Method, device, and program for adjusting insulin injection amount based on predicted blood glucose

Abstract

Disclosed, according to various embodiments of the present invention, is a method for adjusting an insulin injection amount based on predicted blood glucose. The method may comprise the steps of: predicting a future blood glucose value on the basis of the current blood glucose value and an insulin injection history; determining a future blood glucose state on the basis of the future blood glucose value and a predefined correction factor; and adjusting an insulin injection amount so as to correspond to the future blood glucose state.

Description

Method, device, and program for controlling insulin injection volume based on predicted blood glucose.

[0001] The present invention relates to a method, apparatus, and program for controlling insulin injection volume based on predicted blood glucose.

[0002]

[0003] Modern diabetes treatment is becoming automated due to technological advancements, and artificial pancreas technology—a closed-loop system integrating continuous glucose monitoring (CGM) and insulin pumps—is a particularly 주목받는 field. These systems help maintain blood sugar levels within the normal range by detecting real-time changes in the user's blood sugar and automatically adjusting the insulin dosage according to a set algorithm. Key applications include preventing nocturnal hypoglycemia, controlling postprandial hyperglycemia, and responding to sudden blood sugar fluctuations during exercise, and the use of these systems is gradually expanding, primarily among patients with type 1 diabetes.

[0004] The core technology of automated insulin infusion systems is an infusion control algorithm based on real-time blood glucose data, which considers various factors such as not only the absolute value of blood glucose but also the speed and direction of changes, as well as past infusion history. Generally, a combination of strategies is used: 'basal' infusion, which involves continuously injecting small amounts of insulin at regular intervals, and 'bolus' infusion, which involves temporarily injecting high doses when a blood glucose spike is anticipated, such as during a meal. Recently, features that predict future blood glucose levels and take preemptive action have been introduced to some systems. Through this, functions such as PLGS (Predictive Low Glucose Suspend), which temporarily halts infusion before hypoglycemia occurs, and LGS (Low Glucose Suspend), which automatically stops infusion when blood glucose actually drops below a certain level, are being commercialized.

[0005] However, it has been pointed out that existing automated insulin injection systems are not sufficiently flexible for blood glucose control because they mostly operate based on fixed ranges or conditions. For example, if blood glucose status is judged dichotomously based on specific values, or if the same algorithm is applied to various users, it is difficult to adequately reflect individual differences in insulin sensitivity or metabolic responses. Consequently, some users may be exposed to the risk of over-insulin injection or hypoglycemia due to a discrepancy between their actual physical condition and the injection amount. Furthermore, areas such as calculating corrected insulin injection amounts in hyperglycemic states and making rapid control decisions in response to sudden blood glucose fluctuations are still considered to require improvement.

[0006] As such, while technologies aimed at automating blood glucose measurement and insulin injection are steadily advancing, there is still room for improvement in terms of accuracy, personalization, and responsiveness. There is a continuous demand in the industry for blood glucose control technologies that are more precise, safe, and user-customized, reflecting the diverse lifestyle patterns and physiological characteristics of diabetic patients. In this regard, Korean Published Patent No. 10-2017-0088177 discloses a smart care system for diabetic patients using an insulin pump.

[0007]

[0008] The technical problem that the present invention aims to solve is to provide a method, device, and program for controlling insulin injection volume based on predicted blood glucose.

[0009] The technical problems of the present invention are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below.

[0010]

[0011] According to one embodiment of the present invention for solving the problem described above, a method for controlling the insulin injection amount based on a predicted blood glucose level is disclosed. The method may include: a step of predicting a future blood glucose value based on a current blood glucose value and an insulin injection history; a step of determining a future blood glucose state based on the future blood glucose value and a predefined correction factor; and a step of controlling the insulin injection amount to correspond to the future blood glucose state.

[0012] In an alternative embodiment, the step of predicting a future blood glucose value based on the current blood glucose value and insulin injection history may include: obtaining the current blood glucose value from a blood glucose measurement sensor attached to the user's body; accumulating insulin injection data from an insulin injection pump attached to the user's body to generate the insulin injection history; and inputting the current blood glucose value and the insulin injection data into a pre-trained neural network model to obtain the future blood glucose value.

[0013] In an alternative embodiment, the neural network model is configured with a structure combining a convolutional neural network and a recurrent neural network and is pre-trained based on preprocessed training data, and the method may further include the steps of: padding insulin injection data at a time when insulin injection is not performed with zeros, and generating merged data by synchronizing basal insulin injection data, bolus insulin injection data, and blood glucose values ​​on a time basis; extracting the merged data, which has no omissions on a daily basis, as training data; normalizing the training data and removing duplicate data to generate the training data; and pre-training the neural network model based on the training data.

[0014] In an alternative embodiment, the method further comprises the step of defining the correction factor; and the step of defining the correction factor may include the step of recognizing the amount of insulin injected into the user at a past time; the step of recognizing a change in blood glucose corresponding to the past time; and the step of defining the correction factor, which is the predicted blood glucose reduction amount for one unit of insulin injection based on the amount of insulin injected and the change in blood glucose.

[0015] In an alternative embodiment, the step of determining a future blood glucose state based on the future blood glucose value and a predefined correction factor may include: defining a value obtained by subtracting a specific ratio value of the correction factor from a lower limit value of a predefined normal blood glucose range as a hypoglycemic reference value; defining a value obtained by adding a specific ratio value of the correction factor to an upper limit value of the normal blood glucose range as a hyperglycemic reference value; and determining a state including the future blood glucose value as the future blood glucose state among a hypoglycemic state corresponding to the hypoglycemic reference value to the lower limit value, a normal state corresponding to the lower limit value to the upper limit value, and a hyperglycemic state corresponding to the upper limit value to the hyperglycemic reference value.

