Infusion management and control system based on Internet of Things

Abstract

The invention discloses an infusion management and control system based on the Internet of Things, and relates to the technical field of automatic control, and the method comprises the steps: collecting infusion monitoring data distributed at K beds, and obtaining an infusion flow rate, a liquid medicine bag liquid level and a liquid medicine temperature sequence; the flow velocity and the liquid level are subjected to combined anomaly analysis, and a liquid medicine conveying anomaly result is obtained; performing interaction correlation analysis on the temperature sequence to obtain a temperature anomaly result; an infusion valve, a liquid medicine bag replacing device and a heating device are triggered according to the analysis result, and intelligent control over the infusion process is achieved. The technical problems that in the prior art, the infusion process control reliability is low, and the fitting degree with the actual infusion condition is low are solved, and the technical effect of improving the infusion process control reliability and the fitting degree with the actual infusion condition is achieved.

Description

Technical Field

[0001] This application relates to the field of automation control technology, and in particular, to an infusion management and control system based on the Internet of Things. Background Art

[0002] Traditional infusion management usually relies on medical staff to manually monitor the infusion process, such as observing key parameters such as infusion flow rate, remaining liquid volume, and liquid medicine temperature. However, this method has problems of low monitoring efficiency and lagging response during simultaneous infusion of multiple beds or long-term infusion. Especially when the infusion flow rate fluctuates, the liquid medicine is nearly exhausted, or the liquid medicine temperature changes, effective measures may not be taken in time, resulting in infusion interruption or affecting the infusion quality. In addition, the existing technology has limited ability in multi-parameter linkage monitoring. Usually, only a single parameter can be independently monitored, lacking the ability of comprehensive analysis and collaborative processing, and it is difficult to meet the demand for precise control of the infusion process. With the increase in the complexity of the medical system, the above problems reflect the deficiencies of traditional infusion management methods in terms of safety and accuracy.

[0003] In the current related technologies, there are technical problems of low reliability of infusion process control and low degree of fit with the actual infusion situation. Summary of the Invention

[0004] This application solves the technical problems of low reliability of infusion process control and low degree of fit with the actual infusion situation in the existing technology by providing an infusion management and control system based on the Internet of Things.

[0005] This application provides an infusion management and control system based on the Internet of Things, including: Monitoring data acquisition module, which is used to collect the monitoring data of K infusion monitoring devices arranged on K beds in a preset monitoring window, and obtain a sequence of K infusion monitoring data sets, where K is an integer greater than or equal to 1; liquid level sequence acquisition module, which is used to retrieve the sequence of K infusion monitoring data sets with infusion flow rate and liquid level of the medicine package as indexes, and obtain a sequence of K infusion flow rates and a sequence of K liquid levels of the medicine package; abnormal analysis module, which is used to perform joint abnormal analysis on the sequence of K infusion flow rates and the sequence of K liquid levels of the medicine package, and obtain K abnormal analysis results of liquid medicine delivery; temperature sequence acquisition module, which is used to retrieve the sequence of K infusion monitoring data sets with liquid medicine temperature as an index, and obtain a sequence of K liquid medicine temperatures; interactive correlation abnormal analysis module, which is used to perform interactive correlation abnormal analysis on the sequence of K liquid medicine temperatures, and obtain K abnormal analysis results of liquid medicine temperature; infusion control module, which is used to trigger the infusion valves, medicine package replacement devices and heating devices of the K beds according to the K abnormal analysis results of liquid medicine delivery and the K abnormal analysis results of liquid medicine temperature, and complete the infusion control of the K beds.

[0006] It is intended to propose an Internet of Things-based infusion management and control system through this application. First, collect the infusion monitoring data arranged on K beds, and obtain the sequences of infusion flow rate, liquid level of the medicine package and liquid medicine temperature; perform joint abnormal analysis on the flow rate and liquid level to obtain the abnormal result of liquid medicine delivery; perform interactive correlation analysis on the temperature sequence to obtain the abnormal result of temperature; trigger the infusion valve, medicine package replacement device and heating device according to the analysis result to realize the intelligent control of the infusion process, and achieve the technical effect of improving the reliability of infusion process control and the fitting degree of actual infusion situation. Description of the Drawings

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps of operations can be removed from these processes.

[0008] Figure 1 It is a schematic structural diagram of an Internet of Things-based infusion management and control system provided by an embodiment of the present application.

[0009] Figure 2Schematic structural diagram of a preset liquid level requirement judgment unit of an infusion management and control system based on the Internet of Things provided by an embodiment of the present application.

[0010] Explanation of reference numerals: Monitoring data acquisition module 10, liquid level sequence acquisition module 20, anomaly analysis module 30, temperature sequence acquisition module 40, interactive correlation anomaly analysis module 50, infusion control module 60. Specific implementation manners

[0011] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific implementation manners of the present application are specifically exemplified below.

[0012] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0013] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first\second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0014] An embodiment of the present application provides an infusion management and control system based on the Internet of Things, as Figure 1 shown, the system includes: The monitoring data acquisition module 10 is used to collect monitoring data of K infusion monitoring devices arranged at K beds in a preset monitoring window, and obtain K infusion monitoring data set sequences, wherein K is an integer greater than or equal to 1. Specifically, the monitoring data acquisition module 10 is used to obtain real-time data within a preset monitoring window from the infusion monitoring devices arranged at K beds, and generate K infusion monitoring data set sequences. Each infusion monitoring device is equipped with a temperature sensor, a liquid level sensor, and a flow rate sensor, which respectively collect the temperature of the liquid medicine, the liquid level height of the liquid medicine bag, and the current infusion speed. The monitoring window is set to a fixed time interval (for example, every 5 seconds) to ensure the continuity and stability of data collection. The collected data is preliminarily screened before uploading to remove abnormal values ​​and noise. For example, when the temperature data exceeds a reasonable range (lower than room temperature or higher than the safety upper limit) or the liquid level sensor detects unreasonable and drastic fluctuations, it will trigger re-collection to ensure the accuracy of the data. Finally, the collected data sequence is uploaded to the central server through the Internet of Things interface to provide reliable basic data for subsequent abnormal analysis and intelligent control.

