WO2023111668A1

WO2023111668A1 - Dietary recommendation method, apparatus and system, and storage medium, and electronic device

Info

Publication number: WO2023111668A1
Application number: PCT/IB2021/062063
Authority: WO
Inventors: 杜硕
Original assignee: Evyd研究私人有限公司
Priority date: 2021-12-17
Filing date: 2021-12-21
Publication date: 2023-06-22

Abstract

Disclosed in the present application are a dietary recommendation method, apparatus and system, and a storage medium, and an electronic device. The method comprises: acquiring user data; determining, according to the user data, an etiological factor type of a user and a dietary goal corresponding to the etiological factor type; determining, according to the user data, a health risk of the user and a dietary suggestion corresponding to the health risk; generating dietary guidance information for the user according to the dietary goal and the dietary suggestion; acquiring, on the basis of a user weight corresponding to each food material in a food material library, a target food material that matches the dietary goal and the dietary suggestion, wherein the user weight is updated on the basis of a user behavior; and generating a recommended dietary plan for the user on the basis of the dietary guidance information and the target food material. By using the method of the present application, a highly targeted and highly accurate recommended dietary plan can be determined.

Description

A diet recommendation method, device, system, storage medium and electronic equipment Cross-reference to related applications This application is based on application number 2021115451672, application date is December 17, 2021 and application number is 2021115451653. Application date is December 2021 Two Chinese patent applications were filed on the 17th, and the priority of the Chinese patent application is claimed. The entire content of the Chinese patent application is hereby incorporated into this application as a reference. Technical Field The present application relates to the technical field of data processing, and in particular to a diet recommendation method, device, system, storage medium and electronic equipment. BACKGROUND OF THE INVENTION A healthy diet helps prevent malnutrition of all types as well as non-communicable and chronic diseases including such as diabetes, heart disease, stroke and cancer. Among them, for the prevention or control of diabetes, a healthy diet is particularly important, because diet is the most direct way for the human body to obtain sugar. Reasonable dietary intervention can effectively reduce the development speed of diabetes and the risk of complications, and even achieve reversal for users with pre-diabetes or mild diabetes. The user data on which the existing dietary recommendation schemes are based is not accurate enough, or even if accurate data is obtained, there is no effective data analysis method, resulting in problems such as low accuracy in final recipe determination. SUMMARY OF THE INVENTION The purpose of the embodiments of the present application is to provide a diet recommendation method, device, system, storage medium and electronic equipment, so as to at least solve the above-mentioned technical problems. In order to achieve the above purpose, an embodiment of the present application provides a diet recommendation method, including: acquiring user data, where the user data includes at least one of basic data, disease data, exercise data, and diet data; According to the user data, determine the type of etiology of the user and the dietary goal corresponding to the type of etiology; determine the health risk of the user and the diet suggestion corresponding to the health risk according to the user data; generating dietary guidance information for the user based on the dietary goal and the dietary suggestion; and obtaining a first target ingredient matching the dietary goal and the dietary suggestion based on the user weight corresponding to each ingredient in the ingredient database, wherein the The user weight is updated based on the user behavior; based on the dietary guidance information and the first target ingredient, a dietary recommendation plan is generated for the user. Wherein, the determining the etiology type of the user and the diet target corresponding to the etiology type according to the user data includes: inputting the user data into a machine learning-based etiology identification model or a decision tree model, Outputting the type of etiology of the user; determining the dietary goal of the user according to the type of etiology. Wherein, the determining the health risk of the user and the diet suggestion corresponding to the health risk according to the user data includes: inputting the user data into multiple health risk models or decision tree models based on machine learning, Outputting a result of whether the user has the health risk; determining a diet suggestion for the user according to the health risk result. Wherein, the generating dietary guidance information for the user according to the dietary goal and the dietary suggestion includes: determining the metabolic level of the user according to the exercise data; determining the metabolic level of the user according to the basic data, the metabolic level and the The dietary target determines the user's daily dietary energy intake; generates dietary guidance information according to the daily dietary energy intake and the dietary advice, and the dietary guidance information includes at least the number of meals per day and the nutrition of each meal Ingredient intake. The method also includes: determining dietary taboos of the user according to the user data; Before acquiring the first target food, the food is filtered according to the dietary restrictions. Wherein, updating the user weight based on user behavior includes: updating the user weight according to the user's individual behavior and/or environment analysis. Wherein, the user's individual behavior includes the user's replacement operation and search operation for a certain ingredient, and the environmental analysis includes the change of season, the change of the user's location, and the change of the price of the ingredient. Wherein, updating the user weight according to the user's individual behavior includes: if the user has a replacement operation on a certain ingredient and the number of replacement operations is greater than a threshold, reducing the user weight corresponding to the ingredient; and /or if the user performs a search operation on a certain ingredient and selects the ingredient as the first target ingredient, increase the user weight corresponding to the ingredient. Wherein, the generating a dietary recommendation plan for the user based on the dietary guidance information and the first target ingredient includes: determining a recipe corresponding to the first target ingredient according to the first target ingredient; The attribute data of the target ingredients, the intake of each nutrient component in each meal, and the cooking method determine the weight of each first target ingredient in the recipe. The method further includes: acquiring a dietary adjustment request from the user, the dietary adjustment request indicating that the first target ingredient in the dietary recommendation plan is replaced with a second target ingredient, and the second target ingredient is a single ingredient or a mixed ingredient ingredients; based on the dietary adjustment request and the ingredient database, update the diet recommendation scheme. Wherein, when the second target ingredient is a single ingredient, the dietary adjustment request at least includes: the type, name and weight of the first target ingredient; based on the dietary adjustment request and the ingredient database, update The diet recommendation scheme includes: based on the ingredient database, determining a second target ingredient of the same type as the first target ingredient and a corresponding replacement ratio; according to the replacement ratio and the weight of the first target ingredient, determining the second target ingredient Describe the weight of the second target ingredient. Wherein, when the target ingredient is a mixed ingredient, the diet adjustment request at least includes: the type and name of the mixed ingredient; based on the diet adjustment request and the ingredient database, updating the diet recommendation The scheme includes: based on the type of the mixed food, selecting the food component attribute corresponding to the name from the food database; the food component attribute at least includes the proportion range of the food component; based on the basic body data, determining the nutrition that the user needs to ingest Composition ratio; Based on the composition properties of the ingredients and the ratio of the nutritional ingredients, determine the proportion relationship of each ingredient in the mixed ingredients; Based on the ingredients database, the ratio relationship, and the calorie value to be ingested, determine The weight of the mixed ingredients. Wherein, after the determination of the weight of the second target ingredient, it further includes: based on the ingredient database, determining a standard weight and a standard volume corresponding to the second target ingredient; based on the weight of the second target ingredient, Standard weight and standard volume, to determine the volume of the second target ingredient. Wherein, the determining the second target ingredient of the same type as the first target ingredient and the corresponding replacement ratio based on the ingredient database includes: selecting a second target of the same type as the first target ingredient from the ingredient database ingredients; querying the first calorie value per unit weight corresponding to the first target ingredient from the ingredient database, and the second calorie value per unit weight corresponding to the second target ingredient; based on the first calorie per unit weight value and the second calorie value per unit weight to determine the replacement ratio between the second target ingredient and the first target ingredient. Wherein, the diet adjustment request also includes a meal time; the calorie value to be ingested is obtained by the following method: acquiring the user's daily metabolic data; determining the user's calorie to be ingested based on the meal time and the daily metabolic data value. Wherein, the determination of the weight of the mixed food based on the food material database, the proportional relationship, and the calorie value to be ingested includes: Based on the proportional relationship and the ingredient database, determine the calorie value per unit weight of the mixed ingredient; and determine the weight of the mixed ingredient based on the calorie value to be ingested and the calorie value per unit weight. Wherein, the ingredient data is obtained through the following methods: obtaining the ingredient type, ingredient name and ingredient attribute to establish a mapping relationship; the ingredient attribute includes at least the standard weight, standard volume, calorie value per unit weight, and ingredient component attributes of the ingredient; The mapping relationship is stored in the data file to obtain the food material data file. Correspondingly, an embodiment of the present application also provides a diet recommendation device, including: a first acquisition module, configured to acquire user data, where the user data includes at least one of basic data, disease data, exercise data, and diet data; a first determination module, configured to determine the type of etiology of the user and a dietary goal corresponding to the type of etiology according to the user data; a second determination module, configured to determine the health of the user according to the user data risk and dietary advice corresponding to the health risk; a guidance module, configured to generate dietary guidance information for the user according to the dietary goal and the dietary advice; a matching module, configured to use the user corresponding to each ingredient in the ingredient database weight, to obtain the first target ingredient that matches the dietary goal and the dietary suggestion, wherein the user weight is updated based on user behavior; a recommendation module, configured to, based on the dietary guidance information and the target ingredient, for the user Generate dietary recommendations. The device further includes: a second acquiring module, configured to acquire a dietary adjustment request of the user, the dietary adjustment request indicating that the first target ingredient in the dietary recommendation plan is replaced with a second target ingredient, the second The target ingredient is a single ingredient or a mixed ingredient; an update module, configured to update the diet based on the diet adjustment request and the ingredient database Recommended solution. Correspondingly, an embodiment of the present application also provides a dietary recommendation system, including: a client, a server, and a database; the client is configured to receive user data and dietary