Diabetic health data management system based on cloud platform

Abstract

The invention relates to the technical field of diabetic health management, in particular to a diabetic health data management system based on a cloud platform. Obtaining a blood sugar amplification factor according to the blood sugar of the patient; correcting the blood glucose amplification factor according to the metabolic equivalent value and the kinetic energy consumption value of the patient to obtain a blood glucose amplification correction factor; obtaining a blood sugar change characteristic value according to the blood sugar amplification correction factor and the diet sugar content before and after the patient diets; and according to the blood glucose change characteristic values of the patient and other patients in the same kind of patient set, obtaining a blood glucose abnormality amplification index. The method comprises the following steps: acquiring a relative abnormal index according to different characteristics of blood glucose of a patient and other patients in the same kind of patient set and a blood glucose abnormal amplification index of the patient; according to the relative anomaly index of the patient, the health management cloud platform is assisted to make medication and diet suggestions for the patient, so that the evaluation accuracy of the cloud platform on the diabetes symptom of the patient is improved, and the possibility of symptom deterioration is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of health management for diabetic patients, and particularly to a health data management system for diabetic patients based on a cloud platform. Background Art

[0002] Diabetes, as a chronic disease, requires long-term monitoring of indicators such as blood glucose of diabetic patients, so as to assist the health management cloud platform for diabetic patients and doctors to analyze the development trend of the diabetic symptoms of patients, and give more suitable medication and diet suggestions for the patients themselves. At present, there are more and more software and cloud platforms for health management of diabetic patients, which can give reasonable suggestions on medication and diet according to the monitoring data of patients; the long-term monitoring of diabetic patients is mainly to collect the blood glucose data of patients through a portable blood glucose meter, and upload the long-term blood glucose levels of patients to the cloud platform for analysis. However, in daily life, the blood glucose level may be affected by the individual state, eating habits and exercise intensity of patients; as a result, a single blood glucose data is difficult to accurately characterize the physical health status of diabetic patients, affecting the accuracy of the medication and diet suggestions for patients by the cloud platform. Summary of the Invention

[0003] In order to solve the technical problem that a single blood glucose data is difficult to accurately characterize the physical health status of diabetic patients and affects the accuracy of the medication and diet suggestions for patients by the cloud platform, the purpose of the present invention is to provide a health data management system for diabetic patients based on a cloud platform, and the specific technical solutions adopted are as follows: A health data acquisition module, configured to acquire the age, body mass index, blood glucose at different monitoring times, dietary sugar content during diet, metabolic equivalent value and exercise energy consumption value of diabetic patients of the same gender; A first blood glucose analysis module, configured to obtain a blood glucose increase factor according to the change characteristics of blood glucose of a patient within a preset time period; and correct the blood glucose increase factor according to the metabolic equivalent value and exercise energy consumption value of the patient within the preset time period to obtain a blood glucose increase correction factor; A second blood glucose analysis module, configured to obtain blood glucose change characteristic values before and after diet according to the difference characteristics of the blood glucose increase correction factor before and after diet of a patient and the dietary sugar content; perform clustering according to the age and body mass index of the patient to obtain different sets of patients of the same category; and obtain a blood glucose abnormal increase index according to the difference characteristics of the blood glucose change characteristic values of the patient and other patients in the same category of patients in the preset same diet time period; A blood glucose monitoring and management module, configured to obtain a relative abnormality index according to the difference characteristics of the blood glucose of a patient and other patients in the same category of patients on an empty stomach and the blood glucose abnormal increase index of the patient; and assist the health management cloud platform to give medication and diet suggestions for the patient according to the relative abnormality index of the patient.

[0004] Further, the step of obtaining a blood glucose increase factor according to the change characteristics of a patient's blood glucose within a preset time period includes: Calculate the average value of the blood glucose ratios of a patient at each monitoring moment within a preset time period to the previous monitoring moment, and obtain the blood glucose increase factor of the patient within the preset time period.