[0015] The liquid level sequence acquisition module 20 is used to retrieve the K infusion monitoring data set sequences with the infusion flow rate and the liquid level of the medicine bag as indexes, and obtain K infusion flow rate sequences and K medicine bag liquid level sequences. Specifically, the liquid level sequence acquisition module 20 extracts data related to flow rate and liquid level from the infusion monitoring data arranged in K beds by indexing the monitoring data set sequence and taking the infusion flow rate and the liquid level of the medicine bag as conditions. Specifically, the module retrieves the flow rate and liquid level fields from the monitoring data set of each bed, aligns the data according to the timestamp, and generates the corresponding infusion flow rate sequence and medicine bag liquid level sequence. For example, within the monitoring window, if the flow rate data of a bed contains 60 records and the liquid level data contains 58 records, the module unifies the timestamps by interpolation or truncation to ensure that the flow rate and liquid level sequences correspond one to one. At the same time, the module performs anomaly detection and repair on the extracted data, such as eliminating the jump value of the liquid level or the sudden zero value in the flow rate, to ensure data integrity and quality. Finally, the module outputs structured K infusion flow rate sequences and K liquid level sequences of the medicine package, providing high-quality time series data input for the anomaly analysis module.

[0016] Anomaly analysis module 30 is used to perform joint anomaly analysis on the K infusion flow rate sequences and the K liquid medicine bag liquid level sequences to obtain K liquid medicine delivery anomaly analysis results. Specifically, the anomaly analysis module 30 identifies abnormal situations during the infusion process and outputs the analysis results through the joint analysis of the infusion flow rate sequence and the liquid medicine bag liquid level sequence. First, the module extracts the last data point of each liquid level sequence and determines whether it meets the minimum liquid level requirement. If it does not meet the requirement, it is directly determined that the liquid medicine delivery is abnormal and the liquid medicine bag replacement is triggered. If the requirement is met, the adjacent difference of the liquid level sequence is calculated to generate a liquid level difference sequence. At the same time, the flow rate sequence and the liquid level difference sequence are traversed to calculate the fluctuation variance to quantify the stability of the flow rate and the liquid level. On this basis, the module performs stable data screening on the flow rate and the liquid level difference, and extracts the data points with fluctuations less than the threshold as stable values. Finally, the module inputs the flow rate fluctuation variance, the liquid level difference fluctuation variance and their stable values into the stability anomaly identifier for comprehensive analysis, and outputs the anomaly type corresponding to the bed, including normal, liquid level anomaly, flow rate anomaly or joint anomaly, etc., providing an accurate decision-making basis for subsequent intelligent control. For example, when the fluctuation of the liquid level difference of a certain bed exceeds the standard and the flow rate fluctuation variance is abnormal, the module will mark it as a joint anomaly and suggest comprehensive treatment.

[0017] In a possible implementation manner, the anomaly analysis module 30 further includes: a preset liquid level requirement judgment unit, which is used to respectively extract the K last liquid medicine bag liquid levels at the last position in the K liquid medicine bag liquid level sequences, and judge whether the K last liquid medicine bag liquid levels meet the preset liquid level requirement. If so, perform stability anomaly identification on the K infusion flow rate sequences and the K liquid medicine bag liquid level sequences to obtain the K liquid medicine delivery anomaly analysis results. Specifically, the preset liquid level requirement judgment unit extracts the last data point (i.e., the last liquid medicine bag liquid level) of each bed in the liquid medicine bag liquid level sequence and compares it with the preset liquid level threshold to judge whether the liquid medicine bag needs to be replaced. If the last liquid level value is higher than or equal to the liquid level threshold, the system considers that the liquid level is sufficient and there is no need to replace the liquid medicine bag, and enters the subsequent stability anomaly identification step to further analyze the dynamic stability of the infusion flow rate and the liquid level. For example, when the liquid level value is 40mm and the threshold is 20mm, the system enters the stability analysis process. If the last liquid level value is lower than the liquid level threshold, the system directly determines that the liquid level is abnormal, there is no need to perform stability analysis, and immediately outputs the anomaly analysis result and triggers the liquid medicine bag replacement operation. For example, when the liquid level value is only 10mm and lower than 20mm, the system will mark the liquid level as abnormal and issue a replacement instruction. This module effectively avoids infusion interruption while ensuring the monitoring accuracy of the liquid medicine bag liquid level, improving the reliability of the infusion process.

[0018] Abnormal analysis result output unit, which is used to, if not, take the replacement of the medicine package as the analysis results of K liquid medicine delivery abnormalities respectively. Specifically, the function of the abnormal analysis result output unit is to, when it is judged that the liquid level of the medicine package does not meet the preset requirements, take "medicine package replacement" as the abnormal analysis result and output it to the control module. Specifically, this unit traverses the liquid level judgment results of each bed and identifies the beds with liquid levels lower than the threshold. For example, if the last liquid level value of bed 1 is 10mm, which is lower than the preset threshold of 20mm, the system marks it as insufficient liquid level and outputs an abnormal result of "medicine package needs to be replaced". At the same time, for the beds with liquid levels meeting the requirements, no abnormal results are generated. Finally, the system outputs the abnormal analysis results of all beds, including the bed numbers and the corresponding abnormal types, such as {bed 1: replace medicine package, bed 3: replace medicine package}. Through this module, the system can respond to liquid medicine liquid level abnormalities in real time, accurately locate the problem beds, ensure the timeliness and accuracy of subsequent medicine package replacement operations, and effectively avoid infusion interruption.

[0019] In a possible implementation, as Figure 2 shown, the preset liquid level requirement judgment unit further includes: a liquid level difference calculation sub-unit, which is used to calculate the liquid level differences between adjacent two medicine package liquid levels in the K medicine package liquid level sequences respectively, and obtain a sequence of K adjacent medicine package liquid level differences. Specifically, the function of the liquid level difference calculation sub-unit is to calculate the differences between adjacent data points in the medicine package liquid level sequence of each bed one by one, and generate a liquid level difference sequence for analyzing the dynamic change characteristics of the medicine package liquid level. In the specific implementation process, input the liquid level sequence of each bed (such as [100mm, 90mm, 80mm, 70mm]), and calculate the differences between adjacent data points according to the formula to generate a difference sequence (such as [10mm, 10mm, 10mm]). This difference sequence reflects the change rate and trend of the liquid level. The consistency of the differences indicates a stable liquid level drop speed, and the fluctuations of the differences may indicate abnormal situations. For example, if the difference sequence calculated from the sequence [100mm, 80mm, 70mm, 50mm] is [20mm, 10mm, 20mm], it shows that the liquid level drop rate is uneven and further analysis may be required. Through the accurate calculation of the liquid level differences, the system can dynamically capture the liquid level changes and provide data support for subsequent fluctuation variance calculation and abnormality identification.

