Insulin dose fuzzy control method fusing emotion and motion information

Abstract

The invention discloses an insulin dosage fuzzy control method fusing emotion and motion information, and belongs to the technical field of diabetes insulin treatment, and the method comprises the following steps: S1, estimating an emotion state and motion intensity; s2, calculating the current insulin dosage; s3, the structure of a fuzzy controller is determined, input and output fuzzy distribution with the emotional state and the exercise intensity information as input and the insulin dosage adjustment step length as output is defined, and the membership degree of the input relative to different fuzzy subsets is calculated; s4, establishing a fuzzy rule; and S5, performing fuzzy logic reasoning to obtain the output of the fuzzy system, and multiplying the output by the insulin dosage obtained in the step S2 to determine the final insulin dosage. According to the insulin dosage fuzzy control method fusing emotion and motion information, a more personalized and dynamic insulin administration strategy can be realized, a more reasonable insulin dosage can be decided, and the blood glucose management effect of a patient can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of insulin treatment for diabetes, and in particular to a fuzzy control method for insulin dosage integrating emotion and motion information. Background Art

[0002] Insulin decision-making is a key link in diabetes blood sugar management. It involves a detailed assessment of the patient's condition, setting treatment goals, choosing insulin dosage forms, adjusting dosages, and personalizing the regimen. There are various insulin treatment options, which are selected based on the patient's specific needs and conditions. Basal insulin is suitable for patients with type 2 diabetes who have poor fasting blood sugar control, especially those who have failed to reach the target using oral hypoglycemic drugs. Long-acting insulin analogs such as glargine or degludec are often used to maintain basal insulin levels throughout the day and are usually injected before bedtime. Pre-meal insulin: For post-meal blood sugar control, short-acting or rapid-acting insulins such as aspart insulin and lispro insulin are injected before meals to quickly reduce post-meal blood sugar peaks.

[0003] Insulin dose adjustment is a dynamic process that requires regular monitoring of blood sugar and adjustment based on the results. The adjustment frequency is usually once every 3-5 days, with each adjustment amount being 1-4 units until blood sugar reaches the target range. Adjustments are based on blood sugar levels at different time points, including fasting blood sugar, postprandial blood sugar, and bedtime blood sugar, as well as whether hypoglycemia events occur. If the patient's lifestyle changes, weight fluctuates, or encounters stressful situations, the dose needs to be adjusted accordingly. In some cases, it may be necessary to switch from one insulin regimen to another to better match the patient's current blood sugar control needs.

[0004] The patient's metabolism and physical activity have a significant impact on the dynamic changes in glucose levels and insulin requirements. Many patients with type 1 diabetes experience hypoglycemia during or after exercise, and physiological stress activities can also increase the risk of hypoglycemia. Specifically, aerobic exercise can increase glucose uptake by 1.5 to 10 times the resting rate, depending on the duration and intensity of the exercise. Moderate-intensity exercise causes a sharp increase in skeletal muscle demand for glucose, which is matched by an increase in liver glucose production. During high-intensity aerobic and anaerobic exercise, liver glucose production may exceed muscle glucose utilization, causing an individual's glucose level to rise sharply. In addition, psychological and emotional changes can activate the hypothalamic-pituitary-adrenal axis and the sympathetic nervous system, leading to the release of stress hormones such as adrenaline, glucagon, and growth hormone, affecting blood glucose metabolism.

[0005] In the daily life of diabetic patients, the randomness of lifestyle causes the above factors to have coupled and variable effects on blood glucose metabolism, making it difficult to accurately capture changes in insulin demand. Therefore, studying the optimization of insulin dosage decisions that integrates emotion and exercise information is of great significance to improving patients' blood glucose management performance.

[0006] According to investigation and understanding, the currently disclosed prior arts are as follows:

[0007] The invention patent with patent application publication number CN201980042748.9 discloses a system for providing dosage recommendations for basal insulin titration, which uses individualized control targets, historical blood glucose monitoring and insulin injection information to adjust the basal dose; the invention patent with patent application publication number CN201910310314.4 discloses a method and system for selecting insulin dosage forms and adjusting dosages, and provides an insulin dosage adjustment model based on the medical records of patients with type 2 diabetes combined with the Xgboost machine learning model; the invention patent with patent application publication number CN109564775A discloses a system and method for optimizing mealtime insulin dosage, and provides a system and method for adjusting the short-acting dosage of the subject's expected meals using the insulin infusion data recorded in the insulin pen.