[0005] Further, the step of correcting the blood glucose increase factor according to the metabolic equivalent value and exercise energy consumption value of a patient within a preset time period to obtain a blood glucose increase correction factor includes: When the metabolic equivalent value of a patient within a preset time period does not exceed a preset intensity threshold, normalize the exercise energy consumption value and calculate the sum value with the constant 1 to obtain a correction coefficient; when the metabolic equivalent value of a patient within a preset time period exceeds the preset intensity threshold, calculate the difference between the constant 1 and the normalized value of the exercise energy consumption value to obtain a correction coefficient; calculate the correction coefficient and the blood glucose increase factor within the preset time period for correction to obtain the blood glucose increase correction factor of the patient within the preset time period.

[0006] Further, the step of obtaining a blood glucose change characteristic value before and after a meal according to the difference characteristics of the blood glucose increase correction factors of a patient within a preset time period before and after a meal and the sugar content of the meal includes: Calculate the ratio of the blood glucose increase correction factors of a patient in adjacent preset time periods after and before a meal to obtain the blood glucose change range; calculate the ratio of the blood glucose change range to the sugar content of the meal during the meal to obtain the blood glucose change characteristic value of the patient before and after the meal.

[0007] Further, the step of obtaining a blood glucose abnormal increase index according to the difference characteristics of the blood glucose change characteristic values of a patient and other patients in the same type of patient group within a preset same meal time period includes: In the same type of patient group, calculate the average value of the ratios of the blood glucose change characteristic values of a patient to all other patients within a preset same meal time period to obtain the blood glucose abnormal increase index of the patient.

[0008] Further, the step of obtaining a relative abnormal index according to the difference characteristics of the blood glucose of a patient and other patients in the same type of patient group on an empty stomach and the blood glucose abnormal increase index of the patient includes: Calculate the average value of the blood glucose of a patient on an empty stomach to obtain the blood glucose normal value of the patient; calculate the average value of the blood glucose normal values of all other patients in the same type of patient group where the patient is located to obtain the overall blood glucose value; calculate the ratio of the blood glucose normal value of the patient to the overall blood glucose value to obtain a proportionality coefficient; calculate the average value of all the blood glucose abnormal increase indexes of the patient to obtain the average blood glucose abnormal increase index; calculate the product of the blood glucose normal value, the proportionality coefficient, and the average blood glucose abnormal increase index of the patient to obtain the relative abnormal index of the patient.

[0009] Further, the steps for obtaining the exercise energy consumption value include: Calculate the product of the patient's weight, exercise duration, and metabolic equivalent value to obtain the patient's exercise energy consumption value.

[0010] The present invention has the following beneficial effects: In the present invention, since the symptoms of diabetes are reflected in the characteristics that the patient's blood sugar is difficult to control and prone to fluctuations, obtaining the blood sugar increase factor can characterize the degree of the patient's body's control over blood sugar and preliminarily reflect the severity of the patient's diabetes. Since the patient's exercise intensity will cause changes in the body's blood sugar and affect the judgment of blood sugar characteristics, obtaining the blood sugar increase correction factor can reduce the error in analyzing the severity of symptoms based on blood sugar characteristics and improve the analysis accuracy. The degree of blood sugar increase after a diabetic patient eats can characterize the severity of diabetes. Therefore, obtaining the blood sugar change characteristic values before and after the patient's diet can characterize the degree of blood sugar increase after the patient's diet. Obtaining a set of similar patients can analyze patients with similar body functions together. Furthermore, obtaining the blood sugar abnormal increase index can characterize the severity of the patient's symptoms based on the blood sugar change characteristic values among patients with similar body functions, further improving the analysis accuracy of the symptom severity. The obtained relative abnormal index can better characterize the severity of the patient's diabetes symptoms compared to the patient's single blood sugar level, thereby improving the evaluation accuracy of the cloud platform for the patient's diabetes symptoms and reducing the possibility of symptom deterioration. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0012] Figure 1 It is a block diagram of a health data management system for diabetic patients based on a cloud platform provided by an embodiment of the present invention. Detailed Embodiments

[0013] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific embodiments, structures, features, and effects of a health data management system for diabetic patients based on a cloud platform proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0014] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0015] The following specifically describes the specific solution of a diabetes patient health data management system based on a cloud platform provided by the present invention in conjunction with the accompanying drawings.

