Artificial pancreas control system and device

Abstract

The invention relates to an artificial pancreas control system and device. The system comprises a parameter self-learning module and a blood glucose control module, the parameter self-learning module is used for determining a control parameter adjustment proportion corresponding to an artificial pancreas initial control parameter according to the artificial pancreas initial control parameter of the target object; the parameter self-learning module is further used for adjusting the artificial pancreas initial control parameters according to the control parameter adjustment proportion to obtain artificial pancreas adjustment control parameters of the target object; the blood glucose control module is used for inputting the artificial pancreas adjustment control parameters into the artificial pancreas control unit to obtain blood glucose value control parameters; the blood glucose control module is further used for inputting the blood glucose value control parameters into the blood glucose control safety constraint unit, and the current insulin infusion amount corresponding to the target object is obtained. By adopting the method, the deviation of calculating the insulin infusion amount of the target object can be reduced.

Description

Technical Field

[0001] The present application relates to the field of automatic control technology, and in particular to an artificial pancreas control system and device. Background Art

[0002] With the development of automatic control technology, an artificial pancreas control system has emerged. The system consists of a sensor and an insulin pump or patch pump. The sensor monitors the patient's blood sugar level in real time through electrodes connected to the human skin. When the target subject's blood sugar value deviates from the normal standard, the sensor's built-in computer chip will send instructions to the syringe to inject insulin for the target subject in time.

[0003] In traditional technology, the artificial pancreas control system uses continuous glucose monitoring technology (CGM) to monitor the target object's blood sugar value throughout the day. It and insulin infusion data can reflect the body's blood sugar metabolism. Due to the intra-individual / inter-individual differences in the blood sugar metabolism process, the insulin infusion monitoring model in the traditional continuous glucose monitoring technology (CGM) fails to adjust for the intra-individual / inter-individual differences, resulting in deviations in the calculation of the target object's insulin infusion amount. Summary of the invention

[0004] Based on this, it is necessary to provide an artificial pancreas control system, device, computer equipment, computer-readable storage medium and computer program product that can reduce the deviation in calculating the insulin infusion amount of the target object in order to solve the above technical problems.

[0005] In a first aspect, the present application provides an artificial pancreas control system. The system comprises: a parameter self-learning module, a blood sugar control module;

[0006] The parameter self-learning module is used to determine the control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas according to the initial control parameters of the artificial pancreas of the target object;

[0007] The parameter self-learning module is further used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0008] The blood sugar control module is used to input the artificial pancreas adjustment control parameter into the artificial pancreas control unit to obtain the blood sugar value control parameter;

[0009] The blood sugar control module is further used to input the blood sugar value control parameter into the blood sugar control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object.

[0010] In a second aspect, the present application also provides an artificial pancreas control device. The device comprises: a control parameter acquisition end, a controller and an infusion end;

[0011] The control parameter acquisition end is used to acquire the initial control parameters of the artificial pancreas of the target object;

[0012] The controller is used to determine the control parameter adjustment ratio corresponding to the initial control parameter of the artificial pancreas according to the initial control parameter of the artificial pancreas of the target object;

[0013] The controller is further used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0014] The controller is further used to input the artificial pancreas adjustment control parameter into the artificial pancreas control unit to obtain the blood sugar value control parameter;

[0015] The controller is further used to input the blood sugar value control parameter into the blood sugar control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object;

[0016] The infusion end is used to infuse insulin into the target object according to the current insulin infusion amount.

[0017] In a third aspect, the present application also provides an artificial pancreas control method. The method comprises:

[0018] Determining, according to the initial control parameters of the artificial pancreas of the target object, a control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas;

[0019] Adjusting the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0020] Inputting the artificial pancreas adjustment control parameter into the artificial pancreas control module to obtain the blood sugar value control parameter;

[0021] The blood glucose value control parameter is input into the blood glucose control safety constraint module to obtain the current insulin infusion amount corresponding to the target object.

[0022] In a fourth aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0023] Determining, according to the initial control parameters of the artificial pancreas of the target object, a control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas;

[0024] Adjusting the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0025] Inputting the artificial pancreas adjustment control parameter into the artificial pancreas control module to obtain the blood sugar value control parameter;

[0026] The blood glucose value control parameter is input into the blood glucose control safety constraint module to obtain the current insulin infusion amount corresponding to the target object.

[0027] In a fifth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0028] Determining, according to the initial control parameters of the artificial pancreas of the target object, a control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas;

[0029] Adjusting the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0030] Inputting the artificial pancreas adjustment control parameter into the artificial pancreas control module to obtain the blood sugar value control parameter;

[0031] The blood glucose value control parameter is input into the blood glucose control safety constraint module to obtain the current insulin infusion amount corresponding to the target object.

[0032] In a sixth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0033] Determining, according to the initial control parameters of the artificial pancreas of the target object, a control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas;

[0034] Adjusting the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0035] Inputting the artificial pancreas adjustment control parameter into the artificial pancreas control module to obtain the blood sugar value control parameter;

[0036] The blood glucose value control parameter is input into the blood glucose control safety constraint module to obtain the current insulin infusion amount corresponding to the target object.

[0037] The above-mentioned artificial pancreas control system, device, computer equipment, storage medium and computer program product, the system includes: a parameter self-learning module and a blood glucose control module; the parameter self-learning module is used to determine the control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas according to the initial control parameters of the artificial pancreas of the target object; the parameter self-learning module is also used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object; the blood glucose control module is used to input the artificial pancreas adjustment control parameters into the artificial pancreas control unit to obtain the blood glucose value control parameters; the blood glucose control module is also used to input the blood glucose value control parameters into the blood glucose control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object.

