Intelligent nutrition ordering system and ordering method

Abstract

The invention discloses an intelligent nutrition ordering system and an ordering method, and belongs to the technical field of industrial artificial intelligence network system services. The intelligent nutrition ordering system comprises a data acquisition module, a menu screening module, a menu selection module and an intelligent ordering database. Wherein the data acquisition module is used for acquiring basic data of a service object and dish requirements, counting dishes and collecting nutrition and calorie of the dishes; the menu screening module is used for matching nutritional requirements, matching menus, recommending the menus according to the recommendation degree indexes of the initial menus, and obtaining nutritional menus through selection of service objects; and the dish replacement module is used for the service object to select a to-be-replaced dish from the nutrition menu, obtain the content of each nutrient component of each similar dish, analyze to obtain a nutrition similarity degree evaluation value of each similar dish, replace the dish according to the nutrition similarity degree evaluation value of each similar dish, and perform evaluation feedback on a replacement result.

Description

Technical Field

[0001] The present invention application relates to the field of industrial artificial intelligence network system service technology, and in particular to an intelligent nutrition ordering system and ordering method. Background Art

[0002] The intelligent nutrition ordering system is a catering service solution that integrates advanced technologies such as the Internet, artificial intelligence, and big data. It aims to improve the ordering experience of service recipients, meet personalized nutritional needs, and optimize the operating efficiency of restaurants. The existing intelligent ordering system uses artificial intelligence technology to collect and analyze data such as the ordering history and taste preferences of service recipients. During the ordering process of service recipients, the system will recommend suitable dishes in real time based on the service recipients' current choices and taste preferences to help them make decisions.

[0003] For example, a dish recommendation method and device disclosed in the patent application with publication number CN107391531A includes: obtaining ordered dishes in a dish set; determining similar ordering menus based on the similarity between the ordered dishes and the dishes on the historical ordering menu, where the dish similarity is a measure of the difference in dish attributes calculated based on the dish's own attributes; and using the dishes in the similar ordering menu as recommended dishes. For example, a mobile catering ordering and intelligent recommendation system disclosed in the patent application with publication number CN104133901A includes: a mobile catering ordering terminal and an intelligent recommendation module for ordering dishes for service objects, wherein the mobile catering ordering terminal uses a 7-inch screen Android smart tablet with a Cortex-A9 processor, and the catering application software of the terminal includes functions such as front desk ordering, menu browsing, business dynamics, and data maintenance; the intelligent recommendation module for ordering dishes for service objects includes a data mining module and a context analysis module, which extracts features from the previous ordering contexts of service objects, calls the association rules in the model library for intelligent analysis, and then recommends to the service objects. However, in the process of implementing the technical solution of the invention in the present invention, it is found that the above technology has at least the following technical problems:

[0004] In the prior art, the ordering system recommends dishes based more on the user's historical taste preferences, but these dishes may not cover all the nutrients needed by the body, resulting in an unbalanced diet for the user, thereby increasing health risks. Summary of the invention

[0005] The present invention application solves the problem that the ordering system in the prior art recommends dishes based more on the user's historical taste preferences, but these dishes may not cover all kinds of nutrients needed by the body, resulting in unbalanced diet for users, thereby increasing health risks, by providing an intelligent nutritional ordering system and ordering method, thereby achieving a nutritionally balanced dish combination tailored for users.

[0006] In a first aspect, the intelligent nutritional ordering system includes: a data acquisition module, a recipe screening module, a recipe selection module and an intelligent ordering database; wherein the data acquisition module is used to acquire the basic data of the service object and the number of each type of dish demand, count the dishes that can be provided and mark them as target dishes, and collect the content of each nutrient and the calorie of each target dish; the recipe screening module is used to obtain the total amount of each nutrient demand and the basic calorie demand according to the basic data of the service object, match the recipes according to the number of each type of dish demand, obtain each initial recipe, process the recommendation degree index of each initial recipe according to the content of each nutrient and the calorie of each target dish, and recommend the recipe according to the recommendation degree index of each initial recipe, and obtain the nutritional recipe after the service object selects; the dish replacement module is used for the service object to select the dish to be replaced from the nutritional menu, obtain the content of each nutrient of each similar dish, analyze and obtain the nutritional similarity evaluation value of each similar dish, replace the dish according to the nutritional similarity evaluation value of each similar dish, and evaluate and feedback the replacement result.