[0016] Please refer to Figure 1 , which shows a block diagram of a diabetes patient health data management system based on a cloud platform provided by an embodiment of the present invention. The system includes the following modules: A health data acquisition module S1, which is used to acquire the age, body mass index, blood glucose at different monitoring times, dietary sugar content during the diet, metabolic equivalent value and exercise energy consumption value during exercise of diabetic patients of the same gender.

[0017] First, acquire the age, body mass index, blood glucose at different monitoring times, dietary sugar content during the diet, metabolic equivalent value within a preset period and exercise energy consumption value of diabetic patients of the same gender. Since there are differences in blood glucose levels among people of different genders, ages and BMI body mass indexes, in order to comprehensively and accurately analyze the blood glucose differences between patients with similar physical conditions, it is necessary to collect the age and body mass index of the patients. The blood glucose data of the patients is collected through intelligent devices such as portable blood glucose meters or blood glucose watches. In the embodiment of the present invention, the blood glucose data is collected every 30 minutes, and the implementer can set the collection interval according to the blood glucose control degree of the patients. The dietary sugar content during the diet can be identified by taking pictures of food with a mobile phone and uploading them to the existing MyFitnessPal food database, and the dietary sugar content is obtained through the identified sugar content and the weighed food weight. Since exercise will cause fluctuations in the blood glucose of the patients and affect the normal blood glucose analysis, it is necessary to obtain the metabolic equivalent value and exercise energy consumption value during exercise. The calculation of the metabolic equivalent value belongs to the prior art, and the specific steps will not be described in detail. The larger the metabolic equivalent value, the higher the exercise intensity. Calculate the product of the patient's weight, exercise duration during exercise and metabolic equivalent value to obtain the exercise energy consumption value of the patient. The exercise duration is obtained through intelligent wearable devices. The exercise energy consumption value reflects the energy consumption of the patient during exercise. The calculation of the exercise energy consumption value belongs to the prior art.

[0018] A first blood glucose analysis module S2, which is used to obtain a blood glucose increase factor according to the change characteristics of the patient's blood glucose within a preset period; correct the blood glucose increase factor according to the metabolic equivalent value and exercise energy consumption value of the patient within a preset period to obtain a blood glucose increase correction factor.

[0019] In diabetic patients, due to insufficient insulin secretion or weakened body response to insulin, blood sugar is difficult to regulate and control, and it is more likely to cause a rapid increase in blood sugar after meals. If the blood sugar increase of a certain patient after a meal exceeds that of other patients with similar physical function states, it means that the diabetes of this patient is more severe, which is more accurate than simply monitoring the blood sugar value of this patient. Therefore, the blood sugar change characteristics of the patient before and after meals can be analyzed first, and the blood sugar increase factor can be obtained according to the blood sugar change characteristics of the patient within a preset time period. Preferably, in the embodiments of the present invention, the steps of obtaining the blood sugar increase factor include: calculating the average value of the blood sugar ratio of each monitoring moment of the patient within the preset time period to the previous monitoring moment, and obtaining the blood sugar increase factor of the patient within the preset time period. The larger the blood sugar increase factor, the faster the growth and change of blood sugar, the more difficult it is to control blood sugar, and the more severe the diabetes symptoms. In the embodiments of the present invention, every two hours is a preset time period. For example, from 9 am to 11 am is a preset time period, and the implementer can determine it according to the implementation scenario.

