Insulin infusion device, insulin infusion system, and storage medium

Abstract

The invention relates to an insulin infusion device, an insulin infusion system and a storage medium. The device comprises a memory and a processor, a computer program is stored in the memory, the processor executes the steps of the insulin infusion control method when executing the computer program, and the method comprises the steps that real-time monitoring blood glucose data and historical blood glucose data of a user are obtained; calling an initial insulin infusion model pre-stored in the insulin infusion equipment; adjusting preset parameters of the initial insulin infusion model according to the historical blood glucose data to obtain an insulin infusion model; according to the real-time monitoring blood glucose data and the insulin infusion model, the insulin dosage is determined. The preset parameters in the insulin infusion model are adaptively adjusted, so that the adjusted insulin infusion model is more matched with the individual blood glucose change level of the user, the accuracy of the insulin dosage is improved, a more matched and accurate insulin infusion scheme is provided for different users, and the blood glucose control effect of the different users is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical treatment, and in particular, to an insulin infusion device, an insulin infusion system and a storage medium. BACKGROUND

[0002] The pancreas of a normal person can automatically secrete the required insulin / glucagon according to the glucose level in the blood, so as to maintain a reasonable blood glucose fluctuation range. The pancreas of a diabetic patient is abnormal and cannot normally secrete the required insulin of the human body. Diabetes is a metabolic disease and a lifelong disease. Current medical technology cannot cure diabetes, and can only control the occurrence and development of diabetes and its complications by infusing insulin in vitro to stabilize the blood glucose level in the body. With the development of blood glucose monitoring technology, a more accurate insulin infusion scheme can be achieved. The blood glucose monitoring device developed based on continuous glucose monitoring (CGM) monitors the blood glucose level in the body of a patient in real time. According to the blood glucose value detected by the blood glucose monitoring device, the required insulin is infused by the insulin infusion device, thereby constituting a closed-loop or semi-closed-loop insulin infusion management.

[0003] At present, in order to achieve closed-loop or semi-closed-loop control of insulin infusion, insulin activity-time models and carbohydrate absorption models are widely studied. Through these two key models, the prediction and effective control of blood glucose can be achieved. However, when the traditional insulin activity-time model and the carbohydrate absorption model are used to control the blood glucose of individuals, the accuracy of blood glucose control for different individuals is not high due to the existence of individual differences. Therefore, how to accurately determine the insulin infusion scheme of an individual has become a technical problem to be solved. SUMMARY

[0004] Therefore, it is necessary to provide an insulin infusion device, an insulin infusion system, a computer readable storage medium and a computer program product capable of determining a matching insulin infusion scheme for different individuals, so as to improve the accuracy of individual blood glucose control.

[0005] In a first aspect, the present application provides an insulin infusion device, comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to execute the steps of an insulin infusion control method, the method comprising:

[0006] obtaining real-time monitoring blood glucose data and historical blood glucose data of a user;

[0007] calling an initial insulin infusion model pre-stored in the insulin infusion device;

[0008] adjusting preset parameters of an initial insulin infusion model according to historical blood glucose data to obtain the insulin infusion model;

[0009] determining an insulin dose according to the real-time monitored blood glucose data and the insulin infusion model.

[0010] In one of the embodiments, the historical blood glucose data includes actual monitored blood glucose data of a historical period, and adjusting preset parameters of an initial insulin infusion model according to historical blood glucose data to obtain the insulin infusion model includes:

[0011] obtaining theoretical blood glucose data of the user in the historical period according to the historical blood glucose data;

[0012] performing blood glucose peak analysis on the historical blood glucose data according to preset blood glucose peak rules to determine actual blood glucose peak time of the historical period;

[0013] performing blood glucose peak analysis on the theoretical blood glucose data according to preset blood glucose peak rules to determine theoretical blood glucose peak time of the historical period;

[0014] adjusting preset parameters in the initial insulin infusion model according to the actual blood glucose peak time and the theoretical blood glucose peak time to obtain the insulin infusion model.

[0015] In one of the embodiments, the initial insulin infusion model includes an initial insulin activity sub-model and an initial carbohydrate absorption sub-model, and the preset parameters include a time length for insulin activity to reach a peak value and a time length for carbohydrate absorption speed to reach a peak value; adjusting preset parameters in the initial insulin infusion model according to the actual blood glucose peak time and the theoretical blood glucose peak time to obtain the insulin infusion model includes:

[0016] when it is monitored that a time deviation between the actual blood glucose peak time and the theoretical blood glucose peak time is not within a preset deviation range, adjusting the time length for insulin activity to reach the peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach the peak value in the initial carbohydrate absorption sub-model according to the time deviation to determine the insulin infusion model;

[0017] or, when it is monitored that the time deviation is within the preset deviation range, determining the insulin infusion model according to the initial insulin activity sub-model and the initial carbohydrate absorption sub-model.

[0018] In one of the embodiments, the time deviation is used to represent an early or late relationship between the theoretical blood glucose peak time and the actual blood glucose peak time, and adjusting the time length for insulin activity to reach the peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach the peak value in the initial carbohydrate absorption sub-model according to the time deviation includes:

[0019] The monitoring determines that the time deviation indicates that the theoretical blood glucose peak time is later than the actual blood glucose peak time, reduces the time length for the insulin activity in the initial insulin activity sub-model to reach a peak, and reduces the time length for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak.

[0020] Alternatively, the monitoring determines that the time deviation indicates that the theoretical blood glucose peak time is earlier than the actual blood glucose peak time, increases the time length for the insulin activity in the initial insulin activity sub-model to reach a peak, and increases the time length for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak.

[0021] In one of the embodiments, the method further includes:

[0022] Based on the time deviation and a preset adjustment coefficient, a target adjustment value is determined.

[0023] The reducing the time length for the insulin activity in the initial insulin activity sub-model to reach a peak and the reducing the time length for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak include:

[0024] According to the target adjustment value, the time length for the insulin activity in the initial insulin activity sub-model to reach a peak is reduced, and according to the target adjustment value, the time length for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak is reduced.

[0025] The increasing the time length for the insulin activity in the initial insulin activity sub-model to reach a peak and the increasing the time length for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak include:

[0026] According to the target adjustment value, the time length for the insulin activity in the initial insulin activity sub-model to reach a peak is increased, and according to the target adjustment value, the time length for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak is increased.

[0027] In one of the embodiments, the theoretical blood glucose data of the user in the historical period is obtained according to historical blood glucose data, including:

[0028] In response to a carbohydrate intake event triggered by the user in the historical period, an initial blood glucose value at an initial time corresponding to the carbohydrate intake event is obtained.

[0029] According to the initial blood glucose value and an initial insulin infusion model, the theoretical blood glucose data of the user is determined.

