchmark average value and the optimal parameter average benchmark compensation value is not greater than the real-time collaborative accuracy limit, then the following judgment is performed on each similar parameter: obtaining real-time relative collaborative data of similar parameters, if the difference between the average value of the real-time relative collaborative data and the average value of the compensation information of the prediction system of the similar parameters is not greater than the prediction collaborative accuracy limit, then real-time collaborative normal information is formed; if the difference between the average value of the real-time relative collaborative data and the average value of the compensation information of the prediction system of the similar parameters is greater than the prediction collaborative accuracy limit, then the real-time collaborative adjustment value of the average value of the real-time relative collaborative data is determined based on the prediction collaborative accuracy limit.

[0056] Real-time collaborative accuracy analysis primarily aims to eliminate prediction deviations that occur when combining predicted compensation data with real-time data. This analysis includes analysis of baseline parameters and other similar parameters. As you can understand, prediction deviations of baseline parameters have a significant impact, so the collaborative accuracy analysis of the baseline parameters is performed first. The average value and the set real-time collaborative accuracy limit are used as the basis for determining deviations. If a deviation occurs, the difference between the average value of the real-time baseline data and the average value of the real-time baseline data is determined. If the deviation between the baseline parameter and the predicted compensation data is within the allowable range, the collaborative accuracy analysis of other similar parameters is then performed. Even if the baseline parameters are normal, performance variations in collaborative equipment and facilities may occur. Therefore, it is necessary to continue analyzing other similar parameters while the baseline parameters are normal. Again, the predicted collaborative accuracy limit is used as the basis for determining whether a deviation has occurred. For deviations, the difference between the average values ​​is calculated and used as the basis for real-time adjustments. The limit can be determined based on actual conditions.

[0057] According to the results of the real-time collaborative accuracy analysis, the same type of collaborative compensation data is adjusted to form real-time collaborative adjustment data of the same type of parameters, including: when the real-time benchmark average value forms the corresponding real-time benchmark average adjustment value, the real-time benchmark average value is adjusted according to the real-time benchmark average adjustment value to form benchmark real-time collaborative adjustment information; when the real-time relative collaborative data forms the real-time collaborative adjustment value, the average value of the real-time relative collaborative data is adjusted according to the real-time collaborative adjustment value to form parameter real-time collaborative adjustment information.

[0058] After obtaining the adjusted average, the adjustment value can be used to perform translation adjustment on the real-time data to ensure that it is in the best position, achieve high-accuracy regulation, and effectively ensure the stable and reliable operation of the blood exchange instrument.

[0059] The present application also provides the specific composition of the system. It includes a data acquisition unit for collecting historical operation data and real-time collaborative data of similar parameters; a feature extraction unit for performing collaborative change feature analysis of the same type of parameters on the historical operation data acquired by the data acquisition unit to form collaborative change feature data of similar parameters, and performing optimal compensation collaborative analysis to form corresponding similar collaborative compensation data; an operation processing unit for performing real-time collaborative compensation processing based on the similar collaborative compensation data formed by the feature extraction unit to form real-time collaborative data of similar parameters; and a real-time adjustment unit for performing adjustment analysis based on collaborative accuracy based on the real-time collaborative data of similar parameters acquired by the data acquisition unit to form real-time collaborative adjustment data of similar parameters.

[0060] In summary, the beneficial effects of the intelligent fully automatic blood exchange instrument for neonates provided by the embodiment of the present invention are as follows:

[0061] The device collects historical data of the blood exchange machine operation to obtain change characteristic analysis of coordinated regulation between parameters of the same type, and then obtains parameter coordinated characteristic data under the current state of the blood exchange machine. On this basis, predictive compensation analysis is performed to determine reasonable compensation data. While using the compensation data for real-time coordinated control, real-time coordinated monitoring and adjustment are performed. This fully and effectively ensures efficient and intelligent coordination between parameters of the same type of blood exchange machine, further improves the intelligence level of the blood exchange machine, and gets rid of the influence of errors easily caused by human operation, greatly reducing the risk of blood exchange surgery and making blood exchange more accurate and safe.

[0062] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if" and "if" all mean that the device will perform corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the device to perform judgment actions when implemented, nor does it mean that there are other limitations.

