CN114429809A

CN114429809A - Individual nutrition scheme generation method and system for diabetic patients

Info

Publication number: CN114429809A
Application number: CN202210083420.5A
Authority: CN
Inventors: 田飞; 张红广; 王嘉诚; 刘凯
Original assignee: Wuhan Keling Intelligent Technology Co ltd
Current assignee: Wuhan Keling Intelligent Technology Co ltd
Priority date: 2022-01-25
Filing date: 2022-01-25
Publication date: 2022-05-03

Abstract

The invention belongs to the technical field of healthy diet management, and particularly discloses a method and a system for generating an individual nutrition scheme for diabetics, wherein the method comprises the following steps: acquiring the total energy required by the patient for daily normal life maintenance; classifying the patients, and determining the proportion of three nutrients required by the patients every day and the weight of cellulose according to the categories; determining the times of eating of a patient each day and the weight of three nutrients and cellulose in each meal; calculating and adjusting the weight of each food material in the recipe table of each meal by using the meal nutritional weight in each meal as a terminal point and the food material nutritional ingredient table in the recipe table as a starting point through a Support Vector Machine (SVM), and calculating the nutritional ingredient table and the recipe of each meal; and customizing a personalized and customized nutrition scheme, and recommending the recipes to patients of corresponding categories. The scheme can achieve the purpose of intervening the health management of patients through a diet scheme, and can automatically calculate to meet the energy and nutrition intake requirements of different types of patients.

Description

Individual nutrition scheme generation method and system for diabetic patients

Technical Field

The invention belongs to the technical field of healthy diet management, and particularly relates to a method and a system for generating an individual nutrition scheme for diabetics.

Background

The diabetic needs to strictly control diet and eat a small amount of food for a plurality of times, and the condition that the nutrition is improved is ensured not to be too much to be taken. It is important for diabetics to control weight. The diet is well controlled, the physical sign data of the diabetic can be effectively controlled, and the occurrence probability of complications is reduced.

In five horses for diabetes treatment, namely health education, diet therapy, medication, insulin therapy, blood glucose monitoring, diet therapy is the basic therapy. However, in actual life, the self-control effect of the type 2 diabetic on diet is not very ideal, and compliance is relatively low, which is related to that diet therapy is relatively strong in theory, individual differences of diet habits are relatively large in actual operation, and a uniform diet prescription provided by a hospital is difficult to enable the diabetic to perform in real life.

Recent medical studies have shown that diabetics do not need to be strictly averted, i.e. do not have to deliberately avoid eating foods with high sugar content, but need to avoid excessive eating behaviour, i.e. excessive intake of a specific food and eating foods that are softer and waxy, because diabetics need to maintain relatively stable blood glucose levels, while excessive eating and foods that are too soft and waxy tend to cause blood glucose levels to rise rapidly in a short period of time.

The proportion of the three high-capacity substances of fat, protein and carbohydrate required by the diabetics is slightly different from that of healthy people, and the intake part ratios of grain and potato, meat, egg and bean, milk, vegetables, fruits and grease need to be designed correspondingly. How to scientifically and intelligently provide a diet regulation and treatment scheme is a technical problem to be solved urgently.

The current dietary treatment regimen for diabetes has the following problems:

(1) the nutrition scheme needs to be established for the patients manually by nutritionists, so that a plurality of diabetes patients are in shortage of the number of the nutritionists in China;

(2) individual differences of patients, such as height, weight, labor intensity, etc., are not comprehensively considered. Many patients with diabetes are accompanied by diseases such as hypertension, and the current scheme is not comprehensively considered;

(3) the current nutrition scheme focuses on breakfast, lunch and dinner, and the scheme increases auxiliary meals according to the degree of diabetes and draws the principle of a small amount of multiple meals;

(4) the current scheme only outputs a fixed recipe according to the existing input conditions, and can not perform more accurate and personalized adjustment according to the feedback and sign changes of the patient.

Disclosure of Invention

The invention aims to provide a method and a system for generating an individual nutrition scheme for a diabetic, which can solve the technical problem that the diabetic is difficult to treat in diet.

