Method and system for regulating and controlling liquid medicine mixing proportion in real time

Abstract

The invention relates to the technical field of liquid medicine proportions, and discloses a liquid medicine mixing proportion real-time regulation and control method and system.The method comprises the steps that the liquid medicine component concentration and the liquid medicine component flow of target mixed liquid medicine are obtained, and the real-time liquid medicine mixing proportion of the target mixed liquid medicine is generated based on the liquid medicine component concentration and the liquid medicine component flow; generating a reference liquid medicine mixing ratio of the target mixed liquid medicine; and calculating a ratio deviation between the real-time liquid medicine mixing ratio and the reference liquid medicine mixing ratio based on the real-time liquid medicine mixing ratio and the reference liquid medicine mixing ratio. According to the invention, accurate regulation and control of the liquid medicine mixing proportion are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of drug liquid ratio control, and in particular to a real-time control method and system for drug liquid mixing ratio. Background Art

[0002] In the field of drug liquid mixing ratio control technology, existing technologies calculate the ratio deviation between the real-time drug liquid mixing ratio and the reference drug liquid mixing ratio and perform control based on the ratio deviation. Usually, the flow rate or addition amount of each drug liquid component is adjusted according to fixed parameters or empirical formulas. However, this method has the following drawbacks:

[0003] First, the complex interrelationships between the components of the drug solution are not fully taken into account. Different drug solution components do not exist independently during the mixing process, and their concentration changes and reaction characteristics affect each other. The existing technology often ignores this internal connection during regulation, resulting in inaccurate regulation. In addition, when facing changes in environmental factors, the existing technology lacks an effective response mechanism. Fluctuations in environmental parameters will affect the physical and chemical properties of the drug solution, and thus change the mixing ratio. However, the existing technology only regulates based on a fixed benchmark and is difficult to dynamically adjust according to environmental changes, making it difficult to stably meet the quality standards of the final mixed drug solution and difficult to meet the high-precision requirements for the drug solution mixing ratio in production practice. Summary of the Invention

[0004] The present invention provides a method and system for real-time control of the mixing ratio of a drug liquid, the main purpose of which is to solve the problem that the existing technology is difficult to meet the high-precision requirement for the mixing ratio of the drug liquid in production practice.

[0005] To achieve the above-mentioned object, the present invention provides a method for real-time control of the mixing ratio of a liquid medicine, comprising:

[0006] S1. Acquire the concentrations of the drug components and the flow rates of the drug components of the target mixed drug solution, and generate a real-time drug mixing ratio of the target mixed drug solution based on the concentrations of the drug components and the flow rates of the drug components;

[0007] S2, generating a reference liquid medicine mixing ratio of the target mixed liquid medicine;

[0008] S3, calculating a ratio deviation between the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio based on the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio;

[0009] S4. Performing a primary correlation analysis on the liquid components of the target mixed liquid to obtain inter-component correlations of the liquid components, obtaining environmental parameters of the target mixed liquid, and performing a secondary correlation analysis on the liquid components and the environmental parameters to obtain component-environment correlations between the liquid components and the environmental parameters;

[0010] S5. Jointly analyzing the inter-component correlations and the component-environment correlations to obtain a joint correlation degree of the medicinal liquid components, obtaining historical control weights of the medicinal liquid components, and updating the historical control weights based on the joint correlation degree to obtain real-time control weights of the medicinal liquid components;

[0011] S6. Calculate the real-time control amount of the liquid medicine component based on the proportional deviation and the real-time control weight.

[0012] In a preferred embodiment, the expression of the real-time drug solution mixing ratio is as follows:

[0013]

[0014] Where, Indicates the real-time drug solution mixing ratio, Indicates the The flow rate of each liquid component, Indicates the The concentration of each drug solution component, Indicates the flow rate and concentration of liquid chemical components.

[0015] In a preferred embodiment, generating the reference liquid medicine mixing ratio of the target mixed liquid medicine comprises:

[0016] Determine the timestamp of the real-time drug-liquid mixing ratio;

[0017] Determining a reaction start time of the target mixed drug solution;

[0018] Calculating the reaction time of the target mixed liquid based on the timestamp and the reaction start time;

[0019] Obtaining a time-mixing ratio comparison table of the target mixed liquid;

[0020] A time matching query is performed on the reaction time and the time-mixing ratio comparison table to obtain the reference liquid mixing ratio corresponding to the reaction time.

[0021] In a preferred embodiment, the performing of a primary correlation analysis on the components of the target mixed drug solution to obtain the correlation between the components of the drug solution comprises:

[0022] A primary correlation analysis is performed on the liquid components of the target mixed liquid based on a preset first correlation algorithm to obtain correlations between the liquid components. The preset first correlation algorithm is as follows:

[0023]

[0024] Where, Indicates the The first component of the liquid The inter-component correlation between the components of the liquid medicine, Indicates the The liquid components at time The concentration change rate, Indicates the The liquid components at time The concentration change rate, 、 Indicates the identification of the liquid medicine components, represents the number of data points in the sliding window, The identifier of the sampling time in the sliding window.

[0025] In a preferred embodiment, the performing of a secondary correlation analysis on the liquid medicine components and the environmental parameters to obtain the component-environment correlation between the liquid medicine components and the environmental parameters comprises:

[0026] A secondary correlation analysis is performed on the liquid medicine components and the environmental parameters based on a preset second correlation algorithm to obtain component-environment correlations between the liquid medicine components and the environmental parameters, wherein the preset second correlation algorithm is as follows:

[0027]

[0028] Where, Indicates the Component-environment correlations between individual liquid components and environmental parameters, Indicates that at time point k The contribution of each liquid component to the ratio deviation, Indicates the change in the actual environmental parameters at time point k and the standard environmental parameters at time point k, A weighted index representing the absolute value of the difference between the contribution and the change value, represents the normalized exponent of the absolute value of the difference, Indicates the identification of the liquid medicine components, Indicates the monitoring time point of the liquid medicine components, Indicates the number of samples at the monitoring time point.