[0038] By using the control parameter adjustment ratio to adjust the initial control parameters of the artificial pancreas of the target object, it is beneficial to use more accurate artificial pancreas adjustment control parameters as input to provide to the blood glucose control module for calculation; further, based on the artificial pancreas adjustment control parameters, the artificial pancreas control unit in the blood glucose control module can be used to obtain accurate blood glucose value control parameters. Since the actual situation of the target object needs to be constrained, a blood glucose control safety constraint unit is introduced to adjust the blood glucose value control parameters to obtain the current insulin infusion amount. The insulin infusion amount can be adjusted according to the intra-individual / inter-individual differences in the blood glucose metabolism process, which is beneficial to reduce the deviation of the target object's insulin infusion amount. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a schematic diagram of an artificial pancreas control system in one embodiment;

[0040] Figure 2 is a flow chart of an artificial pancreas control method in one embodiment;

[0041] Figure 3 is a schematic diagram of a flow chart of an artificial pancreas control device in one embodiment;

[0042] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0044] The artificial pancreas control system provided in the embodiment of the present application can be applied to Figure 1 In the system interaction diagram shown in FIG. , the system includes: a parameter self-learning module and a blood sugar control module; wherein the parameter self-learning module is used to determine the control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas according to the initial control parameters of the artificial pancreas of the target object; the parameter self-learning module is also used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object; the blood sugar control module is used to input the artificial pancreas adjustment control parameters into the artificial pancreas control unit to obtain the blood sugar value control parameters; the blood sugar control module is also used to input the blood sugar value control parameters into the blood sugar control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object.

[0045] In one embodiment, Figure 1 As shown, an artificial pancreas control system is provided, and the system is applied to Figure 1 Take the system interaction diagram in as an example to illustrate that the system includes:

[0046] The parameter self-learning module is used to determine the control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas according to the initial control parameters of the artificial pancreas of the target object.

[0047] The target object may be a person or an animal with abnormal blood sugar regulation.

[0048] Among them, the initial control parameters of the artificial pancreas can be the initial parameters input into the artificial pancreas control system, which can be obtained by looking up the table according to the situation of the target object. In general, the initial control parameters of the artificial pancreas include: standard basal rate basal (U / h), total daily insulin dose TDD (U), insulin sensitivity coefficient isf (mg / dL / U), carbohydrate coefficient icr (g / U), target blood glucose value Gt (mg / dL). Among them, the artificial pancreas control system can choose an insulin pump or a patch pump according to needs. The volume of the insulin pump is about half of that of an ordinary mobile phone, and the patch pump is close to the size of a piece of paper.

[0049] The control parameter adjustment ratio may be a ratio for adjusting the initial control parameters of the artificial pancreas, which is calculated by collecting the body data of the target object.

[0050] Specifically, according to the blood sugar control needs of the target object, the artificial pancreas control system that matches the target object is started, and the initial control parameters of the artificial pancreas are set in the artificial pancreas control system, that is, the standard basal rate basal, the total daily insulin dose TDD, the insulin sensitivity coefficient isf, the carbohydrate coefficient icr, and the target blood sugar value Gt. After the artificial pancreas control system obtains the initial control parameters of the artificial pancreas, it obtains blood sugar information from the target object according to the preset actual time period of blood sugar monitoring and the blood sugar information detection cycle. The parameter self-learning module learns each blood sugar information of the target object to obtain the blood sugar metabolism law of the target object. In combination with the initial control parameters of the artificial pancreas and the blood sugar metabolism law of the target object, the parameter self-learning module can determine the control parameter adjustment ratio according to the control parameter adjustment ratio calculation formula. Among them, the control parameter adjustment ratio calculation formula is as follows:

[0051]

[0052] Among them, weighted_delta (mg / dL) is the blood sugar correction information, and the blood sugar correction information includes: overall blood sugar correction information and partial blood sugar correction information; x is the blood sugar information detection period.

[0053] The parameter self-learning module is also used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object.

[0054] The artificial pancreas adjustment control parameter may be a parameter used to control the artificial pancreas after being adjusted by a control parameter adjustment ratio.

[0055] Specifically, the initial control parameters of the artificial pancreas are adjusted according to the control parameter adjustment ratio, and the artificial pancreas adjustment control parameters of the target object can be obtained. Among them, for the adjusted standard basal rate basal, the adjustment formula is: the adjusted standard basal rate basal = the standard basal rate basal before adjustment × ratio; for the adjusted total daily insulin dose TDD, the adjustment formula is: the adjusted total daily insulin dose TDD = the total daily insulin dose TDD before adjustment × ratio; for the adjusted insulin sensitivity coefficient isf, the adjustment formula is: the adjusted insulin sensitivity coefficient isf = the insulin sensitivity coefficient isf / ratio before adjustment; for the adjusted carbohydrate coefficient icr, the adjustment formula is: the adjusted carbohydrate coefficient icr = the carbohydrate coefficient icr / ratio before adjustment.

[0056] The blood sugar control module is used to input the artificial pancreas adjustment control parameters into the artificial pancreas control unit to obtain the blood sugar value control parameters.

[0057] The artificial pancreas control unit may be a calculation unit for the amount of insulin infusion in the blood sugar control module.

[0058] The blood sugar level control parameters may be parameters of blood sugar changes and parameters of insulin infusion, including: blood sugar adjustment information, blood sugar level change information, daily insulin infusion limit information, and daily insulin infusion limit information.