[0020] Furthermore, since exercise can cause changes in the patient's blood sugar, during exercise, as the muscles continuously take up and utilize glucose, the blood sugar level will further decrease. However, as the exercise intensity increases, the body may have a stress response, prompting the secretion of some blood sugar-raising hormones such as adrenaline to increase, resulting in the liver releasing more glucose and the blood sugar rising. Therefore, in order to avoid the error of the blood sugar increase factor affected by exercise due to the patient's exercise during the preset time period, it is necessary to correct it according to the patient's exercise level, and correct the blood sugar increase factor according to the metabolic equivalent value and exercise energy consumption value of the patient within the preset time period to obtain the blood sugar increase correction factor.

[0021] Preferably, in the embodiments of the present invention, the step of obtaining the blood glucose increase correction factor includes: when the metabolic equivalent value of the patient within the preset time period does not exceed the preset intensity threshold, it means that the exercise intensity of the patient is low, which will cause the blood glucose level to decrease and the blood glucose increase factor to be on the low side. Therefore, the sum value of the normalized exercise energy consumption value and the constant 1 is calculated to obtain the correction coefficient. In the existing exercise intensity classification standard, a metabolic equivalent value exceeding the constant 6 is considered high-intensity exercise, and the corresponding exercise types are running, swimming, etc.; below the constant 6 is medium-low intensity, and the corresponding exercise types are fast walking, cycling, etc. Therefore, in the embodiments of the present invention, the preset intensity threshold is 6. When the metabolic equivalent value of the patient within the preset time period exceeds the preset intensity threshold, it means that the exercise intensity of the patient is high, which will cause the blood glucose level to increase and the blood glucose increase factor to be on the high side. Therefore, the difference value between the constant 1 and the normalized value of the exercise energy consumption value is calculated to obtain the correction coefficient. The correction coefficient is calculated and corrected with the blood glucose increase factor in the preset time period to obtain the blood glucose increase correction factor of the patient in the preset time period. The blood glucose increase correction factor reduces the influence of the blood glucose change during the patient's exercise on the normal blood glucose fluctuation and improves the credibility of the blood glucose change characteristics. It should be noted that when analyzing the magnitude relationship between the metabolic equivalent value and the preset intensity threshold, the maximum value of the metabolic equivalent value of the patient within the preset time period is taken.

[0022] The second blood glucose analysis module S3 is used to obtain the blood glucose change characteristic values before and after the diet according to the difference characteristics of the blood glucose increase correction factors before and after the diet of the patient and the sugar content of the diet; cluster according to the age and body mass index of the patient to obtain different sets of patients of the same type; obtain the blood glucose abnormal increase index according to the difference characteristics of the blood glucose change characteristic values of the patient and other patients in the same set of patients of the same type during the preset same diet period.

[0023] After obtaining the blood glucose increase correction factors of the patient at different preset time periods, the differential characteristics of the blood glucose increase correction factors of the patient in adjacent time periods before and after meals can be analyzed to obtain the degree of blood glucose increase in the patient's body after meals, and then the severity of diabetes can be judged. Therefore, according to the differential characteristics of the blood glucose increase correction factors of the patient in the preset time periods before and after meals and the sugar content of the diet, the blood glucose change characteristic value before and after meals is obtained; preferably, in the embodiment of the present invention, the step of obtaining the blood glucose change characteristic value includes: calculating the ratio of the blood glucose increase correction factors of the patient in the adjacent preset time periods after and before meals to obtain the blood glucose change range; for example, if the eating process is from 12:00 noon to 1:00 pm, the preset time period before meals is from 10:00 am to 12:00 pm, and the preset time period after meals is from 1:00 pm to 3:00 pm. The greater the blood glucose change range, the higher the degree of blood glucose increase in the patient after this meal, the worse the patient's ability to decompose and metabolize sugar after meals, and the higher the degree of diabetes. Since the degree of blood glucose increase after meals is related to the sugar content in the food, the higher the sugar content in the diet, the higher the blood glucose increase after meals. Therefore, calculate the ratio of the blood glucose change range to the sugar content of the diet during the eating process to obtain the blood glucose change characteristic value of the patient before and after meals. The blood glucose change characteristic value removes the influence of the sugar content in the food on the blood glucose change. The higher the blood glucose change characteristic value, the lower the blood glucose control ability of the patient and the more severe the diabetes symptoms.