[0020] A fluctuation variance calculation sub-unit, which is used to traverse the K infusion flow rate sequences and the K adjacent potion package liquid level difference sequences to calculate the fluctuation variance, and determine the K infusion flow rate fluctuation variances and the K adjacent potion package liquid level difference fluctuation variances. Specifically, the fluctuation variance calculation sub-unit calculates the fluctuation variance one by one by traversing the infusion flow rate sequences and the adjacent potion package liquid level difference sequences of each bed, and quantifies the stability degrees of the flow rate and the liquid level difference. When specifically implemented, first calculate the mean value of each sequence, then find the square of the difference between each data point and the mean value, and take the average value as the fluctuation variance. For example, for the infusion flow rate sequence [4.2, 4.1, 4.3, 4.0], its mean value is 4.15 ml / s, and the calculated fluctuation variance is 0.0125 ml² / s²; for the liquid level difference sequence [15, 14, 16, 14], its mean value is 14.75 mm, and the fluctuation variance is 0.6875 mm². These fluctuation variances reflect the smoothness of the flow rate and the liquid level change during the infusion process. The smaller the fluctuation variance, the more stable the change; if the fluctuation variance is larger, there may be abnormal fluctuation situations. By calculating and outputting the fluctuation variance set for the flow rate and the liquid level difference sequences of all beds one by one, this module provides accurate quantitative data support for subsequent stability analysis and anomaly identification.

[0021] A stable data screening sub-unit, which is used to traverse the K infusion flow rate sequences and the K adjacent potion package liquid level difference sequences to screen the stable data, and obtain the K infusion flow rate stable values and the K adjacent potion package liquid level difference stable values. Specifically, the stable data screening sub-unit constructs a flow rate data space and a liquid level difference data space by traversing the infusion flow rate sequences and the adjacent potion package liquid level difference sequences of each bed one by one. In the flow rate data space, first determine the minimum value of the infusion flow rate, and draw a screening start line parallel to the time axis, and set a preset screening bandwidth (such as ±0.1 ml / s) to construct the screening neighborhood range. Then, gradually move the screening line upward, dynamically adjust the neighborhood range, screen the data within the neighborhood, and record the number of data points within each neighborhood. When the number of data points in the newly added neighborhood is less than that in the previous neighborhood, stop the iteration, and calculate the mean value of the data within the final screening neighborhood to obtain the flow rate stable value of this bed. The same method applies to the liquid level difference data space, and the stable value of the liquid level difference is finally calculated through dynamic screening of the neighborhood. For example, for the flow rate sequence [4.2, 4.1, 4.3, 4.0, 4.2] and the liquid level difference sequence [15, 14, 16, 14, 15], after screening, the flow rate stable value is obtained as 4.1 ml / s, and the liquid level difference stable value is obtained as 14.5 mm. These stable values can accurately reflect the stable state of the infusion process and provide a reliable basis for subsequent anomaly detection.

[0022] Fluctuation variance anomaly identification subunit, which is used to identify anomalies in the fluctuation variances of K infusion flow rates, the stable values of K infusion flow rates, the fluctuation variances of the liquid level differences between K adjacent medicine packs, and the fluctuation variances of the liquid level differences between K adjacent medicine packs by using a stability anomaly identifier, and obtain the abnormal analysis results of the K liquid medicine deliveries. Specifically, the fluctuation variance anomaly identification subunit jointly analyzes the fluctuation variance of the infusion flow rate, the stable value of the infusion flow rate, the fluctuation variance of the liquid level difference, and the stable value of the liquid level difference for each bed by using a neural network model (stability anomaly identifier) to identify abnormal situations during the infusion process. First, the system combines the data of each bed into a feature vector, such as [0.012, 4.1, 0.8, 14.5], which respectively represent the flow rate fluctuation variance, the stable value of the flow rate, the fluctuation variance of the liquid level difference, and the stable value of the liquid level difference. This feature vector is input into the neural network model for abnormal probability calculation. The model adopts a multi-layer structure, including an input layer, a hidden layer, and an output layer, and finally outputs an abnormal probability value. If this probability value exceeds a preset threshold (such as 0.7), the system determines that there is an abnormality in the infusion. For example, the feature vector of bed 1 outputs an abnormal probability of 0.85 and is determined to be abnormal, and a medicine pack replacement or other intervention operations are required; while the abnormal probability of bed 2 is 0.4 and is determined to be normal without adjustment. Through this process, the system can quickly and efficiently identify abnormal problems in the infusion, ensuring the stability and reliability of the infusion process.

[0023] In a possible implementation, the stable data screening subunit further includes: a liquid level difference space construction micro-unit, which is used to construct K infusion flow rate spaces and K adjacent potion package liquid level difference spaces based on the K infusion flow rate sequences and the K adjacent potion package liquid level difference sequences. Among them, the horizontal axis of each infusion flow rate space is time, and the vertical axis is the infusion flow rate. The horizontal axis of each adjacent potion package liquid level difference space is time, and the vertical axis is the adjacent potion package liquid level difference. Specifically, the main function of the liquid level difference space construction micro-unit is to process the infusion flow rate sequence and the adjacent potion package liquid level difference sequence of each bed, and construct the infusion flow rate space and the liquid level difference space respectively, providing an intuitive data model for subsequent stable value screening and anomaly analysis. Specifically, the infusion flow rate space takes time as the horizontal axis and the flow rate as the vertical axis, and represents the dynamic change of the flow rate over time as a curve. For example, the flow rate values [4.1, 4.2, 4.0] corresponding to the time points [t1, t2, t3] can be plotted as points (t1, 4.1), (t2, 4.2), (t3, 4.0) and form a curve. Similarly, the liquid level difference space takes time as the horizontal axis and the liquid level difference as the vertical axis, and plots the liquid level change as a curve. For example, the differences [15, 14, 16] correspond to the points (t1, 15), (t2, 14), (t3, 16). These space models visually display the laws of infusion rate and liquid level change through dynamic visualization, providing intuitive support on the time axis for subsequent data screening and anomaly detection, and enhancing the system's analytical ability for dynamic characteristic changes.