[0016] In an alternative embodiment, the step of adjusting the insulin injection amount to correspond to the future blood glucose state may include: reducing the insulin injection amount by a predetermined ratio when the future blood glucose state is the hypoglycemic state; maintaining the insulin injection amount when the future blood glucose state is the normal state; or increasing the insulin injection amount by a predetermined ratio when the future blood glucose state is the hyperglycemic state.

[0017] In an alternative embodiment, when the future blood glucose state is the hypoglycemic state, the step of reducing the insulin injection amount by a predetermined ratio may further include: a step of stopping the insulin injection when the future blood glucose value falls within the lowest region among the detailed regions included in the hypoglycemic state; or a step of reducing the insulin injection amount by a predetermined ratio when the future blood glucose value falls within a detailed region other than the lowest region.

[0018] In an alternative embodiment, when the future blood glucose state is the hyperglycemic state, the step of increasing the insulin injection amount by a predetermined ratio may include the step of adjusting the insulin injection amount to add a bolus insulin injection amount calculated based on the correction factor when the future blood glucose value is included in a predefined high-risk area among a plurality of detailed areas included in the hyperglycemic state.

[0019] According to one embodiment of the present invention for solving the above-described problem, an apparatus is disclosed. The apparatus comprises: a memory for storing one or more instructions; and a processor for executing the one or more instructions stored in the memory, and the processor can perform the above-described methods by executing the one or more instructions.

[0020] According to one embodiment of the present invention for solving the above-described problem, a computer program stored on a recording medium readable by a computer is disclosed, which is combined with a computer, which is hardware, to perform the above-described methods.

[0021] Other specific details of the present invention are included in the detailed description and drawings.

[0022]

[0023] The present invention predicts future changes in blood glucose based on the user's current blood glucose value and insulin injection history, and can precisely adjust the amount of insulin injected by subdividing the blood glucose status according to the prediction results.

[0024] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0025]

[0026] FIG. 1 is a drawing illustrating a system according to one embodiment of the present invention.

[0027] FIG. 2 is a hardware configuration diagram of a computing device according to one embodiment of the present invention.

[0028] FIGS. 3 to 8 are drawings for explaining a method for controlling insulin injection amount based on predicted blood glucose according to an embodiment of the present invention.

[0029]

[0030] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments presented below, but can be implemented in various different forms and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and scope of the present disclosure. The embodiments presented below are provided to make the present disclosure complete and to fully inform those skilled in the art of the scope of the invention. In describing the present disclosure, detailed descriptions of related prior art are omitted where it is determined that such detailed descriptions may obscure the essence of the present invention.

[0031] The terms used herein are used merely to describe specific embodiments and are not intended to limit the disclosure. Unless otherwise defined, all terms used herein have the same meaning as generally understood by those skilled in the art to which this disclosure pertains.

[0032] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. Furthermore, terms such as "comprising" or "having" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0033] Additionally, terms including ordinal numbers, such as "first" or "second" as used herein, may be used to describe various components, but the components should not be limited by the terms. The terms are used solely for the purpose of distinguishing one component from another.

[0034] Phrases such as "in one embodiment," "according to one embodiment," "related to one embodiment," or "according to an implementation of one embodiment" in this specification do not necessarily refer to the same embodiment. Furthermore, throughout this specification, "examples" are arbitrary distinctions to facilitate the description of the present disclosure, and each embodiment does not need to be mutually exclusive. For example, configurations mentioned for the description of one embodiment may be applied and / or implemented in other embodiments, and may be modified and applied and / or implemented to the extent that they do not depart from the scope of the present disclosure.

[0035] Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented by various numbers of hardware and / or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for a specific function.

[0036] Additionally, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented as algorithms executed on one or more processors. Furthermore, the present disclosure may employ prior art for electronic configuration, signal processing, and / or data processing, etc. Terms such as "mechanism," "element," "means," and "configuration" may be used broadly and are not limited to mechanical and physical configurations. Additionally, terms such as "-part," "-module," etc. refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or as a combination of hardware and software.

[0037] Furthermore, the connecting lines or connecting members between the components depicted in the drawings are merely illustrative of functional connections and / or physical or circuit connections. In the actual device, connections between components may be represented by various alternative or added functional connections, physical connections, or circuit connections.

[0038] In addition, some components in the drawings may be depicted with their size or proportions slightly exaggerated. Also, components depicted in one drawing may not be depicted in another drawing.

[0039] The present disclosure will be described in detail below with reference to the attached drawings.

[0040]

[0041] FIG. 1 is a drawing illustrating a system according to one embodiment of the present invention.

[0042] Referring to FIG. 1, a system according to one embodiment of the present invention may include a computing device (100), an artificial pancreas device (200), a user terminal (300), and an external server (400). The system illustrated in FIG. 1 is according to one embodiment, and its components are not limited to the embodiment illustrated in FIG. 1 and may be added, changed, or deleted as needed.

[0043] In the following description, for the convenience of explanation, it is described that a computing device (100) located outside the artificial pancreas device (200) controls the insulin injection amount of the artificial pancreas device (200) based on predicted blood glucose. However, this is not limited thereto, and blood glucose prediction calculations and injection control may be performed independently by a processor embedded in the artificial pancreas device (200). In this case, the artificial pancreas device (200) operates as a single device in which blood glucose measurement, data processing, status classification, and insulin injection control functions are integrated, and can independently perform periodic blood glucose analysis and adaptive insulin control without communication with an external computing device.

[0044] In one embodiment, the computing device (100) can adjust the amount of insulin injected based on the predicted blood glucose. For example, the computing device (100) can collect the current blood glucose value and insulin injection history in real time, predict the blood glucose value after a certain period of time based on this, and then dynamically adjust the insulin injection strategy by increasing or decreasing the amount of basal insulin injected or injecting additional bolus insulin if necessary, according to the predicted result.