[0030] In one of the embodiments, the method further includes:

[0031] The monitoring determines that the time deviation indicates that the theoretical blood glucose peak time is later than the actual blood glucose peak time, reduces the time length for the insulin activity in the initial insulin activity sub-model to reach a peak, and reduces the time length for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak.

[0032] re-determine the theoretical blood glucose data of the user for the remaining period according to the intermediate blood glucose value and the initial insulin infusion model; the remaining period comprises a time period between the carbohydrate intake event and the insulin injection event in the history period.

[0033] In a second aspect, the present application further provides an insulin infusion device, comprising:

[0034] an acquisition module, configured to acquire real-time monitoring blood glucose data and historical blood glucose data of a user;

[0035] a calling module, configured to call an initial insulin infusion model pre-stored in the insulin infusion device;

[0036] an adjusting module, configured to adjust preset parameters of the initial insulin infusion model according to the historical blood glucose data to obtain the insulin infusion model;

[0037] a first determining module, configured to determine an insulin dose according to the real-time monitoring blood glucose data and the insulin infusion model.

[0038] In a third aspect, the present application further provides an insulin infusion system, comprising a blood glucose monitoring device and the insulin infusion device in the first aspect.

[0039] the blood glucose monitoring device, configured to monitor blood glucose data of a user in real time.

[0040] In a fourth aspect, the present application further provides a computer readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the insulin infusion control method performed by the insulin infusion device in the first aspect.

[0041] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, wherein the computer program, when executed by a processor, implements the steps of the insulin infusion control method performed by the insulin infusion device in the first aspect.

[0042] The insulin infusion device, the insulin infusion system, the storage medium and the computer program product, the insulin infusion device obtains real-time monitoring blood glucose data and historical blood glucose data of a user, and calls an initial insulin infusion model pre-stored in the insulin infusion device; then, preset parameters of the initial insulin infusion model are adjusted according to the historical blood glucose data to obtain an insulin infusion model, and an insulin dose is determined according to the real-time monitoring blood glucose data and the insulin infusion model. That is, the insulin infusion device provided by the embodiment of the present application can continuously adjust and update the related preset parameters in the insulin infusion model according to the historical blood glucose data of the user, so as to obtain an insulin infusion model suitable for the user, and then determine an insulin dose corresponding to the real-time monitoring blood glucose data according to the insulin infusion model. Compared with the traditional insulin infusion device, by adaptively adjusting the related preset parameters in the insulin infusion model, the matching degree between the insulin infusion model and the user can be improved, so that the adjusted insulin infusion model is more matched with the individual blood glucose change level of the user, thereby the accuracy of the insulin dose calculated by the insulin infusion model can be improved, a more matched and accurate insulin infusion scheme is provided for different users, and finally the blood glucose control effect of different users is improved. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technical solutions, the drawings needed to be used in the embodiments or the related technical solution description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 An internal structure diagram of the insulin infusion device in an embodiment;

[0045] Figure 2 A flowchart of the insulin infusion device in an embodiment for determining an insulin dose;

[0046] Figure 3 A flowchart of the insulin infusion device in an embodiment for model adaptive adjustment;

[0047] Figure 4 A flowchart of the insulin infusion device in an embodiment for blood glucose value calculation;

[0048] Figure 5 A structural flowchart of adaptive model adjustment in an embodiment;

[0049] Figure 6 A structural block diagram of the insulin infusion device in an embodiment;

[0050] Figure 7 Structure diagram of an insulin infusion system in an embodiment. DETAILED DESCRIPTION

[0051] For the purposes of the present application, the technical solutions and advantages thereof are more clearly apparent, the following further describes the present application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0052] As a chronic disease that cannot be cured, diabetes requires long-term infusion of insulin to stabilize blood glucose levels. If the patient's blood glucose cannot be stabilized, it will lead to acute and chronic complications in diabetic patients. At present, there is no treatment method to cure diabetes in the medical field, and exogenous insulin is still an effective means to control blood glucose. In order to effectively control the blood glucose level of diabetic patients, a common method is to establish an artificial pancreas system to simulate the working principle of the pancreas, mainly combined with blood glucose monitoring equipment and insulin infusion equipment, such as insulin pens, insulin pumps and other intelligent products to achieve stable control of blood glucose. The blood glucose monitoring equipment uses dynamic glucose monitoring technology (Continuous Glucose Monitoring, CGM) to provide continuous blood glucose monitoring data for patients throughout the day, which can reflect the body's blood glucose metabolism law together with insulin infusion data, and provide big data support for individualized treatment.

[0053] Insulin and carbohydrates are the two main factors affecting blood glucose. The insulin activity-time model is based on pharmacokinetics and is used to describe the activity of insulin in the body over time; the carbohydrate absorption model can simulate the absorption process of carbohydrates in the human body. Through these two key models, blood glucose prediction and effective control can be achieved. However, due to individual differences and external environmental influences, the time it takes for insulin activity to peak and the time it takes for carbohydrate absorption speed to peak can vary significantly, and blood glucose control is usually based on fixed insulin activity curves and carbohydrate absorption curves, which cannot adapt to individual differences and real-time changes. Therefore, how to optimize the design for individual differences in the insulin action process and carbohydrate digestion process, improve the accuracy of the insulin activity-time model and the carbohydrate absorption model, and reduce insulin infusion deviation, so it is of great significance to establish a data-driven artificial pancreas closed-loop control method.

[0054] In the related art, some solutions exist to address the problem that the fixed parameters of the artificial pancreas cannot adapt to individual differences and real-time changes. For example, based on the historical blood glucose data of a patient provided by a CGM, a pharmacokinetics / pharmacodynamics (PK / PD) model is dynamically adjusted, and is used to calculate at least one adjusted parameter of an insulin delivery controller, such as a basal rate, an insulin sensitivity factor (ISF), and a carbohydrate ratio. Alternatively, a target physiological parameter is controlled by using a chemical substance, and a physiological parameter related to the target physiological parameter is adaptively adjusted.

[0055] However, the above-mentioned technology focuses on adjusting preset parameters such as a basal rate or an insulin sensitivity factor (ISF), and still has the problem that insulin infusion cannot meet individual differences.

[0056] Based on this, the embodiments of the present application propose an insulin infusion device for executing an insulin infusion control method. The method can adaptively adjust a key model based on historical blood glucose data of a patient provided by a CGM, obtain a more accurate insulin infusion scheme, and solve the problem of individual differences.

[0057] The internal structure diagram of the insulin infusion device provided by the embodiments of the present application can be as follows Figure 1The insulin infusion device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the insulin infusion device is configured to provide computing and control capabilities. The memory of the insulin infusion device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the insulin infusion device is configured to exchange information between the processor and external devices. The communication interface of the insulin infusion device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. The computer program is executed by the processor to implement an insulin infusion control method. The display unit of the insulin infusion device is configured to form a visually visible screen, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the insulin infusion device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the insulin infusion device, or an external keyboard, touchpad or mouse, etc.