[0029] In a preferred embodiment, the joint analysis of the inter-component correlation and the component-environment correlation to obtain the joint correlation degree of the liquid medicine components includes:

[0030] Determine whether the adjustment trends of the inter-component correlation and the component-environment correlation on the historical control weight are the same, wherein the adjustment trends include an increasing trend and a decreasing trend:

[0031] When the inter-component correlation and the component-environment correlation have the same adjustment trend on the historical control weight, multiplying the inter-component correlation and the component-environment correlation to obtain the joint correlation degree;

[0032] When the adjustment trends of the inter-component correlation and the component-environment correlation on the historical control weight are different, correlation coordination is performed on the inter-component correlation and the component-environment correlation to obtain the joint correlation degree.

[0033] In a preferred embodiment, the correlation between the components and the component-environment correlation is coordinated to obtain the joint correlation, including:

[0034] Calculating a first adjustment strength of the inter-component correlation with respect to the historical control weight, calculating a second adjustment strength of the component-environment correlation with respect to the historical control weight, and calculating a strength difference between the first adjustment strength and the second adjustment strength;

[0035] Determine whether the force difference exceeds a preset force threshold:

[0036] When the force difference exceeds the preset force threshold, obtaining the maximum force between the first adjustment force and the second adjustment force; when the maximum force is the first adjustment force, determining the inter-component correlation corresponding to the first adjustment force as the joint correlation degree; when the maximum force is the second adjustment force, determining the component-environment correlation corresponding to the second adjustment force as the joint correlation degree;

[0037] When the force difference does not exceed the preset force threshold, the first credibility of the inter-component correlation and the second credibility of the component-environment correlation are obtained based on the pre-trained credibility calculation model, the inter-component correlation is updated based on the first credibility to obtain the updated inter-component correlation, the component-environment correlation is updated based on the second credibility to obtain the updated component-environment correlation, and the updated inter-component correlation and the updated component-environment correlation are multiplied to obtain the joint correlation.

[0038] In a preferred embodiment, the calculation formula of the real-time control weight is as follows:

[0039]

[0040] Where, Indicates the The joint correlation degree of the liquid components, Indicates the The historical control weight of each liquid component, Indicates the The real-time control weight of each liquid medicine component.

[0041] In a preferred embodiment, the calculation formula of the real-time control amount is as follows:

[0042]

[0043] Where, Indicates the Real-time control of the amount of each liquid component, Indicates the The basic control amount of each liquid component, Indicates the The basic control amount of each liquid component, z represents the number of liquid components, represents the proportional deviation, Represents the normalized The real-time control weight of each liquid medicine component, 、 Identifier indicating the components of the drug solution.

[0044] In order to solve the above problems, the present invention also provides a real-time control system for the mixing ratio of liquid medicine, the system comprising:

[0045] A real-time mixing ratio calculation module is used to obtain the concentrations of the target mixed liquid components and the flow rates of the target mixed liquid components, and generate a real-time mixing ratio of the target mixed liquid based on the concentrations of the target mixed liquid components and the flow rates of the target mixed liquid components;

[0046] A reference liquid medicine mixing ratio generating module is used to generate a reference liquid medicine mixing ratio of the target liquid medicine mixture;

[0047] A ratio deviation calculation module is configured to calculate a ratio deviation between the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio based on the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio;

[0048] Correlation analysis module: used to perform a primary correlation analysis on the liquid components of the target mixed liquid to obtain the correlation between the components of the liquid components, obtain the environmental parameters of the target mixed liquid, and perform a secondary correlation analysis on the liquid components and the environmental parameters to obtain the component-environment correlation between the liquid components and the environmental parameters;

[0049] A weight updating module is configured to jointly analyze the inter-component correlations and the component-environment correlations to obtain the joint correlation degree of the liquid medicine components, obtain the historical control weights of the liquid medicine components, and update the historical control weights based on the joint correlation degree to obtain the real-time control weights of the liquid medicine components.

[0050] A real-time control quantity calculation module is used to calculate the real-time control quantity of the liquid medicine component based on the proportional deviation and the real-time control weight.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. The present invention performs a primary correlation analysis on the components of the target mixed liquid, converting the complex correlation relationships between the components into measurable quantitative indicators, thereby improving the accuracy of the judgment of the degree of correlation between the liquid components. The component-environment correlation obtained by the secondary correlation analysis provides a precise basis for determining the control direction. By calculating the absolute value of the difference between the contribution of the liquid component and the change value of the environmental parameter at each monitoring time point, and performing weighted summation and normalization processing, the component-environment correlation value obtained can reflect the differences in the impact of environmental changes on each liquid component. Based on these differences, the control amount of each liquid component can be adjusted in a targeted manner to ensure that the ratio of the mixed liquid can remain within the ideal range when the environment changes, meeting the requirement for high precision of the liquid mixing ratio.