[0007] Furthermore, the step of obtaining the total amount of each nutrient requirement and the basic calorie requirement based on the basic data of the service objects includes: the basic data of the service objects include the basal metabolic rate of each service object, the age of each service object and the number of service objects; matching the basal metabolic rate of each service object with the calorie requirement corresponding to each basal metabolic rate interval preset in the smart ordering database to obtain the basal calorie requirement of each service object; matching the age of each service object with the nutrient requirement corresponding to each age interval preset in the smart ordering database to obtain the nutrient requirement of each service object; summing up the calorie requirement of each service object and the nutrient requirement of each service object respectively to obtain the basic calorie requirement and the total amount of each nutrient requirement.

[0008] Furthermore, the step of processing and obtaining the recommendation level index of each initial recipe according to the nutrient content and calorie of each target dish includes: performing sum operations according to the nutrient content of each target dish and the calorie of each target dish in each initial recipe, respectively, to obtain the nutrient content of each initial recipe and the calorie of each initial recipe; subtracting the total amount of each nutrient requirement from the nutrient content of each initial recipe, to obtain the nutrient requirement difference; comparing the nutrient requirement difference with zero, if the nutrient requirement difference is less than zero, setting the nutrient requirement difference to zero, if the nutrient requirement difference is greater than or equal to zero, retaining the original value of the nutrient requirement difference; and comprehensively analyzing to obtain the recommendation level index of each initial recipe.

[0009] Furthermore, the method for obtaining the recommendation index of each initial recipe is as follows:

[0010]

[0011] In the formula, ξ j represents the recommendation index of the jth initial recipe, α 1j represents the weight factor of the recommended degree index corresponding to the j-th nutrient content, α 2j represents the weight factor of the recommended degree index corresponding to the j-th nutrient requirement difference, α 3j Indicates the weight factor of the recommendation index corresponding to the jth calorie, N 2(ij represents the nutrient content of the i-th initial recipe, N 1(ij) N represents the difference in nutrient requirement of the i-th initial recipe, 0(i) represents the total amount of nutrient required for the i-th nutrient, Q 1(j) represents the calorie content of the jth initial recipe, Q0 represents the basic required calorie content, and △Q represents the allowable deviation value preset in the smart ordering database.

[0012] The present invention discloses an intelligent nutrition ordering system and ordering method, which belongs to the field of industrial artificial intelligence network system service technology. The intelligent nutrition ordering system includes: a data acquisition module, a recipe screening module, a recipe selection module and an intelligent ordering database; wherein the data acquisition module is used to obtain the basic data and dish requirements of the service object, count the dishes and collect their nutrition and calories; the recipe screening module is used to match the nutritional requirements, match the recipes, recommend the recipes according to the recommendation degree indicators of each initial recipe, and obtain the nutritional recipes after the service object selects; the dish replacement module is used for the service object to select the dish to be replaced from the nutritional recipe, obtain the content of each nutrient component of each similar dish, analyze and obtain the nutritional similarity evaluation value of each similar dish, replace the dish according to the nutritional similarity evaluation value of each similar dish, and evaluate and feedback the replacement result.

[0013] Nutrient type number, i = 1, 2, 3, ..., n, n is the number of nutrient types.

[0014] Furthermore, recipe recommendations are made based on the recommendation level index of each initial recipe, and the step of obtaining a nutritional recipe after selection by the service object includes: obtaining a recommendation level index threshold from the intelligent ordering database, comparing the recommendation level index of each initial recipe with the recommendation level index threshold, and if the recommendation level index of an initial recipe is greater than or equal to the recommendation level index threshold, marking the initial recipe as a recommended recipe, and counting the recommended recipes; sorting the recommended recipes in descending order according to the recommendation level index, and displaying and outputting them in turn for selection by the service object, and marking the recommended recipe selected by the service object as a nutritional recipe.

[0015] Furthermore, the service object selects the dish to be replaced from the nutritional menu, and the service object selects the dish to be replaced from the nutritional menu, and marks the dish as the dish to be replaced, and obtains the same type of dish as the dish to be replaced, and marks them as each similar dish.

[0016] Furthermore, the step of replacing dishes according to the nutritional similarity evaluation values ​​of each similar dish includes: sorting each similar dish in order from large to small according to the nutritional similarity evaluation values ​​of each similar dish, and displaying and outputting them in sequence for the service object to choose, marking the dish selected by the service object as a replacement dish, and performing dish replacement.

