Catering recommendation method and system based on personal nutrition intake

Abstract

The invention provides a catering recommendation method and system based on personal nutrition intake, and the method comprises the steps: S1, constructing a nutrition analysis model, and obtaining a target nutrition intake parameter according to the nutrition analysis model; s2, meal nutrition intake parameters are obtained according to the user meal data; s3, analyzing to obtain recommended nutrition intake parameters; s4, analyzing to obtain a dish component recommendation coefficient, a dish side dish recommendation coefficient and a dish first recommendation coefficient of the existing dish; s5, according to the restaurant geographic position of the restaurant corresponding to the existing dishes and the user position data, obtaining a second dish recommendation coefficient of the existing dishes; and S6, analyzing to obtain a comprehensive dish recommendation coefficient of the existing dishes, obtaining a dish recommendation sequence of the existing dishes according to the comprehensive dish recommendation coefficient, and forming a catering recommendation scheme of the target user according to the dish recommendation sequence and the restaurant geographic positions of the existing dishes. According to the invention, the comprehensiveness and accuracy of the catering recommendation result are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health management, and in particular to a meal recommendation method and system based on individual nutrient intake. BACKGROUND

[0002] At present, with the significant improvement of living standards, people pay more and more attention to their own health status, and the importance of healthy diet is increasingly highlighted. Reasonable dietary collocation can provide the human body with various nutrients required to maintain life activities and keep the body healthy, including protein, carbohydrates, fats, vitamins, and minerals, etc. Scientific diet not only helps to enhance the body's immunity, prevent diseases, but also improves the overall quality of life. For special groups, such as chronic disease patients, athletes, pregnant women and the elderly, reasonable dietary collocation plays a key role in disease treatment, body recovery and maintaining good body function, etc.

[0003] In related technologies, the meal recommendation method often cannot determine the target nutrient intake of the user according to the user information, nor can it obtain the accurate recommended nutrient intake of the user according to the actual meal data of the user, and it cannot combine the geographical location of the user to recommend the meal location when the user performs meal recommendation, resulting in a lack of accuracy of the meal recommendation result, which needs to be improved. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a meal recommendation method and system based on individual nutrient intake, so as to improve the problem that in related technologies, the meal recommendation method often cannot determine the target nutrient intake of the user according to the user information, nor can it obtain the accurate recommended nutrient intake of the user according to the actual meal data of the user, and it cannot combine the geographical location of the user to recommend the meal location when the user performs meal recommendation, resulting in a lack of accuracy of the meal recommendation result.

[0005] The present application provides a meal recommendation method based on individual nutrient intake, comprising:

[0006] Step S1: obtaining user information data of a target user, the user information data including user basic information and user diet information of the target user; constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting target nutrient intake parameters corresponding to the target user according to the nutrition analysis model;

[0007] Step S2: obtaining user meal data of the target user, analyzing the user meal data to obtain meal nutrient intake parameters of the target user;

[0008] Step S3: comparing and analyzing the target nutrient intake parameters and the meal nutrient intake parameters to obtain recommended nutrient intake parameters of the target user;

[0009] Step S4: obtaining user location data of the target user, and constructing a dish information library according to the user location data, the dish information library containing at least one existing dish; performing analysis according to the existing dish and the recommended nutrient intake parameter to obtain a dish component recommendation coefficient of the existing dish; performing analysis according to the existing dish and user diet information to obtain a dish accompaniment recommendation coefficient of the existing dish; obtaining a dish first recommendation coefficient of the existing dish according to the dish component recommendation coefficient and the dish accompaniment recommendation coefficient;

[0010] Step S5: obtaining a restaurant geographic location of the existing dish corresponding restaurant, and obtaining a dish second recommendation coefficient of the existing dish according to the restaurant geographic location and the user location data;

[0011] Step S6: obtaining a dish comprehensive recommendation coefficient of the existing dish according to the dish first recommendation coefficient and the dish second recommendation coefficient, and obtaining a dish recommendation order of the existing dish according to the dish comprehensive recommendation coefficient, and constructing a catering recommendation scheme of the target user according to the dish recommendation order and the restaurant geographic location of the existing dish.

[0012] Further, user information data of the target user is obtained, the user information data including user basic information and user diet information of the target user, specifically:

[0013] The user basic information includes basic attributes, physiological state, body data, activity level and health status of the target user;

[0014] The user diet information includes a favorite dish accompaniment of the target user.

[0015] Further, a nutrition analysis model is constructed, the user basic information of the target user is input into the nutrition analysis model, and a target nutrient intake parameter corresponding to the target user is output according to the nutrition analysis model, specifically:

[0016] The nutrition analysis model contains a nutrition analysis algorithm;

[0017] Nutrition analysis reference data is obtained, and a nutrition analysis training library is generated according to the nutrition analysis reference data;

[0018] The nutrition analysis algorithm in the nutrition analysis model is trained according to the nutrition analysis reference data in the nutrition analysis training library to obtain a target nutrition analysis algorithm of the nutrition analysis model;

[0019] The user basic information of the target user is taken as a model input parameter, and the model input parameter is input into the nutrition analysis model; the target nutrient intake component corresponding to the target user and the target nutrient component intake amount corresponding to the target nutrient intake component are obtained and output according to the target nutrition analysis algorithm in the nutrition analysis model.