[0024] Furthermore, after obtaining the blood glucose change characteristic value of this patient, it can be compared with the blood glucose change characteristic values of other patients in a similar physical function state to comprehensively evaluate the severity of diabetes of this patient. Therefore, clustering is performed according to the age and body mass index of the patient to obtain different sets of patients of the same category; in the embodiment of the present invention, the K-means++ clustering algorithm is used to cluster all the same-sex patients participating in the monitoring; it should be noted that this algorithm belongs to the prior art and is an improved algorithm of the K-means algorithm, which can cluster patients with similar ages and similar body mass indexes into one category, and the specific steps will not be elaborated. The physical functions of the patients in the set of patients of the same category are relatively close. If the blood glucose characteristic value of this patient exceeds most of the other patients in the set of patients of the same category, the higher the severity of diabetes of this patient; therefore, the blood glucose abnormal increase index is obtained according to the differential characteristics of the blood glucose change characteristic values of this patient and other patients in the set of patients of the same category during the preset same eating time period.

[0025] Preferably, in the embodiments of the present invention, the step of obtaining the blood glucose abnormal increase index includes: calculating the average value of the ratios of the blood glucose change characteristic values of a patient and all other patients during a preset same diet period in a set of patients of the same type to obtain the blood glucose abnormal increase index of the patient. It should be noted that in the embodiments of the present invention, the preset same diet period means that the diet intervals of two patients are within one hour, and the implementer can determine it according to the implementation scenario; since the blood glucose level of the human body fluctuates and changes at different times of the day, and there are significant differences in the amount of food at different diet times, when analyzing the differences in blood glucose change characteristic values between different patients, it is necessary to limit the diet time differences between patients; for example, if the patient has a meal at 12:00 noon and obtains the blood glucose change characteristic value, then the diet time corresponding to the blood glucose change characteristic value obtained by other patients needs to be between 11:00 am and 1:00 pm. If a certain other patient does not meet this time limit, the blood glucose change characteristic value of this other patient is excluded from the calculation process. The greater the abnormal increase in the patient's blood glucose, the greater the degree of increase in the patient's blood glucose after a meal compared to other patients with similar physical functions, the worse the blood glucose control of the patient, and the more severe the diabetes. The formula for obtaining the blood glucose abnormal increase index of this patient includes: In the formula, W represents the blood glucose abnormal increase index of the patient after a certain meal, N represents the number of other patients in the set of patients of the same type as this patient who meet the conditions of the preset same diet period, Y represents the blood glucose change characteristic value of this patient, represents the blood glucose change characteristic value that the nth other patient meets the conditions of the preset same diet period.

[0026] The blood glucose monitoring and management module S4 is used to obtain the relative abnormality index according to the difference characteristics of the blood glucose of the patient and other patients in the set of patients of the same type when fasting and the blood glucose abnormal increase index of the patient; and assist the cloud platform to give medication and diet suggestions to the patient according to the relative abnormality index of the patient.