[0017] Furthermore, the step of analyzing and obtaining nutritional similarity evaluation values ​​of similar dishes includes: obtaining the content of each nutrient component of the dish to be replaced and the content of each nutrient component of similar dishes; subtracting the content of each nutrient component of each similar dish from the content of each nutrient component of the dish to be replaced, performing a ratio operation on the absolute value of the difference and the allowable deviation content of each nutrient component preset in the intelligent ordering database, and obtaining the nutritional similarity evaluation value of similar dishes through logarithmic processing.

[0018] Furthermore, the step of evaluating and providing feedback on the replacement result includes: marking the nutritional recipe after the dish is replaced as the recipe to be evaluated, obtaining the critical nutritional similarity evaluation value from the intelligent ordering database, and calculating the recommendation degree index of the recipe to be evaluated, and obtaining the nutritional value evaluation value of the recipe to be evaluated through comprehensive analysis based on the nutritional similarity evaluation value between the replaced dish and the dish to be replaced and the recommendation degree index of the recipe to be evaluated; obtaining the nutritional value evaluation threshold from the intelligent ordering database, and if the nutritional value evaluation value of the recipe to be evaluated is greater than or equal to the nutritional value evaluation threshold, waiting for the service object to confirm and completing the ordering operation; if the nutritional value evaluation value of the recipe to be evaluated is less than the nutritional value evaluation threshold, issuing a nutritional demand warning and providing a recommended dish addition operation.

[0019] In a second aspect, a smart nutritional ordering method adopts any smart nutritional ordering system of the first aspect, including: obtaining basic data of service objects and the number of demands for each type of dishes, counting the dishes that can be provided and marking them as target dishes, and collecting the content of each nutrient and the calorie of each target dish; obtaining the total amount of each nutrient demand and the basic calorie demand according to the basic data of the service objects, matching recipes according to the number of demands for each type of dishes to obtain each initial recipe, processing to obtain a recommendation level index of each initial recipe according to the content of each nutrient and the calorie of each target dish, and recommending recipes according to the recommendation level index of each initial recipe, and obtaining a nutritional recipe after selection by the service object; the service object selects the dish to be replaced from the nutritional recipe, obtains the content of each nutrient of each similar dish, analyzes to obtain the nutritional similarity evaluation value of each similar dish, replaces the dish according to the nutritional similarity evaluation value of each similar dish, and evaluates and feeds back the replacement result.

[0020] One or more technical solutions provided in the present invention application have at least the following technical effects or advantages:

[0021] 1. The present invention provides an intelligent nutritional ordering system that can accurately match recipes that meet the nutritional needs of users, while taking into account the nutritional components, calories and personal needs of the dishes, making the recommendation results more reasonable and reliable.

[0022] 2. The present invention recommends recipes according to the recommendation degree index of each initial recipe, obtains nutritional recipes after selection by the service object, and can provide personalized recipe recommendations based on the basic data and nutritional needs of the service object, so that the recommended recipes are more in line with the user's actual situation.

[0023] 3. The present invention replaces dishes according to the nutritional similarity evaluation values ​​of similar dishes and evaluates and feeds back the replacement results, thereby retaining the nutritional value of the original recipe to the greatest extent possible, ensuring that the nutritional components of the replaced dishes are similar to those of the original dishes, and avoiding nutritional imbalance caused by replacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a schematic diagram of the structure of the intelligent nutritional ordering system provided in the present invention application.

[0025] Figure 2 A diagram of the difference in nutritional component requirements for a certain initial recipe based on the intelligent nutritional ordering system provided in the present invention application.

[0026] Figure 3 This is a flow chart of the intelligent nutritional ordering method provided in the present invention application. DETAILED DESCRIPTION

[0027] The present invention application provides an intelligent nutritional ordering system and an ordering method, which solves the problem that the ordering system in the prior art recommends dishes based more on the user's historical taste preferences, but these dishes may not cover all kinds of nutrients needed by the body, resulting in unbalanced diet for users, thereby increasing health risks. By collecting basic data, counting dish information, matching nutritional needs, matching initial recipes, recommending the best recipes, supporting dish replacements and collecting feedback, it is possible to achieve a nutritionally balanced dish combination tailored for users, which helps users to have a more comprehensive and healthier dining experience.