[0059] Specifically, the adjusted standard basal rate basal, the adjusted total daily insulin dose TDD, the adjusted insulin sensitivity coefficient isf and the adjusted carbohydrate coefficient icr are input into the artificial pancreas control unit of the blood sugar control module, and the blood sugar adjustment information and blood sugar value change information are calculated by the insulin blood sugar dynamic model in the artificial pancreas control unit, and the daily insulin infusion limit information is calculated by the daily insulin infusion limit model in the artificial pancreas control unit, and the sub-insulin infusion limit information is calculated by the sub-insulin infusion limit model in the artificial pancreas control unit. The above-mentioned blood sugar adjustment information, blood sugar value change information, daily insulin infusion limit information and sub-insulin infusion limit information are the blood sugar value control parameters.

[0060] The blood sugar control module is also used to input the blood sugar value control parameters into the blood sugar control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object.

[0061] The blood sugar control safety constraint unit may be an algorithm for further constraining blood sugar value control parameters to achieve an insulin infusion amount that meets the actual situation of the target subject.

[0062] The current insulin infusion amount may be the insulin dosage infused into the target subject according to the current condition.

[0063] Specifically, the blood sugar adjustment information, the blood sugar level change information, the daily insulin infusion limit information and the sub-insulin infusion limit information are input into the blood sugar control safety constraint unit in the blood sugar control module, and the blood sugar adjustment information and the blood sugar level change information are used to calculate and obtain multiple safe insulin infusion amounts. Since not all of the multiple safe insulin infusion amounts are appropriate infusion amounts for the current actual situation of each target object, the multiple safe insulin infusion amounts are screened by the daily insulin infusion limit information and the sub-insulin infusion limit information, and the safe insulin infusion amount suitable for the current situation of the target object is determined as the current insulin infusion amount.

[0064] In the above-mentioned artificial pancreas control system, the initial control parameters of the artificial pancreas of the target object are adjusted by using the control parameter adjustment ratio, which is conducive to using more accurate artificial pancreas adjustment control parameters as input to provide to the blood glucose control module for calculation; further, on the basis of the artificial pancreas adjustment control parameters, the artificial pancreas control unit in the blood glucose control module can be used to obtain accurate blood glucose value control parameters. Since the actual situation of the target object needs to be constrained, a blood glucose control safety constraint unit is introduced to adjust the blood glucose value control parameters to obtain the current insulin infusion amount. The insulin infusion amount can be adjusted according to the intra-individual / inter-individual differences in the blood glucose metabolism process, which is conducive to reducing the deviation of the target object's insulin infusion amount.

[0065] In one embodiment, the parameter self-learning module is further used to determine the initial insulin supplement requirement and the initial insulin basal infusion amount of the target subject according to the initial control parameters of the artificial pancreas.

[0066] The initial insulin supplementation requirement may be the amount of insulin required to be supplemented for the target object obtained by calculating the initial control parameters of the artificial pancreas.

[0067] The initial basal insulin infusion volume may be the actual amount of insulin that needs to be injected into the target object, obtained by calculating the initial control parameters of the artificial pancreas.

[0068] Specifically, the initial insulin supplement requirement of the target object is calculated based on the preset actual blood glucose monitoring time period corresponding to the blood glucose information obtained from the target object and the initial insulin sensitivity information in the initial control parameters of the artificial pancreas; and the initial insulin basal infusion volume of the target object is calculated based on the preset blood glucose monitoring time interval corresponding to the blood glucose information obtained from the target object and the initial insulin basal injection volume information in the initial control parameters of the artificial pancreas.

[0069] The parameter self-learning module is also used to determine the control parameter adjustment ratio according to the initial insulin supplementation requirement and the initial insulin basal infusion amount.

[0070] Specifically, the initial insulin supplementation requirement and the initial insulin basal infusion amount are substituted into the control parameter adjustment ratio calculation formula, and then the control parameter adjustment ratio of the target object can be calculated. The control parameter adjustment ratio calculation formula is as follows:

[0071]

[0072] Among them, weighted_delta is the blood sugar correction information, and the blood sugar correction information includes: overall blood sugar correction information and partial blood sugar correction information; x is the blood sugar information detection period.

[0073] In this embodiment, by using the initial insulin supplement requirement and the initial insulin basal infusion volume determined by the initial control parameters of the artificial pancreas to calculate the control parameter adjustment ratio, the initial control parameters of the artificial pancreas can be adjusted in combination with the actual blood sugar information detection results to improve the fit of the control parameters input into the blood sugar control module.

[0074] In one embodiment, the initial control parameters of the artificial pancreas include initial insulin sensitivity information and initial insulin basal injection volume information;

[0075] The parameter self-learning module is also used to determine the initial insulin supplement requirement based on the actual blood sugar monitoring time period of the target subject and the initial insulin sensitivity information.

[0076] The initial insulin sensitivity information may be the insulin sensitivity coefficient isf before adjustment.

[0077] Specifically, the artificial pancreas control system obtains the blood glucose value Gc from the target object at the blood glucose monitoring time interval and sends it to the parameter self-learning module. Based on the sending of the blood glucose value Gc, the parameter self-learning module is triggered to calculate the blood glucose correction delta (mg / dL) at this moment according to the user's historical blood glucose data and insulin injection data by the built-in glucose-insulin metabolism physiological model of the parameter self-learning module. The blood glucose correction information weighted_delta can be calculated using multiple blood glucose correction amounts delta; the blood glucose correction information weighted_delta is divided by the initial insulin sensitivity information to obtain the initial insulin basal infusion amount, and the calculation formula is: initial insulin supplement requirement = weighted_delta / isf.