[0053] 2. A joint analysis is conducted on the inter-component correlation obtained from the primary correlation analysis and the component-environment correlation obtained from the secondary correlation analysis to determine the adjustment trend of the two on the historical control weights. If they are the same, they are multiplied to obtain the joint correlation degree. This method amplifies the coupling of the two influences and clearly presents their synergistic effect on the liquid medicine system. If they are different, the joint correlation degree is determined by coordinating the correlation by calculating the difference in adjustment strength, etc. This method can ensure that the joint correlation degree faithfully reflects the true correlation of each factor and avoids one-sided regulation. When calculating the real-time control amount, the formula comprehensively considers factors such as proportion deviation, real-time control weight, and basic control amount of each liquid medicine component. According to environmental changes and actual mixing ratio, the actual control amount required for each liquid medicine component under the current circumstances is accurately determined, thereby achieving precise control of the liquid medicine mixing ratio and meeting the high-precision requirements for the liquid medicine mixing ratio in production practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic flow chart of a method for real-time control of a liquid medicine mixing ratio according to an embodiment of the present invention;

[0055] Figure 2 This is a functional module diagram of a real-time control system for the mixing ratio of liquid medicine provided by one embodiment of the present invention;

[0056] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0057] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] The embodiment of the present application provides a method for real-time control of the mixing ratio of a liquid medicine. The execution subject of the method for real-time control of the mixing ratio of a liquid medicine includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for real-time control of the mixing ratio of a liquid medicine can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0059] Reference Figure 1 FIG. 1 is a flow chart of a method for real-time control of a liquid-drug mixing ratio according to an embodiment of the present invention. In this embodiment, the method for real-time control of a liquid-drug mixing ratio includes:

[0060] S1. Acquire the concentrations of the drug components and the flow rates of the drug components of the target mixed drug solution, and generate a real-time drug mixing ratio of the target mixed drug solution based on the concentrations of the drug components and the flow rates of the drug components;

[0061] In detail, the target mixed liquid is set inside the liquid medicine batching equipment, and the flow rate of the liquid medicine components is measured by a flow sensor (such as an electromagnetic flowmeter) on the liquid medicine batching equipment, and the concentration of the liquid medicine components is measured by a concentration sensor on the liquid medicine batching equipment.

[0062] In an embodiment of the present invention, the expression of the real-time drug liquid mixing ratio is as follows:

[0063]

[0064] Where, Indicates the real-time drug solution mixing ratio, Indicates the The flow rate of each liquid component, Indicates the The concentration of each drug solution component, Indicates the flow rate and concentration of liquid chemical components.

[0065] In detail, the flow Represents the number of times liquid medicine flows into the mixing chamber of the dosing equipment per unit time. Liquid components, The obtained value is the first The actual amount of active ingredient of each liquid component flowing into the mixing chamber. , the concentration of the drug solution components ,So , which means that 10 grams of the active ingredient of the liquid medicine enters the mixing chamber every minute.

[0066] S2, generating a reference liquid medicine mixing ratio of the target mixed liquid medicine;

[0067] In an embodiment of the present invention, generating a reference liquid medicine mixing ratio of the target mixed liquid medicine includes:

[0068] Determine the timestamp of the real-time drug-liquid mixing ratio;

[0069] Determining a reaction start time of the target mixed drug solution;

[0070] Calculating the reaction time of the target mixed liquid based on the timestamp and the reaction start time;

[0071] Obtaining a time-mixing ratio comparison table of the target mixed liquid;

[0072] A time matching query is performed on the reaction time and the time-mixing ratio comparison table to obtain the reference liquid mixing ratio corresponding to the reaction time.

[0073] Specifically, a timestamp records the moment in time when real-time drug-liquid mixing ratio data is generated, with accuracy down to seconds, milliseconds, or even microseconds. During the drug-liquid mixing process, devices like flow sensors and concentration sensors continuously collect data and calculate the real-time drug-liquid mixing ratio. Each time this ratio is calculated, the system attaches a corresponding timestamp. This timestamp acts as a time coordinate for subsequent tracking and analysis of the drug-liquid mixing ratio at that specific moment. For example, if a set of real-time drug-liquid mixing ratio data is calculated at 10:05:10, then 10:05:10 is the timestamp for this data.

[0074] Specifically, the reaction start time refers to the moment when the target mixed liquid begins a chemical reaction or physical mixing process. During the liquid preparation process, the system records the moment when the various liquid components begin to enter the liquid dispensing equipment according to the set program and begin to interact. For example, when the operator presses the start button, the liquid begins to flow into the mixing chamber and the mixing reaction occurs. This moment is recorded by the system as the reaction start time of the target liquid mixture.

[0075] In detail, the time-mixing ratio comparison table is a reference table obtained in advance through experiments, simulations, or previous production experience. It records the ideal mixing ratio that the target mixed liquid should achieve under different reaction times. The horizontal axis of the table is the reaction time, and the vertical axis is the corresponding benchmark liquid mixing ratio. For example, in the experiment, it was found that when a certain target mixed liquid reacts for 1 minute, the benchmark liquid mixing ratio is A:B:C=1:2:3; after 2 minutes of reaction, the benchmark liquid mixing ratio becomes A:B:C=1.2:1.8:3.2. These data will be organized and recorded in the time-mixing ratio comparison table for subsequent comparison and reference.

[0076] In detail, after obtaining the reaction time of the current target mixed liquid, it is necessary to find the matching benchmark liquid mixing ratio in the time-mixing ratio comparison table. According to the reaction time, find the closest or completely matching time point in the comparison table, and then obtain the benchmark liquid mixing ratio corresponding to the time point. For example, the calculated reaction time is 3 minutes and 30 seconds, and the closest time point in the time-mixing ratio comparison table is 3 minutes and 30 seconds. The corresponding mixing ratio is A:B:C=1.5:2.5:4, then this 1.5:2.5:4 is the benchmark liquid mixing ratio under the current reaction time.

[0077] S3, calculating a ratio deviation between the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio based on the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio;

[0078] Specifically, a difference calculation is performed between the real-time drug liquid mixing ratio and the standard drug liquid mixing ratio to obtain a ratio deviation between the real-time drug liquid mixing ratio and the standard drug liquid mixing ratio.

[0079] For example, the target mixed solution is composed of two solution components:

[0080] , ,So ;

[0081] , ,So ;

[0082]

[0083] By querying the time-mixing ratio comparison table, the reference liquid mixing ratio at this time is obtained as .

[0084] The difference between the real-time liquid mixing ratio and the reference liquid mixing ratio is calculated and expressed as the difference between the two liquid component ratios:

[0085] For the first liquid component: ;

[0086] For the second liquid component:

[0087] Here and This indicates proportional deviation.