[0024] A starting line determination micro-unit, which is used to respectively use the lines passing through the minimum infusion flow rate in the K infusion flow rate spaces and parallel to the horizontal axis as the K screening starting lines. Specifically, the main function of the starting line determination micro-unit is to find the minimum flow rate in the infusion flow rate space of each bed and construct a starting screening line parallel to the time axis based on this value as the initial reference for subsequent data screening and iterative operations. The specific process is as follows: The system traverses the infusion flow rate space of each bed. For example, for the flow rate data [4.1, 4.0, 4.2, 3.8] and the time points [t1, t2, t3, t4], determine the minimum flow rate value of 3.8 and the corresponding time range [t1, t4], and then construct the line y = 3.8 with the abscissa range of [t1, t4]. This process is repeated for the infusion flow rate spaces of all beds, and the starting screening line of each bed is output. For example, the minimum value of the flow rate data [3.5, 3.6, 3.4, 3.8] of another bed is 3.4, and its corresponding line is y = 3.4. These lines serve as the initial reference points for the screening operation, ensuring that the screening range conforms to the actual flow rate change, improving the subsequent screening efficiency, and laying a foundation for dynamically capturing the flow rate change and screening stable values.

[0025] Construct micro-units for the starting line neighborhood. The micro-units for constructing the starting line neighborhood are used to construct K screening starting line neighborhoods of the K screening starting lines in the K infusion flow rate spaces according to a preset screening bandwidth. Specifically, the function of the micro-units for constructing the starting line neighborhood is to generate a neighborhood range based on the infusion flow rate space and the screening starting line of each bed, combined with the preset screening bandwidth, providing reasonable upper and lower limits for subsequent screening. The specific process is as follows: Extract the screening starting lines from the infusion flow rate space of each bed (for example, the starting line of bed 1 is y = 3.8, and that of bed 2 is y = 3.4). Taking the starting line value as the center, expand according to the preset bandwidth (such as ±0.5 flow rate units) to form a neighborhood range. For example, the neighborhood of bed 1 is [3.3, 4.3], and that of bed 2 is [2.9, 3.9]. These neighborhoods use the time axis as the abscissa and the flow rate value as the ordinate to construct the upper and lower boundaries in the infusion flow rate space. The dynamic construction of the neighborhoods ensures that the screening range fits the actual flow rate changes, effectively excluding noise data, and at the same time providing accurate initial reference points for subsequent iterative operations, thereby improving the accuracy of anomaly recognition and flow rate stability judgment.

[0026] Construct micro-units for the iterative line neighborhood. The micro-units for constructing the iterative line neighborhood are used to move up the K screening starting lines according to the preset screening bandwidth to obtain K screening first-iteration lines and construct K screening first-iteration line neighborhoods. Specifically, the micro-units for constructing the iterative line neighborhood optimize the screening of flow rate data by dynamically adjusting the position of the screening line and the neighborhood range. Specifically, starting from the initial screening line of each bed (for example, y = 3.8 represents the starting flow rate line of bed 1), move the line up successively according to the preset bandwidth (such as ±0.5) to generate new iterative lines (for example, after the first iteration, it is y = 4.3, and after the second iteration, it is y = 4.8). In each iteration, construct a neighborhood according to the up and down floating range of the line (for example, the neighborhood range of y = 4.3 is [3.8, 4.8]), and count the number of flow rate data points included in the neighborhood. The system verifies whether the data volume in the current iterative neighborhood is more than that in the previous iterative neighborhood. If the data volume is insufficient, stop the iteration, and use the flow rate mean value in the last valid neighborhood as the screening result (for example, the final screening line is y = 4.8). This method is independently executed for each bed to dynamically adapt to the infusion flow rate characteristics of different beds, thereby ensuring that the data screening range comprehensively covers the flow rate changes and excludes noise data, providing a high-precision flow rate stability basis for subsequent analysis.

[0027] Infusion flow rate stability value acquisition micro-unit, the infusion flow rate stability value acquisition micro-unit is used to determine whether the data volumes of the K screening first iteration straight line neighborhoods are greater than or equal to the data volumes of the corresponding K screening starting straight line neighborhoods. If not, the iteration is stopped, and the average infusion flow rate within the K screening starting straight line neighborhoods is calculated to obtain K infusion flow rate stability values. Specifically, the infusion flow rate stability value acquisition micro-unit extracts the flow rate stability values of each bed through multiple iterative screenings, providing accurate references for subsequent analysis. Specifically, the system constructs a straight line neighborhood for the flow rate data of each bed in each iteration, counts its data volume, and compares the data volume of the current iterative neighborhood with that of the starting straight line neighborhood. If the data volume of the iterative straight line neighborhood is less than or equal to that of the starting straight line neighborhood, it is determined that the iteration has reached the convergence condition, and further iteration is stopped. Subsequently, the system calculates the average value of the data within the starting straight line neighborhood as the flow rate stability value of this bed. For example, if the starting straight line neighborhood contains 50 data points and the data volume in the iterative neighborhood decreases to 48 points after iteration, the system stops the iteration and calculates the average flow rate of the 50 points as the stability value. This process is independently executed for all beds, finally generating K flow rate stability values, comprehensively reflecting the flow rate stability state of the infusion process, while avoiding computational redundancy caused by excessive iteration, and providing reliable data support for subsequent anomaly detection and control.

[0028] Liquid level difference stability value acquisition micro-unit, the liquid level difference stability value acquisition micro-unit is used to perform stable data screening in the K adjacent potion package liquid level difference spaces to obtain K adjacent potion package liquid level difference stability values. Specifically, the liquid level difference stability value acquisition micro-unit extracts the liquid level difference stability values of each bed by performing stable data screening in the K adjacent potion package liquid level difference spaces, providing reliable data support for infusion control and anomaly detection. Specifically, the abscissa of the liquid level difference space represents time, and the ordinate represents the difference in liquid levels between adjacent potion packages. The system defines a stability screening window within the space and analyzes the fluctuation range and mean change of the data within the window. For regions where the liquid level difference fluctuation range is small and the mean change is stable, the system determines them as stable data regions and calculates their mean values as the liquid level difference stability values. For example, if the liquid level difference of a certain bed fluctuates in the range of 0.5 to 0.6 and the mean value is 0.55 within a specific time period, the system takes 0.55 as the liquid level difference stability value of this bed. This process is independently executed for all beds, ensuring the removal of noise and abnormal data, and the extracted stability values can accurately reflect the actual state of the infusion process.