[0027] After obtaining the long-term blood glucose levels of patients and the differences in blood glucose increase among different patients, the relative abnormality index can be obtained based on the difference characteristics of the blood glucose of the patient and other patients in the same group of patients on an empty stomach, and the blood glucose abnormal increase index of the patient; preferably, in the embodiments of the present invention, the steps of obtaining the relative abnormality index include: calculating the average value of the blood glucose of the patient on an empty stomach to obtain the normal blood glucose value of the patient; in the embodiments of the present invention, the blood glucose on an empty stomach is the blood glucose value measured for the first time after the patient wakes up every day. The larger the normal blood glucose value, the higher the severity of diabetes of the patient. Calculate the average value of the normal blood glucose values of all other patients in the same group of patients where the patient is located to obtain the overall blood glucose value; the overall blood glucose value represents the comprehensive blood glucose level of patients with similar physical functions. Calculate the ratio of the normal blood glucose value of the patient to the overall blood glucose value to obtain the proportionality coefficient; the larger the proportionality coefficient, the higher the blood glucose level of the patient is than that of other patients with similar physical functions, and the more severe the diabetes symptoms of the patient are. Calculate the average value of all the blood glucose abnormal increase indexes of the patient to obtain the average blood glucose abnormal increase index; the larger the blood glucose abnormal increase indexes after all meals of the patient are, the larger the average blood glucose abnormal increase index is, and the lower the blood glucose control ability of the patient is than that of other patients with similar physical functions, and the more severe the diabetes symptoms are. Calculate the product of the normal blood glucose value, the proportionality coefficient, and the average blood glucose abnormal increase index of the patient to obtain the relative abnormality index of the patient; the larger the relative abnormality index of the patient is, the more severe the diabetes symptoms of the patient are. The formula for obtaining the relative abnormality index includes: In the formula, G represents the relative abnormality index of the patient, S represents the normal blood glucose value of the patient, H represents the overall blood glucose value, represents the proportionality coefficient, M represents the number of the average blood glucose abnormal increase indexes calculated for the patient, represents the m-th blood glucose abnormal increase index, represents the average blood glucose abnormal increase index of the patient.

[0028] Furthermore, the relative anomaly index of the patient can more accurately evaluate and analyze the severity of the patient's diabetic symptoms compared to a single blood glucose data, avoiding the situation where a single blood glucose index is affected by the patient's daily diet and exercise intensity and cannot accurately characterize the diabetic symptoms. At the same time, it combines the difference characteristics of the blood glucose increase degree among patients with similar physical functions, comprehensively evaluates the severity of the patient's diabetic symptoms, and improves the accuracy of the cloud platform in analyzing the development trend of the patient's diabetic symptoms. Finally, based on the relative anomaly index of the patient, the cloud platform is assisted to give medication and diet suggestions to the patient. Different patients can obtain personalized suggestions given by the cloud platform. It should be noted that the specific suggestions of the cloud platform for the patient need to be trained and summarized by combining a large amount of clinical data of patients, which will not be elaborated here; thus, the accuracy of the medication and diet suggestions for the patient is higher, and the possibility of the deterioration of the patient's diabetic symptoms is reduced.

[0029] In summary, the embodiment of the present invention provides a health data management system for diabetic patients based on a cloud platform; obtaining a blood glucose increase factor according to the patient's blood glucose; correcting the blood glucose increase factor according to the patient's metabolic equivalent value and exercise energy consumption value to obtain a blood glucose increase correction factor; obtaining a blood glucose change characteristic value according to the blood glucose increase correction factor before and after the patient's diet and the sugar content of the diet; obtaining a blood glucose abnormal increase index according to the blood glucose change characteristic values of the patient and other patients in the same type of patient group where the patient is located. The present invention obtains a relative anomaly index according to the difference characteristics of the blood glucose of the patient and other patients in the same type of patient group where the patient is located and the blood glucose abnormal increase index of the patient; assisting the health management cloud platform to give medication and diet suggestions to the patient according to the relative anomaly index of the patient, improving the evaluation accuracy of the cloud platform for the patient's diabetic symptoms, and reducing the possibility of symptom deterioration.

[0030] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0031] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A cloud platform-based health data management system for diabetic patients, characterized in that: The system includes the following modules: The health data acquisition module is used to obtain the age, body mass index, blood sugar at different monitoring times, dietary sugar content during diet, metabolic equivalent value during exercise, and exercise energy consumption value of diabetic patients of the same gender; The first blood sugar analysis module is used to obtain a blood sugar increase factor according to the change characteristics of the patient's blood sugar within a preset period of time; Correcting the blood sugar increase factor according to the patient's metabolic equivalent value and exercise energy consumption value within a preset period of time to obtain a blood sugar increase correction factor; The second blood sugar analysis module is used to obtain the blood sugar change characteristic value before and after the meal according to the difference characteristics of the blood sugar increase correction factor of the patient in the preset period before and after the meal and the sugar content of the meal; Clustering is performed based on the age and body mass index of the patients to obtain different sets of patients of the same type; the abnormal blood sugar increase index is obtained based on the difference in the characteristic values ​​of blood sugar changes between the patient and other patients in the same set of patients during the same preset dietary period; The blood glucose monitoring management module is used to obtain a relative abnormality index based on the difference in fasting blood glucose between the patient and other patients in the same group of patients and the patient's abnormal blood glucose increase index; based on the patient's relative abnormality index, the health management cloud platform is used to provide medication and dietary recommendations to the patient.