[0088] S4. Performing a primary correlation analysis on the liquid components of the target mixed liquid to obtain inter-component correlations of the liquid components, acquiring environmental parameters of the target mixed liquid in real time through a sensor, and performing a secondary correlation analysis on the liquid components and the environmental parameters to obtain component-environment correlations between the liquid components and the environmental parameters;

[0089] In an embodiment of the present invention, the performing of a primary correlation analysis on the liquid components of the target mixed liquid to obtain the correlation between the liquid components includes:

[0090] A primary correlation analysis is performed on the liquid components of the target mixed liquid based on a preset first correlation algorithm to obtain correlations between the liquid components. The preset first correlation algorithm is as follows:

[0091]

[0092] Where, Indicates the The first component of the liquid The inter-component correlation between the components of the liquid medicine, Indicates the The liquid components at time The concentration change rate, Indicates the The liquid components at time The concentration change rate, 、 Indicates the identification of the liquid medicine components, represents the number of data points in the sliding window, The identifier of the sampling time in the sliding window.

[0093] In detail, , in this formula, What is calculated is the difference in the concentration change rate of the two liquid components at time k, which reflects the difference in the speed of their concentration change at that moment. Square the difference and make the result of the difference positive; is the number of The liquid components and The components of the drug solution at each sampling time The squares of the differences in the concentration change rates are summed and divided by The method is to find the average and then take the square root to obtain a quantitative value of the average difference degree. The larger the value, the greater the difference in the concentration change rate of the two components, that is, the worse the synchronization of the concentration change.

[0094] In detail, the formula In the equation, the denominator increases as the difference in the rate of change of the two components' concentrations increases. Since the numerator is 1, when the difference in the rate of change of the two components' concentrations is large (the denominator is large), The value approaches 0. When the difference in the concentration change rate of the two components is small (the denominator is small), The value approaches 1, which establishes an inverse correlation between the difference in concentration change rate and the correlation value.

[0095] In an embodiment of the present invention, performing a secondary correlation analysis on the liquid medicine components and the environmental parameters to obtain component-environment correlations between the liquid medicine components and the environmental parameters includes:

[0096] A secondary correlation analysis is performed on the liquid medicine components and the environmental parameters based on a preset second correlation algorithm to obtain component-environment correlations between the liquid medicine components and the environmental parameters, wherein the preset second correlation algorithm is as follows:

[0097]

[0098] Where, Indicates the Component-environment correlations between individual liquid components and environmental parameters, Indicates that at time point k The contribution of each liquid component to the ratio deviation, Indicates the change in the actual environmental parameters at time point k and the standard environmental parameters at time point k, A weighted index representing the absolute value of the difference between the contribution and the change value, represents the normalized exponent of the absolute value of the difference, Indicates the identification of the liquid medicine components, Indicates the monitoring time point of the liquid medicine components, Indicates the number of samples at the monitoring time point.

[0099] In detail, The absolute value of the difference between the contribution of the drug solution components and the change in the environmental parameters at each monitoring time point k is calculated and weighted and summed. Weighting is used to emphasize or weaken the impact of differences at certain time points on the overall correlation. It comprehensively reflects the cumulative difference between the changes in the drug solution components and the environmental parameters over the entire monitoring period. A larger value indicates a more significant cumulative difference between the two at each time point.

[0100] In detail, , based on the absolute value of the difference between the liquid components and the environmental parameters at different time points, but these differences are processed by the normalization index. Its main function is to normalize the value of the molecule so that the calculated within an appropriate and comparable range.

[0101] In detail, The calculation steps are as follows:

[0102] No. The liquid components Proportional deviation of time , Indicates that at time point k The actual ratio of each liquid component, Indicates that at time point k The base ratio of each liquid medicine component is a known value;

[0103] Overall mixture ratio deviation , .

[0104] S5. Jointly analyzing the inter-component correlations and the component-environment correlations to obtain a joint correlation degree of the medicinal liquid components, obtaining historical control weights of the medicinal liquid components, and updating the historical control weights based on the joint correlation degree to obtain real-time control weights of the medicinal liquid components;

[0105] Specifically, during the production or testing of a drug solution, detailed records are kept of the weights assigned to each drug solution component at each adjustment, starting from past operations. These records are stored in a database or related data files. By querying information such as the corresponding time period, batch, or operating conditions, the historical adjustment weights of the corresponding drug solution components can be extracted.

[0106] Specifically, by measuring the changes in various indicators of the drug solution components under different environmental parameters, a secondary correlation analysis is performed between multiple environmental parameters (such as temperature, pressure, and humidity) and the drug solution components using a pre-set secondary correlation algorithm. This analysis identifies environmental parameters with strong correlations with key indicators such as drug solution quality and mixing effectiveness. For example, preliminary experiments revealed that pressure changes have little effect on the solubility and mixing uniformity of a certain drug solution component, while humidity has a significant effect on its stability. Therefore, the "component-humidity correlation" is selected as a combined analysis of the component-environment correlation and the inter-component correlation.

[0107] In an embodiment of the present invention, the joint analysis of the inter-component correlation and the component-environment correlation to obtain the joint correlation degree of the liquid medicine components includes:

[0108] Determine whether the adjustment trends of the inter-component correlation and the component-environment correlation on the historical control weight are the same, wherein the adjustment trends include an increasing trend and a decreasing trend:

[0109] Specifically, the regulation trend refers to the direction of the influence of the inter-component correlation and the component-environment correlation on the historical regulation weight when the mixing ratio of the liquid medicine is regulated. Taking 1 as the boundary, if the inter-component correlation = 0.2 (0.2 is less than 1) and the component-environment correlation = 1.8 (1.8 is greater than 1), then the regulation trend of the inter-component correlation is decreasing, and the regulation trend of the component-environment correlation is increasing.