[0028] The technical solution in the present invention application is to solve the problem that the above-mentioned ordering system recommends dishes based more on the user's historical taste preferences, but these dishes may not cover the various nutrients required by the body, resulting in unbalanced diet nutrition for users, thereby increasing health risks. The overall idea is as follows: by obtaining the basic data of the service object and the number of various dish requirements, the dishes that can be provided are counted and marked as target dishes, and the nutrient content and calories of each target dish are collected; the total amount of each nutrient requirement and the basic calorie requirement are obtained according to the basic data of the service object, and the menu is matched according to the number of various dish requirements to obtain the initial dishes. The system processes the target dishes into a recommendation index for each initial recipe based on the content of each nutrient and the calorie of each target dish, and recommends recipes based on the recommendation index for each initial recipe, and obtains a nutritional recipe after selection by the service recipient; the service recipient selects the dish to be replaced from the nutritional recipe, obtains the content of each nutrient of each similar dish, obtains the nutritional similarity evaluation value of each similar dish through analysis, replaces the dish based on the nutritional similarity evaluation value of each similar dish, and evaluates and feeds back the replacement result, thereby providing the service recipient with a comprehensive, scientific, personalized and flexible nutritional recipe recommendation and adjustment process.

[0029] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0030] First, as Figure 1The figure shows a schematic diagram of the structure of the intelligent nutrition ordering system provided in the present invention. The intelligent nutritional ordering system includes: a data acquisition module, a recipe screening module, a recipe selection module and an intelligent ordering database; wherein the data acquisition module is used to acquire the basic data of the service object and the number of each type of dish demand, count the dishes that can be provided and mark them as target dishes, and collect the content of each nutrient and the calorie of each target dish; the recipe screening module is used to obtain the total amount of each nutrient demand and the basic calorie demand according to the basic data of the service object, match the recipes according to the number of each type of dish demand, obtain each initial recipe, process the recommendation degree index of each initial recipe according to the content of each nutrient and the calorie of each target dish, recommend the recipe according to the recommendation degree index of each initial recipe, and obtain the nutritional recipe after the service object selects; the dish replacement module is used for the service object to select the dish to be replaced from the nutritional menu, obtain the content of each nutrient of each similar dish, analyze and obtain the nutritional similarity evaluation value of each similar dish, replace the dish according to the nutritional similarity evaluation value of each similar dish, and evaluate and feedback the replacement result.

[0031] In the present invention application, the system describes a comprehensive intelligent ordering platform, which provides personalized, nutritionally balanced recipe recommendation and selection services for users (such as restaurant customers or home cooks) through multiple modules working together. When acquiring data, it is based on the specific needs and physical condition of the user to provide basic data for subsequent nutritional analysis and recipe recommendation; when screening recipes, the algorithm automatically screens and recommends recipes to improve the user's selection efficiency and satisfaction, while ensuring that the selected recipes can meet the user's nutritional needs and avoid nutritional excess or deficiency; when replacing dishes, it is evaluated based on the degree of nutritional similarity to ensure that the replaced dishes are nutritionally similar to the original dishes and maintain overall nutritional balance. Among them, the types of dishes can be classified according to the main ingredient type (such as meat dishes, seafood dishes, vegetable dishes, staple foods, etc.), taste characteristics (such as light taste, spicy taste, sweet and sour taste, etc.), nutrient content, etc., and the number of each type of dish requirements can be flexibly adjusted according to the needs and preferences of the user, for example, staple foods are essential options, providing users with carbohydrates and energy required by the human body; and seafood dishes are non-essential options, which can be selected according to the user's taste preferences and economic ability.

[0032] In addition, the smart ordering database is used to store relevant data of the smart nutrition ordering system, including: the required calories corresponding to each basal metabolic rate interval, the required amount of each nutrient corresponding to each age interval, the recommended degree index threshold, the recommended degree index weight factor corresponding to each nutrient content, etc. The data in the smart ordering database can be directly obtained through some recipe-related public databases, third-party data service providers containing catering data, and open source recipe websites, or obtained through social media platforms and review websites after pre-processing and screening based on catering reviews and user feedback.

[0033] Furthermore, the step of obtaining the total amount of each nutrient requirement and the basic calorie requirement based on the basic data of the service objects includes: the basic data of the service objects include the basal metabolic rate of each service object, the age of each service object and the number of service objects; matching the basal metabolic rate of each service object with the calorie requirement corresponding to each basal metabolic rate interval preset in the smart ordering database to obtain the basal calorie requirement of each service object; matching the age of each service object with the nutrient requirement corresponding to each age interval preset in the smart ordering database to obtain the nutrient requirement of each service object; summing up the calorie requirement of each service object and the nutrient requirement of each service object respectively to obtain the basic calorie requirement and the total amount of each nutrient requirement.