[0008] The invention patent with the patent application publication number CN202010930702.5 discloses a pre-meal insulin dosage individualized decision-making system based on Gaussian process. The system uses historical blood sugar management information to establish a post-meal blood sugar prediction model, designs a risk-sensitive control framework, and completes the pre-meal insulin dosage decision; the invention patent with the patent application publication number CN202110117772.3 discloses an expert experience-assisted pre-meal insulin dosage learning optimization decision-making system based on the above patents, which can evaluate the credibility of Gaussian process regression prediction of post-meal blood sugar under a small number of samples and decide whether to assist with expert decision-making. However, none of the above patents consider how to effectively integrate emotional and exercise status information to improve the accuracy of insulin dosage decisions, thereby improving blood sugar management in diabetic patients. Summary of the invention

[0009] The purpose of the present invention is to provide a fuzzy control method for insulin dosage that integrates emotion and motion information, which can realize a more personalized and dynamic insulin administration strategy, decide on a more reasonable insulin dosage, and improve the patient's blood sugar management effect.

[0010] To achieve the above object, the present invention provides a fuzzy control method for insulin dosage integrating emotion and motion information, comprising the following steps:

[0011] S1, estimate emotional state and exercise intensity through the photoelectric volume pulse wave signal and three-axis acceleration signal collected from the wristband sensor;

[0012] S2, calculate the current insulin dose;

[0013] S3, determining the structure of the fuzzy controller, defining the input-output fuzzy distribution with the emotional state and exercise intensity information as input and the insulin dosage adjustment step as output, and calculating the membership degree of the input relative to different fuzzy subsets;

[0014] S4, establish fuzzy rules;

[0015] S5. Perform fuzzy logic reasoning to obtain the output of the fuzzy system, and multiply the output by the insulin dose obtained in step S2 to determine the final insulin dose.

[0016] Preferably, step S1 is divided into two parts, using photoplethysmography signals to evaluate emotional state and using triaxial acceleration to evaluate motion state;

[0017] S101, Photoplethysmography signals reflect the beating of the heart by detecting small changes in the volume of blood in the skin;

[0018] Specifically: by analyzing the characteristics of the pulse wave signal, mainly the time domain characteristics, frequency domain characteristics and nonlinear characteristics, the key features for emotion classification are formed; these key features are modeled using the support vector machine algorithm to achieve emotion classification, mainly including stress state and non-stress state. The Gaussian kernel function is selected as the kernel function of the support vector machine. The Gaussian kernel function maps the low-dimensional input space to the high-dimensional feature space, overcoming the limitations of the linear model. The filtered features are input into the classifier model to obtain the estimated emotional state of the human body;

[0019] S102, evaluating the motion state specifically includes:

[0020] First, the three-axis acceleration data is preprocessed;

[0021] Secondly, the data needs to be organized into time windows of fixed length. The data points in each window constitute a sample for training and testing the CNN model. In the design of the CNN model, a network architecture including a one-dimensional convolutional layer, a pooling layer, and a fully connected layer is designed.

[0022] Finally, the CNN model is used to classify exercise intensity, including running, walking, and resting.

[0023] Preferably, step S2 specifically comprises: using historical blood glucose concentrations, meal information and insulin dosages, combined with current blood glucose monitoring and dietary intake information, and calculating the current insulin dosage based on the doctor's clinical strategy or decision algorithm.