[0078] The parameter self-learning module is also used to determine the initial insulin basal infusion volume according to the blood glucose monitoring time interval of the target object and the initial insulin basal injection volume information.

[0079] The initial basal insulin injection amount information may be the standard basal rate basal before adjustment.

[0080] Specifically, according to the blood sugar monitoring time interval of the target object, the number of times the blood sugar information of the target object is collected per hour is determined, and the initial insulin basal injection amount information is further divided by the number of times the blood sugar information is collected to obtain the initial insulin basal infusion amount.

[0081] In this embodiment, by utilizing the collection results of blood glucose information and the initial control parameters of the artificial pancreas, the initial insulin supplement requirement and the initial insulin basal infusion amount are determined respectively. The blood glucose metabolism law of the target object can be taken into account in the calculation of the control parameter adjustment ratio, thereby improving the credibility of the control parameter adjustment ratio.

[0082] In one embodiment, the parameter self-learning module is further used to obtain the overall blood glucose correction information of the target object according to the blood glucose monitoring time period threshold when the actual blood glucose monitoring time period is greater than the blood glucose monitoring time period threshold of the target object.

[0083] The blood glucose monitoring time period threshold may be the longest time period for blood glucose monitoring, for example, 48 hours, 72 hours, or 96 hours.

[0084] The overall blood sugar correction information may be blood sugar correction information obtained by weighting all blood sugar correction amounts of the blood sugar monitoring time period threshold.

[0085] Specifically, if the actual blood glucose monitoring time period is greater than the target subject's blood glucose monitoring time period threshold, each blood glucose correction amount delta is weighted and calculated to obtain the weighted corrected blood glucose correction amount, that is, the overall blood glucose correction information. The weighted calculation formula is:

[0086]

[0087] Where n is the number of historical blood glucose correction delta data, that is, the number of blood glucose correction delta data of the blood glucose monitoring time period threshold; delta n It is the blood sugar correction amount delta n×x minutes ago from the current time.

[0088] The parameter self-learning module is also used to determine the initial insulin supplement requirement based on the overall blood sugar correction information and the initial insulin sensitivity information.

[0089] Specifically, the overall blood sugar correction information is substituted as the blood sugar correction information weighted_delta into the calculation formula of the initial insulin supplement requirement to obtain the initial insulin supplement requirement with the blood sugar monitoring time period threshold as the collection time.

[0090] In this embodiment, when the actual blood glucose monitoring time period is greater than the blood glucose monitoring time period threshold, the blood glucose information corresponding to the blood glucose monitoring time period threshold is used to calculate the overall blood glucose correction information to further determine the initial insulin supplementation requirement. This can ensure the credibility of the control parameter adjustment ratio while avoiding excessive collection of blood glucose information, which is beneficial to improving the efficiency of the system while ensuring the accuracy of the artificial pancreas control system.

[0091] In one embodiment, the parameter self-learning module is further used to obtain partial blood glucose correction information of the target object according to the actual blood glucose monitoring time period when the actual blood glucose monitoring time period is less than the blood glucose monitoring time period threshold of the target object.

[0092] Part of the blood sugar correction information may be blood sugar correction information obtained by weighting all blood sugar correction amounts in the actual blood sugar monitoring time period.

[0093] Specifically, if the actual blood glucose monitoring time period is less than the target subject's blood glucose monitoring time period threshold, each blood glucose correction amount delta is weighted and calculated to obtain a weighted corrected blood glucose correction amount, that is, partial blood glucose correction information. The weighted calculation formula is also:

[0094]

[0095] Among them, n is the number of historical blood sugar correction delta data, that is, the historical blood sugar correction delta data is less than the blood sugar monitoring time period threshold, that is, n is the actual number of blood sugar correction delta data, delta n It is the blood sugar correction amount delta n×x minutes ago from the current time.

[0096] The parameter self-learning module is also used to determine the initial insulin supplement requirement based on part of the blood sugar correction information and the initial insulin sensitivity information.

[0097] Specifically, part of the blood sugar correction information is substituted as the blood sugar correction information weighted_delta into the calculation formula of the initial insulin supplement requirement to obtain the initial insulin supplement requirement with the blood sugar monitoring time period threshold as the collection time.

[0098] Furthermore, if the actual blood glucose monitoring time period is less than the target subject's blood glucose monitoring time period threshold, and the actual duration of the historical blood glucose correction delta data is the actual blood glucose monitoring time period real_duration (h), the credibility of the control parameter adjustment ratio will be reduced, and the control parameter adjustment ratio will be recalculated according to the following formula:

[0099]

[0100] Among them, max_basal is the maximum value of the initial insulin basal injection amount information.

[0101] In this embodiment, when the actual blood glucose monitoring time period is less than the blood glucose monitoring time period threshold, the blood glucose information in the actual blood glucose monitoring time period is used to calculate the overall blood glucose correction information to further determine the initial insulin supplementation requirement. This allows the correction amount to be introduced in the subsequent calculation of the control parameter adjustment ratio to ensure the credibility of the control parameter adjustment ratio.

[0102] In one embodiment, the artificial pancreas control unit includes an insulin blood sugar dynamic model, a daily insulin infusion volume limitation model, and a sub-insulin infusion volume limitation model;

[0103] The blood sugar control module is also used to input the total daily insulin dose of the artificial pancreas adjustment control parameters into the insulin blood sugar dynamic model to obtain the blood sugar adjustment information and blood sugar value change information of the target object.

[0104] Among them, the insulin blood sugar dynamic model can be constructed based on a model predictive control algorithm and is used to calculate blood sugar change information and blood sugar adjustment information.