adjustment requests, and send the user data and dietary adjustment requests to The server; the server is used to implement the diet recommendation method described in this application; the database is used to store the ingredients database. Correspondingly, the embodiment of the present application also provides a computer-readable storage medium, the storage medium stores a computer program, and the computer program is used to execute the diet recommendation method described in the present application. Correspondingly, the embodiment of the present application also provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; the processor is used for reading the executable instructions from the memory instructions, and execute the instructions to implement the diet recommendation method described in this application. In the above-mentioned embodiment, by acquiring user data and analyzing the user data, the etiology type of the user and the diet target corresponding to the etiology type are determined, and the health risk of the user and the diet suggestion corresponding to the health risk are determined according to the user data. Dietary advice generates dietary guidance information for users, and then obtains target ingredients that match dietary goals and dietary recommendations based on the user weights corresponding to each ingredient in the ingredient database, and finally generates dietary recommendations for users based on dietary guidance information and the first target ingredient plan. This application obtains accurate user data and adopts an effective analysis method for user data to determine a highly targeted and highly accurate diet recommendation plan. At the same time, the application can update the diet recommendation plan based on the diet adjustment request, so as to obtain a diet recommendation plan suitable for the user's physical condition, thereby satisfying the user's diet preference while also achieving balanced nutrition and improving the user's experience. Other features and advantages of the embodiments of the present application will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, together with the following specific implementation methods, are used to explain the embodiments of the present application, but are not intended to limit the embodiments of the present application. In the drawings: Fig. 1 is a schematic flowchart of a diet recommendation method provided by an embodiment of this application; Fig. 2 is a schematic diagram of a food material database provided by an embodiment of this application; Fig. 3 is a diet provided by another embodiment of this application Schematic flow diagram of the recommendation method; FIG. 4 is a schematic flow diagram of updating a recommended diet plan for a single ingredient in the embodiment of the present application; FIG. 5 is a schematic flow diagram of updating a recommended diet plan for mixed ingredients in the embodiment of the application; FIG. A schematic flow chart of updating a diet recommendation plan for mixed ingredients in an embodiment; FIG. 7 is a schematic structural diagram of a diet recommendation device provided in an embodiment of the present application; FIG. 8 is a schematic diagram of a diet recommendation device provided in another embodiment of the present application Schematic diagram of the structure; FIG. 9 is a schematic diagram of the system architecture of a diet recommendation system provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The specific implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific implementation manners described here are only used to illustrate and explain the embodiments of the present application, and are not intended to limit the embodiments of the present application. As shown in Figure 1, it is a diet recommendation method provided by the embodiment of this application. The diet recommendation referred to in this application records the name of the recipe for each meal every day, the required ingredients, the content of nutrients and calories, etc. , the dietary recommendation may be a document or a form, and the present application does not limit the specific form of the dietary recommendation. The method includes: Step S101, acquiring user data, the user data including at least one of basic data, disease data, exercise data and diet data; Step S102, according to the user data, determining the etiology type of the user and Dietary goals corresponding to the type of etiology in question; Step S103. According to the user data, determine the user's health risk and dietary advice corresponding to the health risk; Step S104. Generate dietary guidance information for the user according to the dietary goal and the dietary advice; Step S105. Based on the user weight corresponding to each ingredient in the ingredient database, obtain a first target ingredient that matches the dietary goal and the dietary suggestion, wherein the user weight is updated based on user behavior; Step S106. Based on the dietary guidance information and the first target ingredient to generate a dietary recommendation plan for the user. In the above-mentioned scheme of the present application, by acquiring user data and analyzing the user data, the etiology type of the user and the diet target corresponding to the etiology type are determined, and the user’s health risk and dietary advice corresponding to the health risk are determined according to the user data. and dietary advice to generate dietary guidance information for users, and then based on the user weights corresponding to each ingredient in the ingredient database, obtain the first target ingredient that matches the dietary goal and dietary advice, and finally generate a diet for the user based on the dietary guidance information and target ingredients Recommended program. This application obtains accurate user data and adopts an effective analysis method for user data to determine a highly targeted and highly accurate diet recommendation plan. In one example, in step S101, the basic data is the user's physiological data, wherein the user's physiological data is data representing the user's physiological indicators, for example, the user's physiological data includes the user's gender, age, height, weight, waist circumference, hip circumference, etc. The user's disease data includes the user's disease course (the course of disease refers to the length of time the user has suffered from a certain disease, usually in years), disease type, test indicators corresponding to the disease type, complications, family history, medication information, etc. The test index corresponding to the disease type is the index data characterizing the disease, and the test indexes corresponding to different disease types are different. For example, for diabetes, the test indicators include fasting blood glucose, fasting insulin, average blood glucose, average insulin, random blood glucose, visceral fat level, triglyceride, transaminase, glomerular filtration rate, blood uric acid, blood pressure, insulin, C-peptide , glycosylated hemoglobin and other index data. For example, for liver disease, the test indicators include transaminase, alanine aminotransferase, aspartate Transaminase, albumin, globulin, white blood cell ratio, bilirubin, bile acid and other index data. Exercise data is data that characterizes the user's exercise behavior, and the exercise data includes the user's exercise habits, such as the user's daily exercise type and the exercise duration of each exercise. Diet data reflects the user's preference for diet, for example, he likes rice as a staple food, but he doesn't like steamed buns; among vegetables, he likes spinach and lettuce, but doesn't like carrots. The dietary data may be a table, which records information such as which ingredients the user likes and which ingredients he does not like. And which ingredients are taboo, that is, to classify the ingredients. In this application, by acquiring the user's basic data, disease data, exercise data, and diet data, on the one hand, the content of the user data is enriched; In an example, after the user data is acquired, the method further includes: preprocessing the acquired user data. Wherein, the preprocessing includes data accuracy checking and missing value processing. Check the accuracy of the acquired user data, correct or delete the inaccurate user data. For example, index data such as basic data and disease data in the user data are compared with the valid range corresponding to each index data, and whether the user data is accurate is determined according to the comparison result. If the data is inaccurate, correct or delete the wrong user data according to the comparison result. For example, if the height of an adult user is 120 centimeters, and the height does not meet the data requirements of this application, the user data will be deleted. Or a user's blood pressure is 200, and the blood pressure data does not meet the valid range of blood pressure. The user's blood pressure data is likely to be measurement problematic data, so delete this piece of user data. For example, the commonly used units of blood sugar are mg/dL and mmol/L, and the effective value ranges of different blood sugar units are different. For example, the blood sugar data of a user is 120mmol/L, which is obviously far beyond the effective value range of blood sugar. The data is likely to be an error For example, the blood glucose unit is modified to mg/dL or converted according to the conversion relationship between the two units, and the blood glucose data is corrected to 120mg/dL or 6.67mmol/L » For example, the weight data of a male user is 140 (unit is kg), but the user's waist circumference data is normal, At this time, it is likely that the unit of the weight data is "jin", so the weight data is corrected to 70kg. For the case where there are missing values in the user data, fill in the user data with missing values, for example, use the mean or mode to fill in the missing data, and if the obtained user data is enough, delete the user with missing values Data O In an example, according to step S102, according to the user data, determining the etiology type of the user and the diet target corresponding to the etiology type includes: inputting the user data into a machine learning-based etiology identification model Or a decision tree model, outputting the etiology type of the user; determining the dietary goal of the user according to the etiology type. Input the user's basic data and disease data into the etiology identification model or decision tree model based on machine learning, where the etiology identification model can be a gradient boosting tree model, a multi-category classification model, and not limited to this, and output the user's etiology after model calculation type. For example, taking the user data of diabetic patients as an example, input the user's waist circumference, hip circumference, fasting blood sugar, fasting insulin, mean blood sugar, mean insulin, random blood sugar, visceral fat level, triglycerides, transaminases, glomerular filtration rate, Blood uric acid, blood pressure, insulin, C-peptide, glycosylated hemoglobin and other index data, based on these data, the etiology identification model or decision tree model outputs the user's etiology type, for example, the etiology type is "insulin resistance caused by obesity" or "lipotoxicity with glycotoxicity" Decreased pancreatic islet function” or “Long-term lipotoxicity with glucotoxicity causes decreased pancreatic islet function and muscle loss”. Among them, the dietary goal corresponding to the etiology type of "obesity leading to insulin resistance" is fat loss; the dietary goal corresponding to the etiology type of "lipotoxicity with glycotoxicity caused by decreased islet function" is fat loss and muscle gain; "long-term lipotoxicity with glycotoxicity causes Decreased islet function and muscle loss" The dietary goal corresponding to the etiology type is to increase muscle. In an example, in addition to determining the cause type of the user based on the cause identification model or the decision tree model, the user data can also be compared with the corresponding threshold range, and the user's cause type can be determined according to the comparison result. For example, taking the basic data as an example, if the waist and hip circumference of a male user are known, the waist-to-hip ratio of the user is determined according to the ratio of the waist circumference to the hip circumference. The user's waist-to-hip ratio and a threshold range for the waist-to-hip ratio may determine the first result. For example, if the user's waist-to-hip ratio is 0.78, the comparison result is that the first result is that the user's waist-to-hip ratio does not exceed the standard; If the user's waist-to-hip ratio is 0.95, the first result is that the user's waist-to-hip ratio exceeds the standard. The type of disease takes diabetes as an example. The user’s insulin resistance is evaluated according to the fasting blood glucose and fasting insulin in the test indicators. The specific evaluation method can be HOMA-IR formula, fasting blood glucose x fasting insulin