[0110] When the inter-component correlation and the component-environment correlation have the same adjustment trend on the historical control weight, the inter-component correlation and the component-environment correlation are multiplied to obtain the joint correlation degree, wherein the calculation formula of the joint correlation degree is as follows:

[0111]

[0112] Where, Indicates the The joint correlation degree of the liquid components, Indicates the The first component of the liquid The inter-component correlation between the components of the liquid medicine, Indicates the Component-environment correlations between individual liquid components and environmental parameters, 、 Identifier indicating the components of the drug solution.

[0113] In detail, the multiplication operation can couple and amplify the effects of inter-component correlation and component-environment correlation, because when the changing trends of the two are consistent, their comprehensive effects on the liquid medicine system are synergistically enhanced.

[0114] When the adjustment trends of the inter-component correlation and the component-environment correlation on the historical control weight are different, the inter-component correlation and the component-environment correlation are coordinated to obtain the joint correlation degree.

[0115] Specifically, in a liquid medicine system, the inter-component correlations and component-environment correlations are complex. Sometimes, inter-component correlations require increasing a certain control weight to ensure uniform mixing, while component-environment correlations require decreasing that weight to maintain liquid medicine stability due to environmental changes. These diverging control trends indicate that the two correlations have conflicting effects on the liquid medicine system. Calculating the joint correlation degree through correlation coordination comprehensively considers these conflicting relationships, resulting in a more realistic correlation metric that accurately reflects the comprehensive correlation characteristics of liquid medicine components under complex conditions and avoids overlooking key information due to simplistic treatments.

[0116] In detail, before determining whether the inter-component correlation and the component-environment correlation have the same adjustment trend on the historical control weight, it is necessary to normalize the inter-component correlation and the component-environment correlation so that the value ranges of the two are both between 0-2. If the value of the inter-component correlation is between 0-1, then the adjustment trend of the inter-component correlation on the historical control weight is a decreasing trend. If the value of the inter-component correlation is between 1-2, then the adjustment trend of the inter-component correlation on the historical control weight is an increasing trend. The same applies to the component-environment correlation.

[0117] In an embodiment of the present invention, the step of performing correlation coordination on the inter-component correlation and the component-environment correlation to obtain the joint correlation degree includes:

[0118] Calculating a first adjustment strength of the inter-component correlation with respect to the historical control weight, calculating a second adjustment strength of the component-environment correlation with respect to the historical control weight, and calculating a strength difference between the first adjustment strength and the second adjustment strength;

[0119] Specifically, the first and second regulatory strengths are used to measure the degree of regulation of the inter-component correlation and the component-environment correlation on the historical control weight. The regulatory strengths are both bounded by 1. If the inter-component correlation = 0.2 and the component-environment correlation = 1.8, then the first regulatory strength = |0.2-1| = 0.8, and the second regulatory strength = |1.8-1| = 0.8. The absolute value of the first regulatory strength minus the second regulatory strength is equal to 0, so the strength difference = 0.

[0120] Determine whether the force difference exceeds a preset force threshold:

[0121] When the force difference exceeds the preset force threshold, obtaining the maximum force between the first adjustment force and the second adjustment force; when the maximum force is the first adjustment force, determining the inter-component correlation corresponding to the first adjustment force as the joint correlation degree; when the maximum force is the second adjustment force, determining the component-environment correlation corresponding to the second adjustment force as the joint correlation degree;

[0122] Specifically, if the inter-component correlation = 0.8, the component-environment correlation = 1.9, then the first adjustment strength = |0.8-1| = 0.2, the second adjustment strength = |1.9-1| = 0.9, the absolute value of the first adjustment strength minus the second adjustment strength is equal to 0.7, then the strength difference = 0.7, the preset strength threshold is 0.4, then the strength difference is greater than the preset strength threshold, the maximum value is the second adjustment strength, then the component-environment correlation corresponding to the second adjustment strength is determined as the joint correlation degree, that is, , Indicates the The joint correlation degree of the liquid components, Indicates the Component-environment correlations between individual drug solution components and environmental parameters.

[0123] In general: During the drug-liquid mixing process, the influence of the correlation between components and the correlation between components and the environment on the control weight is complex. When the strength difference exceeds the preset threshold, it indicates that the two correlations have significantly different regulatory effects on the historical control weight. At this time, the correlation with the greatest strength is selected as the joint correlation, which can accurately capture the factors that are more critical to the drug-liquid mixing ratio under the current circumstances. If a comprehensive and complex comprehensive analysis of the correlation between components and the correlation between components and the environment is performed every time, it will consume a lot of time and computing resources.

[0124] When the force difference does not exceed the preset force threshold, the first credibility of the inter-component correlation and the second credibility of the component-environment correlation are obtained based on the pre-trained credibility calculation model, the inter-component correlation is updated based on the first credibility to obtain the updated inter-component correlation, the component-environment correlation is updated based on the second credibility to obtain the updated component-environment correlation, and the updated inter-component correlation and the updated component-environment correlation are multiplied to obtain the joint correlation.

[0125] Specifically, the pre-trained credibility calculation model is an important tool for assessing the credibility of inter-component correlations and component-environmental parameter correlations. It is primarily used to more accurately process these two correlations when the historical regulatory weight adjustment trends of inter-component correlations and component-environment correlations differ, and the difference in their adjustment strength does not exceed a preset threshold. The specific training method for the credibility calculation model is as follows: a large amount of data related to drug solution mixing is collected, covering drug solution component concentrations, flow rates, mixing ratios, environmental parameters, and corresponding inter-component correlations and component-environment correlations from different batches and environmental conditions; the collected data is then processed and analyzed to extract key features. Calculate the correlation between components and the correlation between components and the environment, determine the corresponding standard deviation, and use a neural network algorithm to learn complex correlation and credibility relationships. During the training process, use the known accurate credibility as the label to let the model learn the mapping relationship between input features and credibility. By continuously adjusting the key parameters, the credibility value output by the model is close to the actual label value; divide the processed data into training set and test set, train the model on the training set, optimize the model parameters according to the training results, and use optimization algorithms such as gradient descent to continuously adjust the model parameters to minimize the loss function and improve the performance of the model on the training set and test set.