[0020] According to the target nutrition intake component and the target nutrition component intake amount corresponding to the target nutrition intake component, the target nutrition intake parameter corresponding to the target user is constituted.

[0021] Further, user meal data of the target user is acquired, and the meal nutrition intake parameter of the target user is obtained by analyzing the user meal data, specifically:

[0022] The user meal data includes a user meal picture of the target user;

[0023] According to the user meal picture, the food type of the food eaten by the user is obtained, and the food amount corresponding to the food type is obtained;

[0024] And according to the food type and the food amount of the food eaten by the user, the meal nutrition intake component corresponding to the food eaten by the user is obtained, and the meal nutrition component content corresponding to the meal nutrition intake component is obtained;

[0025] According to the meal nutrition component and the meal nutrition component content corresponding to the meal nutrition component, the meal nutrition intake parameter of the target user is constituted.

[0026] Further, the target nutrition intake parameter and the meal nutrition intake parameter are compared and analyzed to obtain the recommended nutrition intake parameter of the target user, specifically:

[0027] The target nutrition intake component in the target nutrition intake parameter is matched with the parameter nutrition intake component in the meal nutrition intake parameter to obtain a component matching result;

[0028] According to the component matching result, the target nutrition intake component in the target nutrition intake parameter that is consistent with the parameter nutrition intake component is recorded as the same intake component;

[0029] If the target nutrition component content corresponding to the same intake component is greater than the meal nutrition component content, the same intake component is recorded as the recommended nutrition intake component, and the recommended nutrition component intake amount corresponding to the recommended nutrition intake component is obtained according to the target nutrition component content and the meal nutrition component content;

[0030] According to the component matching result, the target nutrition intake component in the target nutrition intake parameter that is inconsistent with the parameter nutrition intake component is recorded as the recommended nutrition intake component, and the target nutrition component intake amount of the target nutrition intake component is recorded as the recommended nutrition component intake amount corresponding to the recommended nutrition intake component.

[0031] Further, user position data of the target user is acquired, and a dish information library is constructed according to the user position data; the existing dish and the recommended nutritional intake parameter are analyzed to obtain a dish component recommendation coefficient of the existing dish, specifically:

[0032] The user position data includes a user geographic position and a user preset dining range of the target user;

[0033] According to the user geographic position and the user preset dining range, restaurant information of the geographic position where the target user is located is acquired, and a dish information library is constructed according to the restaurant information; the dish information library contains at least one existing dish, and each existing dish corresponds to at least one restaurant information;

[0034] The dish nutritional components of the existing dish in the dish information library are acquired, the dish nutritional components of the existing dish are compared with the recommended nutritional intake components of the target user, and the dish nutritional components of the existing dish that are consistent with the recommended nutritional intake components are recorded as matched nutritional components;

[0035] According to the matched nutritional component content of the matched nutritional components in the existing dish and the recommended nutritional component intake of the recommended nutritional intake component corresponding to the matched nutritional component, a first component recommendation coefficient of the existing dish is obtained;

[0036] The nutritional component proportion of the matched nutritional component in the recommended nutritional intake component in the existing dish is acquired, and a second component recommendation coefficient of the existing dish is obtained according to the nutritional component proportion;

[0037] The dish component recommendation coefficient of the existing dish is obtained according to the first component recommendation coefficient and the second component recommendation coefficient.

[0038] Further, the existing dish and the user diet information are analyzed to obtain a dish side dish recommendation coefficient of the existing dish; a first dish recommendation coefficient of the existing dish is obtained according to the dish component recommendation coefficient and the dish side dish recommendation coefficient, specifically:

[0039] A side dish database is established according to the target user's favorite side dish; the side dish database contains at least one favorite side dish;

[0040] The dish side dish in the existing dish is acquired, and the dish side dish is compared with the favorite side dish in the side dish database to obtain a favorite side dish proportion of the dish side dish in the existing dish in the favorite side dish in the side dish database;

[0041] The dish side dish recommendation coefficient of the existing dish is obtained according to the favorite side dish proportion;

[0042] The component recommendation weight value and the side dish recommendation weight value are set; the dish first recommendation coefficient of the existing dish is obtained according to the component recommendation weight value, the dish component recommendation coefficient, the side dish recommendation weight value and the dish side dish recommendation coefficient.

[0043] Further, step S5 is specifically:

[0044] The dining distance value corresponding to the existing dish is obtained according to the user geographic position of the target user and the restaurant geographic position, and the dish second recommendation coefficient of the existing dish is obtained according to the dining distance value.

[0045] Further, step S6 is specifically:

[0046] The first coefficient weight value and the second coefficient weight value are set;

[0047] The dish comprehensive recommendation coefficient of the existing dish is obtained according to the first coefficient weight value, the dish first recommendation coefficient, the second coefficient weight value and the dish second recommendation coefficient;

[0048] The dish recommendation priority corresponding to the existing dish is obtained according to the dish comprehensive recommendation coefficient, and the dish recommendation order is obtained according to the dish recommendation priority.