HOMA - IR index =

22.5 where the unit of fasting blood glucose is mmlo/L, the unit of fasting insulin is fiU/mL, and 22.5 is the correction factor. Insulin resistance can also be assessed by using the HOMA-IR formula, Matsuda index, Li Guangwei index, QUISKI index, etc. For example, the Matsuda index formula is commonly used to evaluate insulin resistance.

, , 10000

Matsuda Index = - Medium

(fasting blood glucose x fasting insulin x average insulin x average blood glucose) This application does not specifically limit the method for evaluating insulin resistance. The second result can be determined according to the insulin resistance index and the threshold range of the insulin resistance index, for example, the second result is a high degree of insulin resistance, a normal degree of insulin resistance, or a low degree of insulin resistance. Similarly, the second result is determined according to the visceral fat level and the threshold range of the visceral fat level in the test index, for example, the second result is that the visceral fat level exceeds the standard or the visceral fat level does not exceed the standard. The second result is determined according to the HbA1c and the threshold range of HbA1c in the test indicators, assuming that the threshold range of HbA1c is 4% to 6%, if the user's HbA1c is 10%, the second result is that HbA1c is too high. In this application, how to determine the second result based on other inspection indexes and inspection index thresholds is not enumerated any more. According to the first result, the second result and the combination of the first result and the second result, multiple arrays are obtained, that is, an array can be a first result, a second result, or a first result and a second result A combination of results, wherein the combination of the first result and the second result includes at least one first result and one second result. The constructed knowledge base is used to record the mapping relationship between etiology types and arrays and the mapping relationship between risk types and arrays. The constructed knowledge base is shown in Table 1: Table 1

According to the user's first result and second result, determine the array where the first result and the second result are located, and determine the cause type from the knowledge base according to the mapping relationship between the array and the cause type, for example:

(1) If the first result determined based on the user's basic data and test indicators is that the waist-to-hip ratio exceeds the standard, the second result is high insulin resistance and visceral fat levels that exceed the standard. The level of visceral fat exceeds the limit in array 1. According to Table 1, there is a mapping relationship between array 1 and cause 1. Cause 1 is "insulin resistance caused by obesity". Therefore, the user's etiology type can be determined according to the user's basic data and test indicators , at this time, the user's dietary goal is to lose fat; (2) If the first result determined according to the user's basic data and inspection indicators is that the waist-to-hip ratio exceeds the standard, the second result is that the degree of insulin resistance is normal, the level of visceral fat exceeds the standard, and there is Fatty liver, in which the waist-to-hip ratio exceeds the standard, the degree of insulin resistance is normal, the level of visceral fat exceeds the standard, and there is fatty liver in group 2. According to Table 1, there is a mapping relationship between group 2 and etiology 2. The etiology type of etiology 2 is "lipotoxicity Islet function decline caused by glucose toxicity", at this time the user's dietary goal is to reduce fat and increase muscle; (3) If the first result determined according to the user's basic data and test indicators is the body mass index