[0058] Those skilled in the art can understand that, Figure 1 The skilled in the art can understand that,

[0059] Exemplarily, the insulin infusion device can be an insulin pump configured to infuse insulin into a patient according to a control instruction; or can be a comprehensive insulin infusion device, such as an artificial pancreas, which can not only continuously monitor the blood glucose level of the patient, but also infuse insulin into the patient according to a control instruction. The insulin infusion device infuses insulin in a continuous and small dose, simulating the working mode of a normal pancreas.

[0060] Exemplarily, for the insulin infusion device with wireless function, the insulin infusion device can be wirelessly connected with a blood glucose monitoring device. The blood glucose monitoring device is configured to acquire blood glucose data of the patient in real time and send the blood glucose data to the insulin infusion device. The insulin infusion device determines the insulin dose to be infused according to the acquired blood glucose data, so as to realize insulin infusion. Exemplarily, the blood glucose monitoring device can simultaneously have a data storage function, and monitor and store the blood glucose data of the patient in real time. The embodiments of the present application do not make specific limitation on this.

[0061] In one example embodiment, as shown in Figure 2 Fig. 1, an insulin infusion control method is provided, which is applied to an insulin infusion device as shown in Figure 1 Fig. 1, and includes the following steps 201-204. In which:

[0062] Step 201, obtaining real-time monitoring blood glucose data and historical blood glucose data of the user.

[0063] The real-time monitoring blood glucose data can be the blood glucose data at the current time, or the blood glucose data in the current time period; the historical blood glucose data can be the blood glucose data before the current time or the current time period, which can be the blood glucose data at the last time or the last time period connected with the current time or the current time period, or the blood glucose data at the historical time or the historical time period separated by a preset time length from the current time or the current time period, etc. The historical time period blood glucose data represents the change of the patient's blood glucose value in the past period of time.

[0064] Exemplarily, the insulin infusion device can obtain the real-time monitoring blood glucose data and the historical blood glucose data of the user from the blood glucose monitoring device.

[0065] In one implementation, the blood glucose monitoring device can be integrated in the insulin infusion device; based on this, the blood glucose monitoring device can store the monitored blood glucose data in the memory of the insulin infusion device while monitoring the blood glucose of the user in real time; the insulin infusion device can obtain the real-time monitoring blood glucose data and the corresponding historical blood glucose data of the user from the memory when infusing insulin to the user.

[0066] Step 202, calling an initial insulin infusion model pre-stored in the insulin infusion device.

[0067] Optionally, the initial insulin infusion model can be a general insulin infusion model trained or modeled based on the blood glucose data of different users stored in a preset database, or an insulin infusion model obtained by adjusting the parameters of the general insulin infusion model based on the historical blood glucose data of the user. That is, for different users, the insulin infusion device can continuously adjust and update the general insulin infusion model during continuous operation to adapt to the differences in human blood glucose of different users, and to adapt to the differences in blood glucose control of the user in different scenarios.

[0068] Exemplarily, the insulin infusion device can call a general insulin infusion model pre-stored in the insulin infusion device as an initial insulin infusion model at initial start-up, and can call an insulin infusion model obtained after previous model adjustment as an initial insulin infusion model for current model adjustment after the insulin infusion device has been in operation for a period of time.

[0069] It should be noted that the initial start-up herein can represent the first start-up for insulin infusion control after user registration. If the insulin infusion device is restarted but the logged-in user is a registered user, the insulin infusion model obtained after the last model adjustment corresponding to the user can be acquired as the initial insulin infusion model for current model adjustment.

[0070] In step 203, preset parameters of the initial insulin infusion model are adjusted according to historical blood glucose data to obtain an insulin infusion model.

[0071] The preset parameters of the initial insulin infusion model can include one or more parameters in the initial insulin infusion model, and can include parameters related to insulin and carbohydrates, etc.

[0072] Exemplarily, the insulin infusion device can determine theoretical blood glucose data corresponding to the historical blood glucose data according to the historical blood glucose data, where the theoretical blood glucose data and the historical blood glucose data are blood glucose data at the same historical time / historical period; then, preset parameters in the initial insulin infusion model are adjusted according to the difference between the historical blood glucose data and the theoretical blood glucose data corresponding thereto, to obtain an adjusted insulin infusion model.

[0073] Optionally, when the parameters are adjusted, the preset parameters in the initial insulin infusion model can be adjusted according to the difference between the historical blood glucose data and the corresponding theoretical blood glucose data; or the preset parameters in the initial insulin infusion model can be adjusted according to preset adjustment rules or preset adjustment steps; the implementation manner of the parameter adjustment in the embodiments of the present application is not limited specifically.

[0074] In step 204, an insulin dose is determined according to real-time monitoring blood glucose data and the insulin infusion model.

[0075] Exemplarily, the insulin infusion device can input real-time monitoring blood glucose data of a user into the adjusted insulin infusion model for calculation, so as to output an insulin dose corresponding to the real-time monitoring blood glucose data.

[0076] In some implementations, the insulin infusion device can also control the infusion component in the insulin infusion device to infuse insulin to the user based on the insulin dose. For example, upon determining the insulin dose, the infusion component can be controlled to infuse the insulin corresponding to the insulin dose to the user. In one implementation, the infusion component can include an insulin pump, and the insulin infusion device can control the insulin pump disposed therein to infuse the insulin corresponding to the insulin dose to the user according to the insulin dose.

[0077] For example, upon determining the insulin dose, the insulin infusion device can infuse the insulin corresponding to the insulin dose to the user in real time, or after a preset time period, etc. The embodiments of the present application do not make specific limitations in this regard.

[0078] In the above insulin infusion control method, the insulin infusion device can obtain the real-time monitoring blood glucose data and the historical blood glucose data of the user, and call the initial insulin infusion model pre-stored in the insulin infusion device. Then, the preset parameters of the initial insulin infusion model are adjusted based on the historical blood glucose data to obtain the insulin infusion model, and the insulin dose is determined based on the real-time monitoring blood glucose data and the insulin infusion model. That is, the insulin infusion device provided by the embodiments of the present application can continuously adjust and update the related preset parameters in the insulin infusion model according to the historical blood glucose data of the user, to obtain the insulin infusion model suitable for the user, and then determine the insulin dose corresponding to the real-time monitoring blood glucose data based on the insulin infusion model. Compared with the traditional insulin infusion device, the matching degree between the insulin infusion model and the user can be improved by self-adaptive adjustment of the related preset parameters in the insulin infusion model, so that the adjusted insulin infusion model is more matched with the individual blood glucose change level of the user, thereby improving the accuracy of the insulin dose calculated by the insulin infusion model, providing more matched and accurate insulin infusion schemes for different users, and ultimately improving the blood glucose control effect of different users.