[0049] In a second aspect, the application provides a meal recommendation system based on individual nutritional intake, which is applied to a meal recommendation method based on individual nutritional intake, and the system comprises:

[0050] A target intake parameter analysis module: obtaining user information data of a target user, the user information data comprising user basic information and user diet information of the target user; constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting target nutritional intake parameters corresponding to the target user according to the nutrition analysis model;

[0051] A meal intake parameter analysis module: obtaining user meal data of the target user, and analyzing the user meal data to obtain meal nutritional intake parameters of the target user;

[0052] A recommended intake parameter analysis module: comparing and analyzing the target nutritional intake parameters and the meal nutritional intake parameters to obtain recommended nutritional intake parameters of the target user;

[0053] The first dish recommendation module: obtaining user location data of the target user, and constructing a dish information library according to the user location data; obtaining dish component recommendation coefficients of the existing dish by analyzing the existing dish and the recommended nutrition intake parameter; obtaining dish side dish recommendation coefficients of the existing dish by analyzing the existing dish and the user diet information; obtaining a first dish recommendation coefficient of the existing dish according to the dish component recommendation coefficients and the dish side dish recommendation coefficients;

[0054] The second dish recommendation module: obtaining the restaurant geographic location of the existing dish corresponding restaurant, and obtaining a second dish recommendation coefficient of the existing dish according to the restaurant geographic location and the user location data;

[0055] The dish recommendation scheme recommendation module: obtaining a comprehensive dish recommendation coefficient of the existing dish according to the first dish recommendation coefficient and the second dish recommendation coefficient, and obtaining a dish recommendation order of the existing dish according to the comprehensive dish recommendation coefficient, and constructing a dish recommendation scheme of the target user according to the dish recommendation order and the restaurant geographic location of the existing dish.

[0056] In summary, the beneficial effects of the present application are: the present application constructs a nutrition analysis model, inputs the user basic information of the target user into the nutrition analysis model, and outputs the target nutrition intake parameter corresponding to the target user according to the nutrition analysis model; the nutrition intake parameter of the target user is obtained by analyzing the user meal data of the target user; and the recommended nutrition intake parameter of the target user is obtained by comparing and analyzing the target nutrition intake parameter and the meal nutrition intake parameter; in addition, a dish information library is constructed according to the user location data of the target user, and dish component recommendation coefficients of the existing dish are obtained by analyzing the existing dish and the recommended nutrition intake parameter; dish side dish recommendation coefficients of the existing dish are obtained by analyzing the existing dish and the user diet information; a first dish recommendation coefficient of the existing dish is obtained according to the dish component recommendation coefficients and the dish side dish recommendation coefficients; a second dish recommendation coefficient of the existing dish is obtained through the restaurant geographic location of the existing dish corresponding restaurant and the user location data; finally, a comprehensive dish recommendation coefficient of the existing dish is obtained according to the first dish recommendation coefficient and the second dish recommendation coefficient, and a dish recommendation order of the existing dish is obtained according to the comprehensive dish recommendation coefficient, and a dish recommendation scheme of the target user is constructed according to the dish recommendation order and the restaurant geographic location of the existing dish, which improves the comprehensiveness and accuracy of the dish recommendation result. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present application, some of the drawings in the embodiments of the present application will be briefly described below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be considered as limiting the scope of the present application.

[0058] Figure 1 A flowchart of a meal recommendation method based on personal nutritional intake provided by the present application is shown in FIG. 1.

[0059] Figure 2 A structural diagram of a meal recommendation system based on personal nutritional intake provided by the present application is shown in FIG. 2. DETAILED DESCRIPTION

[0060] The present application is further described in detail by the following embodiments and drawings. Figure 1 and Figure 2 The present application is further described in detail by the following embodiments and drawings.

[0061] Referring to FIG. 1, a flowchart of a meal recommendation method based on personal nutritional intake provided by an embodiment of the present application is shown. Figure 1 The meal recommendation method based on personal nutritional intake comprises the following steps.

[0062] Step S1: obtaining user information data of a target user, the user information data comprising user basic information and user diet information of the target user; constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting target nutritional intake parameters corresponding to the target user according to the nutrition analysis model;

[0063] Step S2: obtaining user meal data of the target user, and analyzing the user meal data to obtain meal nutritional intake parameters of the target user;

[0064] Step S3: comparing and analyzing the target nutritional intake parameters and the meal nutritional intake parameters to obtain recommended nutritional intake parameters of the target user;

[0065] Step S4: obtaining user location data of the target user, and constructing a dish information database according to the user location data, the dish information database comprising at least one existing dish; analyzing the existing dish and the recommended nutritional intake parameters to obtain a dish ingredient recommendation coefficient of the existing dish; analyzing the existing dish and the user diet information to obtain a dish side dish recommendation coefficient of the existing dish; and obtaining a dish first recommendation coefficient of the existing dish according to the dish ingredient recommendation coefficient and the dish side dish recommendation coefficient;

[0066] Step S5: obtaining a restaurant geographic location of the existing dish corresponding to a restaurant, and obtaining a dish second recommendation coefficient of the existing dish according to the restaurant geographic location and the user location data;

[0067]

[0068] ​Step S6: obtaining a dish comprehensive recommendation coefficient of the existing dish according to the dish first recommendation coefficient and the dish second recommendation coefficient, and obtaining a dish recommendation order of the existing dish according to the dish comprehensive recommendation coefficient, and constructing a meal recommendation scheme of the target user according to the dish recommendation order and the restaurant geographic position of the existing dish.