[0024] Preferably, the main components of the fuzzy controller in step S3 are described as follows:

[0025] The input is the historical emotional state and exercise intensity information. The input is fuzzified and the historical emotional state and exercise intensity at 8 moments in the evaluation period T = 15 minutes are selected. That is, only the emotional state and exercise intensity within 2 hours of the current insulin decision may have an impact on the current insulin dosage decision. The historical emotional state x1 and exercise intensity sequence x2 are expressed by the following formula:

[0026] x1=[m0,m1,m2,m3,m4,m5,m6,m7]

[0027] x2=[n0,n1,n2,n3,n4,n5,n6,n7]

[0028] Among them, m i Indicates the emotional state of the ith period from the current time. If it is a stress state, the value is 1, and if it is a non-stress state, the value is 0; n i Indicates the exercise intensity of the i-th cycle from the current time. If it is in the running state, the value is 2; if it is in the walking state, the value is 1; if it is in the resting state, the value is 0;

[0029] The corresponding weight matrices of the 8 historical emotional states and exercise intensities are set as follows:

[0030] w=[w0,w1,w2,w3,w4,w5,w6,w7]

[0031] Among them, w0 and w7 are 1, w1 and w6 are 2, w2 and w5 are 3, and w3 and w4 are 4;

[0032] Define the contribution of historical emotional state to current blood sugar as h1=5x1*w T , the contribution of historical exercise intensity to current blood sugar is h2=2.5x2*w T .

[0033] Preferably, in step S3, the impact contribution value is fuzzified, and the fuzzy sets are respectively defined as {more stress, more stress, medium stress, less stress, less stress} and {high exercise intensity, higher exercise intensity, medium exercise intensity, lower exercise intensity, low exercise intensity}, and a triangular membership function is used, whose input is the impact contribution value;

[0034] The output of the fuzzy controller is the dosage adjustment percentage, which is used to adjust the insulin dosage calculated in step S2; the percentage is controlled in the range of [0,150], and the fuzzy set of the change in insulin dosage demand after considering the emotion and exercise information is defined as {more insulin dosage, more insulin dosage, medium insulin dosage, less insulin dosage, less insulin dosage}, and a triangular membership function is used, whose input is the normalized dosage adjustment percentage.

[0035] Preferably, the fuzzy rule in step S4 is as follows:

[0036] S401, the more stressed one is in the fuzzy subset with the largest membership degree confirmed according to the historical emotional state contribution value, the greater the impact of the emotional state on blood sugar (the faster the blood sugar drops), and the less insulin dose is needed;

[0037] S402. The more intense the exercise intensity is in the fuzzy subset with the largest membership determined according to the historical exercise intensity contribution value, the greater the effect of the exercise intensity on blood sugar (the faster the blood sugar drops), and the less insulin dose is needed.

[0038] Preferably, the fuzzy logic reasoning in step S5 adopts the Mamdani method, and the fuzzy results output by each rule are aggregated based on the minimum-maximum reasoning using the fuzzy rules in step S4 to obtain the final fuzzy set, which is then defuzzified to obtain the final output.

[0039] Preferably, the maximum membership method is used for defuzzification, and the normalized insulin dosage adjustment percentage calculated by the maximum membership method is denoted as y max , the final insulin dose injected is:

[0040]

[0041] in, is the insulin dose calculated in step S2, and λ=0.67 is the denormalization coefficient.

[0042] Therefore, the present invention adopts the above-mentioned insulin dosage fuzzy control method that integrates emotion and movement information to achieve a more personalized and dynamic insulin administration strategy, and decide on a more reasonable insulin dosage, thereby improving the patient's blood sugar management effect.

[0043] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a method framework diagram of an embodiment of a method for fuzzy control of insulin dosage integrating emotion and motion information of the present invention;

[0045] Figure 2 This is a schematic diagram of clinical data verification of a certain type 1 diabetes patient provided by the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0047] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0048] Embodiment 1

[0049] like Figure 1 As shown, the present invention provides an insulin dosage fuzzy control method integrating emotion and motion information, including an emotion and motion state evaluation module, an insulin dosage decision module, and a fuzzy control-based decision dosage adjustment module. At the same time, each parameter in the present invention is determined based on the clinical experience of doctors and clinical data of diabetic patients using multiple daily insulin injection therapy in hospitals.

[0050] The emotion and motion state assessment module mainly uses the photoplethysmographic signal and three-axis acceleration signal collected from the wristband sensor to estimate the emotional state and motion intensity respectively.