[0126] In detail, in the pre-trained credibility calculation model, the calculation formula for calculating the first credibility is as follows:

[0127]

[0128] Where, represents the first credibility, Indicates the The first component of the liquid The inter-component correlation between the components of the liquid medicine, represents the standard deviation of the correlation between the components, Indicates the absolute value, Represents the maximum function.

[0129] Specifically, , The standard deviation measures the degree of dispersion of the correlation data between components. When it is smaller, it means that the correlation data between components are more concentrated. will approach 1, indicating that the correlation is highly reliable. On the contrary, when When it is larger, it means that the data is more discrete and less stable. It will approach 0, that is, the credibility is low, which partially reflects the impact on credibility from the perspective of overall data stability. , is the absolute value of the inter-component correlation between the i-th and j-th drug solution components, It is the maximum absolute value of the correlation between all components. This ratio reflects the specific correlation between components. The relative size of all correlations. The closer the ratio is to 1, the stronger and more prominent the correlation is, and the higher the credibility is. The closer the ratio is to 0, the weaker the correlation is, and the lower the credibility is. Multiplying these two parts together will combine the overall stability of the data and the relative strength of the specific correlation. Only when the correlation data between components is stable ( Approaching 1), and the specific correlation is relatively prominent among all correlations ( When approaching 1), the first credibility It will approach 1, that is, the reliability is high; if one of the aspects is not satisfied, such as the data is highly discrete or the specific correlation is relatively weak, it will make becomes smaller and the credibility is reduced, so that the credibility of the correlation between components can be evaluated more comprehensively and accurately.

[0130] In detail, in the pre-trained credibility calculation model, the calculation formula for calculating the second credibility is as follows:

[0131]

[0132] Where, represents the second credibility, represents the historical standard deviation of the component-environment correlation, Represents the short-term standard deviation of the environmental parameter.

[0133] Specifically, Reflecting the impact of historical stability, It reflects the dispersion degree of component-environment correlation data over a long period of time. Small, which means that in the historical period, the component-environment correlation data are relatively concentrated. If it approaches 1, it means that from a historical perspective, the component-environment correlation is highly credible; on the contrary, if Large, indicating that the component-environment correlation has fluctuated greatly in history and has poor stability. Approaching 0, the credibility is low. is the short-term standard deviation of the environmental parameter, which is used to measure the dispersion of the environmental parameter in the short term. Small, indicating that the recent environmental parameters have little fluctuation and are relatively stable; if If it is large, it means that the environmental parameters change frequently in a short period of time. In this item, when When it is small, its value approaches 1, which means that from the perspective of short-term environmental parameter stability, the credibility of the component-environment correlation is high, and vice versa. Multiplying these two parts achieves a comprehensive assessment of the credibility of the component-environment correlation. Only when the component-environment correlation is historically stable ( Approaching 1), and the recent environmental parameters are also stable ( When approaching 1), the second credibility It will approach 1, that is, the credibility is high. If the stability of some aspects in history or short term is poor, it will make becomes smaller, reducing the credibility, thereby comprehensively and accurately reflecting the credibility of the component-environment correlation.

[0134] In detail, the specific steps of “updating the inter-component correlation based on the first credibility to obtain an updated inter-component correlation, and updating the component-environment correlation based on the second credibility to obtain an updated component-environment correlation” are as follows:

[0135] Multiply the inter-component correlation by the corresponding first credibility to obtain the updated inter-component correlation, that is, the updated inter-component correlation = ; Multiply the component-environment correlation by the corresponding second credibility to obtain the updated component-environment correlation, that is, the updated component-environment correlation = .

[0136] Specifically, in “performing a multiplication operation on the updated inter-component correlation and the updated component-environment correlation to obtain the joint correlation”, that is, .

[0137] In detail, when the strength difference does not exceed the preset strength threshold, it means that the adjustment strength of the correlation between components and the component-environment correlation on the historical control weight is not much different. In this case, both correlations are more important for the mixing ratio of the liquid medicine. Selecting the "largest" correlation alone (in fact, the difference in strength between the two is not obvious at this time) will break the balance and fail to fully reflect the comprehensive effect of various factors in the liquid medicine system. For example, in a certain liquid medicine mixing scenario, environmental factors such as temperature and humidity affect each component of the liquid medicine, and the degree of influence is similar. If only one correlation is selected as the joint correlation based on a slightly larger adjustment strength, the important role of the other correlation will be ignored, resulting in inaccurate control of the mixing ratio.

[0138] In summary, the first credibility factor combines the dispersion of inter-component correlation data and the relative magnitude of specific correlation values, assessing credibility from both data stability and correlation strength perspectives. The second credibility factor combines the historical stability of component-environment correlations with the short-term stability of environmental parameters. Updating the corresponding correlations based on these two credibility factors comprehensively incorporates multi-dimensional information, including historical, short-term, and data dispersion. This avoids biased correlation assessments based on a single factor, enabling the combined correlation factor to better reflect the true relationship between various factors in the drug solution mixture.

[0139] In an embodiment of the present invention, the calculation formula of the real-time control weight is as follows:

[0140]

[0141] Where, Indicates the The joint correlation degree of the liquid components, Indicates the The historical control weight of each liquid component, Indicates the The real-time control weight of each liquid medicine component.