[0069] Obtaining user information data of the target user, the user information data including user basic information and user diet information of the target user, specifically:

[0070] The user basic information including basic attributes, physiological state, body data, activity level and health condition of the target user.

[0071] The user diet information including a favorite dish of the target user.

[0072] In some embodiments, the basic attributes include age and gender of the target user, which are used to determine the baseline reference value of the basal metabolic rate; the physiological state refers to physiological states such as ordinary adult, pregnant woman, lactating woman, infant, and elderly person; the body data includes height (cm), weight (kg), and BMI (weight kg / height m²) of the target user; the activity level refers to activity levels such as sedentary (e.g., office work), light activity (1-3 times of exercise per week), moderate activity (3-5 times per week), and high-intensity activity (6-7 times per week); and the health condition includes whether the target user has a chronic disease (e.g., diabetes needs to control sugar, and high blood pressure needs to control sodium) or an allergy history (e.g., lactose intolerance needs to adjust dairy product intake).

[0073] The favorite dish of the target user can be manually input by the target user or obtained according to historical dining habits of the target user.

[0074] Constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting a target nutrition intake parameter corresponding to the target user according to the nutrition analysis model, specifically:

[0075] The nutrition analysis model includes a nutrition analysis algorithm.

[0076] Obtaining nutrition analysis reference data, and generating a nutrition analysis training library according to the nutrition analysis reference data;

[0077] Training the nutrition analysis algorithm in the nutrition analysis model according to the nutrition analysis reference data in the nutrition analysis training library, to obtain a target nutrition analysis algorithm of the nutrition analysis model.

[0078] The user basic information of the target user is taken as a model input parameter, and the model input parameter is input into a nutrition analysis model; a target nutrition intake component corresponding to the target user and a target nutrition component intake amount corresponding to the target nutrition intake component are obtained and output according to a target nutrition analysis algorithm in the nutrition analysis model;

[0079] The target nutrition intake component and the target nutrition component intake amount corresponding to the target nutrition intake component constitute a target nutrition intake parameter corresponding to the target user.

[0080] In some embodiments, the nutrition analysis algorithm can be preset based on a nutrition analysis tool of the Chinese Nutrition Society official website, the United States Department of Agriculture, etc.

[0081] The nutrition analysis reference data can be obtained by referring to the Dietary Guidelines for Chinese Residents, the Dietary Nutrient Reference Intake of Chinese Residents, the Chinese Food Composition Table, and various food and nutrition guidelines, dietary guidelines, etc. data officially and officially published by the National Health Commission of China, the Chinese Nutrition Society, etc. and professional information nutrition recommendation data such as the United States Department of Agriculture Nutrition Database and Singapore Beverage Sugar Standard;

[0082] The target nutrition intake component specifically includes three macro-nutrient requirements (protein, fat, and carbohydrate), micro-nutrient requirements (calcium, iron, vitamins, etc.), and other nutritional elements.

[0083] User meal data of the target user is obtained, and meal nutrition intake parameters of the target user are obtained by analyzing the user meal data, specifically:

[0084] The user meal data includes a user meal picture of the target user.

[0085] The food type of the food eaten by the user and the food amount corresponding to the food type are obtained according to the user meal picture.

[0086] The meal nutrition intake component corresponding to the food eaten by the user and the meal nutrition component content corresponding to the meal nutrition intake component are obtained according to the food type of the food eaten by the user and the food amount.

[0087] The meal nutrition component and the meal nutrition component content corresponding to the meal nutrition component constitute the meal nutrition intake parameter of the target user.

[0088] In some embodiments, the user meal picture is specifically a meal and drink comparison picture before and after eating of the target user. In actual application, the food type and the food amount of the food eaten in the user meal picture can be automatically recognized by AI visual recognition technology, and the meal nutrition intake component contained by the food type and the food amount and the meal nutrition component content corresponding to the meal nutrition intake component can be automatically obtained according to the food type and the nutrition component table.

[0089] The target nutritional intake parameter and the meal nutritional intake parameter are compared and analyzed to obtain a recommended nutritional intake parameter of the target user, specifically:

[0090] The target nutritional intake components in the target nutritional intake parameter are matched with the parameter nutritional intake components in the meal nutritional intake parameter to obtain a component matching result;

[0091] According to the component matching result, the target nutritional intake components in the target nutritional intake parameter that are consistent with the parameter nutritional intake components are recorded as the same intake components;

[0092] If the target nutritional component content corresponding to the same intake components is greater than the meal nutritional component content, the same intake components are recorded as the recommended nutritional intake components, and the recommended nutritional component intake corresponding to the recommended nutritional intake components is obtained according to the target nutritional component content and the meal nutritional component content;

[0093] According to the component matching result, the target nutritional intake components in the target nutritional intake parameter that are inconsistent with the parameter nutritional intake components are recorded as the recommended nutritional intake components, and the target nutritional component intake of the target nutritional intake components is recorded as the recommended nutritional component intake corresponding to the recommended nutritional intake components.