[0029] In a possible implementation, the micro-unit for obtaining the stable infusion flow rate value further includes: an upward iteration nano-unit, which is configured to, if not, perform upward iteration based on the K once-screened iteration lines. After N iterations, K N-time-screened iteration lines are obtained, and a neighborhood of the K N-time-screened iteration lines is constructed, where N is an integer greater than or equal to 2. Specifically, the upward iteration nano-unit constructs and optimizes the neighborhood of the screened line by gradually adjusting the position of the screened line to finally extract the stable infusion flow rate value. Specifically, the unit starts from the once-screened iteration line and gradually moves the line position upward according to a fixed preset bandwidth. After each adjustment, the neighborhood of the line is reconstructed and the number of data points therein is counted. In each iteration, the system compares the data volume of the current neighborhood with that of the previous neighborhood. If the data volume of the current neighborhood is not less than that of the previous round, the iteration continues; otherwise, the iteration stops and the system reverts to the previous neighborhood, and the mean value of its data is used as the stable value. At the same time, when the number of iterations reaches the preset maximum value, regardless of whether the data volume continues to increase, the system forcibly stops the iteration, and the mean value of the neighborhood of the last iteration is used as the final result. For example, in a certain infusion monitoring, if the data volume of the neighborhood in the third iteration decreases, the system will revert to the second iteration and use its mean value as the stable value. This mechanism effectively balances data optimization and computational reliability, providing an accurate basis for subsequent stability analysis and control of the infusion flow rate.

[0030] Flow rate stable value output unit. The flow rate stable value output unit is used to determine whether N is greater than or equal to the preset maximum number of iterations when the data volume of the K screened N - th iteration straight line neighborhoods is greater than or equal to the corresponding data volume of the K screened (N - 1)-th iteration straight line neighborhoods. If so, stop the iteration and use the average infusion flow rate of the K screened N - th iteration straight line neighborhoods as the K infusion flow rate stable values. Specifically, the main task of the flow rate stable value output unit is to accurately obtain the infusion flow rate stable values corresponding to K beds through step - by - step iterative calculation. During the iteration process, this unit compares the data volume of the current N - th iteration straight line neighborhood with the data volume of the previous (N - 1)-th iteration straight line neighborhood: if the data volume of the N - th iteration straight line neighborhood is greater than or equal to the data volume of the (N - 1)-th straight line neighborhood, continue to iterate upward to construct the (N + 1)-th straight line neighborhood until one of the following two situations is met: 1) Reach the preset maximum number of iterations, at this time stop the iteration and use the average infusion flow rate of the N - th iteration straight line neighborhood as the stable value; 2) If at the N - th iteration, the data volume of the straight line neighborhood is less than the data volume of the (N - 1)-th straight line neighborhood, immediately stop the iteration and roll back to the (N - 1)-th iteration, and use the average infusion flow rate of the (N - 1)-th straight line neighborhood as the stable value. For example, in the calculation of the infusion flow rate of a certain bed, if at the 5th iteration, the neighborhood data volume is less than that of the 4th iteration, the system will automatically roll back and use the average value of the 4th iteration neighborhood as the final stable value. Through this iterative and dynamic adjustment mechanism, this unit can effectively process the infusion flow rate data of K beds, ensure reliable stable values can still be obtained under data fluctuations and noise interference, and thus provide basic data support for subsequent precise infusion control.

[0031] Temperature sequence acquisition module 40. The temperature sequence acquisition module 40 is used to retrieve the K infusion monitoring data set sequences with the liquid medicine temperature as the index to obtain K liquid medicine temperature sequences. Specifically, the temperature sequence acquisition module 40 is used to extract the liquid medicine temperature sequence corresponding to each bed from the infusion monitoring devices arranged at K beds. This module groups and traverses the infusion monitoring data set sequences by setting the liquid medicine temperature as the retrieval index. The temperature sensors of each infusion monitoring device record the liquid medicine temperature in real - time and upload these data to the system. The module locks the data set of each bed one by one, extracts the temperature - related records from it, and arranges them in chronological order into K independent liquid medicine temperature sequences. For example, if the monitoring data of a certain bed includes three dimensions: flow rate, liquid level, and temperature, the module will filter out the temperature data points and sort them by time to generate the temperature sequence of this bed. In this way, the temperature sequence acquisition module ensures the integrity and accuracy of the liquid medicine temperature data of all beds, providing reliable data support for subsequent temperature anomaly analysis and control.

[0032] The interactive correlation anomaly analysis module 50 is used to perform interactive correlation anomaly analysis on the K liquid medicine temperature sequences to obtain K liquid medicine temperature anomaly analysis results. Specifically, the interactive correlation anomaly analysis module 50 analyzes the K liquid medicine temperature sequences to identify the anomalies of the liquid medicine temperature at each bed and generate corresponding anomaly analysis results. First, the module receives the K liquid medicine temperature sequences provided by the temperature sequence acquisition module. These sequences are arranged in chronological order and reflect the dynamic changes of the liquid medicine temperature at each bed. The module evaluates the overall consistency and anomaly trend of the liquid medicine temperature change by calculating the correlation and difference between each temperature sequence and other sequences, combined with the geographical distribution information of each bed. For example, when the liquid medicine temperature at a certain bed deviates significantly from the average value of other beds, or shows abnormal fluctuations in time, that bed will be marked as abnormal. In addition, the module also identifies local anomalies or changes in the overall pattern by dynamically comparing the fluctuation range, change rate, and difference values at adjacent time points of the liquid medicine temperature at each bed. The analysis results are output in the form of K liquid medicine temperature anomaly analysis results, with each bed corresponding to one result, clearly indicating the abnormal state of the liquid medicine temperature, providing an accurate basis for subsequent temperature adjustment or control decisions. For example, if the liquid medicine temperature at a certain bed suddenly drops below the critical value, the module will immediately mark that bed as abnormal, facilitating the timely triggering of the temperature adjustment mechanism.

[0033] In a possible implementation manner, the interactive correlation anomaly analysis module 50 further includes: a mean value calculation unit, which is used to calculate the mean values of the K liquid medicine temperature sequences respectively to obtain K liquid medicine temperature mean values. Specifically, the mean value calculation unit is used to process the K liquid medicine temperature sequences. By summing the temperature data at each time point in each sequence and dividing by the total number of time points, the time mean value of each sequence is calculated, thereby generating K liquid medicine temperature mean values. For example, for the liquid medicine temperature sequence [36.5, 36.6, 36.4, 36.5, 36.7, 36.6, 36.5, 36.4, 36.6, 36.5] of a certain bed, this unit divides its sum 365.4 by the number of time points 10 to obtain a mean value of 36.54 °C. This process is executed one by one for all beds, and the set of K liquid medicine temperature mean values generated comprehensively reflects the temperature conditions of different beds, providing data support for subsequent neighborhood anomaly analysis and system optimization. This unit ensures the accuracy of temperature data processing and lays a foundation for quickly identifying temperature deviations and timely adjusting the liquid medicine temperature.