(BMI) is too low, the second result is low insulin resistance, high glycosylated hemoglobin, and long course of disease, among which body mass index (BMI) is too low, low insulin resistance, high glycosylated hemoglobin, and long course of disease are in group 3 , according to Table 1, there is a mapping relationship between group 3 and etiology 3, and the etiology type of etiology 3 is "long-term lipotoxicity with glucotoxicity causing decreased islet function and muscle loss". The user's dietary goal is to gain muscle. The above three types of etiology are only examples for this application, and the types of etiology are not limited to the above three types, and this application does not limit the number of types of etiology and specific content of etiology. In one example, in step S103, the determining the health risk of the user and the diet suggestion corresponding to the health risk according to the user data includes: inputting the user data into multiple machine learning-based A health risk model or a decision tree model, outputting a result of whether the user has the health risk; determining a diet suggestion for the user according to the result of the health risk. Input the user's basic data and disease data into multiple machine learning-based health risk models or decision tree models, where the health risk model can be a gradient boosting tree model, a multi-category classification model, and not limited to this, and output the user after model calculation health risks. For example, take the user data of diabetic patients as an example, input user medication information, average blood sugar, glomerular filtration rate, blood uric acid, blood pressure, and other index data, based on these data, the health risk model or decision tree model outputs the results of health risks . For example, the results of health risks are "risk of hypoglycemia" or "risk of chronic glomerulonephritis" or "risk of high blood pressure" or "high risk of uric acid". "Chronic glomerulonephritis risk" corresponds to a low-protein diet, "hypertension risk" corresponds to a low-salt diet, and "high uric acid risk" corresponds to a low-salt diet. In one example, in addition to determining the user's health risk according to the above-mentioned health risk model or decision tree model, the array in which the first result and the second result are located can also be judged according to the user's first result and second result, and according to the array The mapping relationship between health risks and health risks is determined from the knowledge of health risks, for example:

(1) Determine the first result according to the user's medication information and the threshold value of the medication information, set the first result as hypoglycemia, hypoglycemia is in array 11, according to table 1, the mapping relationship with array 11 is risk 1, risk 1 The result of the health risk is the risk of hypoglycemia, and the corresponding dietary advice for users with this risk type is to add meals, especially before going to bed;

(2) determined according to the glomerular filtration test index and the glomerular filtration test threshold in the test index The second result, assuming that the second result is that the glomerular filtration test index exceeds the standard, the glomerular filtration test index exceeds the standard in group 12, according to Table 1, the risk relationship with group 12 that maps chronic glomerulonephritis is risk 2, risk The result of the health risk of 2 is the risk of chronic glomerulonephritis, and the corresponding dietary suggestion for users with this risk is a low-protein diet;

(3) Determine the second result according to the blood pressure index and the blood pressure threshold, assuming that the second result is high blood pressure, and the high blood pressure is in the array 13. According to Table 1, the risk type that has a mapping relationship with the array 13 is risk 3, and the health risk of risk 3 The result of is the risk of high blood pressure, and the corresponding dietary suggestion for users with this risk type is a low-salt diet;

(4) Determine the second result according to the uric acid index and the uric acid threshold, assuming that the second result is high uric acid, and the high uric acid is in the array 4. According to Table 1, the mapping relationship with the array 4 is risk 4, and the health risk result of risk 4 For high uric acid, the corresponding dietary suggestion for users with this risk type is a low-babbling diet. The above four types of health risks are only examples of this application, and the types of health risks are not limited to the above four types, and this application does not limit the number of types of health risks and specific risk content. The result of determining the user's etiology type and health risk can guide the determination of the subsequent dietary recommendation plan, thereby further improving the accuracy of the dietary recommendation. In one example, in step S104, the generating dietary guidance information for the user according to the dietary goal and the dietary suggestion includes: determining the metabolic level of the user according to the exercise data; determining the user's daily dietary energy intake based on the data, the metabolic level, and the dietary goal; generating dietary guidance information based on the daily dietary energy intake and the dietary advice, the dietary guidance information at least including The number of daily meals and the intake of each nutrient in each meal. For example, the user's metabolic level is determined according to the user's exercise data, and then the user's daily dietary energy intake is determined according to the user's basic data, metabolic level and dietary goals. For example, according to the gender, height, weight, and age in the user's basic data, the Mifflin-St Jeor The Equations equation calculates the daily calories required by the user, male: BMR(kcal)=9.99W+6.25H-4.92A+5 female: BMR(kcal)=9.99W+6.25H-4.92A-161 where W is body weight ( kg ), H is height (cm), A is age (one year old). The user's daily calorie needs can also be calculated according to Henry's equation:

18-30 years old: Male: BMR(kJ)=51x body weight (kg)+3500 Female: BMR(kJ)=47x body weight (kg)+2880

30-60 years old: Male: BMR(kJ)=53x body weight (kg)+3070 Female: BMR(kJ)=39x body weight (kg)+3070 In addition to determining the daily calorie requirement of the user using the two methods illustrated , It can also be determined by other methods, such as Cunningham Equation. LIU equation, etc. This application does not limit the method of determining the daily calorie requirement. After the user's daily calorie requirement is determined, the user's daily dietary energy intake is determined according to the user's metabolic level and dietary goals. For example, the daily calorie requirement of the user is 1800 kcal, and the metabolic level of the user is poor. And if the user's dietary goal is to lose fat, the daily dietary energy intake should be less than 1800 calories. For example, the user's metabolic level, dietary goals, and basic data are input into the model, and the model outputs the user's daily dietary energy intake according to the input data. The model can be a logistic regression model, etc., which is not limited in this application. Generate dietary guidance information based on the user's daily dietary energy intake and dietary recommendations. Dietary guidance information includes the number of meals per day, the intake of each nutrient in each meal, the content of each nutrient under standard calories; and the content of each meal under standard calories. The quality of each ingredient. The user's daily meal frequency is related to the user's disease type, user basic data and user disease data, and the meal frequency can also be determined according to the meal suggestion in the dietary suggestion. For example, some users are suitable for three meals a day, and for users with diabetes and "Somogyi phenomenon", they are suitable for four meals a day, that is, regular breakfast, lunch and evening meals and snacks before going to bed; some users are suitable for a day five meals or Six meals, this application does not set specific restrictions on the number of meals per day. The calorie ratio of each meal for each meal frequency, for example, for a user who eats four meals a day, the calorie ratio of breakfast, lunch, dinner, and extra meals before going to bed is 3:4:2:1. The intake of each nutrient in each meal is the content of carbohydrates, protein, cellulose and other nutrients required for each meal. The intake of nutrients in each meal can be determined according to the nutrient recommendations in the dietary advice. For example, the dietary advice is low protein diet, the protein intake in each meal should be reduced. The content of various nutrients under standard calories, such as the daily required content of carbohydrates, protein, fat, cellulose and other nutrients, according to the calorie ratio of each meal under each meal frequency, the required amount of each meal can also be determined The content of carbohydrates, protein, fat, cellulose and other nutrients. The quality of each ingredient in each meal under standard calories, for example, steamed buns for breakfast are 80g, milk 200g, eggs 60g, and bananas 100g _. The amount of each meal is determined according to the user's daily calorie needs and the calorie ratio of each meal under each meal frequency. The required calories; and then determine the quality of the ingredients to be selected according to the calories needed for each meal and the calories contained in a unit of ingredients. By adopting the above scheme, the accuracy of diet recommendation can be improved. In an example, the method further includes: determining dietary restrictions of the user according to the user data; and filtering the ingredients according to the dietary restrictions before acquiring the target ingredients. Dietary taboos refer to specific ingredients or ingredients that must not be included in the dietary recommendation plan due to allergies and other factors. Other ingredients made from peanuts. In one example, in step S105, based on the user weight corresponding to each ingredient in the ingredient database, the first target ingredient matching the dietary goal and the dietary suggestion is acquired, wherein the user weight is updated based on user behavior. The ingredient database is used to record ingredient information, and the ingredient information includes ingredient name, ingredient type, nutritional composition of ingredients, nutritional content and calories contained in a unit ingredient, and user weights corresponding to ingredients. Among them, the user weight corresponding to the ingredients is the weight set according to environmental factors such as region, season, urban and rural areas, and the user's personal factors. For example, for users in coastal cities, fish and shrimp are among high-quality protein The weight of fish and shrimp in high-quality protein is relatively low for users in non-coastal cities. The user's personal factors refer to the user's preference for ingredients. If the user likes a certain ingredient, the user weight of the ingredient is relatively high; if the user does not like a certain ingredient, the user weight of the ingredient is relatively low; If there is a taboo, the user weight corresponding to the taboo ingredient is 0. Figure 2 is a schematic diagram of the constructed ingredient data, such as rice, the ingredient information of rice includes the ingredient name rice, the ingredient type is the staple food, the nutritional composition of the ingredient includes carbohydrates, fat, protein, cellulose, and the nutrition of 100g rice The ingredient content is 25.9g of carbohydrates, 0.3g of fat, 2.6g of protein, and 0.3g of cellulose. The heat of 100g of rice is 116 calories, and the initial weight of rice is _2. Obtain the list of ingredients to be selected from the ingredients database, among which All the ingredients in the ingredient list are edible ingredients for the user. By combining the user's etiology type, dietary goals, dietary data and dietary taboos, the ingredients that are not suitable for the user's consumption are filtered out from the ingredient database, and the list of ingredients to be selected is obtained. For example, if the user's etiology type is "obesity leads to insulin resistance", the high-fat food in the ingredient database is not suitable for the user to eat, so the high-fat food needs to be filtered out in the ingredient database; for example, it is determined in the user's dietary taboo data that the user is allergic to shrimp , if you cannot eat shrimp, the list of ingredients to be selected does not include shrimp, for example, the list of ingredients to be selected is shown in Table 2: Table 2