The invention provides a method for generating an individual nutrition scheme for a diabetic patient, which comprises the following steps:

s1, acquiring the total energy required by the patient for daily normal life maintenance;

s2, classifying the patients, and determining the proportion of three nutrients required by the patients each day and the weight of cellulose according to the categories;

s3, determining the daily meal times of the patient, three nutrients in each meal and the meal nutrient weight of cellulose;

s4, calculating and adjusting the weight of each food material in the recipe table of each meal by using the meal nutritional weight in each meal as a terminal point and the food material nutritional ingredient table in the recipe table as a starting point through a Support Vector Machine (SVM), and calculating the nutritional ingredient table and the recipe of each meal;

and S5, customizing the personalized and customized nutrition scheme, and recommending the recipes to the patients of the corresponding category.

Preferably, the S1 specifically includes: and comprehensively calculating and judging the total energy required every day according to the height, the weight, the activity intensity and the pregnant and lactating conditions of the diabetic.

Preferably, the S2 specifically includes: patients are classified according to their BMI, biochemical indicators, disease.

Preferably, the S2 specifically includes: clustering is carried out by adopting a K-means clustering method based on the health level H, the favorite cuisine classification C and the food material accessibility A, and the weighted average HCA score of each clustered patient is calculated to determine the classification of the patient.

Preferably, said health level H is a weighted average score of blood glucose values, glycated hemoglobin values, BMI;

the favorite cuisine classification C comprises two conditions, namely that a patient selects a favorite cuisine by himself, and that the patient marks 'like' or 'dislike' for a recommended recipe to perform system automatic adjustment marking;

the accessibility of the food material A is marked by the patient and comprises the inaccessibility of the food material and economic factors.

Preferably, the S5 is followed by S6: and updating the category of the patient and the meal nutritional weight of each meal every day according to the favorite feedback and the latest value of the physical sign measurement of the patient.

The present invention also provides a system for enabling an individualized nutritional regimen generation for a diabetic patient, comprising:

the patient classification module is used for acquiring the total energy required by the normal life maintenance of the patient every day, classifying the patient, and determining the three nutrition proportions required by the patient every day and the weight of cellulose according to the categories;

the recipe determining module is used for determining the daily dining times of the patient and the dining nutrient weight of three nutrients and cellulose in each meal; calculating and adjusting the weight of each food material in the recipe table of each meal by using the meal nutritional weight in each meal as a terminal point and the food material nutritional ingredient table in the recipe table as a starting point through a Support Vector Machine (SVM), and calculating the nutritional ingredient table and the recipe of each meal;

and the personalized customization module is used for customizing a personalized customized nutrition scheme and recommending the recipes to patients of corresponding categories.

The invention also provides an electronic device comprising a memory, a processor for implementing the steps of the personalized nutritional regimen generation method for a diabetic patient when executing a computer management-like program stored in the memory.

The invention also provides a computer readable storage medium, characterized in that a computer management like program is stored thereon, which, when being executed by a processor, realizes the steps of the personalized nutritional regimen generation method for a diabetic patient.

Compared with the prior art, the method and the system for generating the individualized nutrition scheme aiming at the diabetes patient comprise the following steps: s1, acquiring the total energy required by the patient for daily normal life maintenance; s2, classifying the patients, and determining the proportion of three nutrients required by the patients each day and the weight of cellulose according to the categories; s3, determining the daily meal times of the patient, three nutrients in each meal and the meal nutrient weight of cellulose; s4, calculating and adjusting the weight of each food material in the recipe table of each meal by using the meal nutritional weight in each meal as a terminal point and the food material nutritional ingredient table in the recipe table as a starting point through a Support Vector Machine (SVM), and calculating the nutritional ingredient table and the recipe of each meal; and S5, customizing the personalized and customized nutrition scheme, and recommending the recipes to the patients of the corresponding category. According to parameters such as height, weight, physical activity type, biochemical indexes and the like of a patient, a recipe of each meal every week or every day, a picture of each recipe and the weight of various food materials in the recipe are provided for the patient, and customized propaganda and education materials are provided for the patient, so that the aim of intervening on health management of the patient through a diet scheme is fulfilled. And the energy and nutrition intake requirements of different types of patients can be met through automatic calculation.