[0094] User location data of the target user is obtained, and a dish information library is constructed according to the user location data; the dish component recommendation coefficients of the existing dishes are obtained by analyzing the existing dishes and the recommended nutritional intake parameters, specifically:

[0095] The user location data includes the user geographic location and the user preset dining range of the target user;

[0096] According to the user geographic location and the user preset dining range, restaurant information of the geographic location where the target user is located is obtained, and a dish information library is constructed according to the restaurant information; the dish information library contains at least one existing dish, and each existing dish corresponds to at least one restaurant information;

[0097] The dish nutritional components of the existing dishes in the dish information library are obtained, the dish nutritional components of the existing dishes are compared with the recommended nutritional intake components of the target user, and the dish nutritional components of the existing dishes that are consistent with the recommended nutritional intake components are recorded as matching nutritional components;

[0098] According to the matching nutritional component content of the matching nutritional components in the existing dishes and the recommended nutritional component intake of the matching nutritional components corresponding to the recommended nutritional intake components, a first component recommendation coefficient of the existing dishes is obtained;

[0099] obtaining a nutrition component proportion of the matching nutrition component in the recommended nutrition intake component in the existing dish, and obtaining a second component recommendation coefficient of the existing dish according to the nutrition component proportion;

[0100] obtaining a dish component recommendation coefficient of the existing dish according to the first component recommendation coefficient and the second component recommendation coefficient.

[0101] In some embodiments, the user preset dining range can be specifically set as a specific range value of two kilometers, five kilometers, etc., and a target user's candidate dining area is obtained based on a circular point of the user's geographic location, and the specific range value is a circular radius. The restaurants in the candidate dining area are all recorded as restaurant information of the geographic location where the target user is located. According to the restaurant information, a dish information library is constructed, which means that all menu dishes in the restaurant are obtained and recorded to obtain all existing dishes, and the dish information library is constructed according to the existing dishes.

[0102] In some embodiments, a recommendation intake interval is set based on the recommended nutrition component intake amount corresponding to the recommended nutrition component, wherein the recommended nutrition component intake amount is the center value of the interval, and the interval radius is a preset intake amount deviation value. Each recommended nutrition intake component corresponds to an intake amount deviation value, that is, each recommended nutrition intake component corresponds to a recommended intake amount interval. In actual application, if the matching nutrition component content of the matching nutrition component is not within the recommended intake amount interval of the recommended nutrition intake component corresponding to the matching nutrition component, the matching nutrition component does not have a component recommendation coefficient. If the matching nutrition component content of the matching nutrition component is within the recommended intake amount interval of the recommended nutrition intake component corresponding to the matching nutrition component, the matching nutrition component has a component recommendation coefficient. At this time, the component recommendation coefficient of the matching nutrition component is obtained according to the difference between the matching nutrition component content and the recommended nutrition intake component amount. Specifically, the function: component recommendation coefficient = inverse proportional factor * absolute value of the difference between the matching nutrition component content and the recommended nutrition intake component amount can be used, that is, the component recommendation coefficient of the matching nutrition component is inversely proportional to the absolute value of the difference between the matching nutrition component content and the recommended nutrition intake component amount. The smaller the absolute value of the difference between the matching nutrition component content and the recommended nutrition intake component amount, the higher the component recommendation coefficient of the matching nutrition component. The first component recommendation coefficient of the existing dish is obtained by cumulative calculation of the component recommendation coefficients of the matching nutrition components in the existing dish.

[0103] In some embodiments, the second component recommendation coefficient of the existing dish is positively correlated with the nutrition component proportion of the matching nutrition component in the recommended nutrition intake component in the existing dish. Specifically, the function: second component recommendation coefficient = positive proportional factor * nutrition component proportion can be used to calculate.

[0104] In some embodiments, the first component weight value and the second component weight value can be set, and the dish component recommendation coefficient can be calculated by a calculation function: dish component recommendation coefficient = first component weight value * first component recommendation coefficient + second component weight value * second component recommendation coefficient, wherein the first component weight value and the second component weight value are the influence weight values of the first component recommendation coefficient and the second component recommendation coefficient on the dish component recommendation coefficient respectively.

[0105] According to the analysis of the existing dish and the user diet information, the dish dish recommendation coefficient of the existing dish is obtained; and the dish first recommendation coefficient of the existing dish is obtained according to the dish component recommendation coefficient and the dish dish recommendation coefficient, specifically:

[0106] A dish database is established according to the target user's favorite dish, and the dish database contains at least one favorite dish;

[0107] The dish dish of the existing dish is obtained, and the dish dish is compared with the favorite dish in the dish database to obtain the favorite dish proportion of the dish dish in the existing dish in the dish database;

[0108] The dish dish recommendation coefficient of the existing dish is obtained according to the favorite dish proportion;

[0109] The component recommendation weight value and the dish recommendation weight value are set; and the dish first recommendation coefficient of the existing dish is obtained according to the component recommendation weight value and the dish component recommendation coefficient, the dish recommendation weight value and the dish dish recommendation coefficient.