[0051] For emotional state assessment, first, by analyzing the characteristics of the pulse wave signal, mainly the time domain characteristics, frequency domain characteristics and nonlinear characteristics, key features for emotion classification are formed. This embodiment selects 32 feature forms. For detailed descriptions, please refer to the invention patent with patent application publication number CN202410448222.3. Then, these features are modeled using the support vector machine algorithm to achieve emotion classification, mainly including stress state and non-stress state. The Gaussian kernel function is selected as the kernel function of the support vector machine. The Gaussian kernel function maps the low-dimensional input space to the high-dimensional feature space, overcoming the limitations of the linear model. The screened features are input into the trained classifier model to obtain the estimated human emotional state.

[0052] For exercise intensity assessment, the three-axis acceleration data is first preprocessed. The original acceleration data usually contains noise, and high-frequency interference needs to be removed by low-pass filtering. Secondly, the data needs to be organized into time windows of fixed length. The data points in each window constitute a sample for training and testing the CNN model. This embodiment selects a time window of 4 seconds in length and performs operations such as resampling and normalization on the data in the window. In the design of the CNN model, considering the spatiotemporal characteristics of the acceleration data, a network architecture including a one-dimensional convolutional layer, a pooling layer, and a fully connected layer is designed, and cross-validation is used to evaluate the generalization ability of the model. In this embodiment, the cross entropy function is used as the loss function and the Adam optimizer is used as the gradient optimizer. Finally, the CNN model is used to implement exercise intensity classification, which mainly includes three categories: running, walking, and resting.

[0053] The insulin dosage decision module uses historical blood glucose concentration, meal information and insulin dosage, combined with current blood glucose monitoring and meal information, to calculate the current insulin dosage based on the doctor's clinical strategy or decision algorithm. This embodiment uses a data-driven decision algorithm to complete insulin dosage decisions, see the invention patent with patent number CN202110117772.3 for details.

[0054] The decision-making dosage adjustment module based on fuzzy control mainly completes the design of the fuzzy controller, whose input is the historical emotional state and exercise intensity information, and the output is the insulin dosage adjustment percentage. First, the historical emotional state and exercise intensity at 8 moments in the evaluation period T = 15min are selected, that is, only the emotional state and exercise intensity within 2h of the current insulin decision may have an impact on the insulin dosage decision this time. The historical emotional state x1 and exercise intensity sequence x2 can be expressed by the following formula:

[0055] x1=[m0,m1,m2,m3,m4,m5,m6,m7],

[0056] x2=[n0,n1,n2,n3,n4,n5,n6,n7],

[0057] Where m i Indicates the emotional state of the ith period from the current time. If it is a stress state, the value is 1, and if it is a non-stress state, the value is 0. i Indicates the exercise intensity of the i-th cycle from the current time. If it is a running state, the value is 2; if it is a walking state, the value is 1; if it is a resting state, the value is 0.

[0058] The effects of emotions and exercise status on blood sugar are not immediately visible, but there is a significant delay. This delayed effect reflects the complexity and long-term response characteristics of the human body's physiological regulation mechanism. When an individual experiences emotional stress, the body immediately releases stress hormones such as cortisol and adrenaline. These hormones affect blood sugar in the body with a significant lag. For the current moderate to high-intensity exercise, since it takes a corresponding delay time to act on the blood sugar system, the drop in blood sugar levels will not be observed immediately. Therefore, for the historical emotional state and exercise intensity, the impact on blood sugar levels is not positively correlated. According to the empirical formula, the corresponding weight matrix of the 8 historical emotional states and exercise intensities is set as follows:

[0059] w=[w0,w1,w2,w3,w4,w5,w6,w7],

[0060] Among them, w0 and w7 are 1, w1 and w6 are 2, w2 and w5 are 3, and w3 and w4 are 4.

[0061] Furthermore, the contribution of historical emotional state to current blood sugar is defined as h1=5x1*w T , the contribution of historical exercise intensity to current blood sugar is h2=2.5x2*w T .