[0045] Specifically, the computing device (100) can predict future blood glucose values ​​based on current blood glucose values ​​and insulin injection history. Additionally, the computing device (100) can determine future blood glucose states based on future blood glucose values ​​and predefined correction factors. Furthermore, the computing device (100) can adjust the insulin injection amount to correspond to the future blood glucose state.

[0046] Accordingly, the computing device (100) of the present invention can preemptively determine the user's blood glucose status and adjust the insulin injection amount more precisely and safely according to the individual's insulin response characteristics.

[0047] Hereinafter, an example of a method in which a computing device (100) adjusts the amount of insulin injected based on predicted blood glucose is described with reference to FIGS. 3 to 8.

[0048] In various embodiments, the computing device (100) may provide Web or Application-based services. However, it is not limited thereto.

[0049] The computing device (100) may include any type of computer system or computer device, such as, for example, a microprocessor, a mainframe computer, a digital processor, a portable device, and a device controller. However, it is not limited thereto.

[0050] Hereinafter, the hardware configuration of the computing device (100) will be described with reference to FIG. 2.

[0051] Meanwhile, the artificial pancreas device (200) may be a device that is attached to the user's body to measure the user's blood sugar and inject insulin into the user.

[0052] Here, the artificial pancreas device (200) is an integrated device including a continuous glucose monitoring (CGM) and an insulin infusion pump, and receives an infusion control signal based on blood glucose data measured through a sensor, and can continuously infuse basal insulin at a constant rate or temporarily infuse bolus insulin when necessary. In addition, the artificial pancreas device (200) operates based on infusion control commands provided by the computing device (100) and can transmit and receive data through a wired or wireless communication interface with the computing device (100).

[0053] Meanwhile, the user terminal (300) may be connected to the computing device (100) via a network (500) and may be a terminal of a user using an artificial pancreas device (200) in which the amount of insulin injected is adjusted based on the predicted blood glucose performed by the computing device (100). That is, the user terminal (300) may include a user terminal that supports a user suffering from diabetes to check the operating status, blood glucose change history, injection history, warning notifications, etc., of the artificial pancreas device (200) in real time or to change settings.

[0054] Here, the user terminal (300) may include, for example, various types of computer devices. Specifically, for example, the user terminal (300) may refer to various terminal devices such as smartphones, tablet PCs, desktops, and laptops.

[0055] The user terminal (300) includes a display on at least a part of the terminal and may include an operating system for running applications or extension-based services provided by the computing device (100). For example, the user terminal (300) may be a smartphone, but is not limited thereto, and the user terminal (300) may include all kinds of handheld-based wireless communication devices such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartpad, tablet PC, etc., as wireless communication devices that ensure portability and mobility.

[0056] An external server (400) can be connected to a computing device (100) via a network (500), and can transmit and receive various information / data necessary for the computing device (100) to adjust the insulin injection amount based on predicted blood glucose, and can store and manage various information / data generated as the computing device (100) adjusts the insulin injection amount based on predicted blood glucose.

[0057] For example, the external server (400) may be a database server that stores information used in the predictive blood glucose-based insulin injection volume control method. As another example, the external server (400) may be a server that provides information used in the predictive blood glucose-based insulin injection volume control method.

[0058] The network (500) may refer to a connection structure capable of exchanging information between each node, such as computing devices, multiple terminals, and servers. For example, the network (500) includes a Local Area Network (LAN), a Wide Area Network (WAN), the World Wide Web (WWW), a wired and wireless data network, a telephone network, a wired and wireless television network, etc.

[0059] Wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0060]

[0061] FIG. 2 is a hardware configuration diagram of a computing device according to one embodiment of the present invention.

[0062] Referring to FIG. 2, a computing device (100) according to one embodiment of the present invention may include one or more processors (110), a memory (120) for loading a computer program (151) executed by the processor (110), a bus (130), a communication interface (140), and a storage (150) for storing the computer program (151). Here, FIG. 2 illustrates only the components related to the embodiment of the present invention. Therefore, a person skilled in the art to which the present invention pertains will understand that other general-purpose components may be included in addition to the components illustrated in FIG. 2.

[0063] The processor (110) controls the overall operation of each component of the computing device (100). The processor (110) may be composed of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of the computing device. Alternatively, it may be configured to include any type of processor well known in the art of the present invention.

[0064] Additionally, the processor (110) can perform operations for at least one application or program for executing the method according to embodiments of the present invention, and the computing device (100) may have one or more processors.

[0065] In various embodiments, the processor (110) may further include RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor (110). Additionally, the processor (110) may be implemented in the form of a system-on-chip (SoC) comprising at least one of a graphics processing unit, RAM, and ROM.

[0066] Memory (120) stores various data, instructions and / or information. Memory (120) may load a computer program (151) from storage (150) to execute a method / operation according to various embodiments of the present invention. When the computer program (151) is loaded into memory (120), the processor (110) may perform the method / operation by executing one or more instructions constituting the computer program (151). Memory (120) may be implemented as volatile memory such as RAM, but the technical scope of the present invention is not limited thereto.

[0067] The bus (130) provides communication functions between components of the computing device (100). The bus (130) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0068] The communication interface (140) supports wired and wireless internet communication of the computing device (100). Additionally, the communication interface (140) may support various communication methods other than internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the art of the present invention. In some embodiments, the communication interface (140) may be omitted.

[0069] Storage (150) can store a computer program (151) non-temporarily. When performing a process according to an embodiment of the present invention through a computing device (100), storage (150) can store various information necessary to perform a method according to the disclosed embodiment or to provide a service.

[0070] The storage (150) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0071] A computer program (151) may include one or more instructions that cause a processor (110) to perform a method / operation according to various embodiments of the present invention when loaded into memory (120). That is, the processor (110) may perform the method / operation according to various embodiments of the present invention by executing the one or more instructions.