[0034] Anomaly analysis result acquisition unit, which is used to obtain the K bed positions of the K beds, perform neighborhood anomaly analysis on the K average liquid medicine temperatures based on the K bed positions, and obtain K liquid medicine temperature anomaly analysis results. Specifically, the anomaly analysis result acquisition unit performs neighborhood anomaly analysis by combining the position information of the K beds and the corresponding average liquid medicine temperatures to generate K liquid medicine temperature anomaly analysis results. Specifically, the system first obtains the position information of all beds, which is used to determine the spatial relationship between the beds, such as the logical or physical positions of adjacent beds. Then, for each bed, the unit extracts the set of average liquid medicine temperatures of its neighboring beds and calculates the average of this set as the neighborhood reference value. Subsequently, the difference between the average liquid medicine temperature of this bed and the neighborhood reference value is calculated. If the difference exceeds a preset anomaly threshold, such as 0.5 °C, it is determined that there is a temperature anomaly in this bed; if the difference is within the threshold range, the temperature is considered normal. In this way, the anomaly analysis result acquisition unit can effectively identify possible temperature anomalies based on the comprehensive comparison of a single bed and its neighborhood temperature data. For example, if the average liquid medicine temperature of a certain bed is 37.2 °C and the neighborhood average is 36.5 °C, this bed will be marked as abnormal to indicate that there may be a heating device failure or environmental factor interference in the system. This process ensures the accuracy and reliability of the system detection results and provides an important basis for subsequent regulation.

[0035] In a possible implementation manner, the anomaly analysis result acquisition unit further includes: a first average liquid medicine temperature extraction subunit, which is used to randomly extract a first average liquid medicine temperature from the K average liquid medicine temperatures. Specifically, the role of the first average liquid medicine temperature extraction subunit is to randomly select a value from the K average liquid medicine temperatures as the benchmark for subsequent neighborhood analysis. This process first loads the set of average liquid medicine temperatures of all beds and assigns an equal probability of being selected to each value through a random selection algorithm to ensure the fairness and randomness of the selection. The subunit randomly extracts an average liquid medicine temperature, named "the first average liquid medicine temperature", and records and marks it for subsequent analysis. For example, in an infusion system with 5 beds, the average liquid medicine temperatures are 36.7 °C, 36.9 °C, 37.0 °C, 37.1 °C, and 36.8 °C respectively. The subunit may randomly select 37.1 °C as the first average liquid medicine temperature for subsequent neighborhood matching and anomaly analysis. Through this random extraction process, the system provides a diverse starting point for subsequent analysis, ensuring the robustness and reliability of the results.

[0036] The bed position matching subunit is used to match the bed position corresponding to the first average liquid medicine temperature with the K bed positions, and extract the K average liquid medicine temperatures according to the matching result to obtain the neighborhood of the first average liquid medicine temperature. Specifically, the bed position matching subunit determines the target position to be matched by loading the first average liquid medicine temperature and its corresponding bed position. For example, if the first average liquid medicine temperature is 37.1 °C and the corresponding bed is Bed 3, the system will load the average liquid medicine temperature data and their positions of all beds. Then, according to the matching rule (such as the neighborhood includes the beds before and after by 1 position), the neighborhood data related to the target bed is extracted. Taking Bed 3 as an example, its neighborhood may include Bed 2 and Bed 4, and the corresponding average liquid medicine temperatures are 36.9 °C and 37.0 °C. Finally, the subunit outputs the extracted neighborhood liquid medicine temperature data (such as 36.9 °C, 37.1 °C, 37.0 °C) as the neighborhood of the first average liquid medicine temperature for subsequent anomaly analysis. This matching process ensures that the system can accurately extract the relevant neighborhood data, improving the pertinence and accuracy of the analysis.

[0037] The liquid medicine temperature anomaly judgment subunit is used to calculate the difference between the average value of the neighborhood of the first average liquid medicine temperature and the first average liquid medicine temperature. If the calculation result is greater than or equal to the preset difference of the average liquid medicine temperature, the first liquid medicine temperature anomaly analysis result is that the liquid medicine temperature is abnormal. Specifically, the liquid medicine temperature anomaly judgment subunit judges whether the liquid medicine temperature is abnormal by calculating the difference between the average value of the neighborhood of the first average liquid medicine temperature and the first average liquid medicine temperature. Specifically, first, the temperature values are extracted from the neighborhood data and the average value is calculated. For example, the neighborhood average value is 37.0 °C. Subsequently, the difference between this average value and the first average liquid medicine temperature (such as 36.5 °C) is calculated, and the difference is 0.5 °C. Then, this difference is compared with the preset temperature anomaly threshold (such as 0.4 °C). If the difference is greater than or equal to the threshold, it is determined that the liquid medicine temperature is abnormal; if it is less than the threshold, it is determined that the temperature is normal. For example, when the difference is 0.5 °C and exceeds the threshold of 0.4 °C, the system will record the analysis result as "the liquid medicine temperature is abnormal" and feedback it to the control module to trigger subsequent adjustment operations. This judgment process can quickly and accurately detect temperature anomalies, ensuring the reliability and stability of the system operation.

[0038] Sub-unit for obtaining analysis results of liquid medicine temperature anomalies. The sub-unit for obtaining analysis results of liquid medicine temperature anomalies is used to perform neighborhood anomaly analysis on the remaining K - 1 average liquid medicine temperatures to obtain K - 1 analysis results of liquid medicine temperature anomalies. Specifically, the function of the sub-unit for obtaining analysis results of liquid medicine temperature anomalies is to perform neighborhood anomaly analysis one by one on the remaining K - 1 average liquid medicine temperatures, and finally obtain K - 1 analysis results of liquid medicine temperature anomalies. Specifically speaking, this unit sequentially extracts each average liquid medicine temperature from the queue to be analyzed, determines the neighborhood range based on its corresponding bed position. The neighborhood range can be set by spatial or logical distance. For example, adjacent beds or beds within a certain range are selected as the neighborhood. Subsequently, the average value of all liquid medicine temperature data within the neighborhood is calculated, and the difference is calculated with the extracted average liquid medicine temperature. If the difference is greater than or equal to the preset anomaly threshold (e.g., 0.5 ), then this temperature data is marked as abnormal; otherwise, it is marked as normal. And so on, analyze the K - 1 average liquid medicine temperatures one by one, and record the anomaly analysis results each time. Finally, these analysis results will be integrated and transmitted to the control module of the system for further decision-making and control operations to ensure that the system can effectively identify and handle liquid medicine temperature anomalies. For example, when the liquid medicine temperature of a certain bed is 37.4 , and its neighborhood average value is 36.8 , the calculated difference is 0.6 , exceeding the preset threshold of 0.5 , this bed is marked as having an abnormal temperature, thus triggering relevant processing.