[0063] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0064] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0065] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0066] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0067] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0068] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A newborn intelligent fully automatic blood exchange instrument, characterized in that: Configured to: Collect historical operation data, analyze the coordinated change characteristics of the same type of parameters, and form the coordinated change characteristic data of the same type of parameters; Performing optimal compensation synergy analysis based on the similar parameter synergy change characteristic data to generate corresponding similar synergy compensation data; Performing real-time collaborative compensation processing based on the same type collaborative compensation data to form real-time collaborative data of the same type of parameters; Performing adjustment analysis on the real-time collaborative data of similar parameters based on collaborative accuracy to generate real-time collaborative adjustment data of similar parameters; The collecting of historical operation data and analysis of the coordinated change characteristics of the same type of parameters to form the coordinated change characteristic data of the same type of parameters include: Extract the coordinated change data of the same type of parameters for each operation according to the historical operation data in the order of time dimension to form the historical coordinated change data of the same type of parameters for a single operation; Clustering and dividing the different single-run similar parameter historical collaborative change data in order of time dimension to form a previous single-run similar parameter historical collaborative change data set and a subsequent single-run similar parameter historical collaborative change data set respectively; Extracting collaborative change trend features of similar parameters based on the historical collaborative change data set of similar parameters in the previous single run to form initial collaborative change feature data of similar parameters; Performing time series data matching analysis on the initial similar parameter collaborative change characteristic data based on the subsequent single-run similar parameter historical collaborative change data to form the similar parameter collaborative change characteristic data; The extracting of collaborative change trend features of similar parameters based on the previous single-run historical collaborative change data set of similar parameters to form initial collaborative change feature data of similar parameters includes: For the different historical collaborative change data of the same type of parameters in the previous single operation, the first controlled parameter of the same type is calibrated as the same type benchmark parameter, and the previous single full-process change data of the same type of parameters in the whole single operation process are determined. , wherein m represents the number of the different single-run similar parameter historical coordinated change data in the previous single-run similar parameter historical coordinated change data set; According to the single full-process change data of the previous similar parameters , determine the change data of other similar parameters in the whole single operation process relative to the previous similar parameters The difference between the two forms the corresponding single-time relative collaborative data of the previous similar parameters. , n represents the number of different parameters of the same type as the same type of benchmark parameters; For the different single-run similar parameter historical collaborative change data in the previous single-run similar parameter historical collaborative change data set, the previous similar parameter single full-process relative collaborative data corresponding to the same similar parameter Clustering is performed and sorted in time dimension order to form a single relative collaborative order data set of the previous similar parameters, and the collaborative change trend analysis is performed in the following ways: For the single relative coordination sequence data set of the previous similar parameter, determine the adjacent single relative coordination data set of the previous similar parameter The difference of numerical integration in the whole process is used, and linear fitting is performed based on the difference to form the linear change information of the relative synergistic difference of similar parameters; According to the linear change information of the relative synergy difference of the same type of parameters, the previous single relative synergy sequence data set of the same type of parameters closest to the previous single relative synergy sequence data set in the time dimension is determined. The previous and subsequent similar parameters predict the single full-process relative coordination data ; Collect all the previous similar parameters to predict the relative synergy data of a single full trip , forming the initial similar parameter collaborative change characteristic data; The optimal compensation collaborative analysis is performed based on the collaborative change characteristic data of the same type of parameters to form corresponding collaborative compensation data of the same type, including: According to the single full-process change data of the subsequent similar parameter in the most recent single-run similar parameter historical collaborative change data , conduct comparative analysis of the best benchmark compensation synergy to form the best benchmark compensation synergy information; Based on the optimal benchmark compensation coordination information and in combination with the similar parameter coordination change characteristic data, an optimal compensation coordination analysis is performed to form the corresponding similar coordination compensation data; The performing adjustment analysis on the real-time collaborative data of similar parameters based on collaborative accuracy to form real-time collaborative adjustment data of similar parameters includes: Acquire real-time benchmark parameter change data of the same type of benchmark parameters during the real-time operation period, and perform collaborative accuracy analysis in combination with the average benchmark compensation value of the best parameter to form a real-time collaborative accuracy analysis result; According to the real-time collaborative accuracy analysis result, the same type collaborative compensation data is adjusted to form the same type parameter real-time collaborative adjustment data.

2. The intelligent fully automatic blood exchange instrument for newborns according to claim 1, characterized in that: The performing of time series data matching analysis on the initial similar parameter collaborative change characteristic data based on the subsequent single-run similar parameter historical collaborative change data to form the similar parameter collaborative change characteristic data includes: For the different historical collaborative change data of the same parameter in the subsequent single run, the subsequent single full-process change data of the same parameter in the entire single run are determined. , wherein k represents the number of the different single-run similar parameter historical coordinated change data in the subsequent single-run similar parameter historical coordinated change data set; According to the single full-process change data of the same type of parameters , determine the change data of other similar parameters in the whole single operation process relative to the single full-process change data of the following similar parameters The difference between the two forms the corresponding single-pass relative coordination data of the same type of parameters. ; For the different single-run similar parameter historical collaborative change data in the subsequent single-run similar parameter historical collaborative change data set, the subsequent similar parameter single full-process relative collaborative data corresponding to the same similar parameter Clustering is performed and sorted in the order of time dimension to form a single relative collaborative sequence data set of similar parameters, and time series data matching analysis is performed in the following way: Set the prediction error limit, according to the single relative coordination sequence data set of the same type of parameters in the future, the single relative coordination data set of the same type of parameters in the future Extract the relative collaborative data of the same type of parameters in the subsequent single process in the order of Compare the following methods: The first extracted relative synergy data of the same type of parameters , determine the relative synergy data of the same parameters as above If the predicted difference is not greater than the prediction error limit, then according to the linear change information of the relative synergy difference of the same type of parameters and the extracted first single full-process relative synergy data of the following same type of parameters , forming a single full-process relative collaborative data for similar parameters prediction If the predicted difference is greater than the predicted error limit, the first extracted relative collaborative data of the subsequent similar parameters is obtained. Single full-process relative collaborative data of the same type of parameters as the adjacent previous ones The difference of the numerical integration in the whole process is used to fit and adjust the linear change information of the relative synergistic difference of the similar parameters to form new linear change information of the relative synergistic difference of the similar parameters, and the relative synergistic data of the subsequent similar parameters predicted in a single whole process is determined based on the new linear change information of the relative synergistic difference of the similar parameters. ; The single full-process relative collaborative data of the same type parameters after the first one extracted , and obtain the corresponding subsequent similar parameter prediction single full-process relative collaborative data in sequence Compare the corresponding data and form the corresponding subsequent similar parameters to predict the single full-process relative collaborative data and linear change information of relative synergistic differences of similar parameters; Until all the subsequent similar parameter single relative coordination sequence data sets are extracted And the final formed similar parameters will be used to predict the single full-process relative synergy data The linear change information of the relative synergistic difference of the same type of parameters is determined as the synergistic change feature information of the same type of parameters; The similar parameter collaborative change characteristic information corresponding to all similar parameters is collected to form the similar parameter collaborative change characteristic data.