In an example, determining the first target ingredient from the list of ingredients to be selected includes: constructing an ingredient pool according to user weights corresponding to the ingredients, the ingredient data includes multiple types of ingredients, and the quantity of each type of ingredient According to the determination of the user weight corresponding to the type of food, the first target food is randomly selected from the food pool. For the list of ingredients to be selected obtained above, a ingredient pool is constructed according to the user weights corresponding to the ingredients. For example, the ingredient pool includes 10 types of ingredients, numbered as ingredients 1 to 10, and the weights of ingredients 1 to 10 are 1. , 2, 2, 3, 2, 2, 1, 4, 3, 5, assuming that the number of ingredients in the ingredient pool is 100, the numbers of ingredients 1 to 10 in the ingredient pool are 4, 8, 8, 12, 8, 8, 4, 16, 12, 20, randomly select ingredients 1 to 10 from the ingredient pool, and since ingredient 10 has the largest weight, the probability of being selected for ingredient 10 is the highest. In an example, updating the user weight based on user behavior includes: updating the user weight according to the user's individual behavior and/or environment analysis. The user's individual behavior includes the user's replacement operation and search operation for a certain ingredient, and the environmental analysis includes changes in seasons, changes in the user's location, and changes in the price of the ingredient. In an example, updating the user weight according to the user's individual behavior includes: if the user has a replacement operation on a certain ingredient and the number of replacement operations is greater than a threshold, reducing the weight of the user corresponding to the ingredient. Weights; If the user performs a search operation on a certain ingredient and selects the ingredient as the target ingredient, the user weight corresponding to the ingredient is increased. For example, the user has 30 days of behavior records. If the user chooses not to eat beef today (if beef is included in the dietary recommendation plan, choose to replace it), and the beef in the previous 30-day record is normally adopted, this situation will not reduce the beef corresponding The user weight of , the reason may be "there is no beef in the refrigerator and cannot be made". Similarly, if the user chooses not to eat beef several times in the past week, it at least indicates that the user has not eaten beef recently or is inconvenient to eat beef, then the weight of the user corresponding to beef should be reduced to ensure that the probability of beef being recommended in the next period of time is certain The magnitude is reduced. For example, if a user searches for shovel fish and adds shovel fish to his diet recommendation plan, the user weight corresponding to shovel fish will be increased. In one example, environmental analysis includes changes in seasons, changes in user locations, and changes in food prices. For example, summer in a certain area is the harvest season for shrimp, and the weight of users corresponding to shrimp increases in summer, while the weight of users corresponding to shrimp decreases in winter. . Or if the price of a certain ingredient increases and exceeds the user's expectations, the user weight corresponding to the ingredient will be reduced accordingly. By dynamically adjusting the user weight corresponding to each ingredient, it is beneficial to improve the efficiency and accuracy of the diet recommendation plan. In one example, in step S106, generating a dietary recommendation plan for the user based on the dietary guidance information and the first target ingredient includes: determining the first target ingredient according to the first target ingredient The weight of each first target ingredient in the recipe is determined according to the attribute data of the first target ingredient, the intake of each nutrient in each meal, and the cooking method. In an example, after the first target ingredient is determined, the recipe corresponding to the first target ingredient is determined from a recipe library, the recipe library is used to record recipe information, and the recipe information includes recipe preparation method, cooking method, attention Items, ingredient lists, and recipe weights. Determine the list of recipes to be selected from the ingredient database according to the dietary taboo and ingredient list, and if the ingredient list contains ingredients in the dietary taboo data, filter the recipes containing the ingredient list from the ingredient database. For example, if the user is allergic to peanuts, although the ingredients in recipe A do not include peanuts, when recipe A is made, the ingredient list includes peanut butter, then recipe A is filtered and cannot become a candidate recipe. After filtering out unselectable recipes in the recipe library, the list of remaining recipes is A list of recipes to choose from. In an example, determining the first target recipe from the list of candidate recipes includes: constructing a recipe pool according to the weight of the recipes, the recipe library includes multiple types of recipes, and the number of recipes of each type is based on the weight of the type The weight of the recipe is determined, and the target recipe is randomly selected from the recipe pool. For example, there are five recipes in the list of recipes to be selected, numbered respectively as recipe 1 to recipe 5, and the weights of recipe 1 to recipe 5 are respectively 1, 2, 2, 3, 2, and a recipe pool with a total of 100 recipes is constructed. Then the numbers of recipes 1 to 5 in the recipe pool are 10, 20, 20, 30, and 20 respectively, and the first target recipe is randomly selected from the recipe pool. Finally, the weight of each first target ingredient in the first target recipe is determined according to the attribute data of the first target ingredient, the intake of each nutrient in each meal, and the cooking method. As shown in FIG. 3 , it is a schematic flowchart of a diet recommendation method provided by another embodiment of the present application. The diet recommendation method further includes: Step S107, acquiring a user's diet adjustment request, and the diet adjustment request indicates that the diet recommendation plan will include: The first target ingredient is replaced by the second target ingredient, and the second target ingredient is a single ingredient or a mixed ingredient; Step S108, based on the diet adjustment request and the ingredient database, update the diet recommendation plan. The embodiment of the present application can update the diet recommendation plan based on the diet adjustment request, so as to obtain a diet recommendation plan suitable for the user's physical condition, thereby achieving nutritional balance while satisfying the user's diet preference. As shown in FIG. 4, it is a schematic flowchart of updating a dietary recommendation plan for a single ingredient in an embodiment of the present application. The method at least includes the following operation process: Step S201, based on the ingredient database, determine a second target that is the same type as the first target ingredient The ingredients and the corresponding replacement ratio; step S202, according to the replacement ratio and the weight of the first target ingredient, determine the weight of the second target ingredient; step S203, based on the ingredient database, determine the standard weight and standard corresponding to the second target ingredient Volume; step S204, based on the weight, standard weight and standard volume of the second target food, determine the volume of the second target food. In S201, a dietary adjustment request is acquired based on a user's trigger. At this time, the second target ingredient used to replace the first target ingredient in the dietary adjustment request is a single ingredient. The ingredient database is mainly generated based on the ingredient knowledge graph. Specifically, a mapping relationship is established between the type of ingredients, the name of the ingredients, and the attributes of the ingredients; the attributes of the ingredients include at least the standard weight, standard volume, calorie value per unit weight, and ingredient attributes of the ingredients; the mapping relationship is stored in the data. Knowledge map, get the ingredients database. Based on the mapping relationship in the ingredient database, a second target ingredient of the same type as the first target ingredient and a corresponding replacement ratio are determined to generate a replacement interface. For example, select a second target ingredient of the same type as the first target ingredient from the ingredient database; query the calorie value per unit weight corresponding to the first target ingredient and the second unit weight corresponding to the second target ingredient from the ingredient database calorie value; based on the first calorie value per unit weight and the second calorie value per unit weight, determine the replacement ratio between the second target ingredient and the first target ingredient, and generate a replacement interface. In S202, based on the user's selection of the second target ingredient option on the replacement interface, determine the second target ingredient; and calculate the weight of the second target ingredient according to the replacement ratio corresponding to the second target ingredient and the weight of the first target ingredient. In this embodiment of the present application, a request for dietary adjustment is obtained; and based on the ingredient database, a second target ingredient of the same type as the first target ingredient and a corresponding replacement ratio are determined to generate a replacement interface; the replacement interface includes at least two options for the second target ingredient ; Then, based on the selection of the replacement interface option, the weight of the second target ingredient is determined according to the replacement ratio and the weight of the first target ingredient. Thus, based on the ingredients database, the basic ingredients can be replaced according to the user's preferences, which improves the user's experience. In S203 and S204, query the standard weight and standard volume corresponding to the second target ingredient from the ingredient data; calculate the volume of the second target ingredient by using the weight, standard weight and standard volume of the second target ingredient. Therefore, the embodiment of the present application can determine the target ingredient based on the mapping relationship in the ingredient database The volume improves user experience. The embodiments of the present application will be described in detail below in conjunction with specific applications. Obtain the diet adjustment request of the first target ingredient A. The diet adjustment request includes at least the type, name and weight of ingredient A (single ingredient); for example, the type is staple food, the name is Yangmai noodles and the weight is 200g. A second target ingredient of the same type as ingredient A is queried from the ingredient database (in this case, the second target ingredient is a single ingredient), such as glutinous rice and vermicelli. Query from the ingredients database that the calorie value per unit weight corresponding to dried noodles is 130cal/100g, the calorie value per unit weight corresponding to glutinous rice is 125cal/100g, and the calorie value per unit weight corresponding to wheat noodles is 120cal/100g; based on dried noodles The corresponding calorie value per unit weight, the calorie value per unit weight corresponding to glutinous rice, and the calorie value per unit weight corresponding to wheat-raising noodles, the replacement ratio between glutinous rice and wheat-raising noodles is 1.04, and the replacement between dry noodles and wheat-raising noodles The ratio is 1.08, and a replacement interface is generated; the replacement interface includes the option of shaking glutinous rice and noodles. Based on the selection of the glutinous rice option on the replacement interface, according to the corresponding replacement ratio of glutinous rice and the weight of wheat-raising noodles, the weight of glutinous rice is 208g. The calculation formula of the replacement ratio is shown in the following formula (1), and the calculation formula of the target ingredient weight is shown in the formula (2). Substitution ratio = Calorie value per unit weight of the target ingredient/Calorie value per unit weight of the first target ingredient formula (1); Target ingredient weight = First target ingredient weight * Replacement ratio formula (2). Query the glutinous rice corresponding to a standard weight of 50 g and a standard volume of 160 mL from the food material database. Based