[0110] In some embodiments, the dish dish recommendation coefficient of the existing dish is positively correlated with the favorite dish proportion of the dish dish in the existing dish in the dish database, and the dish dish recommendation coefficient can be calculated by a calculation function: dish dish recommendation coefficient = positive proportion factor * favorite dish proportion, that is, the higher the favorite dish proportion of the dish dish in the existing dish in the dish database, the greater the value of the dish dish recommendation coefficient of the existing dish.

[0111] The dish first recommendation coefficient of the existing dish can be calculated by a calculation function: dish first recommendation coefficient = component recommendation weight value * dish component recommendation coefficient + dish recommendation weight value * dish dish recommendation coefficient, wherein the component recommendation weight value and the dish recommendation weight value are the influence weight values of the dish component recommendation coefficient and the dish dish recommendation coefficient on the dish first recommendation coefficient respectively.

[0112] Step S5, specifically:

[0113] According to the user geographic location of the target user and the restaurant geographic location, the dining distance value corresponding to the existing dish is obtained; and the dish second recommendation coefficient of the existing dish is obtained according to the dining distance value.

[0114] In some embodiments, the dining position refers to a straight-line geographical position of the user geographical position and the visiting geographical position, the second dish recommendation coefficient is negatively correlated with the dining distance value, that is, the larger the dining distance value is, the smaller the second dish recommendation coefficient of the existing dish is, and the second dish recommendation coefficient can be specifically calculated by a calculation function: second dish recommendation coefficient = inverse proportional factor * dining distance value.

[0115] Step S6, specifically:

[0116] The first coefficient weight and the second coefficient weight are set.

[0117] The first coefficient weight and the first dish recommendation coefficient, and the second coefficient weight and the second dish recommendation coefficient are used to obtain the dish comprehensive recommendation coefficient of the existing dish.

[0118] The dish recommendation priority corresponding to the existing dish is obtained according to the dish comprehensive recommendation coefficient, and the dish recommendation order is obtained according to the dish recommendation priority.

[0119] In some embodiments, the dish comprehensive recommendation coefficient of the existing dish can be calculated by a calculation function: dish comprehensive recommendation coefficient = first coefficient weight * first dish recommendation coefficient + second coefficient weight * second dish recommendation coefficient, wherein the first coefficient weight and the second coefficient weight are the influence weight of the first dish recommendation coefficient and the second dish recommendation coefficient on the dish comprehensive recommendation coefficient; the larger the dish comprehensive recommendation coefficient of the existing dish is, the higher the dish recommendation priority is, and the existing dish with higher recommendation priority is arranged in the front in the dish recommendation order. The meal recommendation scheme not only includes the dish recommendation order of the existing dish, but also includes the restaurant geographical position of the restaurant where the existing dish is located.

[0120] It should be noted that the proportional factor and the inverse proportional factor in the present application can be preset based on historical data, or can be preset according to actual recommendation requirements.

[0121] Referring to Figure 2 Fig. 1 is a structural schematic diagram of a meal recommendation system based on individual nutritional intake provided by an embodiment of the present application, which comprises:

[0122] A target intake parameter analysis module: obtaining user information data of a target user, the user information data comprising user basic information and user diet information of the target user; constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting a target nutritional intake parameter corresponding to the target user according to the nutrition analysis model;

[0123] A meal intake parameter analysis module: obtaining user meal data of the target user, and analyzing the user meal data to obtain a meal nutritional intake parameter of the target user;

[0124] The recommended intake parameter analysis module: compares and analyzes the target nutrition intake parameter and the meal nutrition intake parameter, and obtains the recommended nutrition intake parameter of the target user;

[0125] The first dish recommendation module: acquires the user location data of the target user, and constructs a dish information library according to the user location data; analyzes the existing dishes and the recommended nutrition intake parameter, and obtains the dish component recommendation coefficient of the existing dishes; analyzes the existing dishes and the user diet information, and obtains the dish accompaniment recommendation coefficient of the existing dishes; obtains the dish first recommendation coefficient of the existing dishes according to the dish component recommendation coefficient and the dish accompaniment recommendation coefficient;

[0126] The second dish recommendation module: acquires the restaurant geographical position of the restaurant corresponding to the existing dishes, and obtains the dish second recommendation coefficient of the existing dishes according to the restaurant geographical position and the user location data;

[0127] The meal arrangement scheme recommendation module: obtains the dish comprehensive recommendation coefficient of the existing dishes according to the dish first recommendation coefficient and the dish second recommendation coefficient, and obtains the dish recommendation order of the existing dishes according to the dish comprehensive recommendation coefficient, and constitutes the meal arrangement recommendation scheme of the target user according to the dish recommendation order and the restaurant geographical position of the existing dishes.

[0128] The above is only the preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments. Any technical solution falling within the scope of the present application shall be considered as falling within the protection scope of the present application. It should be noted that, for ordinary skilled persons in the art, some improvements and refinements without departing from the principles of the present application shall also be considered as falling within the protection scope of the present application.