Drawings

FIG. 1 is a flow chart of a method for generating an individualized nutrition program for a diabetic patient according to the present invention;

FIG. 2 is a schematic diagram of a hardware structure of a possible electronic device provided in the present invention;

fig. 3 is a schematic diagram of a hardware structure of a possible computer-readable storage medium according to the present invention.

Detailed Description

The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.

Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.

As shown in fig. 1, a method for generating a personalized nutritional regimen for a diabetic patient according to a preferred embodiment of the present invention comprises the steps of:

s1, acquiring the total energy required by the patient for daily normal life maintenance; the total energy required every day can be calculated according to the conditions of height, weight, activity intensity, lactation, disease complications and the like.

S2, classifying the patients, and determining the proportion of three nutrients required by the patients each day and the weight of cellulose according to the categories; classifying patients according to BMI, biochemical indexes and diseases, and determining the proportion of three nutrients required every day and the gram of cellulose according to user categories.

S3, determining the daily meal times of the patient, three nutrients in each meal and the meal nutrient weight of cellulose; for example, three meals, namely breakfast, lunch and supper, have moderate effect, and the Chinese meal has more meal and the supper has less meal. The total required weight of one day is divided according to different specific gravities.

S4, calculating and adjusting the weight of each food material in the recipe table of each meal by using the meal nutritional weight in each meal as a terminal point and the food material nutritional ingredient table in the recipe table as a starting point through a Support Vector Machine (SVM), and calculating the nutritional ingredient table and the recipe of each meal; a Support Vector Machine (SVM) is a generalized linear classifier (generalized linear classifier) that binary classifies data according to a supervised learning (supervised learning) mode, and a decision boundary of the SVM is a maximum-margin hyperplane (maximum-margin hyperplane) that solves learning samples. Here, the number of meals per day is determined according to the user situation, and the number of grams of three nutrients in each meal is determined as the end point of the calculation of a Support Vector Machine (SVM) for each meal. And then selecting the menu of each meal from the menu table according to the setting of the number of the menus in each meal and the setting of diet taboos of users, and determining the starting point calculated by a Support Vector Machine (SVM) of each meal according to the food material nutrient composition table. Therefore, the intelligent calculation of the nutrient composition table of each meal and the selected menu by the support vector machine can be completed. And then displayed together for the user to see.

According to parameters such as height, weight, physical activity type, biochemical indexes and the like of a patient, a recipe of each meal every week or every day, a picture of each recipe and the weight of various food materials in the recipe are provided for the patient, and customized propaganda and education materials are provided for the patient, so that the aim of intervening on health management of the patient through a diet scheme is fulfilled. And the energy and nutrition intake requirements of different types of patients can be met through automatic calculation.

Among them, three major nutrients including sugars, fats, proteins are in the human and animal body. These three types of substances are available in food, but are not stored in the same body organ. The three nutrients are rich in nature, especially in human body, and their basic functions in life are to maintain normal life functions.

Preferably, S1 specifically includes: and comprehensively calculating and judging the total energy required every day according to the height, the weight, the activity intensity and the pregnant and lactating conditions of the diabetic. Many diabetic patients have diseases such as hypertension, and need to comprehensively consider individual differences of patients, such as height, weight, labor intensity, complications, and the like. The dietician can judge the daily total energy required by the patient according to the comprehensive condition of the human body.

Preferably, step S2 specifically includes: patients are classified according to their BMI, biochemical indicators, disease. BMI, biochemical indicators, and diseases all affect the energy consumption of the patient, i.e., the consumption rate, and these indicators are classified and registered, for example, biochemical indicators are excellent, good, medium, and poor, or others may be classified according to this classification. After each index is classified, a total classification is then generated. For example, if there are two excellent categories, one excellent category can be determined as excellent; two good, one bad, can be determined as one medium, and so on. The specific classification can be determined artificially, and the classification determination can be performed according to actual conditions.