[0039] Sub-unit for determining analysis results of liquid medicine temperature anomalies. The sub-unit for determining analysis results of liquid medicine temperature anomalies is used to take the first analysis result of liquid medicine temperature anomaly and the K - 1 analysis results of liquid medicine temperature anomalies as K analysis results of liquid medicine temperature anomalies. Specifically, the function of the sub-unit for determining analysis results of liquid medicine temperature anomalies is to integrate and output the analysis results of liquid medicine temperature anomalies of all beds to form a complete set of K analysis results of liquid medicine temperature anomalies. Specifically speaking, this sub-unit first receives the first analysis result of liquid medicine temperature anomaly generated by the process of extracting and analyzing the first average liquid medicine temperature, and then combines the neighborhood anomaly analysis results of the remaining K - 1 average liquid medicine temperatures. These results are organized according to the bed number or index order to generate a structured set of analysis results { , ,..., }, where each Indicates whether there is an abnormal state in the liquid medicine temperature corresponding to the bed, such as "abnormal" or "normal". This integration process not only ensures the integrity of the analysis results for all beds but also supports the subsequent invocation of decision-making and control modules. For example, in an infusion monitoring scenario, if the liquid medicine temperatures of the 1st and 4th beds are detected to be abnormal and the rest are normal, the subunit will generate a result set {abnormal, normal, normal, abnormal, normal} and pass it to the control module to trigger corresponding heating or alarm operations. Through this mechanism, the system realizes the comprehensive monitoring and timely response to the abnormal state of the liquid medicine temperature.

[0040] In a possible implementation manner, the liquid medicine temperature abnormal judgment subunit further includes: calculating the difference between the mean value of the neighborhood of the first liquid medicine temperature mean value and the first liquid medicine temperature mean value. If the calculation result is less than the preset liquid medicine temperature mean value difference, the first liquid medicine temperature abnormal analysis result is that the liquid medicine temperature is normal. Specifically, calculate the difference between the mean value of the neighborhood of the first liquid medicine temperature mean value and the first liquid medicine temperature mean value to determine whether the current liquid medicine temperature is within the normal range. Specifically, this micro-unit first receives the first liquid medicine temperature mean value and its neighborhood mean value, and calculates the difference between the two through subtraction. Subsequently, compare this difference with the preset liquid medicine temperature mean value difference threshold of the system. If the difference is less than the preset threshold, it is determined that the current liquid medicine temperature state is "normal", and this judgment result is recorded as the first liquid medicine temperature abnormal analysis result. For example, if the first liquid medicine temperature mean value is 37.5°C, the neighborhood mean value is 37.6°C, and the difference is 0.1°C, which is less than the preset threshold of 0.5°C, the system will mark the result as "temperature normal". This judgment mechanism can effectively filter out false alarms caused by minor fluctuations and provide accurate and reliable basic data for subsequent liquid medicine temperature monitoring and control.

[0041] Infusion control module 60, the infusion control module 60 is used to trigger the infusion valves, medicine pack replacement devices and heating devices of the K beds according to the K analysis results of abnormal medicine delivery and the K analysis results of abnormal medicine temperature, and complete the infusion control of the K beds. Specifically, the infusion control module 60 realizes the infusion control of the K beds by comprehensively analyzing the K analysis results of abnormal medicine delivery and the K analysis results of abnormal medicine temperature. Specifically, the module judges the situation of insufficient liquid level or abnormal flow rate according to the analysis result of abnormal medicine delivery, and triggers the medicine pack replacement device of the corresponding bed or adjusts the opening of the infusion valve to ensure sufficient liquid level and stable flow rate. At the same time, if the analysis result of abnormal medicine temperature shows that the temperature exceeds the preset range, the module starts the heating device to adjust the medicine temperature to the target range. For example, when the liquid level is detected to be insufficient at a certain bed, the system immediately triggers the medicine pack replacement device to complete the replacement of the medicine pack; if the flow rate is detected to be unstable, the opening of the infusion valve is adjusted until the flow rate returns to normal; if the medicine temperature is lower than 36°C (the target range is 36°C to 38°C), the system activates the heating device to raise the temperature to 37°C. The entire module ensures a stable and uninterrupted infusion process, maintains the flow rate and temperature of the medicine in the best state through real-time monitoring, command triggering and closed-loop adjustment, and comprehensively guarantees the accuracy and reliability of infusion control.

[0042] The embodiment of the present application adopts the method of collecting the infusion monitoring data arranged at K beds to obtain the infusion flow rate, the liquid level of the medicine pack and the medicine temperature sequence; conducts a joint abnormal analysis on the flow rate and the liquid level to obtain the abnormal result of medicine delivery; conducts an interactive correlation analysis on the temperature sequence to obtain the abnormal result of temperature; triggers the infusion valve, the medicine pack replacement device and the heating device according to the analysis results to realize the intelligent control of the infusion process, and achieves the technical effect of improving the reliability of the infusion process control and the fitting degree of the actual infusion situation.

[0043] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0044] The above specific implementation manners do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to the design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. An infusion management and control system based on the Internet of Things, characterized in that, The system includes: A monitoring data acquisition module, which is used to acquire the monitoring data of K infusion monitoring devices arranged on K beds in a preset monitoring window, and obtain a sequence of K infusion monitoring data sets, where K is an integer greater than or equal to 1; A liquid level sequence acquisition module, which is used to retrieve the sequence of K infusion monitoring data sets with the infusion flow rate and the liquid level of the medicine package as indexes, and obtain a sequence of K infusion flow rates and a sequence of K medicine package liquid levels; An anomaly analysis module, which is used to perform joint anomaly analysis on the sequence of K infusion flow rates and the sequence of K medicine package liquid levels, and obtain K analysis results of abnormal liquid medicine delivery; A temperature sequence acquisition module, which is used to retrieve the sequence of K infusion monitoring data sets with the liquid medicine temperature as an index, and obtain a sequence of K liquid medicine temperatures; An interactive correlation anomaly analysis module, which is used to perform interactive correlation anomaly analysis on the sequence of K liquid medicine temperatures, and obtain K analysis results of abnormal liquid medicine temperature; An infusion control module, which is used to trigger the infusion valves, medicine package replacement devices and heating devices of the K beds according to the K analysis results of abnormal liquid medicine delivery and the K analysis results of abnormal liquid medicine temperature, and complete the infusion control of the K beds.