[0072] In one embodiment, the computer program (151) may include one or more instructions to perform various methods related to various tasks related to learning a neural network model.

[0073] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0074] The components of the present invention may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors.

[0075]

[0076] FIGS. 3 to 8 are drawings for explaining a method for controlling insulin injection amount based on predicted blood glucose according to an embodiment of the present invention.

[0077] Referring to FIG. 3, the computing device (100) can predict future blood glucose values ​​based on current blood glucose values ​​and insulin injection history (S110).

[0078] Specifically, with reference to FIG. 4, the computing device (100) can obtain a current blood glucose value from a blood glucose measurement sensor attached to the user's body (S111).

[0079] For example, the computing device (100) can receive blood glucose sensor data collected in real time from a continuous glucose meter (i.e., a blood glucose measurement sensor) equipped in an artificial pancreas device (200) attached to the user's body at periodic intervals (e.g., every 5 minutes).

[0080] That is, the computing device (100) receives a blood glucose value transmitted from a blood glucose measurement sensor, stores it as a value reflecting the current blood glucose status, and can use it as input data for subsequent blood glucose prediction calculations.

[0081] Additionally, the computing device (100) can accumulate insulin injection data from an insulin injection pump attached to the user's body to generate an insulin injection history (S112).

[0082] For example, the computing device (100) can receive data on basal insulin injection volume recorded at regular time intervals from the insulin injection pump and bolus insulin injection volume manually requested by the user.

[0083] The computing device (100) can generate an insulin injection history that reflects the flow of insulin injection over a certain period by accumulating such insulin injection amount data in chronological order and mapping the time at which each injection amount was recorded together. Here, the insulin injection history can be used as an input value for a prediction model.

[0084] And, the computing device (100) can obtain future blood glucose values ​​by inputting current blood glucose values ​​and insulin injection data into a pre-trained neural network model (S113).

[0085] For example, a computing device (100) can take a sequence of blood glucose values ​​collected within a specific time range and an insulin injection history as input values, provide them to a prediction model composed of multiple neural network layers, and obtain future blood glucose levels after a certain period of time. Here, the neural network model may be designed to increase prediction accuracy by reflecting the temporal correlation between blood glucose and insulin, and the predicted future blood glucose values ​​may be used to determine whether there is a risk of hyperglycemia or hypoglycemia or to adjust the amount of insulin injected.

[0086] The neural network model of the present invention is composed of a structure combining a convolutional neural network and a recurrent neural network, and can be pre-trained based on preprocessed training data.

[0087] Accordingly, the computing device (100) can generate training data.

[0088] Specifically, the computing device (100) can pad the insulin injection data at the time when insulin injection was not performed with zeros, and synchronize the basal insulin injection data, bolus insulin injection data, and blood glucose values ​​on a time basis to generate merged data.

[0089] For example, the computing device (100) can perform time synchronization by aligning basal and bolus injection data existing within each time interval to the same reference time based on the collection cycle (e.g., 5-minute interval) of blood glucose values ​​collected from a continuous glucose meter, and assigning the value to 0 if there was no insulin injection at that time. In this process, each data is merged based on a common timestamp and can be composed of merged data in the form of a single time series.

[0090] In addition, the computing device (100) can extract merged data that has no omissions on a daily basis as training target data.

[0091] For example, the computing device (100) may include the data as a learning target only when blood glucose data, basal injection data, and bolus injection data all exist for a specific date, and exclude the data for that date when data for some time points has not been collected or is invalid, thereby preventing the learning quality from deteriorating. That is, the computing device (100) can increase the consistency and reliability of the training data by selectively extracting only complete data on a daily basis.

[0092] Additionally, the computing device (100) can generate training data by normalizing the training target data and removing duplicate data. And, the computing device (100) can pre-train a neural network model based on the training data.

[0093] For example, the computing device (100) can equalize the distribution of data by normalizing collected blood glucose values ​​and insulin injection data to a certain range (e.g., minimum-maximum). Additionally, if duplicate data collected at the same time exists due to communication errors of the continuous glucose meter, the computing device (100) can remove duplicate data according to a standard priority or a time-time duplicate removal standard. In this way, the normalized and refined training data can subsequently be used as input values ​​for a CNN-LSTM-based neural network model. In this case, the neural network model can obtain a parameter configuration optimized for future blood glucose prediction by learning the time-series correlation between blood glucose and insulin. By repeatedly training the neural network model using the training data configured in this manner, the computing device (100) can pre-configure the model to have generalized prediction performance for various user situations.

[0094] According to various embodiments of the present invention, a computing device (100) may define a correction factor for quantitatively adjusting the insulin injection amount in response to changes in blood glucose. Here, the correction factor is a value that numerically represents the expected reduction in blood glucose by a unit insulin injection, and may be an individualized parameter reflecting insulin sensitivity, metabolic response rate, lifestyle habits, etc., which differ for each user. Additionally, the correction factor may be used for classifying blood glucose status, calculating the corrective insulin (bolus) injection amount in case of hyperglycemia, setting safety boundaries, etc.

[0095] Specifically, referring to FIG. 5, the computing device (100) can recognize the amount of insulin injected into the user at a past point in time (S210).

[0096] More specifically, the computing device (100) can identify the injection dose and injection method (e.g., manual / automatic) at a given time point based on the time point when the bolus insulin was injected among the insulin injection history recorded over a certain period.

[0097] For example, the computing device (100) can extract insulin injection events by detecting a section in which the insulin dose injected at a specific point in time changes rapidly above a reference value (e.g., 0.3U or more) among the time series data recorded from the user's insulin pump, and can organize timestamp and injection amount information for each of these injection events and store them as an injection log.

[0098] Additionally, the computing device (100) can recognize changes in blood sugar corresponding to a past point in time (S220).