[0079] In one exemplary embodiment, the historical blood glucose data can include the actual monitoring blood glucose data in the historical period, such as Figure 3 As shown in FIG. 3, the step 203 can include steps 301-304. In which:

[0080] In step 301, the theoretical blood glucose data of the user in the historical period is obtained based on the historical blood glucose data.

[0081] In which, the historical blood glucose data can include the actual monitoring blood glucose data at each time point in the historical period, and the theoretical blood glucose data can include the theoretical blood glucose data at each time point in the historical period.

[0082] Exemplarily, the insulin infusion device can invoke a pre-stored blood glucose calculation model, and input the historical blood glucose data into the blood glucose calculation model for calculation, so as to output theoretical blood glucose data corresponding to the historical blood glucose data (i.e. actual monitoring blood glucose data) of the same historical period.

[0083] In an optional implementation, the historical blood glucose data can include initial blood glucose data of the historical period, which can be blood glucose data at an initial time point of the historical period, or blood glucose data at a time point of intake of carbohydrates in the historical period, etc.; based on this, the insulin infusion device can also input the initial blood glucose data into the blood glucose calculation model, so as to obtain theoretical blood glucose data corresponding to the actual monitoring blood glucose data of the historical period.

[0084] Step 302, according to a preset blood glucose peak rule, performing blood glucose peak analysis on the historical blood glucose data to determine an actual blood glucose peak time point of the historical period.

[0085] Step 303, according to a preset blood glucose peak rule, performing blood glucose peak analysis on the theoretical blood glucose data to determine a theoretical blood glucose peak time point of the historical period.

[0086] Wherein, the preset blood glucose peak rule is used to determine a time point corresponding to a blood glucose peak (i.e. maximum value) from blood glucose data of multiple time points, to obtain a blood glucose peak time point.

[0087] Exemplarily, the blood glucose data of the historical period can be expressed as bg(t num ), bg(t num-1 ),..., bg(t0), which contains blood glucose values of num+1 time points; wherein, t num may represent the first time point in the historical period, bg(t num ) represents the blood glucose value at the first time point, t0may represent the last time point in the historical period, and bg(t0) represents the blood glucose value at the last time point.

[0088] Exemplarily, the preset blood glucose peak rule can be expressed by the following formula:

[0089] (1)

[0090] Wherein, m-1>n, the number of blood glucose data used for peak determination is m+1, firstThreshold and secondThreshold are first threshold and second threshold respectively, and the first threshold and the second threshold can be the same or different.

[0091] When the above conditions are met, it can be determined that the blood glucose peak appears at t n time point, i.e. the blood glucose peak time point is tn .

[0092] The preset blood glucose peak value rule of formula (1) is used to analyze the historical blood glucose data, to determine the actual blood glucose peak time of the historical period, and to analyze the theoretical blood glucose data, to determine the theoretical blood glucose peak time of the historical period.

[0093] In step 304, the preset parameters in the initial insulin infusion model are adjusted according to the actual blood glucose peak time and the theoretical blood glucose peak time to obtain the insulin infusion model.

[0094] The initial insulin infusion model can include an initial insulin activity sub-model and an initial carbohydrate absorption sub-model, and the preset parameters can include a time length for insulin activity to reach a peak value and a time length for carbohydrate absorption speed to reach a peak value. The time length for insulin activity to reach a peak value is a parameter in the initial insulin activity sub-model, indicating the time length required for the activity of insulin to reach the time point of the maximum activity (i.e., the peak time) from the initial 0 time point. The time length for carbohydrate absorption speed to reach a peak value is a parameter in the initial carbohydrate absorption sub-model, indicating the time length required for the absorption speed of the carbohydrate to reach the time point of the maximum absorption speed (i.e., the peak time) from the initial 0 time point.

[0095] For example, the time length for insulin activity to reach a peak value in the initial insulin activity sub-model can be adjusted according to the time deviation between the actual blood glucose peak time and the theoretical blood glucose peak time, and the time length for carbohydrate absorption speed to reach a peak value in the initial carbohydrate absorption sub-model can be adjusted.

[0096] For example, when it is determined by monitoring that the time deviation between the actual blood glucose peak time and the theoretical blood glucose peak time is not within the preset deviation range, it indicates that the actual blood glucose peak time and the theoretical blood glucose peak time are quite different, i.e., it can be indicated that the initial insulin activity sub-model and the initial carbohydrate absorption sub-model are not very accurate. At this time, the time length for insulin activity to reach a peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach a peak value in the initial carbohydrate absorption sub-model can be adjusted according to the time deviation to determine the insulin infusion model.

[0097] In some other implementations, the time deviation can also be used to adjust the time length of the peak insulin activity in the initial insulin activity sub-model to obtain an adjusted insulin activity sub-model, and then the insulin infusion model can be determined based on the adjusted insulin activity sub-model and the initial carbohydrate absorption sub-model. Alternatively, the time deviation can also be used to adjust the time length of the peak carbohydrate absorption rate in the initial carbohydrate absorption sub-model to obtain an adjusted carbohydrate absorption sub-model, and then the insulin infusion model can be determined based on the initial insulin activity sub-model and the adjusted carbohydrate absorption sub-model. Alternatively, the time deviation can also be used to adjust the time length of the peak insulin activity in the initial insulin activity sub-model to obtain an adjusted insulin activity sub-model, and adjust the time length of the peak carbohydrate absorption rate in the initial carbohydrate absorption sub-model to obtain an adjusted carbohydrate absorption sub-model, and then the insulin infusion model can be determined based on the adjusted insulin activity sub-model and the adjusted carbohydrate absorption sub-model.

[0098] For example, when the monitoring determines that the time deviation between the actual blood glucose peak time and the theoretical blood glucose peak time is within the preset deviation range, it indicates that the actual blood glucose peak time and the theoretical blood glucose peak time are relatively close, i.e., the initial insulin activity sub-model and the initial carbohydrate absorption sub-model are relatively accurate, and then the initial insulin infusion model can be used as the insulin infusion model, i.e., the insulin infusion model can be determined based on the initial insulin activity sub-model and the initial carbohydrate absorption sub-model.