2. The infusion management and control system based on the Internet of Things according to claim 1, characterized in that, The anomaly analysis module includes: A preset liquid level requirement judgment unit, which is used to respectively extract the K last medicine package liquid levels located at the last position in the sequence of K medicine package liquid levels, and judge whether the K last medicine package liquid levels meet the preset liquid level requirements. If so, perform stability anomaly identification on the sequence of K infusion flow rates and the sequence of K medicine package liquid levels, and obtain the K analysis results of abnormal liquid medicine delivery; An anomaly analysis result output unit, which is used to, if not, respectively take medicine package replacement as the K analysis results of abnormal liquid medicine delivery.

3. The infusion management and control system based on the Internet of Things according to claim 2, wherein, The preset liquid level requirement judgment unit includes: A liquid level difference calculation sub-unit, which is used to respectively calculate the liquid level differences between adjacent medicine package liquid levels in the sequence of K medicine package liquid levels, and obtain a sequence of K adjacent medicine package liquid level differences; A fluctuation variance calculation sub-unit, which is used to traverse the sequence of K infusion flow rates and the sequence of K adjacent medicine package liquid level differences to calculate the fluctuation variance, and determine the K infusion flow rate fluctuation variances and the K adjacent medicine package liquid level difference fluctuation variances; A stable data screening sub-unit, which is used to traverse the sequence of K infusion flow rates and the sequence of K adjacent medicine package liquid level differences to perform stable data screening, and obtain the K infusion flow rate stable values and the K adjacent medicine package liquid level difference stable values; A variance anomaly recognition subunit, which is configured to use a stability anomaly recognizer to perform anomaly recognition on the variances of the K infusion flow rates and the K stable values of the infusion flow rates, as well as the variances of the fluctuations of the K adjacent potion package liquid level differences and the variances of the K adjacent potion package liquid level differences, so as to obtain the K analysis results of abnormal liquid medicine delivery.

4. The infusion management and control system based on the Internet of Things according to claim 3, characterized in that, The stable data screening subunit includes: A liquid level difference space construction micro-unit, which is configured to construct K infusion flow rate spaces and K adjacent potion package liquid level difference spaces based on the K infusion flow rate sequences and the K adjacent potion package liquid level difference sequences. Among them, the horizontal axis of each infusion flow rate space is time, and the vertical axis is the infusion flow rate. The horizontal axis of each adjacent potion package liquid level difference space is time, and the vertical axis is the adjacent potion package liquid level difference; A starting line determination micro-unit, which is configured to use the lines passing through the minimum infusion flow rates in the K infusion flow rate spaces and parallel to the horizontal axis as the K screening starting lines respectively; A starting line neighborhood construction micro-unit, which is configured to construct K screening starting line neighborhoods of the K screening starting lines in the K infusion flow rate spaces according to a preset screening bandwidth; An iterative line neighborhood construction micro-unit, which is configured to move up the K screening starting lines according to the preset screening bandwidth to obtain K screening first-iteration lines, and construct K screening first-iteration line neighborhoods; An infusion flow rate stable value acquisition micro-unit, which is configured to determine whether the data amounts of the K screening first-iteration line neighborhoods of the K screening first-iteration line neighborhoods are greater than or equal to the data amounts of the K screening starting line neighborhoods of the corresponding K screening starting line neighborhoods. If not, stop the iteration, calculate the average infusion flow rate within the K screening starting line neighborhoods, and obtain the K stable values of the infusion flow rates; A liquid level difference stable value acquisition micro-unit, which is configured to perform stable data screening in the K adjacent potion package liquid level difference spaces to obtain the K stable values of the adjacent potion package liquid level differences.

5. The infusion management and control system based on the Internet of Things according to claim 4, characterized in that, The infusion flow rate stable value acquisition micro-unit includes: An upward iteration unit, which is configured to, if not, perform upward iteration based on the K screening first-iteration lines. After N iterations, obtain K screening N-iteration lines, and construct K screening N-iteration line neighborhoods, where N is an integer greater than or equal to 2; A flow rate stable value output unit, which is configured to, when the data amounts of the K screening N-iteration line neighborhoods of the K screening N-iteration line neighborhoods are greater than or equal to the data amounts of the K screening N-1-iteration line neighborhoods of the corresponding K screening N-1-iteration lines, determine whether N is greater than or equal to a preset maximum iteration number. If so, stop the iteration, and use the average infusion flow rate of the K screening N-iteration line neighborhoods as the K stable values of the infusion flow rates.

6. The infusion management and control system based on the Internet of Things according to claim 1, wherein The interaction correlation anomaly analysis module includes: A mean calculation unit, which is used to calculate the means of the K liquid medicine temperature sequences respectively to obtain K liquid medicine temperature means; An abnormal analysis result acquisition unit, which is used to obtain the K bed positions of the K beds, and perform neighborhood abnormal analysis on the K liquid medicine temperature means based on the K bed positions to obtain K liquid medicine temperature abnormal analysis results.

7. The infusion management and control system based on the Internet of Things according to claim 6, wherein, The abnormal analysis result acquisition unit includes: A first liquid medicine temperature mean extraction subunit, which is used to randomly extract a first liquid medicine temperature mean from the K liquid medicine temperature means; A bed position matching subunit, which is used to match the bed position corresponding to the first liquid medicine temperature mean with the K bed positions, and extract the K liquid medicine temperature means according to the matching result to obtain a neighborhood of the first liquid medicine temperature mean; A liquid medicine temperature abnormality judgment subunit, which is used to calculate the difference between the mean of the neighborhood of the first liquid medicine temperature mean and the first liquid medicine temperature mean. If the calculation result is greater than or equal to a preset liquid medicine temperature mean difference, the first liquid medicine temperature abnormal analysis result is that the liquid medicine temperature is abnormal; A liquid medicine temperature abnormal analysis result acquisition subunit, which is used to perform neighborhood abnormal analysis on the remaining K - 1 liquid medicine temperature means to obtain K - 1 liquid medicine temperature abnormal analysis results; A liquid medicine temperature abnormal analysis result determination subunit, which is used to use the first liquid medicine temperature abnormal analysis result and the K - 1 liquid medicine temperature abnormal analysis results as the K liquid medicine temperature abnormal analysis results.

8. The infusion management and control system based on the Internet of Things according to claim 7, characterized in that Calculate the difference between the mean of the neighborhood of the first liquid medicine temperature mean and the first liquid medicine temperature mean. If the calculation result is less than the preset liquid medicine temperature mean difference, the first liquid medicine temperature abnormal analysis result is that the liquid medicine temperature is normal.

Images