[0062] The influence contribution value is fuzzified as follows. For the emotional state and exercise state, the fuzzy sets are defined as {more stress, more stress, moderate stress, less stress, less stress} and {high exercise intensity, higher exercise intensity, moderate exercise intensity, lower exercise intensity, low exercise intensity}, respectively. The triangular membership function is used to determine the membership of the influence contribution value in each fuzzy set. The specific form is as follows:

[0063] The emotional state membership function is:

[0064] Less stressful situations:

[0065]

[0066] Less stressful situations:

[0067]

[0068] Moderate stress:

[0069]

[0070] More stressful situations:

[0071]

[0072] Many stressful situations:

[0073]

[0074] Where x is the contribution value of the historical emotional state to the current blood sugar, and y1, y2, y3, y4, and y5 are the membership degrees in different fuzzy subsets (few stressful situations, few stressful situations, moderate stressful situations, more stressful situations, and more stressful situations) under the corresponding contribution values ​​of the historical emotional state to the current blood sugar.

[0075] The exercise intensity membership function is:

[0076] Low intensity exercise:

[0077]

[0078] Lower intensity exercise:

[0079]

[0080] Moderate intensity exercise:

[0081]

[0082] Higher intensity exercise:

[0083]

[0084] High intensity exercise:

[0085]

[0086] Where x is the contribution value of historical exercise intensity to current blood sugar, and y1, y2, y3, y4, and y5 are the membership degrees in different fuzzy subsets (low exercise intensity, low exercise intensity, medium exercise intensity, high exercise intensity, and high exercise intensity) under the corresponding contribution values ​​of historical exercise intensity to current blood sugar.

[0087] In this embodiment, the output percentage is controlled within the range of [0,150], and the corresponding fuzzy set is defined as {high insulin dose, high insulin dose, medium insulin dose, low insulin dose, low insulin dose}, and a triangular membership function is used, as follows:

[0088] Low insulin dose:

[0089]

[0090] Lower insulin doses:

[0091]

[0092] Moderate insulin doses:

[0093]

[0094] Higher insulin doses:

[0095]

[0096] Insulin dose:

[0097]

[0098] Where x is the normalized dosage adjustment percentage, and y1, y2, y3, y4, and y5 are the membership degrees of the model output results in different fuzzy subsets (small insulin dosage, less insulin dosage, medium insulin dosage, more insulin dosage, and more insulin dosage).

[0099] According to the input and output of the above fuzzy controller and combined with the doctor's experience and knowledge in the field of blood sugar regulation, the following fuzzy rules are set:

[0100] 1) The more stressed one is in the fuzzy subset with the largest membership degree confirmed by the historical emotional state contribution value, the greater the impact of emotional state on blood sugar (the faster blood sugar drops), and the less insulin dose is needed;

[0101] 2) The more intense the exercise intensity is in the fuzzy subset with the largest membership confirmed by the historical exercise intensity contribution value, the greater the impact of the exercise intensity on blood sugar (the faster the blood sugar drops), and the less insulin dose is needed.

[0102] The rule base is a collection of all designed fuzzy rules, which represents a complete knowledge base of the control strategy. According to the above fuzzy rules, the present invention sets a fuzzy control rule base as shown in Table 1 for insulin dosage decision-making in combination with historical emotional state and exercise intensity.

[0103] Table 1 Fuzzy control system rules table

[0104]

[0105] Fuzzy reasoning is based on the current input fuzzy set and rule base to perform fuzzy logic reasoning. Commonly used reasoning methods include the Mamdani method and the Tsukamoto method. The Mamdani method combines the outputs of all rules by "maximum membership", that is, each output dimension takes the maximum membership of all rules. The Tsukamoto method is more inclined to mathematical operations and directly operates on the membership function. The result of this stage is a composite fuzzy set of one or more output variables, which represents the combined influence of all activated rules.