Claims

1. A meal recommendation method based on individual nutritional intake, characterized by, The method comprises the following steps: Step S1: obtaining user information data of a target user, wherein the user information data comprises user basic information and user diet information of the target user; constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting target nutrition intake parameters corresponding to the target user according to the nutrition analysis model; Step S2: obtaining user meal data of the target user, and analyzing the user meal data to obtain meal nutrition intake parameters of the target user; Step S3: comparing and analyzing the target nutrition intake parameters and the meal nutrition intake parameters to obtain recommended nutrition intake parameters of the target user; Step S4: obtaining user location data of the target user, and constructing a dish information library according to the user location data, wherein the dish information library comprises at least one existing dish; analyzing the existing dish and the recommended nutrition intake parameters to obtain a dish ingredient recommendation coefficient of the existing dish; and analyzing the existing dish and the user diet information to obtain a dish side dish recommendation coefficient of the existing dish; obtaining a dish first recommendation coefficient of the existing dish according to the dish ingredient recommendation coefficient and the dish side dish recommendation coefficient; Step S5: obtaining a restaurant geographic location corresponding to the existing dish, and obtaining a dish second recommendation coefficient of the existing dish according to the restaurant geographic location and the user location data; Step S6: obtaining a dish comprehensive recommendation coefficient of the existing dish according to the dish first recommendation coefficient and the dish second recommendation coefficient, and obtaining a dish recommendation order of the existing dish according to the dish comprehensive recommendation coefficient, and constructing a catering recommendation scheme of the target user according to the dish recommendation order and the restaurant geographic location of the existing dish.

2. The meal recommendation method based on individual nutritional intake according to claim 1, characterized in that, Obtaining user information data of a target user, wherein the user information data comprises user basic information and user diet information of the target user, specifically: The user basic information comprises basic attributes, physiological states, body data, activity levels and health conditions of the target user; The user diet information comprises favorite side dishes of the target user.

3. The meal recommendation method based on individual nutritional intake according to claim 2, characterized in that, Constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting target nutrition intake parameters corresponding to the target user according to the nutrition analysis model, specifically: The nutrition analysis model comprises a nutrition analysis algorithm; Obtaining nutrition analysis reference data, and generating a nutrition analysis training library according to the nutrition analysis reference data; Training the nutrition analysis algorithm in the nutrition analysis model according to the nutrition analysis reference data in the nutrition analysis training library to obtain a target nutrition analysis algorithm of the nutrition analysis model; Inputting the user basic information of the target user as a model input parameter into the nutrition analysis model; Obtaining target nutrition intake ingredients and target nutrition ingredient intake amounts corresponding to the target nutrition intake ingredients according to the target nutrition analysis algorithm in the nutrition analysis model; According to the target nutrition intake ingredients and the target nutrition ingredient intake amounts corresponding to the target nutrition intake ingredients, target nutrition intake parameters corresponding to the target user are constructed.

4. The meal recommendation method based on individual nutritional intake according to claim 3, characterized by, Obtaining user meal data of the target user, analyzing the user meal data to obtain meal nutrition intake parameters of the target user, specifically: The user meal data includes user meal pictures of the target user; According to the user meal pictures, the food types of the food consumed by the user are obtained, and the food types correspond to food quantities; And according to the food types and food quantities of the food consumed by the user, the meal nutrition intake components corresponding to the food consumed by the user are obtained, and the meal nutrition component contents corresponding to the meal nutrition intake components are obtained; According to the meal nutrition components and the meal nutrition component contents corresponding to the meal nutrition components, the meal nutrition intake parameters of the target user are constituted.

5. The meal recommendation method based on individual nutritional intake according to claim 4, characterized in that, Comparing and analyzing the target nutrition intake parameters and the meal nutrition intake parameters to obtain recommended nutrition intake parameters of the target user, specifically: Component matching is performed between the target nutrition intake components in the target nutrition intake parameters and the parameter nutrition intake components in the meal nutrition intake parameters to obtain a component matching result; According to the component matching result, the target nutrition intake components in the target nutrition intake parameters that are consistent with the parameter nutrition intake components are recorded as the same intake components; If the target nutrition component content corresponding to the same intake component is greater than the meal nutrition component content, the same intake component is recorded as a recommended nutrition intake component, and the recommended nutrition component intake amount corresponding to the recommended nutrition intake component is obtained according to the target nutrition component content and the meal nutrition component content; According to the component matching result, the target nutrition intake components in the target nutrition intake parameters that are inconsistent with the parameter nutrition intake components are all recorded as recommended nutrition intake components, and the target nutrition component intake amount of the target nutrition intake component is recorded as the recommended nutrition component intake amount corresponding to the recommended nutrition intake component.