[0105] The blood sugar adjustment information may be a deviation between a measured blood sugar value and a target blood sugar value of the artificial pancreas control system.

[0106] The blood sugar level change information may be the blood sugar rate at a certain moment.

[0107] Specifically, the total daily insulin dose of the artificial pancreas adjustment control parameters is input into the insulin blood glucose dynamic model, and the blood glucose adjustment information and blood glucose value change information of the target object are obtained through dynamic calculation of the insulin blood glucose dynamic model.

[0108] Among them, the insulin blood sugar dynamic model can be expressed by the following equations:

[0109] x i+1 =Ax i +Bu i ,y i =C y x i , v i =C v x i

[0110]

[0111]

[0112] C y =[0 0 1]

[0113] C v =[0.1 0-0.1]

[0114] Among them, x i is the model state at time i. i is the deviation between the insulin dose infused by the algorithm at time i and the basal rate. If the basal insulin rate is basal i , the insulin dose output by the algorithm is u in，i , then u i =u in，i -basal i .y iis the deviation between the blood glucose value measured by the artificial pancreas control system at time i and the target blood glucose value. If the blood glucose value measured by the artificial pancreas control system is y BG，i , the target blood sugar value is y s , then y i =y BG，i -y s .v i is the blood glucose rate at time i. A, C y , C v is a given constant coefficient matrix, K1, K2, K3 are given proportional coefficients. Total daily insulin dose TDD i is the user parameter adjusted in real time and adaptively, K1 is the proportional coefficient, then the coefficient matrix B can be adjusted in real time with the user's TDD. The control performed by the MPC algorithm based on this insulin blood sugar dynamic model can better adapt to the changes in the user parameter TDD.

[0115] The blood sugar control module is also used to input the basic information of adjusting insulin standards for adjusting the control parameters of the artificial pancreas into the daily insulin infusion amount limitation model to obtain the daily insulin infusion limitation information of the target object.

[0116] The daily insulin infusion amount restriction model may be a constraint model for the infusion amount of insulin infused into the body of the target subject every day.

[0117] The daily insulin infusion restriction information may be a lower limit value and an upper limit value of the infusion amount of insulin infused into the body of the target subject every day.

[0118] Specifically, the basic information of adjusting insulin standards of the artificial pancreas adjustment control parameters is input into the daily insulin infusion amount restriction model, and the daily insulin infusion amount restriction information of the target object is obtained through the constraint calculation of the daily insulin infusion amount restriction model.

[0119] Among them, the daily insulin infusion limitation model can be expressed by the following equations:

[0120]

[0121]

[0122] Among them, the basal insulin rate i is the user parameter for real-time adaptive adjustment, K2 is the proportional coefficient. i is the time change within 1440 minutes a day, that is, 0≤i≤1440min. This formula calculates the upper and lower limits of insulin dosage at time i and adjusts it according to the basal rate adjusted by the user's adaptive adjustment.

[0123] The blood sugar control module is also used to input the insulin sensitivity adjustment information of the artificial pancreas adjustment control parameters into the sub-insulin infusion amount limitation model to obtain the sub-insulin infusion limitation information of the target object.

[0124] The insulin infusion amount restriction model may be a constraint model for the amount of insulin infused into the body of the target subject each time.

[0125] The insulin infusion limit information may be an upper limit of the amount of insulin infused into the body of the target subject each time.

[0126] Specifically, the basic information of adjusting insulin standards of the artificial pancreas adjustment control parameters is input into the sub-insulin infusion amount limitation model, and the sub-insulin infusion limitation information of the target object is obtained through constraint calculation of the sub-insulin infusion amount limitation model.

[0127] Among them, the subinsulin infusion volume limitation model can be expressed by the following equations:

[0128]

[0129]

[0130] Ω i =(y BG，i -y s ) / isf i

[0131] Among them, Ω i represents the insulin dose required to restore the blood sugar level to the target blood sugar level at time i, Φ i It represents the remaining active insulin IOB calculated according to the remaining active insulin decay curve at time i, Indicates the upper limit of IOB at time i. This upper limit is mainly set to prevent excessive insulin dose infusion, such as preventing excessive insulin dose infusion after pre-meal insulin infusion. Insulin sensitivity coefficient isf i This is a user parameter that is adjusted in real time. This limit is the same as the upper limit in the daily insulin infusion limit information. The minimum value is taken as the upper limit of the final insulin infusion.

[0132] Among them, after receiving the artificial pancreas adjustment control parameters of the target object adaptively adjusted by the parameter self-learning module, the insulin blood sugar dynamic model receives the adaptively adjusted basal, TDD, and isf at each moment and adjusts in real time.

[0133] The blood sugar control module is also used to obtain blood sugar value control parameters according to the blood sugar adjustment information, blood sugar value change information, daily insulin infusion limit information and sub-insulin infusion limit information.

[0134] Specifically, the blood sugar adjustment information, the blood sugar level change information, the daily insulin infusion limit information and the sub-insulin infusion limit information are integrated to obtain the blood sugar level control parameters.

[0135] In this embodiment, by utilizing the insulin blood sugar dynamic model, daily insulin infusion limit model and sub-insulin infusion limit model in the artificial pancreas control unit to calculate the blood sugar value control parameters, the upper and lower limits can be set by considering the current blood sugar condition and insulin infusion condition of the target object, thereby ensuring that blood sugar is controlled and insulin is infused within a reasonable range according to the current specific condition of the target object, thereby improving the blood sugar control effect.

[0136] In one embodiment, the blood glucose control module is further used to input the blood glucose adjustment information and the blood glucose value change information into the blood glucose control safety constraint unit to obtain at least one safe insulin infusion amount.