[0106] In this embodiment, the Mamdani method is used. After the membership of the current historical emotional state and exercise intensity to each fuzzy subset is known, the fuzzy results output by each rule are aggregated based on the minimum-maximum (Min-Max) reasoning using the rule base in Table 1 to obtain the final output membership function, which is specifically in the following form:

[0107]

[0108] Where i = 1, 2, ..., N; N is the total number of fuzzy rules in Table 1; The current historical emotional state input in the i-th rule belongs to the emotional state fuzzy subset A i The degree of membership; The input current historical motion intensity in the i-th rule belongs to the motion intensity fuzzy subset B i The membership degree of Ci (x) is the relative percentage of the corresponding output insulin dose belonging to the insulin dose adjustment fuzzy subset C i The degree of membership.

[0109] Then, defuzzification is performed to obtain the final output. In this embodiment, the maximum membership method is used for defuzzification, that is, the central value of the fuzzy set with the largest membership is selected as the final output, which is the normalized insulin dosage adjustment percentage, recorded as y max , then the final insulin dose injected by the patient is

[0110]

[0111] in is the insulin dosage recommended by the insulin dosage decision module, and λ=0.67 is the denormalization coefficient.

[0112] Finally, using the clinical data of a patient with type 1 diabetes who was treated with MDI in a hospital, this paper describes the insulin dosage decision-making scenario that integrates emotion and exercise information and how this embodiment improves the decision-making performance. For the specific steps of conducting retrospective insulin dosage decision-making, please refer to the invention patent with patent number CN202110117772.3.

[0113] In addition, during the treatment process, this embodiment will synchronously collect the patient's historical photoplethysmographic pulse wave signal and triaxial acceleration signal through the bracelet, and use the method provided by this embodiment to complete the insulin dosage decision, and at the same time compare it with the decision-making method that does not consider emotion and movement information (i.e., the method provided by the invention patent with patent number CN202110117772.3). The comparison results are as follows: Figure 2 shown.

[0114] from Figure 2 It can be seen that when the patient does not exercise and has little emotional stress, compared with the decision-making method that does not consider emotional and exercise information, this embodiment will recommend a higher insulin dose based on the current blood sugar level, which can effectively reduce postprandial hyperglycemia.

[0115] When the patient's exercise intensity is high and emotional stress is high, this embodiment will recommend a smaller insulin dose compared to a decision method that does not consider emotional and exercise information, which helps reduce subsequent hypoglycemia events. Figure 2 It can be seen that after effectively evaluating the patient's exercise intensity and emotional state, this embodiment will decide on a more reasonable insulin dosage and improve the patient's blood sugar management effect.

[0116] It is worth noting that the contents not elaborated in detail in the present invention are all prior art and are well known to those skilled in the art.

[0117] Therefore, the present invention adopts the above-mentioned insulin dosage fuzzy control method that integrates emotion and movement information to achieve a more personalized and dynamic insulin administration strategy, and decide on a more reasonable insulin dosage, thereby improving the patient's blood sugar management effect.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A fuzzy control method for insulin dosage integrating emotion and motion information, characterized in that: The following steps are involved: S1, estimate emotional state and exercise intensity through the photoelectric volume pulse wave signal and three-axis acceleration signal collected from the wristband sensor; S2, calculate the current insulin dose; S3, determining the structure of the fuzzy controller, defining the input-output fuzzy distribution with the emotional state and exercise intensity information as input and the insulin dosage adjustment step as output, and calculating the membership degree of the input relative to different fuzzy subsets; S4, establish fuzzy rules; S5. Perform fuzzy logic reasoning to obtain the output of the fuzzy system, and multiply the output by the insulin dose obtained in step S2 to determine the final insulin dose.

2. The method for fuzzy control of insulin dosage integrating emotion and motion information according to claim 1, characterized in that: Step S1 is divided into two parts, using photoplethysmography signals to evaluate emotional state and using triaxial acceleration to evaluate motion state; S101, Photoplethysmography signals reflect the beating of the heart by detecting small changes in the volume of blood in the skin; Specifically, by analyzing the characteristics of the pulse wave signal, key features for emotion classification are formed; these key features are modeled using the support vector machine algorithm to achieve emotion classification, and the Gaussian kernel function is selected as the kernel function of the support vector machine. The filtered features are input into the classifier model to obtain the estimated emotional state of the human body; S102, evaluating the motion state specifically includes: First, the three-axis acceleration data is preprocessed; Secondly, the data needs to be organized into time windows of fixed length. The data points in each window constitute a sample for training and testing the CNN model. In the design of the CNN model, a network architecture including a one-dimensional convolutional layer, a pooling layer, and a fully connected layer is designed. Finally, the CNN model is used to classify exercise intensity, including running, walking, and resting.