on the weight of glutinous rice, standard weight and standard volume, the volume of glutinous rice is obtained as 520 mL. The calculation formula for the second target food material volume is shown in the following formula (3). Volume of the second target ingredient=(weight of the second target ingredient/standard weight of the second target ingredient)*standard volume of the second target ingredient formula (3). The ingredients database in the embodiment of the present application may also include GI value, GI level first-level recommendation weight, and the like. The establishment of the ingredient database is determined in combination with actual application scenarios. It should be noted that the method in the embodiment of the present application is applicable to the replacement of a single ingredient, and for mixing Substitution of a single ingredient in the ingredients is also possible. A single ingredient includes a single staple food, high-quality protein, vegetables, etc. As shown in FIG. 5 , it is a schematic flow chart of updating a dietary adjustment plan for mixed ingredients in an embodiment of the present application; the method at least includes the following operation flow: Step S301, obtaining a dietary adjustment request indicating that the first target ingredient is replaced with a mixed ingredient ; The dietary adjustment request includes at least the type and name of the mixed ingredients; step S302, based on the type of mixed ingredients, select the ingredient attribute corresponding to the name from the ingredient database; the ingredient attribute at least includes the ratio range of ingredients; Based on the basic data, determine the proportion of nutrients that the user needs to ingest; Step S304, based on the properties of ingredients and the proportion of nutrients, determine the proportion of each ingredient in the mixed ingredients; Step S305, based on the database of ingredients, the ratio, and Enter the calorie value to determine the weight of the mixed ingredients. In S301 to S302, when the name of the mixed ingredient is pork and chive dumplings, the ingredients of the ingredient are, for example, tenderloin and leek. Attributes of ingredient ingredients include the proportion range of tenderloin in dumplings and leeks in dumplings; ingredients attribute also includes information such as protein content and fat content of tenderloin, and corresponding vitamin content of leeks. In S303 to S305, the basic body data includes the user's body composition data and disease data. Body composition data such as height, weight, age, etc.; disease data such as comorbidities and complications. The calorie value to be ingested is obtained by the following methods: acquiring the user's daily metabolic data; determining the user's calorie value to be ingested based on the meal time and the daily metabolic data. Here, the calorie value to be ingested corresponds to the meal time, such as morning, noon or evening. The daily metabolic data refers to the user's average daily metabolic data, which includes the user's diet data, exercise data, and the like. The ingredient database is obtained through the following methods: Obtain the ingredient type, ingredient name and ingredient attribute to establish a mapping relationship; the ingredient attribute includes at least the standard weight, standard volume, unit weight calorie value of the ingredient, and the ingredient attribute of the ingredient; store the mapping relationship in the database , to get the ingredient database. As shown in Figure 6, it is an updated dietary adjustment plan for mixed ingredients in another embodiment of the present application. The flow chart, the method at least includes the following operation process: Step S401, obtain a diet adjustment request for the mixed ingredients; the diet adjustment request includes at least the type and name of the mixed ingredients; Step S402, based on the type, select from the ingredient database corresponding to the name Attributes of food ingredients; The attributes of ingredients include at least the proportion of ingredients; Step S403, based on the basic body data, determine the proportion of nutrients that the user needs to ingest; Step S404, Based on the attributes of ingredients and the proportion of nutrients, determine The proportion relationship of ingredients; Step S405, based on the proportion relationship and the ingredients database, determine the calorie value per unit weight of the mixed ingredients; Step S406, determine the weight of the mixed ingredients based on the calorie value to be ingested and the calorie value per unit weight. Wherein, the specific implementation processes of S401, S402, S403, and S404 are similar to those of S301, S302, S303, and S304, and will not be repeated here. In S405 and S406, the calorie value per unit weight of each food component in the proportional relationship is queried from the food material database, so as to obtain the calorie value per unit weight of the mixed food material. The weight of the mixed food is calculated by using the calorie value to be ingested and the calorie value per unit weight. It should be understood that in various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not be implemented in this application. The implementation of the examples constitutes no limitation. The following describes the embodiments of the present application in detail in combination with specific application scenarios. Obtain the user's request for pork and leek; select the tenderloin component attribute and leek component attribute corresponding to pork and leek dumplings from the ingredient database. Based on the user's basic body data, determine the proportion of nutrients that the user needs to ingest; based on the composition attributes of tenderloin and leeks, as well as the proportion of nutrients, determine the ratio of tenderloin and leeks in pork and leek dumplings. Since the basic body data of different users are different, the proportions of ingredients in the corresponding pork and leek dumplings are also different. The final proportional relationship will be reflected in the dumpling making process. Based on the proportional relationship, from food Query the calorie value per unit weight corresponding to pork and leek dumplings in the material database. Based on the user's basic physical data, determine the calorie value to be ingested by the user in a day; if the meal time is noon, then the calorie value to be ingested corresponding to noon is to divide the calorie value to be ingested in the day into three parts on average, and obtain the calorie value corresponding to noon Calorie value to be ingested. According to the calorie value to be ingested and the calorie value per unit weight, the weight and volume (or number) of pork and leek dumplings recommended for consumption are calculated. For example: the user chooses pork and leek dumplings, and according to the user’s basic body data, it is determined that the calorie intake is 420kcal, and the nutritional content focuses on high-quality protein (through calculation, pork accounts for 50%, leeks account for 45%, other (sesame oil and other ingredients) 5 %), and based on this ratio, it is calculated that every 100g of dumplings contains 189kcal of calories, so the user should eat 196g of dumplings to meet the calorie demand. Users of this application may be ordinary users, or patients with chronic diseases, such as type 2 diabetes patients, or hypertensive patients. In terms of mixing ingredients, the embodiment of the present application can determine the proportion of ingredients in combination with the user's real physical condition, so as to achieve a better nutritional balance. FIG. 7 is a schematic structural diagram of a diet recommendation device provided by an embodiment of the present application. The device includes: a first acquisition module 501, configured to acquire user data, and the user data includes basic data, disease data, and exercise data and at least one item of dietary data; a first determination module 502, configured to determine the user's etiology type and a diet target corresponding to the etiology type according to the user data; a second determination module 503, configured to determine the etiology type according to The user data is used to determine the health risk of the user and the dietary advice corresponding to the health risk; the guidance module 504 is used to generate dietary guidance information for the user according to the dietary goal and the dietary advice; a matching module 505. Based on the user weight corresponding to each ingredient in the ingredients, obtain the first target ingredient that matches the dietary goal and the dietary suggestion, wherein the user weight is updated based on user behavior; the recommendation module 506 is used for Based on the dietary guidance information and the first target ingredient, for the user Generate dietary recommendations. FIG. 8 is a schematic structural diagram of a diet recommendation device provided by another embodiment of the present application, the device further includes: a second acquisition module 507, configured to acquire the user's diet adjustment request, the diet adjustment request Instructing to replace the first target ingredient in the dietary recommendation plan with a second target ingredient, the second target ingredient being a single ingredient or a mixed ingredient; an update module 508, configured to adjust the diet based on the request and the ingredient database , updating the dietary recommendation scheme. The embodiment of the present application also provides a dietary recommendation system, including: a client, a server, and a database; the client is used to receive user data and dietary adjustment requests, and send the user data and dietary adjustment requests to the server; The server is used to implement the diet recommendation method described in this application; the database is used to store a food material database. As shown in FIG. 9, it is an exemplary system architecture diagram to which this embodiment of the present application can be applied. The system architecture 800 may include terminal devices 801, 802, and 803, a network 804, and a server 805. The network 804 is used to provide a communication link medium between the terminal devices 801, 802, 803 and the server 805. Network 804 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others. Users can use terminal devices 801, 802, and 803 to interact with the server 805 through the network 804 to receive or send messages and the like. Various communication client applications can be installed on the terminal devices 801, 802, and 803, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (just examples). Terminal devices 801, 802, and 803 may be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like. The server 805 may be a server that provides various services, such as a background management server that provides support for click events generated by users using terminal devices 801, 802, and 803 (just an example). The background management server can analyze and process the received click data, text content and other data, and process the Results (eg target push information, product information - just an example) are fed back to the end device. It should be noted that the diet adjustment method provided in the embodiment of the present application is generally executed by the server 805, and correspondingly, the diet adjustment device is generally set in the server 805. It should be understood that the numbers of terminal devices, networks, and servers in FIG. 9 are only illustrative. According to implementation requirements, there may be any number of terminal devices, networks and servers. The embodiment of the present application also provides a computer-readable storage medium, the storage medium stores a computer program, and the computer program is used to implement the diet recommendation method described in the present application. The embodiment of the present application also provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; the processor is used for reading the executable instructions from the memory, and The instructions are executed to implement the diet recommendation method described in this application. In addition to the above-mentioned methods and devices, embodiments of the present application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the above-mentioned "exemplary method" in this specification. Steps in methods according to various embodiments of the application described in section. The computer program product can be written in any combination of one or more programming languages for executing the program codes for the operations of the embodiments of the present application, and the programming languages include object-oriented programming languages, such as Java, C++, etc. , including conventional procedural programming languages such as