[0137] The safe insulin infusion amount may be a safe and reasonable insulin dose for the target subject, but it is not the optimal insulin infusion dose.

[0138] Specifically, the blood sugar adjustment information and the blood sugar level change information are input into the blood sugar control safety constraint unit to obtain at least one safe insulin infusion amount that meets the target object. The loss function of the blood sugar control safety constraint unit is the following formula:

[0139]

[0140] in, Indicates the distance between the predicted blood sugar value and the ideal blood sugar area when the blood sugar level is lower than the ideal blood sugar area. Indicates the distance between the predicted blood sugar value and the ideal blood sugar area when the blood sugar level is higher than the ideal blood sugar area. represents the blood sugar rate when blood sugar rises, Q(v) represents the penalty coefficient that changes with the blood sugar rate, For punishment The coefficient of . and is the asymmetric penalty coefficient, used to penalize asymmetric insulin dosage and in Indicates the insulin dose when blood sugar rises. Indicates the insulin dose when blood sugar drops. The method for real-time adjustment of the penalty coefficient by the blood sugar control safety constraint module is:

[0141] Safety zone 1: If the blood glucose concentration G i ≤ the first preset threshold, and the blood glucose rate v i≤0. This situation indicates that blood sugar is decreasing and there is a risk of hypoglycemia, so a "conservative" blood sugar control strategy is needed. The controller of the insulin blood sugar dynamic model reduces the insulin dose to prevent hypoglycemia. The penalty coefficient

[0142]

[0143] Safety zone 2: If the first preset threshold ≤ blood glucose concentration G i ≤ the second preset threshold, and the blood glucose rate v i > 0. This situation indicates that blood sugar is in the ideal range and blood sugar is rising, and blood sugar control is in a "normal" state. The controller of the insulin blood sugar dynamic model infuses a normal dose of insulin, and the penalty coefficient

[0144]

[0145] Safety zone 3: If the second preset threshold ≤ blood glucose concentration G i ≤ the third preset threshold, and the blood glucose rate v i > 0. This situation indicates that blood sugar is rising and there is a risk of hyperglycemia, and an "aggressive" blood sugar control strategy is needed. The controller of the insulin blood sugar dynamic model increases the insulin dose, and the penalty coefficient

[0146]

[0147] Safety zone 4: If the blood glucose concentration G i > the third preset threshold, and the blood glucose rate v i > 0. This is when the blood glucose waveform has passed the safety zone 3. At this time, the control strategy should be restricted to prevent excessive insulin from being infused based on the insulin infused in the safety zone 3. The controller of the insulin blood glucose dynamic model adopts a "conservative" infusion strategy, and the penalty coefficient

[0148] The blood sugar control module is also used to select each safe insulin infusion amount according to the daily insulin infusion limit information and the sub-insulin infusion limit information to obtain the current insulin infusion amount.

[0149] Specifically, based on the daily insulin infusion limit information and the sub-insulin infusion limit information for the target object, a safe insulin infusion amount that satisfies both of the above-mentioned restriction information conditions is selected from each safe insulin infusion amount as the target insulin infusion amount, and further combined with the loss function value of the blood sugar control safety constraint unit, the optimal insulin infusion amount is selected from each target insulin infusion amount as the current insulin infusion amount.

[0150] In this embodiment, the various safe insulin infusion amounts of the target object are obtained by using the loss function of the blood sugar control safety constraint unit, and further screening is performed based on the insulin infusion limit information for each time and each day to ensure that the current insulin infusion amount meets the needs of the target object and that the current insulin infusion amount does not cause abnormal conditions for the target object.

[0151] In one embodiment, the blood sugar control module is further used to select insulin infusion amounts that meet the daily insulin infusion limit information and the sub-insulin infusion limit information from the safe insulin infusion amounts as the target insulin infusion amounts.

[0152] The target insulin infusion amount may be an insulin infusion amount that complies with both the daily insulin infusion restriction information and the sub-insulin infusion restriction information.

[0153] Specifically, the daily insulin infusion limit information and the sub-insulin infusion limit information are used as constraints, and under the combined effect of the daily insulin infusion limit information and the sub-insulin infusion limit information, each insulin infusion amount that meets the lower limit of the daily insulin infusion limit information is obtained.

[0154] Similarly, taking the daily insulin infusion limit information and the sub-insulin infusion limit information as constraints, under the joint effect of the daily insulin infusion limit information and the sub-insulin infusion limit information, the various insulin infusion amounts contained in the minimum value of the upper limits of the daily insulin infusion limit information and the sub-insulin infusion limit information are obtained.

[0155] Take the intersection of each insulin infusion amount that meets the lower limit of the daily insulin infusion limit information and the minimum value of the upper limit of the daily insulin infusion limit information and the sub-insulin infusion limit information as each target insulin infusion amount

[0156] The blood sugar control module is also used to select the insulin infusion amount with the smallest blood sugar control safety constraint loss value from each target insulin infusion amount as the current insulin infusion amount; each target insulin infusion amount has a mapping relationship with each blood sugar control safety constraint loss value.

[0157] The blood sugar control safety constraint loss value may be a constraint loss value calculated by a loss function of a blood sugar control safety constraint unit.