6. The meal recommendation method based on individual nutritional intake according to claim 5, characterized in that, Obtaining user location data of the target user, and constructing a dish information library according to the user location data; analyzing the existing dishes and the recommended nutrition intake parameters to obtain dish component recommendation coefficients of the existing dishes, specifically: The user location data includes the user geographic location and the user preset dining range of the target user; According to the user geographic location and the user preset dining range, restaurant information of the geographic location where the target user is located is obtained, and a dish information library is constructed according to the restaurant information; the dish information library contains at least one existing dish, and each existing dish corresponds to at least one restaurant information; Obtaining dish nutrition components of the existing dishes in the dish information library, comparing the dish nutrition components of the existing dishes with the recommended nutrition intake components of the target user, and recording the dish nutrition components in the existing dishes that are consistent with the recommended nutrition intake components as matched nutrition components; According to the matched nutrition component contents of the matched nutrition components in the existing dishes and the recommended nutrition component intake amounts of the matched nutrition components corresponding to the recommended nutrition intake components, first component recommendation coefficients of the existing dishes are obtained; Obtaining the nutrition component proportion of the matched nutrition components in the recommended nutrition intake components in the existing dishes, and obtaining second component recommendation coefficients of the existing dishes according to the nutrition component proportion; According to the first ingredient recommendation coefficient and the second ingredient recommendation coefficient, a dish ingredient recommendation coefficient of the existing dish is obtained.

7. The meal recommendation method based on individual nutritional intake according to claim 6, characterized in that, According to analysis of the existing dish and user diet information, a dish matching recommendation coefficient of the existing dish is obtained; and according to the dish ingredient recommendation coefficient and the dish matching recommendation coefficient, a dish first recommendation coefficient of the existing dish is obtained, specifically as follows: A matching database is established according to the target user's favorite matching, and the matching database contains at least one favorite matching; A dish matching in the existing dish is obtained, and the dish matching is compared with the favorite matching in the matching database to obtain a favorite matching proportion of the dish matching in the existing dish in the favorite matching in the matching database; According to the favorite matching proportion, a dish matching recommendation coefficient of the existing dish is obtained; A component recommendation weight and a matching recommendation weight are set; and according to the component recommendation weight, the dish ingredient recommendation coefficient, the matching recommendation weight and the dish matching recommendation coefficient, a dish first recommendation coefficient of the existing dish is obtained.

8. The meal recommendation method based on individual nutritional intake according to claim 7, characterized in that, Step S5, specifically as follows: According to the target user's user geographic location and the restaurant geographic location, a dining distance value corresponding to the existing dish is obtained; and according to the dining distance value, a dish second recommendation coefficient of the existing dish is obtained.

9. The meal recommendation method based on individual nutritional intake according to claim 8, characterized in that, Step S6, specifically as follows: A first coefficient weight and a second coefficient weight are set; According to the first coefficient weight, the dish first recommendation coefficient, the second coefficient weight and the dish second recommendation coefficient, a dish comprehensive recommendation coefficient of the existing dish is obtained; And according to the dish comprehensive recommendation coefficient, a dish recommendation priority corresponding to the existing dish is obtained, and according to the dish recommendation priority, a dish recommendation order is obtained.

10. A meal recommendation system based on individual nutritional intake, the system being configured to implement the method of recommending a meal based on individual nutritional intake according to any one of claims 1 to 9, characterized in that, The system comprises: A target intake parameter analysis module: obtaining user information data of a target user, the user information data including user basic information and user diet information of the target user; constructing a nutrition analysis model, inputting the user basic information of the target user into the nutrition analysis model, and outputting target nutrition intake parameters corresponding to the target user according to the nutrition analysis model; A meal intake parameter analysis module: obtaining user meal data of the target user, and analyzing the user meal data to obtain meal nutrition intake parameters of the target user; A recommended intake parameter analysis module: comparing and analyzing the target nutrition intake parameters and the meal nutrition intake parameters to obtain recommended nutrition intake parameters of the target user; A first dish recommendation module: obtaining user location data of the target user, and constructing a dish information database according to the user location data; analyzing the existing dish and the recommended nutrition intake parameters to obtain a dish ingredient recommendation coefficient of the existing dish; analyzing the existing dish and user diet information to obtain a dish matching recommendation coefficient of the existing dish; and obtaining a dish first recommendation coefficient of the existing dish according to the dish ingredient recommendation coefficient and the dish matching recommendation coefficient; A second dish recommendation module: obtaining a restaurant geographic location of a restaurant corresponding to the existing dish, and obtaining a dish second recommendation coefficient of the existing dish according to the restaurant geographic location and the user location data; A third dish recommendation module: obtaining a first coefficient weight and a second coefficient weight; obtaining a dish comprehensive recommendation coefficient of the existing dish according to the first coefficient weight, the dish first recommendation coefficient, the second coefficient weight and the dish second recommendation coefficient; and obtaining a dish recommendation priority corresponding to the existing dish according to the dish comprehensive recommendation coefficient, and obtaining a dish recommendation order according to the dish recommendation priority. The meal arrangement recommendation module obtains a meal comprehensive recommendation coefficient of the existing meal according to the meal first recommendation coefficient and the meal second recommendation coefficient, and obtains a meal recommendation order of the existing meal according to the meal comprehensive recommendation coefficient, and forms a meal arrangement recommendation scheme of the target user according to the meal recommendation order and the restaurant geographic position of the existing meal.

Images