Executes partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on the remote computing device, or entirely on the remote computing device or server. In addition, the embodiment of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the processor executes the above-mentioned "Exemplary Method" part of this specification. Steps in methods according to various embodiments of the application described in . The computer readable storage medium may employ any combination of one or more readable media. Can The read medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, advantages, effects, etc. mentioned in this application are only examples rather than limitations, and these advantages, advantages, effects, etc. cannot be considered to be Various embodiments of this application must have. In addition, the specific details disclosed above are only for the purpose of illustration and understanding, rather than limitation, and the above details do not limit the application to be implemented by using the above specific details. The block diagrams of devices, devices, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be recognized by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having" and the like are open-ended words meaning "including but not limited to" and may be used interchangeably therewith. As used herein, the words "or" and "and" refer to the word "and/or" and are used interchangeably therewith, unless the context clearly dictates otherwise. As used herein, the word "such as" refers to the phrase "such as but not limited to" and can be used interchangeably. It should also be pointed out that in the devices, equipment and methods of the present application, each component or each step can be decomposed and/or reassembled. These decompositions and/or recombinations should be considered equivalents of this application. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to The embodiments of the application are limited to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and subcombinations thereof.

Claims

1. A diet recommendation method, comprising: acquiring user data, the user data including at least one of basic data, disease data, exercise data and diet data; according to the user data, determining the etiology type of the user and a dietary target corresponding to the etiology type; according to the user data, determine the user's health risk and a dietary suggestion corresponding to the health risk; generate a diet for the user according to the dietary target and the dietary suggestion guidance information; based on the user weight corresponding to each ingredient in the ingredient database, obtain a first target ingredient that matches the dietary goal and the dietary suggestion, wherein the user weight is updated based on user behavior; based on the dietary guidance information and The first target ingredient generates a dietary recommendation plan for the user.