[0099] Specifically, the computing device (100) can numerically evaluate the effect of the insulin injection on the user's blood sugar by extracting blood sugar levels before and after the insulin injection time and calculating the degree of blood sugar reduction or rate of change over a certain time interval.

[0100] For example, the computing device (100) can compare the blood glucose value at a time immediately before insulin injection (e.g., time T) with the blood glucose value at a time after a certain period of time has elapsed since injection (e.g., T+60 minutes) to calculate the amount of blood glucose reduction in the form ΔBG = BG(T) - BG(T+60), and this ΔBG value can be used to define a correction factor later.

[0101] And, the computing device (100) can define a correction factor, which is the predicted blood glucose reduction amount for one unit of insulin injection, based on the insulin injection amount and blood glucose change (S230).

[0102] Specifically, the computing device (100) can calculate a value by dividing the decrease in blood glucose for each event by the corresponding injection amount based on the change in blood glucose corresponding to a plurality of injection events, and integrate this into an average or statistical correction method to set it as a correction coefficient.

[0103] For example, the computing device (100) can collect multiple samples in the form of ΔBG₁ / U₁, ΔBG₂ / U₂, ..., ΔBG / U, and then calculate a final correction factor through a simple average, moving average, or weighted average processing after outlier removal. This correction factor is a value that reflects the unique insulin sensitivity of the user and can subsequently be used to set blood glucose status classification boundaries and determine the bolus insulin injection amount.

[0104] In an additional embodiment, the computing device (100) can correct the correction factor by additionally utilizing the basal insulin injection history as well as the bolus injection history.

[0105] Specifically, the computing device (100) can recognize a pattern in which blood glucose changes gradually solely through basal injection in a stable state where external factors such as night, meals, or exercise are minimized, and can estimate the range of blood glucose change occurring per unit of basal injection amount. Additionally, the computing device (100) can assign additional weight to the correction coefficient calculated based on the bolus based on the range of blood glucose change occurring per unit of basal injection amount, or use it as a supplementary factor when calculating the correction coefficient for a user with insufficient bolus injection events.

[0106] For example, the computing device (100) can detect a time interval during which activity is relatively low and blood glucose changes due to meals do not occur, such as the user's sleep time, and then extract data on the amount of basal insulin injected and blood glucose changes during that interval. Subsequently, if the amount of basal insulin injected is constant within the same time interval, the computing device (100) can analyze the corresponding blood glucose reduction rate to estimate the amount of blood glucose change corresponding to a unit of basal insulin injection. The basal response coefficient calculated through this analysis reflects a smaller and milder response than a general correction coefficient, but for users who do not have enough bolus injection cases, it can be applied as a correction weight to increase reliability when calculating the correction coefficient.

[0107] For example, the computing device (100) can correct the correction factor by estimating that the change in blood glucose for 0.4 U of basal insulin is -10 mg / dL when a decrease in blood glucose of about 10 mg / dL is observed while 0.1 U / hr of basal insulin is injected at a constant rate for 4 hours at night, calculating a blood glucose response of about -25 mg / dL / U by converting this to 1 U, and then integrating it with the existing bolus-based correction factor. In this way, the computing device (100) can further increase the reliability of the correction factor by using basal insulin-based blood glucose response information.

[0108] Referring again to FIG. 3, the computing device (100) can determine a future blood glucose state based on a future blood glucose value and a predefined correction factor (S120). Here, the future blood glucose state refers to state information classified based on the blood glucose range where the predicted future blood glucose value is located, and can be classified into one of the categories of hypoglycemia, normal, or hyperglycemia depending on the predicted blood glucose level.

[0109] Specifically, referring to FIG. 6, the computing device (100) may define a value obtained by subtracting a specific ratio value of a correction factor from a lower limit value of a predefined normal blood glucose range as a reference value for hypoglycemia (S121). Here, the predefined normal blood glucose range may be set according to clinical standards or user settings, for example, a range of 100 mg / dL or more and 140 mg / dL or less. This is a range in which blood glucose levels are considered to remain stable during fasting and within 2 hours after a meal, and may be variably defined according to diabetes diagnostic guidelines or user custom settings.

[0110] For example, when the calibration factor is set to 20 mg / dL / U, the computing device (100) may use 6 mg / dL, which is 30% of the calibration factor, as a reference correction value. In this case, the reference value for hypoglycemia may be set to 94 mg / dL, which is the lower limit of the normal range (100 mg / dL) minus 6 mg / dL. That is, if the predicted future blood glucose value is less than 94 mg / dL, it may be determined to be in a hypoglycemic state.

[0111] Additionally, the computing device (100) may define a value obtained by adding a specific ratio value of a correction factor to the upper limit value of the normal blood glucose range as a high blood glucose reference value (S122).

[0112] For example, if the upper limit of the normal range is 140 mg / dL and 6 mg / dL, which is 30% of the correction factor, is added, the hyperglycemia threshold value is set to 146 mg / dL. Accordingly, if the predicted future blood glucose value exceeds 146 mg / dL, it may be classified as a hyperglycemic state.

[0113] And, the computing device (100) can determine a future blood sugar state that includes a future blood sugar value among a low blood sugar state corresponding to a low blood sugar reference value to a lower limit value, a normal state corresponding to a lower limit value to an upper limit value, and a high blood sugar state corresponding to an upper limit value to a high blood sugar reference value (S123).

[0114] For example, the computing device (100) may classify the future blood glucose state as normal if the future blood glucose value is 138 mg / dL, as this falls within the normal range (100 to 140 mg / dL), and as hypoglycemic if the future blood glucose value is 91 mg / dL, as this is lower than the hypoglycemic standard value (94 mg / dL). Additionally, the computing device (100) may determine the future blood glucose state as hyperglycemic if the future blood glucose value is 150 mg / dL, as this exceeds the hyperglycemic standard value (146 mg / dL).