3. The method for fuzzy control of insulin dosage integrating emotion and motion information according to claim 2, characterized in that: Step S2 specifically comprises: using historical blood glucose concentrations, meal information and insulin dosages, combined with current blood glucose monitoring and dietary intake information, and calculating the current insulin dosage based on the doctor's clinical strategy or decision algorithm.

4. The method for fuzzy control of insulin dosage integrating emotion and motion information according to claim 3, characterized in that: The main components of the fuzzy controller in step S3 are described as follows: The input is the historical emotional state and exercise intensity information. The input is fuzzified and the historical emotional state and exercise intensity at 8 moments in the evaluation period T = 15 minutes are selected. The historical emotional state x1 and exercise intensity sequence x2 are expressed by the following formula: x1=[m0,m1,m2,m3,m4,m5,m6,m7] x2=[n0,n1,n2,n3,n4,n5,n6,n7] Among them, m i Indicates the emotional state of the ith period from the current time. If it is a stress state, the value is 1, and if it is a non-stress state, the value is 0; n i Indicates the exercise intensity of the i-th cycle from the current time. If it is in the running state, the value is 2; if it is in the walking state, the value is 1; if it is in the resting state, the value is 0; The corresponding weight matrices of the 8 historical emotional states and exercise intensities are set as follows: w=[w0,w1,w2,w3,w4,w5,w6,w7] Among them, w0 and w7 are 1, w1 and w6 are 2, w2 and w5 are 3, and w3 and w4 are 4; Define the contribution of historical emotional state to current blood sugar as h1=5x1*w T , the contribution of historical exercise intensity to current blood sugar is h2=2.5x2*w T .

5. The method for fuzzy control of insulin dosage integrating emotion and motion information according to claim 4, characterized in that: In step S3, the impact contribution value is fuzzified, and the fuzzy sets are defined as {more stress, more stress, medium stress, less stress, less stress} and {high exercise intensity, higher exercise intensity, medium exercise intensity, lower exercise intensity, low exercise intensity}, and a triangular membership function is used, whose input is the impact contribution value; The output of the fuzzy controller is the dosage adjustment percentage, which is used to adjust the insulin dosage calculated in step S2; The percentages were controlled within the range of [0,150], and the fuzzy set of changes in insulin dosage requirements after considering emotion and exercise information was defined as {more insulin dosage, more insulin dosage, moderate insulin dosage, less insulin dosage, less insulin dosage}, and a triangular membership function was used, with the input being the normalized dosage adjustment percentage.

6. The method for fuzzy control of insulin dosage integrating emotion and motion information according to claim 5, characterized in that: The fuzzy rules in step S4 are as follows: S401, the more stress there is in the fuzzy subset with the largest membership degree confirmed according to the historical emotional state contribution value, the greater the impact of the emotional state on blood sugar will be, and a smaller insulin dose will be required; S402. The more intense the exercise intensity is in the fuzzy subset with the largest membership determined according to the historical exercise intensity contribution value, the greater the impact of the exercise intensity on blood sugar will be, and a smaller insulin dose will be required.

7. The method for fuzzy control of insulin dosage integrating emotion and motion information according to claim 6, characterized in that: In step S5, the fuzzy logic reasoning adopts the Mamdani method, and the fuzzy results output by each rule are aggregated based on the minimum-maximum reasoning using the fuzzy rules in step S4 to obtain the final fuzzy set, which is then defuzzified to obtain the final output.

8. The method for fuzzy control of insulin dosage integrating emotion and motion information according to claim 7, characterized in that: The maximum membership method is used for defuzzification. The normalized insulin dosage adjustment percentage calculated by the maximum membership method is y max , the final insulin dose injected is: in, is the insulin dose calculated in step S2, and λ=0.67 is the denormalization coefficient.

Images