[0099] In this embodiment, the insulin infusion device can obtain the theoretical blood glucose data of the user in the historical period based on the historical blood glucose data, perform blood glucose peak analysis on the historical blood glucose data based on the preset blood glucose peak rule to determine the actual blood glucose peak time in the historical period, perform blood glucose peak analysis on the theoretical blood glucose data based on the preset blood glucose peak rule to determine the theoretical blood glucose peak time in the historical period, and then adjust the preset parameters in the initial insulin infusion model based on the actual blood glucose peak time and the theoretical blood glucose peak time to obtain the insulin infusion model. That is, when the preset parameters in the initial insulin infusion model are adjusted to obtain the insulin infusion model, the difference between the actual blood glucose peak time corresponding to the actual monitoring blood glucose data in the historical period and the theoretical blood glucose peak time corresponding to the theoretical blood glucose data can be used to adjust the preset parameters in the initial insulin infusion model to obtain the insulin infusion model, so that the insulin dose output by the adjusted insulin infusion model is more accurate, and the difference between the theoretical blood glucose peak time and the actual blood glucose peak time in the next period is smaller, or even the theoretical blood glucose peak time is consistent with the actual blood glucose peak time, thereby improving the accuracy of blood glucose control.

[0100] In one exemplary embodiment, the time deviation can be used to represent the early or late relationship between the theoretical blood glucose peak time and the actual blood glucose peak time, and then the adjustment of the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model according to the time deviation includes: when the monitoring determines that the time deviation represents that the theoretical blood glucose peak time is later than the actual blood glucose peak time, reducing the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model; or when the monitoring determines that the time deviation represents that the theoretical blood glucose peak time is earlier than the actual blood glucose peak time, increasing the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model.

[0101] Exemplarily, when the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model are reduced, the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model can be reduced according to a preset time interval. Similarly, when the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model are increased, the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model can also be increased according to a preset time interval.

[0102] Exemplarily, the insulin infusion device can also determine a target adjustment value based on the time deviation and a preset adjustment coefficient; then, the reduction of the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model can include: reducing the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model according to the target adjustment value; and similarly, the increase of the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model can include: increasing the time length of the insulin activity reaching the peak value in the initial insulin activity sub-model and the time length of the carbohydrate absorption rate reaching the peak value in the initial carbohydrate absorption sub-model according to the target adjustment value.

[0103] The preset adjustment coefficient can be a value greater than 0 and less than 1.

[0104] In an exemplary embodiment, as shown in FIG. 4, the step 301 can include steps 401-402. Wherein: Figure 4

[0105] Step 401: In response to a user triggering a carbohydrate intake event within a historical period, an initial blood glucose value at an initial time corresponding to the carbohydrate intake event is obtained.

[0106] Exemplarily, the insulin infusion device can determine the carbohydrate intake event by monitoring the rate of change of blood glucose data. For example, in the case of a sudden increase in blood glucose value, it can be determined that the user has ingested carbohydrates, i.e., that the user has triggered a carbohydrate intake event. Alternatively, the insulin infusion device can also determine the carbohydrate intake event by monitoring the user triggering the carbohydrate intake event through an input device, which can include but is not limited to a physical input button, an input control on the display screen, etc. For example, in the case of the user ingesting carbohydrates, the user can trigger the carbohydrate intake event by triggering the input device.

[0107] Exemplarily, within the historical period, if the user triggers a carbohydrate intake event, the initial blood glucose value at the initial time corresponding to the carbohydrate intake event can be obtained, and the theoretical blood glucose data of the historical period can be calculated from the initial time, i.e., the theoretical blood glucose value at each time from the initial time.

[0108] Step 402: According to the initial blood glucose value and the initial insulin infusion model, the theoretical blood glucose data of the user is determined.

[0109] Exemplarily, the initial insulin infusion model can include an initial insulin activity sub-model and an initial carbohydrate absorption sub-model. The insulin infusion device can determine the theoretical blood glucose data of the user at each time within the historical period according to the initial blood glucose value, the initial insulin activity sub-model, and the initial carbohydrate absorption sub-model.

[0110] In an implementation, the initial insulin activity sub-model can be expressed as iobModel(t i , t), representing a curve of insulin activity changing over time, where t i is the time of insulin injection, and the time length for the insulin activity to reach a peak value is denoted as t ip ; the initial carbohydrate absorption sub-model can be expressed as cobModel(t c , t), representing a curve of carbohydrate absorption speed changing over time, where t c is the time of the user ingesting carbohydrates within the historical period, i.e., the carbohydrate intake time within the historical period, and the time length for the carbohydrate absorption speed to reach a peak value is denoted as t cp .​

[0111] Exemplarily, in the case of the historical period being the previous period of the current time period / current time, t c It can also be expressed as the time of the last carbohydrate intake.

[0112] After the user inputs the carbohydrate, the expected blood glucose value bg_expected(t) from the initial time of inputting the carbohydrate to the future time t can be calculated as:

[0113] (2)

[0114] Wherein, DIA is the insulin active duration, i.e. the duration from insulin activity to inactivity, t carbs is the carbohydrate digestion duration, i.e. the duration from carbohydrate intake to complete digestion, which can be determined in advance or set by the user; t c ≤t≤t c +t delta , t delta is the larger value of t carbs and DIA; bg(t0) represents the initial blood glucose value actually measured at the time of carbohydrate intake; isf represents the insulin sensitivity coefficient for converting the insulin activity value into the corresponding blood glucose value; icr represents the carbohydrate coefficient for converting the carbohydrate amount into the corresponding blood glucose value.

[0115] The physical meaning of the expression is that the remaining active insulin amount of all bolus insulin injected between the time t0-DIA and the time t0 at the time t; optionally, It can be one or a combination of models such as the Walsh model, the rapid-acting insulin model (based on the published Humalog, Novolog, Apidra insulin absorption model), the Fiasp model (based on the published Fiasp insulin absorption model), etc. Wherein, t is the calculation time, t ip is the duration of insulin activity reaching the peak value, and i is the time of bolus insulin injection.

[0116] The physical meaning of the expression is that the remaining active carbohydrate amount of all carbohydrates ingested between the time t0-t carbs and the time t0 at the time t; optionally, It can be a linear carbohydrate absorption model, a dynamic carbohydrate absorption model, etc. Wherein, t is the calculation time, t cp is the duration of carbohydrate absorption rate reaching the peak value, and i is the time of inputting the carbohydrate.

[0117] Using the above formula (2), the theoretical blood glucose data of the user at each time in the historical period can be obtained.

[0118] Exemplarily, after the above-mentioned monitoring of the carbohydrate intake event, the insulin injection event can also be monitored; when the monitoring triggers the insulin injection event within the historical period, the intermediate blood glucose value at the intermediate moment corresponding to the insulin injection event can be acquired; then, according to the intermediate blood glucose value and the initial insulin infusion model, the theoretical blood glucose data of the user in the remaining period is re-determined; wherein the remaining period includes the time period between the carbohydrate intake event and the insulin injection event in the historical period.