[0115] In various embodiments, referring to FIG. 7, the computing device (100) may further subdivide each state of hypoglycemia, normal, and hyperglycemia into multi-stage detailed regions. For example, the hypoglycemia state may be divided into L1, L2, and L3, where the risk increases as the blood glucose value decreases, and the hyperglycemia state may be divided into H1, H2, H3, H4, etc., ranging from a mild increase to a high-risk state. These detailed regions may be divided based on a certain ratio of a correction factor or a fixed interval, and more precise blood glucose control may be possible by applying different insulin injection strategies according to each section.

[0116] Specifically, the computing device (100) can form multi-stage detailed regions by calculating a certain division unit based on a correction coefficient to set a detailed section of each state and arranging it at regular intervals around a reference value.

[0117] For example, the computing device (100) can define 6 mg / dL, which is 30% of the correction factor of 20 mg / dL / U, as a reference unit and extend this into continuous detailed intervals within each state.

[0118] For example, if the lower limit of the normal blood glucose range is 100 mg / dL and the hypoglycemic threshold is 94 mg / dL, the hypoglycemic state can be set by dividing the area below 94 mg / dL into three parts: L1: 94-88 mg / dL, L2: 88-82 mg / dL, and L3: less than 82 mg / dL. Similarly, if the upper limit of the normal range is 140 mg / dL and the hyperglycemic threshold is 146 mg / dL, the hyperglycemic state can be set by dividing the area corresponding to the range from the upper limit of the normal range to the hyperglycemic threshold (i.e., H1) into equal reference units (e.g., 6 mg / dL): H1: 140-146 mg / dL, H2: 146-152 mg / dL, H3: 152-158 mg / dL, etc. In addition, for the range exceeding 158 mg / dL, it can be further expanded to high-risk areas such as H4 and H5, and the setting method can be flexibly determined based on clinical judgment, user-customized settings, or algorithm-based automatic settings.

[0119] Meanwhile, the computing device (100) can use a predetermined insulin injection amount for each detailed area to adjust the insulin injection amount corresponding to that area as soon as it enters each blood glucose range. Through this, the computing device (100) can respond in real time to changes in blood glucose status and perform consistent injection control based on a quantified injection policy.

[0120] For example, the computing device (100) can be configured to increase the basal insulin injection amount by 10% when corresponding to the H1 range, and to additionally inject a corrected bolus insulin calculated based on a correction factor when entering a high-risk range corresponding to H2 or higher. As another example, the computing device (100) can apply a preset profile to reduce the basal injection amount by 50% when corresponding to L2 among the hypoglycemic sub-ranges, and to immediately stop the insulin injection when corresponding to L3.

[0121] This method has a faster response speed than a structure that makes dynamic decisions every time a threshold is exceeded, and can execute a predictable injection strategy based on set criteria, thereby providing users with a more stable and reliable blood glucose control effect.

[0122] In an additional embodiment, the computing device (100) can dynamically adjust the interval width by taking into account the blood glucose change trend over a certain period of time or the sensitivity history of each user when setting the detailed area.

[0123] Specifically, the computing device (100) can statistically evaluate how sensitively the user's blood glucose changes for the same amount of insulin injection based on the insulin injection history and the corresponding blood glucose response data recorded over a past period (e.g., the last 7 or 30 days).

[0124] For example, the computing device (100) can classify a user as a high-sensitivity user if the user generally shows a rapid blood glucose reduction response of 25 mg / dL or more for an insulin 1U injection, and can set the width of each detailed interval relatively narrow.

[0125] As another example, for a low-sensitivity user whose blood glucose changes less than 10 mg / dL for the same injection amount (i.e., 1 U of insulin), the computing device (100) can be adjusted so as not to overreact to small changes by setting the width of each detailed area wide.

[0126] Additionally, the computing device (100) may also incorporate behavioral data of a user whose blood glucose response characteristics vary depending on the time of day or lifestyle patterns (e.g., sleep, meals, exercise). For example, the computing device (100) may set high-risk low-glycemic zones such as L2 and L3 widely during nighttime, and set high-glycemic reserve response zones such as H1 and H2 densely during periods of high activity, thereby performing time-based zone adjustment. In this way, unlike the conventional method of applying uniform boundary values ​​based solely on blood glucose levels, the computing device (100) can perform blood glucose state classification optimized for the precision of zone setting and user specificity by comprehensively reflecting the rate of change in blood glucose, insulin response patterns, and daily behavioral information.

[0127] Referring again to FIG. 3, the computing device (100) can adjust the amount of insulin injected to correspond to a future blood glucose state (S130).

[0128] Specifically, referring to FIG. 8, the computing device (100) can reduce the insulin injection amount by a predetermined rate when the future blood glucose state is a hypoglycemic state (S131).

[0129] More specifically, the computing device (100) can stop insulin injection if the future blood glucose value falls into the lowest area among the detailed areas included in the hypoglycemic state.

[0130] For example, if the computing device (100) determines that the predicted future blood glucose value is less than 75 mg / dL, it recognizes that the value corresponds to a predefined L3 range and can transmit a control signal to the artificial pancreas device (200) to temporarily stop even the basal insulin injection to minimize the risk of hypoglycemia.

[0131] The judgment of stopping the injection of such a computing device (100) corresponds to PLGS (Predictive Low Glucose Suspend) or LGS (Low Glucose Suspend), and if it is predicted that the blood glucose level will drop below a certain level or if it is already in a hypoglycemic state, the insulin injection can be stopped preemptively to prevent the worsening of hypoglycemia.

[0132] Meanwhile, the computing device (100) can reduce the insulin injection amount by a predetermined rate if the future blood glucose value is included in a different sub-region other than the lowest region.