2. The method according to claim 1, wherein according to the user data, determining the etiology type of the user and the dietary goal corresponding to the etiology type comprises: inputting the user data into the etiology based on machine learning An identification model or a decision tree model, outputting the etiology type of the user; determining the dietary goal of the user according to the etiology type.

3. The method according to claim 1, said determining the health risk of the user and the dietary advice corresponding to the health risk according to the user data, comprising: inputting the user data into a plurality of machine learning-based A health risk model or a decision tree model, outputting a result of whether the user has the health risk; determining a diet suggestion for the user according to the health risk result.

4. The method according to claim 1, said generating dietary guidance information for said user according to said dietary goal and said dietary suggestion, comprising: determining the metabolic level of said user according to said exercise data; determining the user's daily dietary energy intake from the basic data, the metabolic level and the dietary target; Dietary guidance information is generated according to the daily dietary energy intake and the dietary suggestion, and the dietary guidance information at least includes the number of meals per day and the intake of each nutrient component per meal.

5. The method according to claim 1, further comprising: determining dietary taboos of the user according to the user data; and filtering ingredients according to the dietary taboos before obtaining the first target food material.

6. The method according to claim 1, wherein the user weight is updated based on user behavior, comprising: updating the user weight according to the user's individual behavior and/or environment analysis.

7. The method according to claim 6, the user's individual behavior includes the user's replacement operation and search operation for a certain food material, and the environmental analysis includes changes in seasons, changes in user locations, and changes in food prices.

8. The method according to claim 7, updating the user weight according to the user's individual behavior, comprising: if the user has a replacement operation on a certain ingredient and the number of times of the replacement operation is greater than a threshold, reducing the weight The user weight corresponding to the ingredient; and/or if the user performs a search operation on a certain ingredient and selects the ingredient as the first target ingredient, increasing the user weight corresponding to the ingredient.

9. The method according to claim 1, said generating a dietary recommendation plan for the user based on the dietary guidance information and the first target ingredient, comprising: determining the first target ingredient according to the first target ingredient The corresponding recipe; determine the weight of each first target ingredient in the recipe according to the attribute data of the first target ingredient, the intake of each nutrient in each meal, and the cooking method.

10. The method according to claim 1, further comprising: obtaining the user's diet adjustment request, the diet adjustment request indicating that the first target ingredient in the diet recommendation plan should be replaced by a second target ingredient, The second target ingredient is a single ingredient or a mixed ingredient; based on the diet adjustment request and the ingredient database, the diet recommendation plan is updated.

11. The method according to claim 10, when the second target ingredient is a single ingredient Herein, the dietary adjustment request at least includes: the type, name and weight of the first target ingredient; the updating of the dietary recommendation plan based on the dietary adjustment request and the ingredient database includes: based on the ingredient database, determining the same A second target ingredient of the same type as the first target ingredient and a corresponding replacement ratio; according to the replacement ratio and the weight of the first target ingredient, determine the weight of the second target ingredient.

12. The method according to claim 10, when the target ingredient is a mixed ingredient, the dietary adjustment request at least includes: the type and name of the mixed ingredient; The above-mentioned ingredient database, and updating the recommended diet plan includes: based on the type of the mixed ingredient, selecting an ingredient attribute corresponding to the name from the ingredient database; the ingredient attribute at least includes an ingredient ratio range; based on the body Based on the basic data, determine the proportion of nutritional components that the user needs to ingest; Based on the ingredients of the ingredients and the proportion of the nutritional components, determine the proportional relationship of each ingredient in the mixed ingredients; Based on the ingredient database, the proportional relationship , and the calorie value to be ingested, to determine the weight of the mixed food.

13. The method according to claim 11, after determining the weight of the second target ingredient, further comprising: based on the ingredient database, determining a standard weight and a standard volume corresponding to the second target ingredient; The weight, standard weight, and standard volume of the second target ingredient determine the volume of the second target ingredient.

14. The method according to claim 11, said determining a second target ingredient of the same type as the first target ingredient and a corresponding replacement ratio based on the ingredient database, comprising: selecting the second target ingredient from the ingredient database A second target ingredient of the same type as the target ingredient; querying the ingredient database for a first calorie value per unit weight corresponding to the first target ingredient, and a second calorie value per unit weight corresponding to the second target ingredient ; Based on the first calorie value per unit weight and the second calorie value per unit weight, determine the second A replacement ratio between the target ingredient and the first target ingredient.

15. The method according to claim 12, wherein the diet adjustment request further includes a meal time; the value of the calories to be ingested is obtained by the following method: obtaining the user's daily metabolism data; based on the meal time and the daily metabolism data to determine the calorie value to be ingested by the user.

16. The method according to claim 12, the determining the weight of the mixed food based on the food material database, the proportional relationship, and the calorie value to be ingested, comprising: based on the proportional relationship and the food material a database, determining the calorie value per unit weight of the mixed food; and determining the weight of the mixed food based on the calorie value to be ingested and the calorie value per unit weight.

18. A diet recommendation device, comprising: a first acquisition module, configured to acquire user data, the user data including at least one of basic data, disease data, exercise data, and diet data; a first determination module, configured to According to the user data, determine the type of etiology of the user and the dietary goal corresponding to the type of etiology; a second determining module, configured to determine the health risk of the user and the health risk related to the user according to the user data Corresponding dietary advice; a guidance module, configured to generate dietary guidance information for the user according to the dietary goal and the dietary advice; a matching module, configured to obtain the diet information based on the user weight corresponding to each ingredient in the ingredient database. A first target ingredient that matches the target and the dietary suggestion, wherein the user weight is updated based on user behavior; a recommendation module, configured to generate a dietary recommendation plan for the user based on the dietary guidance information and the target ingredient.

19. The device according to claim 18, further comprising: a second acquiring module, configured to acquire the dietary adjustment request of the user, the dietary adjustment request Instructing to replace the first target ingredient in the dietary recommendation plan with a second target ingredient, the second target ingredient being a single ingredient or a mixed ingredient; an update module, configured to, based on the dietary adjustment request and the ingredient database, The dietary recommendations are updated. 20. A diet recommendation system, comprising: a client, a server, and a database; the client is used to receive user data and diet adjustment requests, and send the user data and diet adjustment requests to a server; the server is used to Executing the method described in any one of claims 1-17; the database is used to store a food material database. 21. A computer-readable storage medium, the storage medium stores a computer program, and the computer program is used to execute the diet recommendation method according to any one of claims 1-17.

22. An electronic device, comprising: a processor; a memory for storing instructions executable by the processor; the processor is used for reading the executable instructions from the memory and executing the instructions To realize the diet recommendation method described in any one of the above claims 1-17.