[0158] Specifically, since each target insulin infusion amount has a corresponding blood sugar control safety constraint loss value, among the target insulin infusion amounts that have been screened by the daily insulin infusion limit information and the sub-insulin infusion limit information, the target insulin infusion amount with the smallest blood sugar control safety constraint loss value is selected as the current insulin infusion amount required by the target object under the current situation. Finally, the corresponding dose of insulin is infused into the target object according to the current insulin infusion amount using the infusion module. During the use of the artificial pancreas control system, in addition to infusing insulin into the target object when the blood sugar level of the target object is higher than the normal value, the basal rate at the current moment can also be lowered or suspended when the blood sugar level of the target object is lower than the normal value, and an alarm will be sounded in critical situations.

[0159] In this embodiment, by selecting the safe insulin infusion amount corresponding to the minimum loss value in the blood sugar control safety constraint loss value among the insulin infusion amounts that meet the daily insulin infusion limit information and the sub-insulin infusion limit information as the current insulin infusion amount, the optimal solution can be selected from various safe insulin infusion amounts that meet the target object, thereby improving the calculation accuracy of the current insulin infusion amount and reducing the target object's insulin usage to reduce the risks of hyperglycemia and hypoglycemia.

[0160] In one embodiment, the system further comprises: a specific dose infusion module;

[0161] The specific dose infusion module is used to determine the food large dose insulin infusion amount of the target object according to the artificial pancreas adjustment control parameters and the carbohydrate intake of the target object.

[0162] The carbohydrate intake may be the amount of carbohydrates ingested by the target subject during a meal, and is generally indicated by CHO (g).

[0163] The large dose of insulin infusion for food may be the large dose of insulin required to be infused after eating carbohydrates.

[0164] Specifically, when the target subject inputs meal carbohydrate information into the artificial pancreas control system, the blood glucose control module issues an instruction to control the specific dose infusion module to perform a large dose infusion. Therefore, the carbohydrate intake CHO is divided by the adjusted carbohydrate coefficient icr of the artificial pancreas adjustment control parameter to obtain the target subject's food large dose insulin infusion amount.

[0165] The specific dose infusion module is also used to determine the corrected large dose insulin infusion amount of the target object according to the artificial pancreas adjustment control parameters, the current blood glucose value of the target object and the target blood glucose value of the target object.

[0166] The current blood sugar value may be the blood sugar value measured by the target subject at the current moment.

[0167] The target blood glucose level may be a blood glucose level that the target subject needs to reach.

[0168] The correction large-dose insulin infusion amount may be an infusion amount for correcting the large-dose insulin infusion required after eating carbohydrates.

[0169] Specifically, the difference between the current blood sugar value of the target object and the target blood sugar value of the target object is used as the numerator, and the adjusted insulin sensitivity coefficient isf in the artificial pancreas adjustment control parameter is used as the denominator to obtain the corrected large-dose insulin infusion amount of the target object.

[0170] The specific dose infusion module is further used to determine the bolus insulin infusion amount of the target object according to the food bolus insulin infusion amount and the correction bolus insulin infusion amount.

[0171] The bolus insulin infusion amount may be the insulin infusion amount calculated by a standard bolus calculator instead of a blood sugar control module after the target subject eats carbohydrates.

[0172] Specifically, the food bolus insulin infusion amount is corrected using the correction bolus insulin infusion amount to obtain the bolus insulin infusion amount of the target object. The expression of the bolus insulin infusion amount is as follows:

[0173]

[0174] Among them, CHO is carbohydrate intake, y BG is the current blood sugar value, y s is the target blood sugar value, icr is the adjusted carbohydrate factor, and isf is the adjusted insulin sensitivity factor. Among them, the adjusted standard basal rate basal is still controlled by the blood sugar control module.

[0175] In this embodiment, by adopting a large dose of insulin infusion when the target subject ingests carbohydrates, the insulin can be changed according to the special situation of the target subject, thereby improving the safety of the target subject.

[0176] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0177] Based on the same inventive concept, the embodiment of the present application also provides an artificial pancreas control method for realizing the artificial pancreas control system involved above. The implementation scheme for solving the problem provided by the method is similar to the implementation scheme recorded in the above system, so the specific limitations of one or more artificial pancreas control method embodiments provided below can refer to the limitations of the artificial pancreas control system above, and will not be repeated here.

[0178] In one embodiment, Figure 2 As shown, an artificial pancreas control method is provided, comprising:

[0179] Step 202, determining a control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas of the target object according to the initial control parameters of the artificial pancreas;

[0180] Step 204, adjusting the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0181] Step 206, inputting the artificial pancreas adjustment control parameter into the artificial pancreas control unit to obtain the blood sugar value control parameter;

[0182] Step 208: input the blood glucose control parameter into the blood glucose control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object.

[0183] Based on the same inventive concept, the embodiment of the present application also provides an artificial pancreas control device for realizing the artificial pancreas control system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above system, so the specific limitations of one or more artificial pancreas control device embodiments provided below can refer to the limitations of the artificial pancreas control system above, and will not be repeated here.

[0184] In one embodiment, Figure 3As shown, an artificial pancreas control device is provided, comprising: a control parameter acquisition end, a controller and an infusion end;

[0185] A control parameter acquisition terminal is used to acquire initial control parameters of the artificial pancreas of the target object;

[0186] A controller, for determining a control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas according to the initial control parameters of the artificial pancreas of the target object;

[0187] The controller is further used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object;

[0188] The controller is also used to input the artificial pancreas adjustment control parameters into the artificial pancreas control unit to obtain the blood sugar value control parameters;

[0189] The controller is further used to input the blood glucose value control parameter into the blood glucose control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object;

[0190] The infusion end is used to infuse insulin into the target object according to the current insulin infusion amount.

[0191] Each module in the above-mentioned artificial pancreas control device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0192] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an artificial pancreas control method is implemented.