[0133] For example, when the predicted blood glucose value is lower than the hypoglycemic threshold, such as 85 mg / dL, but higher than L3, the computing device (100) can respond to the risk of hypoglycemia by reducing the currently set basal insulin injection amount by a certain level (e.g., 50% to 75%). This reduction in injection amount can prevent the progression of hypoglycemia due to insulin accumulation and, by avoiding a complete cessation, allow the blood glucose to return to the normal range.

[0134] Additionally, the computing device (100) can maintain the insulin injection amount when the future blood glucose state is a normal state (S132).

[0135] For example, the computing device (100) can control the current insulin injection state to continue without any increase or decrease when the predicted blood glucose value is within the normal range (e.g., 100 to 140 mg / dL), such as 110 mg / dL. In this case, since it is determined that the blood glucose is being maintained stably, additional adjustment of the injection amount is omitted, and a blood glucose prediction can be performed again after a certain period of time.

[0136] Additionally, the computing device (100) can increase the insulin injection amount by a predetermined rate if the future blood sugar state is a high blood sugar state (S133).

[0137] Specifically, the computing device (100) can adjust the insulin injection amount to add a bolus insulin injection amount calculated based on a correction factor when the future blood glucose value falls into a predefined high-risk area (e.g., H2 or higher) among a plurality of detailed areas included in a high blood glucose state.

[0138] For example, if the predicted blood glucose value is 175 mg / dL or higher, the computing device (100) determines that the value belongs to the H2 or higher range, and if the user's correction factor is set to 20 mg / dL / U and the target blood glucose is 130 mg / dL, it can transmit a control command to the artificial pancreas device (200) to inject additional bolus insulin calculated as (175-130) / 20 = 2.25U. The amount of injection calculated here can be used to set a safe injection upper limit by considering the user's situation or previous injection history, and additional control can be performed, such as rounding to 2U or splitting the injection if necessary.

[0139] Accordingly, the computing device (100) of the present invention can provide an automatic insulin injection control function that classifies predicted blood glucose values ​​into intervals according to quantitative criteria and applies different response strategies according to each state and detailed area, thereby avoiding hypoglycemia and hyperglycemia and maintaining blood glucose within a stable range. Through this, the user can receive a safer and more precise blood glucose management service and reduce the inconvenience of manual operation and the risk associated with blood glucose fluctuations.

[0140] According to various embodiments of the present invention, a computing device (100) can detect a blood glucose spike based on the change amount of each of the current blood glucose value (i.e., sensor blood glucose value) and future blood glucose value (i.e., estimated blood glucose value) obtained in step (S110). And, when a blood glucose spike is detected, the computing device (100) can increase the basal insulin injection amount or inject insulin corresponding to the correction bolus.

[0141] Specifically, the computing device (100) can merge and analyze blood sugar change-related indicators of different natures to determine whether there is a blood sugar spike.

[0142] For example, a computing device (100) can detect a surge in blood glucose based on the change in the sensor blood glucose value (e.g., ΔBG_sensor), the change in the estimated blood glucose value (e.g., ΔBG_predicted), and the acceleration of the sensor blood glucose value (e.g., d²BG_sensor / dt²). Here, each variable can be quantified by approximating the derivative coefficient using a three-point backward difference method within a certain time interval, or by correcting noise through a Kalman filter.

[0143] And, the computing device (100) can independently determine whether each of the predefined threshold values ​​of each variable (e.g., sensor change amount > 2.0 mg / dL / min, predicted change amount > 1.8 mg / dL / min, sensor acceleration > 0.4 mg / dL / min²) is exceeded. In this case, if two or more of the three variables simultaneously exceed the threshold value, the computing device (100) determines that point in time as a state of rapid blood glucose increase. In this way, the computing device (100) utilizes multiple conditions to prevent misjudgment caused by temporary outliers or prediction noise of a single indicator, and can more precisely detect the actual danger zone where blood glucose rises rapidly.

[0144] Accordingly, the computing device (100) can determine whether there is a rapid increase in blood glucose through a complex condition that considers not only the blood glucose prediction result but also the measurement-based change amount and acceleration, and can increase the reliability of the clinical response during the rapid increase in blood glucose by preemptively adjusting the insulin injection amount, such as correcting the bolus injection, increasing the basal injection amount, or blocking entry into a high-risk state, only when the condition is met.

[0145]

[0146] According to an additional embodiment of the present invention, the computing device (100) can adjust the amount of insulin injected according to the user's physiological context and behavioral patterns as well as time series data analysis in a blood glucose prediction-based insulin injection control process.

[0147] Specifically, the computing device (100) can additionally analyze daily behavior data (e.g., sleep time, meal time, exercise frequency, stress response, etc.) collected from a user terminal (300) or a wearable device linked to the user terminal (300), in addition to insulin injection history and blood glucose change information.

[0148] More specifically, the computing device (100) can quantitatively calculate the change in blood glucose and the amount of insulin injected before and after the corresponding time period based on the time of occurrence of events such as sleep, exercise, and meal, and can numerically compare the difference in blood glucose response at different time points for the same amount of insulin injected.

[0149] For example, the computing device (100) can numerically calculate the relative insulin sensitivity during exercise by calculating the value obtained by dividing the change in blood glucose within 2 hours immediately after exercise by the insulin injection amount, and the value obtained by dividing the change in blood glucose under the same conditions at rest by the insulin injection amount. At this time, the response value for each condition is stored as an independent correction coefficient candidate, and the computing device (100) can correct the insulin injection amount by reflecting a suitable correction coefficient depending on the situation or by assigning a weight corresponding to the correction coefficient according to the situation.