[0142] In detail, the joint correlation integrates factors such as the correlation between components and the correlation between components and the environment, reflecting the comprehensive impact of the current i-th liquid component with other components and the environment. It is used to correct the historical control weights so that the real-time control weights are more in line with the current actual situation.

[0143] S6. Calculate the real-time control amount of the liquid medicine component based on the proportional deviation and the real-time control weight.

[0144] In an embodiment of the present invention, the calculation formula of the real-time control amount is as follows:

[0145]

[0146] Where, Indicates the Real-time control of the amount of each liquid component, Indicates the The basic control amount of each liquid component, Indicates the The basic control amount of each liquid component, z represents the number of liquid components, represents the proportional deviation, Represents the normalized The real-time control weight of each liquid medicine component, 、 Identifier indicating the components of the drug solution.

[0147] Specifically, , is for all The basic control amount of each liquid component is summed up to reflect the total basic control amount of the entire liquid system; It reflects that after comprehensively considering factors such as the relationship between components and the relationship between components and the environment, the The relative importance of each drug solution component in the current regulation; As the first The basic control amount of each liquid component is the basis of real-time control amount; The significance of this step is to determine the amount of adjustment required for the i-th component due to the proportional deviation, based on the size of the proportional deviation, combined with the sum of the basic control amounts of all components and the relative control weight of the i-th component. That is to say, when there is a proportional deviation, the amount of additional regulation required for the component should be calculated based on the basic regulation of all the components of the liquid medicine and the weight of the i-th component of the liquid medicine; the basic regulation amount and Adding them together, we get The final real-time control amount of each liquid medicine component is calculated by this method. This calculation method comprehensively considers the basic control requirements, the basic control status of the overall liquid medicine system, the proportion deviation and the control weight of each liquid medicine component. It can more accurately determine the actual control amount required for each liquid medicine component under the current situation, so as to achieve precise control of the liquid medicine mixing ratio.

[0148] like Figure 2 2 is a functional module diagram of a real-time control system for a liquid medicine mixing ratio provided by an embodiment of the present invention.

[0149] The real-time control system 100 for controlling the mixing ratio of a liquid medicine according to the present invention can be installed in an electronic device. Depending on the functionality implemented, the real-time control system 100 can include a real-time mixing ratio calculation module 101, a reference liquid medicine mixing ratio generation module 102, a ratio deviation calculation module 103, a correlation analysis module 104, a weight update module 105, and a real-time control amount calculation module 106. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and perform fixed functions, and are stored in the memory of the electronic device.

[0150] In this embodiment, the functions of each module / unit are as follows:

[0151] A real-time mixing ratio calculation module is used to obtain the concentrations of the target mixed liquid components and the flow rates of the target mixed liquid components, and generate a real-time mixing ratio of the target mixed liquid based on the concentrations of the target mixed liquid components and the flow rates of the target mixed liquid components;

[0152] A reference liquid medicine mixing ratio generating module is used to generate a reference liquid medicine mixing ratio of the target liquid medicine mixture;

[0153] A ratio deviation calculation module is configured to calculate a ratio deviation between the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio based on the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio;

[0154] Correlation analysis module: used to perform a primary correlation analysis on the liquid components of the target mixed liquid to obtain the correlation between the components of the liquid components, obtain the environmental parameters of the target mixed liquid, and perform a secondary correlation analysis on the liquid components and the environmental parameters to obtain the component-environment correlation between the liquid components and the environmental parameters;

[0155] A weight updating module is configured to jointly analyze the inter-component correlations and the component-environment correlations to obtain the joint correlation degree of the liquid medicine components, obtain the historical control weights of the liquid medicine components, and update the historical control weights based on the joint correlation degree to obtain the real-time control weights of the liquid medicine components.

[0156] A real-time control quantity calculation module is used to calculate the real-time control quantity of the liquid medicine component based on the proportional deviation and the real-time control weight.

[0157] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0158] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0159] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0160] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0161] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for real-time control of liquid medicine mixing ratio, characterized in that: The method comprises: S1. Acquire the concentrations of the drug components and the flow rates of the drug components of the target mixed drug solution, and generate a real-time drug mixing ratio of the target mixed drug solution based on the concentrations of the drug components and the flow rates of the drug components; S2, generating a reference liquid medicine mixing ratio of the target mixed liquid medicine; S3, calculating a ratio deviation between the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio based on the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio; S4. Performing a primary correlation analysis on the liquid components of the target mixed liquid to obtain inter-component correlations of the liquid components, obtaining environmental parameters of the target mixed liquid, and performing a secondary correlation analysis on the liquid components and the environmental parameters to obtain component-environment correlations between the liquid components and the environmental parameters; S5. Jointly analyzing the inter-component correlations and the component-environment correlations to obtain a joint correlation degree of the medicinal liquid components, obtaining historical control weights of the medicinal liquid components, and updating the historical control weights based on the joint correlation degree to obtain real-time control weights of the medicinal liquid components; S6. Calculate the real-time control amount of the liquid medicine component based on the proportional deviation and the real-time control weight.

2. The method for real-time control of the liquid medicine mixing ratio according to claim 1, wherein: The expression of the real-time liquid medicine mixing ratio is as follows: Where, Indicates the real-time drug solution mixing ratio, Indicates the The flow rate of each liquid component, Indicates the The concentration of each drug solution component, Indicates the flow rate and concentration of liquid chemical components.

3. The method for real-time control of the liquid medicine mixing ratio according to claim 1, wherein: The step of generating a reference liquid medicine mixing ratio for the target liquid medicine mixture includes: Determine the timestamp of the real-time drug-liquid mixing ratio; Determining a reaction start time of the target mixed drug solution; Calculating the reaction time of the target mixed liquid based on the timestamp and the reaction start time; Obtaining a time-mixing ratio comparison table of the target mixed liquid; A time matching query is performed on the reaction time and the time-mixing ratio comparison table to obtain the reference liquid mixing ratio corresponding to the reaction time.