[0193] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0194] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0195] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0196] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0197] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0198] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0199] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0200] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An artificial pancreas control system, characterized in that: The system comprises: a parameter self-learning module and a blood sugar control module; The parameter self-learning module is used to determine the control parameter adjustment ratio corresponding to the initial control parameters of the artificial pancreas according to the initial control parameters of the artificial pancreas of the target object; The parameter self-learning module is further used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object; The blood sugar control module is used to input the artificial pancreas adjustment control parameter into the artificial pancreas control unit to obtain the blood sugar value control parameter; The blood sugar control module is further used to input the blood sugar value control parameter into the blood sugar control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object.

2. The system according to claim 1, characterized in that The parameter self-learning module is further used to determine the initial insulin supplement requirement and the initial insulin basal infusion amount of the target subject according to the initial control parameters of the artificial pancreas; The parameter self-learning module is also used to determine the control parameter adjustment ratio according to the initial insulin supplementation requirement and the initial insulin basal infusion amount.

3. The system according to claim 2, characterized in that The initial control parameters of the artificial pancreas include initial insulin sensitivity information and initial insulin basal injection volume information; The parameter self-learning module is further used to determine the initial insulin supplementation requirement according to the actual blood sugar monitoring time period of the target subject and the initial insulin sensitivity information; The parameter self-learning module is also used to determine the initial insulin basal infusion amount according to the blood glucose monitoring time interval of the target object and the initial insulin basal injection amount information.

4. The system according to claim 3, characterized in that The parameter self-learning module is further used to obtain the overall blood glucose correction information of the target object according to the blood glucose monitoring time period threshold when the actual blood glucose monitoring time period is greater than the blood glucose monitoring time period threshold of the target object; The parameter self-learning module is further used to determine the initial insulin supplement requirement according to the overall blood sugar correction information and the initial insulin sensitivity information.

5. The system according to claim 3, characterized in that The parameter self-learning module is further used to obtain partial blood sugar correction information of the target object according to the actual blood sugar monitoring time period when the actual blood sugar monitoring time period is less than the blood sugar monitoring time period threshold of the target object; The parameter self-learning module is further used to determine the initial insulin supplement requirement according to the partial blood sugar correction information and the initial insulin sensitivity information.

6. The system according to claim 1, characterized in that The artificial pancreas control unit includes an insulin blood sugar dynamic model, a daily insulin infusion volume limitation model, and a sub-insulin infusion volume limitation model; The blood sugar control module is further used to input the total daily insulin dose of the artificial pancreas adjustment control parameter into the insulin blood sugar dynamic model to obtain the blood sugar adjustment information and blood sugar value change information of the target object; The blood sugar control module is further used to input the standard basic information of adjusting insulin for adjusting the control parameters of the artificial pancreas into the daily insulin infusion amount restriction model to obtain the daily insulin infusion restriction information of the target object; The blood sugar control module is further used to input the insulin sensitivity adjustment information of the artificial pancreas adjustment control parameters into the sub-insulin infusion amount limitation model to obtain the sub-insulin infusion limitation information of the target object; The blood sugar control module is further used to obtain the blood sugar value control parameter according to the blood sugar adjustment information, the blood sugar value change information, the daily insulin infusion limit information and the sub-insulin infusion limit information.

7. The system according to claim 6, characterized in that The blood sugar control module is further used to input the blood sugar adjustment information and the blood sugar value change information into the blood sugar control safety constraint unit to obtain at least one safe insulin infusion amount; The blood sugar control module is further used to select each of the safe insulin infusion amounts according to the daily insulin infusion limit information and the sub-insulin infusion limit information to obtain the current insulin infusion amount.

8. The system according to claim 7, characterized in that The blood sugar control module is further used to select the insulin infusion amount that meets the daily insulin infusion limit information and the sub-insulin infusion limit information from the safe insulin infusion amounts as the target insulin infusion amounts; The blood sugar control module is also used to select the insulin infusion amount with the smallest blood sugar control safety constraint loss value from each target insulin infusion amount as the current insulin infusion amount; each target insulin infusion amount and each blood sugar control safety constraint loss value have a mapping relationship.

9. The system according to claim 1, characterized in that The system further comprises: a specific dose infusion module; The specific dose infusion module is used to determine the food large dose insulin infusion amount of the target object according to the artificial pancreas adjustment control parameters and the carbohydrate intake of the target object; The specific dose infusion module is further used to determine the corrected large dose insulin infusion amount of the target subject according to the artificial pancreas adjustment control parameter, the current blood glucose value of the target subject and the target blood glucose value of the target subject; The specific dose infusion module is further used to determine the large dose insulin infusion amount of the target object according to the large dose insulin infusion amount for food and the correction large dose insulin infusion amount.

10. An artificial pancreas control device, characterized in that: The device comprises: a control parameter acquisition end, a controller and an infusion end; The control parameter acquisition end is used to acquire the initial control parameters of the artificial pancreas of the target object; The controller is used to determine the control parameter adjustment ratio corresponding to the initial control parameter of the artificial pancreas according to the initial control parameter of the artificial pancreas of the target object; The controller is further used to adjust the initial control parameters of the artificial pancreas according to the control parameter adjustment ratio to obtain the artificial pancreas adjustment control parameters of the target object; The controller is further used to input the artificial pancreas adjustment control parameter into the artificial pancreas control unit to obtain the blood sugar value control parameter; The controller is further used to input the blood sugar value control parameter into the blood sugar control safety constraint unit to obtain the current insulin infusion amount corresponding to the target object; The infusion end is used to infuse insulin into the target object according to the current insulin infusion amount.

Images