2. A cloud platform-based diabetes patient health data management system according to claim 1, characterized in that: The step of obtaining the blood sugar increase factor according to the change characteristics of the patient's blood sugar within a preset period of time includes: The average value of the ratio of the patient's blood sugar at each monitoring moment within the preset time period to the previous monitoring moment is calculated to obtain the patient's blood sugar increase factor within the preset time period.

3. A cloud platform-based diabetes patient health data management system according to claim 1, characterized in that: The step of correcting the blood sugar increase factor according to the metabolic equivalent value and exercise energy consumption value of the patient in a preset time period to obtain the blood sugar increase correction factor includes: When the metabolic equivalent value of the patient within the preset time period does not exceed the preset intensity threshold, the exercise energy consumption value is normalized and then calculated as the sum with the constant 1 to obtain the correction coefficient; when the metabolic equivalent value of the patient within the preset time period exceeds the preset intensity threshold, the difference between the constant 1 and the normalized value of the exercise energy consumption value is calculated to obtain the correction coefficient; the correction coefficient is calculated and corrected with the blood glucose increase factor of the preset time period to obtain the blood glucose increase correction factor of the patient during the preset time period.

4. A cloud platform-based diabetes patient health data management system according to claim 1, characterized in that: The step of obtaining the blood sugar change characteristic value before and after eating according to the difference characteristics of the blood sugar increase correction factor of the patient in the preset time period before and after eating and the sugar content of the diet includes: The ratio of the correction factors of the blood sugar increase in adjacent preset time periods after and before a meal is calculated to obtain the blood sugar variation range; the ratio of the blood sugar variation range to the dietary sugar content during the diet process is calculated to obtain the characteristic value of the blood sugar variation of the patient before and after a meal.

5. A cloud platform-based diabetes patient health data management system according to claim 1, characterized in that: The step of obtaining the abnormal blood sugar increase index according to the difference characteristics of the blood sugar change characteristic values ​​of the patient and other patients in the same patient group during the same preset diet period includes: In the set of similar patients, the average value of the ratio of the blood glucose change characteristic value between the patient and all other patients in the same preset dietary period is calculated to obtain the patient's blood glucose abnormality increase index.

6. A cloud platform-based diabetes patient health data management system according to claim 1, characterized in that: The step of obtaining a relative abnormal index based on the difference characteristics of the fasting blood sugar of the patient and other patients in the same patient group and the abnormal blood sugar increase index of the patient comprises: Calculate the average value of the patient's fasting blood sugar to obtain the patient's normal blood sugar value; calculate the average value of the normal blood sugar values ​​of all other patients in the same patient group to obtain the overall blood sugar value; calculate the ratio of the patient's normal blood sugar value to the overall blood sugar value to obtain the proportionality coefficient; calculate the average value of all the patient's abnormal blood sugar increase indexes to obtain the average abnormal blood sugar increase index; calculate the product of the patient's normal blood sugar value, the proportionality coefficient, and the average abnormal blood sugar increase index to obtain the patient's relative abnormality index.

7. A cloud platform-based diabetes patient health data management system according to claim 1, characterized in that: The step of obtaining the exercise energy consumption value comprises: Calculate the product of the patient's weight, exercise duration and metabolic equivalent value to obtain the patient's exercise energy expenditure value.

Images