[0119] That is, after the user ingests the carbohydrate, if a large dose of insulin is injected, the theoretical blood glucose data at each subsequent moment can be re-calculated according to the intermediate blood glucose value at the time of injecting the insulin; since the activity of the insulin is high after the injection of the insulin, the control effect on the blood glucose is also good, and the subsequent blood glucose level is greatly affected; therefore, after the injection of the insulin, the theoretical blood glucose data at each subsequent moment needs to be re-calculated according to the intermediate blood glucose value after the injection of the insulin, so as to improve the calculation accuracy of the theoretical blood glucose data within the historical period.

[0120] In this embodiment, by responding to the carbohydrate intake event triggered by the user within the historical period, the initial blood glucose value at the initial moment corresponding to the carbohydrate intake event is acquired, and then according to the initial blood glucose value and the initial insulin infusion model, the theoretical blood glucose data of the user is determined. By using the method proposed in this embodiment, the calculation of the theoretical blood glucose data within the historical period can be realized, so that the preset parameters in the initial insulin infusion model are adjusted based on the theoretical blood glucose data and the actual measured blood glucose data within the historical period, so that the adjusted insulin infusion model is more matched with the blood glucose change of the user, so that the insulin infusion scheme suitable for the user is determined based on the adjusted insulin infusion model, the insulin infusion accuracy is improved, and the blood glucose control effect is further improved.

[0121] In an exemplary embodiment, an adaptive adjustment scheme of an insulin infusion model is provided, wherein the insulin infusion model includes an insulin activity sub-model and a carbohydrate absorption sub-model, the time length for the insulin activity to reach a peak value and the time length for the carbohydrate absorption speed to reach a peak value are two key parameters in the insulin activity sub-model and the carbohydrate absorption sub-model, the time length for the insulin activity to reach a peak value describes the time point at which the insulin reaches the maximum activity in the body, and the time length for the carbohydrate absorption speed to reach a peak value describes the time point at which the carbohydrate is absorbed in the body to reach the fastest speed; if there is a large difference between the two parameters and the actual situation, the accuracy of blood glucose prediction can be affected, and then the insulin control effect of the insulin infusion model is affected; therefore, adaptive adjustment needs to be made according to individual differences and real-time changes.

[0122] In an alternative implementation, reference is made to Figure 5As shown, a structural flow diagram of model adaptive adjustment is provided; wherein the specific formula and steps of adaptive adjustment are as follows:

[0123] 1. Data monitoring and calculation module

[0124] This module is mainly responsible for monitoring the blood glucose data of the patient in real time, and calculating the actual blood glucose peak time.

[0125] Optionally, the collected original historical blood glucose data can be subjected to linear interpolation and sliding filter processing to obtain processed historical blood glucose data, which can be expressed as: bg(t num ), bg(t num-1 ),..., bg(t0), wherein t0 can also represent the current time, and bg(t0) can also represent the current blood glucose value.

[0126] Next, the actual blood glucose peak time bg_peak_real_time is determined according to the historical blood glucose data using the above formula (1).

[0127] 2. Parameter comparison module

[0128] First, the expected theoretical blood glucose data can be calculated. The above formula (2) can be used to calculate the theoretical blood glucose data at each time from the time of carbohydrate intake to the completion of carbohydrate digestion according to the initial blood glucose value at the time of carbohydrate intake and the intermediate blood glucose value at the time of insulin injection.

[0129] Second, the theoretical blood glucose peak time bg_peak_expected_time can be determined according to the theoretical blood glucose data using the above formula (1).

[0130] Next, the blood glucose peak time deviation bg_peak_time_dev can be calculated, which can be expressed as:

[0131] bg_peak_time_dev=bg_peak_expected_time - bg_peak_real_time

[0132] 3. Parameter adjustment module

[0133] When the absolute value of the time deviation bg_peak_time_dev is greater than the set time deviation threshold, the duration t ip at which the insulin activity reaches the peak value and the duration t cp at which the carbohydrate absorption speed reaches the peak value in the initial insulin activity sub-model and the initial carbohydrate absorption sub-model are adjusted to reduce the blood glucose peak time deviation.

[0134] Optionally, the target adjustment value adjustment can be calculated according to the time deviation bg_peak_time_dev, as follows:

[0135] adjustment = bg_peak_time_dev x w

[0136] wherein w is a preset adjustment coefficient.

[0137] When updating t ip and t cp , if bg_peak_time_dev > 0, it means that the actual blood glucose peak time is earlier than the theoretical blood glucose peak time, i.e. the theoretical blood glucose peak time is later than the actual blood glucose peak time, which means that the actual insulin action or carbohydrate absorption is faster than expected, so the time length for insulin activity to reach the peak and the time length for carbohydrate absorption speed to reach the peak need to be reduced to make them closer to the actual situation, i.e.

[0138] t ip = t ip - adjustment; t cp = t cp - adjustment.

[0139] On the contrary, if bg_peak_time_dev < 0, it means that the actual blood glucose peak time is later than the theoretical blood glucose peak time, i.e. the theoretical blood glucose peak time is earlier than the actual blood glucose peak time, which means that the actual insulin action or carbohydrate absorption is slower than expected, so the time length for insulin activity to reach the peak and the time length for carbohydrate absorption speed to reach the peak need to be increased to make them closer to the actual situation, i.e.

[0140] t ip = t ip + adjustment; t cp = t cp + adjustment.

[0141] 4. Control loop module

[0142] This module is mainly responsible for controlling the loop execution of the above process. It will continuously call the data monitoring and calculation module, the parameter comparison module and the parameter adjustment module to realize the function of self-adaptively adjusting the time length for insulin activity to reach the peak and the time length for carbohydrate absorption speed to reach the peak until the absolute value of bg_peak_time_dev is less than the set time deviation threshold.

[0143] Of course, in actual use, due to the dynamic change of blood glucose level in the user's body, even if the absolute value of bg_peak_time_dev has been reduced to the time deviation threshold value last time, there may still be a case that the absolute value of bg_peak_time_dev of the next time is greater than the time deviation threshold value, so the above process can be executed in a loop during insulin infusion.

[0144] By using the above method, the insulin infusion model can be adaptively adjusted according to the differences of different individuals, so that the insulin infusion model can be matched with different individual characteristics, thereby determining the insulin infusion scheme for different individuals, improving the accuracy of insulin infusion, and further improving the blood glucose control effect.

[0145] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which 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 sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0146] Based on the same inventive concept, the embodiments of the present application also provide an insulin infusion device for implementing the above-mentioned insulin infusion control method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more insulin infusion device embodiments provided below can refer to the limitations of the insulin infusion control method described above, which will not be repeated here.

[0147] In one exemplary embodiment, as shown in Figure 6 An insulin infusion device is provided, comprising: an acquisition module 601, a calling module 602, an adjusting module 603, and a first determination module 604, wherein:

[0148] The acquisition module 601 is configured to acquire real-time monitoring blood glucose data and historical blood glucose data of a user.