4. The method for real-time control of the liquid medicine mixing ratio according to claim 1, wherein: The performing of a primary correlation analysis on the liquid components of the target mixed liquid to obtain the correlation between the liquid components includes: A primary correlation analysis is performed on the liquid components of the target mixed liquid based on a preset first correlation algorithm to obtain correlations between the liquid components. The preset first correlation algorithm is as follows: Where, Indicates the The first component of the liquid The inter-component correlation between the components of the drug solution, Indicates the The liquid components at time The concentration change rate, Indicates the The liquid components at time The concentration change rate, 、 Indicates the identification of the liquid medicine components, represents the number of data points in the sliding window, The identifier of the sampling time in the sliding window.

5. The method for real-time control of the liquid medicine mixing ratio according to claim 1, wherein: The performing of a secondary correlation analysis on the liquid medicine components and the environmental parameters to obtain component-environment correlations between the liquid medicine components and the environmental parameters includes: A secondary correlation analysis is performed on the liquid medicine components and the environmental parameters based on a preset second correlation algorithm to obtain component-environment correlations between the liquid medicine components and the environmental parameters, wherein the preset second correlation algorithm is as follows: Where, Indicates the Component-environment correlations between individual liquid components and environmental parameters, Indicates that at time point k The contribution of each liquid component to the ratio deviation, Indicates the change in the actual environmental parameters at time point k and the standard environmental parameters at time point k, A weighted index representing the absolute value of the difference between the contribution and the change value, represents the normalized exponent of the absolute value of the difference, Indicates the identification of the liquid medicine components, Indicates the monitoring time point of the liquid medicine components, Indicates the number of samples at the monitoring time point.

6. The method for real-time control of the liquid medicine mixing ratio according to claim 1, wherein: The joint analysis of the inter-component correlation and the component-environment correlation to obtain the joint correlation degree of the liquid medicine components includes: Determine whether the adjustment trends of the inter-component correlation and the component-environment correlation on the historical control weight are the same, wherein the adjustment trends include an increasing trend and a decreasing trend: When the inter-component correlation and the component-environment correlation have the same adjustment trend on the historical control weight, multiplying the inter-component correlation and the component-environment correlation to obtain the joint correlation degree; When the adjustment trends of the inter-component correlation and the component-environment correlation on the historical control weight are different, correlation coordination is performed on the inter-component correlation and the component-environment correlation to obtain the joint correlation degree.

7. The method for real-time control of the liquid medicine mixing ratio according to claim 6, wherein: The step of performing correlation coordination on the inter-component correlation and the component-environment correlation to obtain the joint correlation degree includes: Calculating a first adjustment strength of the inter-component correlation with respect to the historical control weight, calculating a second adjustment strength of the component-environment correlation with respect to the historical control weight, and calculating a strength difference between the first adjustment strength and the second adjustment strength; Determine whether the force difference exceeds a preset force threshold: When the force difference exceeds the preset force threshold, obtaining the maximum force between the first adjustment force and the second adjustment force; when the maximum force is the first adjustment force, determining the inter-component correlation corresponding to the first adjustment force as the joint correlation degree; when the maximum force is the second adjustment force, determining the component-environment correlation corresponding to the second adjustment force as the joint correlation degree; When the force difference does not exceed the preset force threshold, the first credibility of the inter-component correlation and the second credibility of the component-environment correlation are obtained based on the pre-trained credibility calculation model, the inter-component correlation is updated based on the first credibility to obtain the updated inter-component correlation, the component-environment correlation is updated based on the second credibility to obtain the updated component-environment correlation, and the updated inter-component correlation and the updated component-environment correlation are multiplied to obtain the joint correlation.

8. The method for real-time control of the liquid medicine mixing ratio according to claim 1, wherein: The calculation formula of the real-time control weight is as follows: Where, Indicates the The joint correlation degree of the liquid components, Indicates the The historical control weight of each liquid component, Indicates the The real-time control weight of each liquid medicine component.

9. The method for real-time control of the liquid medicine mixing ratio according to claim 1, wherein: The calculation formula of the real-time control amount is as follows: Where, Indicates the Real-time control of the amount of each liquid component, Indicates the The basic control amount of each liquid component, Indicates the The basic control amount of each liquid component, z represents the number of liquid components, represents the proportional deviation, Represents the normalized The real-time control weight of each liquid medicine component, 、 Identifier indicating the components of the drug solution.

10. A real-time control system for liquid medicine mixing ratio, characterized in that: The system comprises: A real-time mixing ratio calculation module is used to obtain the concentrations of the target mixed liquid components and the flow rates of the target mixed liquid components, and generate a real-time mixing ratio of the target mixed liquid based on the concentrations of the target mixed liquid components and the flow rates of the target mixed liquid components; A reference liquid medicine mixing ratio generating module is used to generate a reference liquid medicine mixing ratio of the target liquid medicine mixture; A ratio deviation calculation module is configured to calculate a ratio deviation between the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio based on the real-time drug-liquid mixing ratio and the reference drug-liquid mixing ratio; Correlation analysis module: used to perform a primary correlation analysis on the liquid components of the target mixed liquid to obtain the correlation between the components of the liquid components, obtain the environmental parameters of the target mixed liquid, and perform a secondary correlation analysis on the liquid components and the environmental parameters to obtain the component-environment correlation between the liquid components and the environmental parameters; A weight updating module is configured to jointly analyze the inter-component correlations and the component-environment correlations to obtain the joint correlation degree of the liquid medicine components, obtain the historical control weights of the liquid medicine components, and update the historical control weights based on the joint correlation degree to obtain the real-time control weights of the liquid medicine components. A real-time control quantity calculation module is used to calculate the real-time control quantity of the liquid medicine component based on the proportional deviation and the real-time control weight.

Images