Preferably, S2 specifically includes: clustering is carried out by adopting a K-means clustering method based on the health level H, the favorite cuisine classification C and the food material accessibility A, and the weighted average HCA score of each clustered patient is calculated to determine the classification of the patient. The health level of a patient can be given a level value according to the degree of diabetes, the degree of complications and the overall physical quality of the individual, and the health level H is a weighted average score of the blood glucose level, the glycated hemoglobin level, and the BMI. Such as good, medium, bad, etc. The same reasoning applies to the favorite cuisine classification. The favorite cuisine classification C comprises 2 conditions, namely that a patient selects favorite cuisine by himself, and the patient marks 'likes' and 'dislikes' according to recommended recipes, and the system automatically adjusts and marks. The accessibility of the food material A is marked by the patient and comprises the inaccessibility of the food material and economic factors. For example, if the patient is too expensive, the patient may want to have the highest unreachability, or may want to have the lowest unreachability. The final artificial declustering weights determine the patient classification by taking a weighted average of the three components.

Preferably, step S5 is followed by step S6: and updating the category of the patient and the meal nutritional weight of each meal every day according to the favorite feedback and the latest value of the physical sign measurement of the patient. After the recipe is recommended, unsupervised learning training is carried out on preference feedback, the latest value of physical sign measurement and the like of the patient, and finally, a scheme which is scientific nutrition from a nutrient level is obtained, so that the preference degree, economic acceptable degree and the like of the patient on the recipe are met, and indexes such as blood sugar value and the like of the patient are fed back to the recipe scheme in time. Improve the diet precision of the patients.

An embodiment of the present invention further provides a system for implementing an individualized nutrition plan generation for a diabetic patient, including:

Fig. 2 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 2, an embodiment of the present invention provides an electronic device, which includes a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320, where the processor 1320 executes the computer program 1311 to implement the following steps: s1, acquiring the total energy required by the patient for daily normal life maintenance;

s3, determining the daily meal times of the patient, the three nutrients in each meal and the meal nutrient weight of the cellulose;

Please refer to fig. 3, which is a schematic diagram of an embodiment of a computer-readable storage medium according to the present invention. As shown in fig. 3, the present embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored, the computer program 1411 when executed by a processor implements the steps of: s1, acquiring the total energy required by the patient for daily normal life maintenance;

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.

Claims

1. A method of generating an individualized nutritional regimen for a diabetic patient, comprising the steps of:

2. The method for personalized nutritional regimen for diabetic patients according to claim 1, wherein the S1 specifically comprises: and comprehensively calculating and judging the total energy required every day according to the height, the weight, the activity intensity and the pregnant and lactating conditions of the diabetic.

3. The method for personalized nutritional regimen for diabetic patients according to claim 1, wherein the S2 specifically comprises: patients are classified according to their BMI, biochemical indicators, disease.

4. The method for personalized nutritional regimen for diabetic patients according to claim 1, wherein the S2 specifically comprises: clustering is carried out by adopting a K-means clustering method based on the health level H, the favorite cuisine classification C and the food material accessibility A, and the weighted average HCA score of each clustered patient is calculated to determine the classification of the patient.

5. The method of claim 4, wherein the health level H is a weighted average score of blood glucose values, glycated hemoglobin values, BMI;

6. The method for personalized nutritional regimen for diabetic patients of claim 1, further comprising, after the S5, S6: and updating the category of the patient and the meal nutritional weight of each meal every day according to the favorite feedback and the latest value of the physical sign measurement of the patient.

7. A system for enabling individualized nutritional regimen generation for a diabetic patient, comprising:

8. An electronic device, comprising a memory, a processor for implementing the steps of the personalized nutritional regimen generation method for a diabetic patient of any of claims 1-6 when executing a computer management like program stored in the memory.

9. A computer readable storage medium, having stored thereon a computer management like program, which when executed by a processor, carries out the steps of the individualized nutrition scheme generation method for a diabetic patient according to any of claims 1-6.