[0149] The calling module 602 is configured to call an initial insulin infusion model pre-stored in the insulin infusion device.

[0150] The adjusting module 603 is configured to adjust preset parameters of the initial insulin infusion model according to the historical blood glucose data to obtain an insulin infusion model.

[0151] The first determination module 604 is configured to determine the insulin dose according to the real-time monitored blood glucose data and the insulin infusion model.

[0152] In one of the embodiments, the historical blood glucose data comprises actual monitored blood glucose data of a historical period, and the adjustment module 603 comprises:

[0153] The acquisition unit is configured to acquire theoretical blood glucose data of the user in the historical period according to the historical blood glucose data;

[0154] The first determination unit is configured to perform blood glucose peak analysis on the historical blood glucose data according to a preset blood glucose peak rule, and determine an actual blood glucose peak time of the historical period;

[0155] The second determination unit is configured to perform blood glucose peak analysis on the theoretical blood glucose data according to the preset blood glucose peak rule, and determine a theoretical blood glucose peak time of the historical period;

[0156] The adjustment unit is configured to adjust preset parameters in the initial insulin infusion model according to the actual blood glucose peak time and the theoretical blood glucose peak time, and obtain the insulin infusion model.

[0157] In one of the embodiments, the initial insulin infusion model comprises an initial insulin activity sub-model and an initial carbohydrate absorption sub-model, and the preset parameters comprise a time length for insulin activity to reach a peak value and a time length for carbohydrate absorption speed to reach a peak value; the adjustment unit is specifically configured to, when a time deviation between the actual blood glucose peak time and the theoretical blood glucose peak time is not within a preset deviation range, adjust the time length for insulin activity to reach the peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach the peak value in the initial carbohydrate absorption sub-model according to the time deviation, and determine the insulin infusion model; or, when the time deviation is within the preset deviation range, determine the insulin infusion model according to the initial insulin activity sub-model and the initial carbohydrate absorption sub-model.

[0158] In one of the embodiments, the time deviation is used to represent an early-late relationship between the theoretical blood glucose peak time and the actual blood glucose peak time, and the adjustment unit is specifically configured to, when the time deviation indicates that the theoretical blood glucose peak time is later than the actual blood glucose peak time, reduce the time length for insulin activity to reach the peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach the peak value in the initial carbohydrate absorption sub-model; or, when the time deviation indicates that the theoretical blood glucose peak time is earlier than the actual blood glucose peak time, increase the time length for insulin activity to reach the peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach the peak value in the initial carbohydrate absorption sub-model.

[0159] In one embodiment, the device further comprises:

[0160] A second determining module is used to determine a target adjustment value based on the time deviation and a preset adjustment coefficient;

[0161] The regulating unit is specifically configured to reduce the time it takes for the insulin activity in the initial insulin activity sub-model to reach a peak value according to the target adjustment value, and reduce the time it takes for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak value according to the target adjustment value;

[0162] The regulating unit is further specifically configured to increase the time it takes for the insulin activity in the initial insulin activity sub-model to reach a peak value according to the target adjustment value, and to increase the time it takes for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak value according to the target adjustment value.

[0163] In one embodiment, the acquisition unit is specifically configured to, in response to a carbohydrate intake event triggered by a user within a historical period, obtain an initial blood glucose value at an initial moment corresponding to the carbohydrate intake event; and determine the user's theoretical blood glucose data based on the initial blood glucose value and the initial insulin infusion model.

[0164] In one embodiment, the acquisition unit is further used to monitor the insulin injection events triggered within the historical period, and obtain the intermediate blood glucose value at the intermediate moment corresponding to the insulin injection event; based on the intermediate blood glucose value and the initial insulin infusion model, the user's theoretical blood glucose data for the remaining period is re-determined; the remaining period includes the time period in the historical period excluding the carbohydrate intake event and the insulin injection event.

[0165] Each module in the aforementioned insulin infusion device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of the processor in the insulin infusion device in hardware form, or may be stored in a memory in the insulin infusion device in software form, so that the processor can call and execute the corresponding operations of each module.

[0166] In an exemplary embodiment, an insulin infusion system is provided, such as Figure 7 As shown, the system includes a blood glucose monitoring device 701 and an insulin infusion device 702 in any of the above embodiments, wherein the insulin infusion device 702 includes a memory, a processor, and an infusion component (not shown in the figure); wherein the blood glucose monitoring device 701 is used to monitor the user's blood glucose data in real time; the memory stores a computer program, and when the processor executes the computer program, the steps of the insulin infusion control method in any of the above embodiments are implemented to control the infusion component in the insulin infusion device 702.

[0167] Exemplarily, the infusion assembly can include a driving mechanism, a liquid reservoir and an infusion pipeline. The driving mechanism drives a push rod in the liquid reservoir to move, so as to output insulin liquid from the liquid reservoir and inject into the human body via the infusion pipeline.

[0168] Exemplarily, the processor can acquire real-time monitoring blood glucose data and historical blood glucose data of the user from the blood glucose monitoring device 701, or acquire real-time monitoring blood glucose data and historical blood glucose data of the user from the memory. The blood glucose monitoring device 701 can store the blood glucose data of the user in the memory in the case of real-time monitoring of the blood glucose data of the user.

[0169] Exemplarily, the processor can be integrated in the insulin infusion device 702, or be independent of the blood glucose monitoring device 701 and the insulin infusion device 702. The blood glucose monitoring device 701 can be in communication connection with the memory and the processor, the insulin infusion device 702 can be in communication connection with the memory and the processor, and the memory can be in communication connection with the processor.

[0170] The insulin infusion system in the embodiment can not only realize real-time monitoring of blood glucose data of the user, but also adaptively adjust an insulin infusion model based on the blood glucose data of the user, and further formulate a more accurate insulin infusion scheme for the user based on the adjusted insulin infusion model, so as to ensure that the blood glucose level in the user is within a normal blood glucose level range and improve the blood glucose control effect for different individuals.

[0171] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the insulin infusion control method in any of the above embodiments.

[0172] In one embodiment, a computer program product is provided, and the computer program product includes a computer program. The computer program is executed by a processor to implement the steps of the insulin infusion control method in any of the above embodiments.

[0173] 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 for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with relevant regulations.

[0174] 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. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to 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 storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric 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 but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0175] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0176] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An insulin infusion device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: The processor executes the steps of the insulin infusion control method when executing the computer program, and the method comprises: obtaining real-time monitoring blood glucose data and historical blood glucose data of a user; calling an initial insulin infusion model pre-stored in the insulin infusion device; adjusting preset parameters of the initial insulin infusion model according to the historical blood glucose data to obtain an insulin infusion model; determining an insulin dose according to the real-time monitoring blood glucose data and the insulin infusion model.