3. The intelligent fully automatic blood exchange instrument for newborns according to claim 1, characterized in that: The subsequent single full-process change data of the same type of parameters in the most recent single-run historical collaborative change data of the same type of parameters , conduct comparative analysis of the best benchmark compensation coordination and form the best benchmark compensation coordination information, including: According to the single full-process change data of the subsequent similar parameter in the most recent single-run similar parameter historical collaborative change data , determining an average benchmark value of the same type of benchmark parameter for the same type of benchmark parameter during the entire single operation; Determine the corresponding optimal parameter average benchmark value based on the operating control allowable range of the similar benchmark parameters; The difference between the average reference value of the same type of parameters corresponding to the same type of reference parameters and the average reference value of the best parameter is determined as the average reference compensation value of the best parameter.

4. The intelligent fully automatic blood exchange instrument for newborns according to claim 3, characterized in that: The optimal compensation coordination analysis is performed based on the optimal benchmark compensation coordination information and combined with the similar parameter coordination change characteristic data to form the corresponding similar coordination compensation data, including: According to the average benchmark compensation value of the optimal parameter, the single full-process relative collaborative data of the subsequent similar parameters corresponding to different similar parameters is predicted , determine the relative synergy data of the subsequent similar parameters prediction for a single full trip The sum of the average benchmark compensation value of the optimal parameter forms the corresponding similar parameter prediction collaborative compensation information; The same type parameter prediction synergistic compensation information corresponding to different same type parameters is aggregated to form the same type synergistic compensation data.

5. The intelligent fully automatic blood exchange instrument for newborns according to claim 1, characterized in that: The real-time benchmark parameter change data of the same benchmark parameter in the real-time operation period is obtained, and the collaborative accuracy analysis is performed in combination with the average benchmark compensation value of the optimal parameter to form a real-time collaborative accuracy analysis result, including: Determining a real-time benchmark average value based on the real-time benchmark parameter change data; Based on the real-time benchmark average value and the optimal parameter average benchmark compensation value, the following collaborative accuracy analysis is performed: If the difference between the real-time benchmark average value and the optimal parameter average benchmark compensation value is greater than the real-time collaborative accuracy limit, determining a real-time benchmark average adjustment value of the real-time benchmark average value based on the real-time collaborative accuracy limit; If the difference between the real-time benchmark average value and the optimal parameter average benchmark compensation value is not greater than the real-time collaborative accuracy limit, the following judgment is performed on each similar parameter: Obtain real-time relative collaborative data of similar parameters. If the difference between the average value of the real-time relative collaborative data and the average value of the predicted collaborative compensation information of the similar parameters is not greater than the predicted collaborative accuracy limit, then real-time collaborative normal information is generated. If the difference between the average value of the real-time relative collaborative data and the average value of the predicted collaborative compensation information of the similar parameters is greater than the predicted collaborative accuracy limit, then the real-time collaborative adjustment value of the average value of the real-time relative collaborative data is determined based on the predicted collaborative accuracy limit.

6. The intelligent fully automatic blood exchange instrument for newborns according to claim 5, characterized in that: The adjusting the similar collaborative compensation data according to the real-time collaborative accuracy analysis result to form the similar parameter real-time collaborative adjustment data includes: When the real-time benchmark average value forms the corresponding real-time benchmark average adjustment value, adjusting the real-time benchmark average value according to the real-time benchmark average adjustment value to form benchmark real-time collaborative adjustment information; When the real-time relative collaborative data forms the real-time collaborative adjustment value, the average value of the real-time relative collaborative data is adjusted according to the real-time collaborative adjustment value to form parameter real-time collaborative adjustment information.

Images