[0150] For example, if the computing device (100) confirms that the user injected 2U of insulin immediately after exercise and the blood glucose level decreased by 60 mg / dL, it can calculate the sensitivity as approximately 30 mg / dL per 1U of insulin under exercise conditions. Additionally, if the computing device (100) only decreased by 30 mg / dL with the injection of 2U under rest conditions, it can calculate the sensitivity as 15 mg / dL / U under rest conditions. The sensitivity values ​​calculated in this way are tagged and stored by situation, and the computing device (100) can refer to the corresponding correction factor and apply it to the calculation of the injection amount when the same situation is detected later.

[0151] Accordingly, the computing device (100) can adjust the insulin injection amount for each situation based on data that quantitatively calculates and classifies insulin response characteristics for each behavioral event, and can determine a more accurate and safe insulin injection amount based on a wider variety of conditions rather than a single standard.

[0152]

[0153] Meanwhile, embodiments according to the present disclosure may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include, but is not limited to, magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, and flash memory.

[0154] Meanwhile, the above computer program may be one specifically designed and configured for the present disclosure or one known and available to those skilled in the art of computer software. Examples of computer programs may include machine code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0155] According to one embodiment, the method according to various embodiments of the present disclosure may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0156] Unless explicitly stated otherwise, the steps constituting the method according to the present disclosure may be performed in a suitable order. The present disclosure is not necessarily limited by the order in which the steps are described. The use of any examples or exemplary terms (e.g., etc.) in the present disclosure is merely for the purpose of describing the present disclosure in detail and, unless limited by the claims, the scope of the present disclosure is not limited by such examples or exemplary terms. Furthermore, those skilled in the art will understand that various modifications, combinations, and changes may be made according to design conditions and factors within the scope of the claims or equivalents to which they are added.

[0157] Accordingly, the scope of the present disclosure should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the scope of the present disclosure.

Claims

1. A method performed by a computing device comprising at least one processor, A step of predicting future blood glucose values ​​based on current blood glucose values ​​and insulin injection history; A step of determining a future blood glucose state based on the above future blood glucose value and a predefined correction factor; and A step of adjusting the insulin injection amount to correspond to the future blood glucose state; including, Predicted blood glucose-based insulin injection dosage control method.

2. In Paragraph 1, The step of predicting future blood glucose values ​​based on the above current blood glucose values ​​and insulin injection history is, A step of obtaining the current blood glucose value from a blood glucose measurement sensor attached to the user's body; A step of accumulating insulin injection data of an insulin injection pump attached to the body of the user to generate the insulin injection history; and A step of obtaining the future blood glucose value by inputting the current blood glucose value and the insulin injection data into a pre-trained neural network model; including, Predicted blood glucose-based insulin injection dosage control method.

3. In Paragraph 2, The above neural network model is, It is composed of a structure combining convolutional neural networks and recurrent neural networks, is pre-trained based on preprocessed training data, and The above method is, A step of padding insulin injection data at the time when insulin injection was not performed with zeros, and generating merged data by synchronizing basal insulin injection data, bolus insulin injection data, and blood glucose values ​​based on time; A step of extracting merged data with no omissions on a daily basis as training data; A step of normalizing the training target data and removing duplicate data to generate the training data; and A step of pre-training the neural network model based on the above training data; including, Predicted blood glucose-based insulin injection dosage control method.

4. In Paragraph 1, The above method is, Step of defining the above correction coefficient; Includes more, The step of defining the above correction coefficient is, A step of recognizing the amount of insulin injected into the user at a past point in time; A step of recognizing a change in blood glucose corresponding to the above past point in time; and A step of defining the correction factor, which is the predicted blood glucose reduction amount resulting from the injection of one unit of insulin, based on the insulin injection amount and the blood glucose change; including, Predicted blood glucose-based insulin injection dosage control method.

5. In Paragraph 1, The step of determining a future blood glucose state based on the above future blood glucose value and a predefined correction factor is, A step of defining a hypoglycemia reference value by subtracting a specific ratio value of the correction factor from the lower limit value of a predefined normal blood glucose range; A step of defining a high blood sugar reference value by adding a specific ratio value of the correction factor to the upper limit value of the normal blood sugar range; and A step of determining a state including the future blood glucose value among the hypoglycemic state corresponding to the hypoglycemic reference value to the lower limit value, the normal state corresponding to the lower limit value to the upper limit value, and the hyperglycemic state corresponding to the upper limit value to the hyperglycemic reference value as the future blood glucose state; including, Predicted blood glucose-based insulin injection dosage control method.

6. In Paragraph 5, The step of adjusting the insulin injection amount to correspond to the future blood glucose state is: If the above future blood glucose state is the above hypoglycemic state, a step of reducing the insulin injection amount by a predetermined ratio; If the future blood glucose state is the normal state, a step of maintaining the insulin injection amount; or If the future blood glucose state is the hyperglycemia state, a step of increasing the insulin injection amount by a predetermined ratio; including, Predicted blood glucose-based insulin injection dosage control method.

7. In Paragraph 6, If the above future blood glucose state is the above hypoglycemia state, the step of reducing the insulin injection amount by a predetermined ratio is A step of stopping insulin injection if the future blood glucose value falls within the lowest region among the detailed regions included in the hypoglycemic state; or If the above future blood glucose value falls within a sub-region other than the above lowest region, a step of reducing the insulin injection amount by a predetermined ratio; including, Predicted blood glucose-based insulin injection dosage control method.

8. In Paragraph 6, If the above future blood glucose state is the above hyperglycemia state, the step of increasing the insulin injection amount by a predetermined ratio is A step of adjusting the insulin injection amount to add a bolus insulin injection amount calculated based on the correction factor when the future blood glucose value is included in a predefined high-risk area among a plurality of detailed areas included in the hyperglycemic state; including, Predicted blood glucose-based insulin injection dosage control method.

9. Memory for storing one or more instructions; and A processor that executes one or more instructions stored in the memory. Including, The above processor executes the above one or more instructions, A device that performs the method of claim 1.

10. A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method of claim 1.

Images