2. The insulin infusion device of claim 1, wherein, The historical blood glucose data comprises actual monitoring blood glucose data of a historical period, and the adjusting of the preset parameters of the initial insulin infusion model according to the historical blood glucose data to obtain an insulin infusion model comprises: obtaining theoretical blood glucose data of the user in the historical period according to the historical blood glucose data; performing blood glucose peak analysis on the historical blood glucose data according to preset blood glucose peak rules to determine actual blood glucose peak time in the historical period; performing blood glucose peak analysis on the theoretical blood glucose data according to the preset blood glucose peak rules to determine theoretical blood glucose peak time in the historical period; adjusting preset parameters in the initial insulin infusion model according to the actual blood glucose peak time and the theoretical blood glucose peak time to obtain the insulin infusion model.

3. The insulin infusion device of claim 2, wherein, The initial insulin infusion model comprises an initial insulin activity sub-model and an initial carbohydrate absorption sub-model, and the preset parameters comprise a time length for insulin activity to reach a peak value and a time length for carbohydrate absorption speed to reach a peak value; and the adjusting of the preset parameters in the initial insulin infusion model according to the actual blood glucose peak time and the theoretical blood glucose peak time to obtain the insulin infusion model comprises: when it is monitored that a time deviation between the actual blood glucose peak time and the theoretical blood glucose peak time is not within a preset deviation range, adjusting the time length for insulin activity to reach a peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach a peak value in the initial carbohydrate absorption sub-model according to the time deviation to determine the insulin infusion model; or when it is monitored that the time deviation is within the preset deviation range, determining the insulin infusion model according to the initial insulin activity sub-model and the initial carbohydrate absorption sub-model.

4. The insulin infusion device of claim 3, wherein, The time deviation is used to represent the early or late relationship between the theoretical blood glucose peak time and the actual blood glucose peak time, and the adjusting of the time length for insulin activity to reach a peak value in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach a peak value in the initial carbohydrate absorption sub-model according to the time deviation comprises: when it is monitored that the time deviation indicates that the theoretical blood glucose peak time is later than the actual blood glucose peak time, reducing the insulin activity in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach a peak value in the initial carbohydrate absorption sub-model; or when it is monitored that the time deviation indicates that the theoretical blood glucose peak time is earlier than the actual blood glucose peak time, increasing the insulin activity in the initial insulin activity sub-model and the time length for carbohydrate absorption speed to reach a peak value in the initial carbohydrate absorption sub-model. Or, monitoring determines that the time deviation represents that the theoretical blood glucose peak time is earlier than the actual blood glucose peak time, increasing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and increasing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak.

5. The insulin infusion device of claim 4, wherein, The method further comprises: determining a target adjustment value based on the time deviation and a preset adjustment coefficient; the reducing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and the reducing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak, comprises: according to the target adjustment value, reducing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and according to the target adjustment value, reducing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak; the increasing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and the increasing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak, comprises: according to the target adjustment value, increasing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and according to the target adjustment value, increasing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak.

6. The insulin infusion device according to any one of claims 2 to 5, characterized in that The obtaining the theoretical blood glucose data of the user in the historical period from the historical blood glucose data comprises: in response to a carbohydrate intake event triggered by the user in the historical period, obtaining an initial blood glucose value at an initial time corresponding to the carbohydrate intake event; determining the theoretical blood glucose data of the user according to the initial blood glucose value and the initial insulin infusion model.

7. The insulin infusion device of claim 6, wherein, The method further comprises: monitoring an insulin injection event triggered in the historical period, obtaining an intermediate blood glucose value at an intermediate time corresponding to the insulin injection event; redetermining the theoretical blood glucose data of the user in a remaining period according to the intermediate blood glucose value and the initial insulin infusion model; the remaining period includes a time period between the carbohydrate intake event and the insulin injection event in the historical period.

8. An insulin infusion device characterized by, The device comprises: an obtaining module, configured to obtain real-time monitoring blood glucose data and historical blood glucose data of a user; a calling module, configured to call an initial insulin infusion model pre-stored in the insulin infusion device; an adjusting module, configured to adjust preset parameters of the initial insulin infusion model according to the historical blood glucose data to obtain an insulin infusion model; a first determining module, configured to determine an insulin dose according to the real-time monitoring blood glucose data and the insulin infusion model.

9. An insulin infusion system, characterized by The blood glucose monitoring device and the insulin infusion device according to any one of claims 1 to 7; The blood glucose monitoring device is configured to monitor blood glucose data of a user in real time.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the steps of the method performed by the insulin infusion device according to any one of claims 1 to 7. Or, monitoring determines that the time deviation represents that the theoretical blood glucose peak time is earlier than the actual blood glucose peak time, increasing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and increasing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak. The method further comprises: determining a target adjustment value based on the time deviation and a preset adjustment coefficient; the reducing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and the reducing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak, comprises: according to the target adjustment value, reducing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and according to the target adjustment value, reducing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak; the increasing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and the increasing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak, comprises: according to the target adjustment value, increasing the length of time for the insulin activity in the initial insulin activity sub-model to reach a peak, and according to the target adjustment value, increasing the length of time for the carbohydrate absorption rate in the initial carbohydrate absorption sub-model to reach a peak. The obtaining the theoretical blood glucose data of the user in the historical period from the historical blood glucose data comprises: in response to a carbohydrate intake event triggered by the user in the historical period, obtaining an initial blood glucose value at an initial time corresponding to the carbohydrate intake event; determining the theoretical blood glucose data of the user according to the initial blood glucose value and the initial insulin infusion model. The method further comprises: monitoring an insulin injection event triggered in the historical period, obtaining an intermediate blood glucose value at an intermediate time corresponding to the insulin injection event; redetermining the theoretical blood glucose data of the user in a remaining period according to the intermediate blood glucose value and the initial insulin infusion model; the remaining period includes a time period between the carbohydrate intake event and the insulin injection event in the historical period. The device comprises: an obtaining module, configured to obtain real-time monitoring blood glucose data and historical blood glucose data of a user; a calling module, configured to call an initial insulin infusion model pre-stored in the insulin infusion device; an adjusting module, configured to adjust preset parameters of the initial insulin infusion model according to the historical blood glucose data to obtain an insulin infusion model; a first determining module, configured to determine an insulin dose according to the real-time monitoring blood glucose data and the insulin infusion model. The blood glucose monitoring device and the insulin infusion device according to any one of claims 1 to 7; The blood glucose monitoring device is configured to monitor blood glucose data of a user in real time. The computer program, when executed by a processor, implements the steps of the method performed by the insulin infusion device according to any one of claims 1 to 7.

Images