[0034] In the present application, the total amount of each nutrient requirement refers to the total amount of each nutrient requirement, and each nutrient includes carbohydrates, fats, proteins, vitamin C, vitamin A, calcium and phosphorus. The basal metabolic rate refers to the minimum energy consumption required for the human body to maintain life activities in a quiet state (such as sleeping or sitting still), and is an important basis for estimating daily energy requirements. The basal metabolic rate can be directly measured by a basal metabolic meter, or obtained by a related calculation formula based on height, weight and age, for example:

[0035] Male basal metabolic rate = 66 + (13.7 * weight (kg)) + (5 * height (cm)) - (6.8 * age);

[0036] Female basal metabolic rate = 66 + (9.6 * weight (kg)) + 91.8 * height (cm)) - (4.7 * age);

[0037] Because people of different ages have different needs, for example, children need more protein to promote growth and development, while the elderly may need more calcium to maintain bone health, so the age of the service recipient is matched with the nutritional requirements of each age range preset in the database. Ensuring that the calories and nutrients consumed by users meet their physiological characteristics and health needs helps maintain a good physical condition and prevent problems such as malnutrition or overnutrition.

[0038] Furthermore, the step of processing and obtaining the recommendation level index of each initial recipe according to the nutrient content and calorie of each target dish includes: performing sum operations according to the nutrient content of each target dish and the calorie of each target dish in each initial recipe, respectively, to obtain the nutrient content of each initial recipe and the calorie of each initial recipe; subtracting the total amount of each nutrient requirement from the nutrient content of each initial recipe, to obtain the nutrient requirement difference; comparing the nutrient requirement difference with zero, if the nutrient requirement difference is less than zero, setting the nutrient requirement difference to zero, if the nutrient requirement difference is greater than or equal to zero, retaining the original value of the nutrient requirement difference; and comprehensively analyzing to obtain the recommendation level index of each initial recipe.

[0039] In the present application, the difference in the requirement of each nutrient component is the difference between the total requirement of each nutrient component and the content of each nutrient component in each initial recipe, which reflects whether each ingested nutrient component meets the nutritional needs of the user. When the difference in the requirement of a certain nutrient component is less than or equal to zero, it means that the recipe has reached the total requirement of the nutrient component, so the difference in the requirement of the nutrient component is marked as zero; when the difference in the requirement of a certain nutrient component is greater than zero, it means that the recipe has not reached the total requirement of the nutrient component, and the difference in the requirement of each nutrient component is negatively correlated with the recommended degree index of each initial recipe (the larger the difference in the requirement of the nutrient component, the smaller the recommended degree index of the initial recipe). Calories are the direct embodiment of energy in food, and nutrients (such as protein, fat, carbohydrates, etc.) will also release energy after digestion, absorption, and metabolism in the human body. Therefore, there is a direct correlation between the content of nutrients and calories, that is, the content of nutrients will directly affect the level of calories. By comprehensively analyzing the content of each nutrient and calorie-related parameters, we can get the recommendation level index of each initial recipe, accurately calculate the degree to which the selected recipe satisfies the user's nutritional needs, and help users understand whether the nutrients they consume are sufficient or excessive.

[0040] Furthermore, the method for obtaining the recommendation index of each initial recipe is as follows:

[0041]

[0042] In the formula, ξ j represents the recommendation index of the jth initial recipe, α 1j represents the weight factor of the recommended degree index corresponding to the j-th nutrient content, α 2j represents the weight factor of the recommended degree index corresponding to the j-th nutrient requirement difference, α 3j Indicates the weight factor of the recommendation index corresponding to the jth calorie, N 2(ij represents the nutrient content of the i-th initial recipe, N 1(ij)N represents the difference in nutrient requirement of the i-th initial recipe, 0(i) represents the total amount of nutrient required for the i-th nutrient, Q 1(j) represents the calories of the jth initial recipe, Q0 represents the basic required calories, △Q represents the allowable deviation calories preset in the intelligent ordering database, where j is the initial recipe number, j=1, 2, 3, ..., N, N is the number of initial recipes, i is the nutrient type number, i=1, 2, 3, ..., n, n is the number of nutrient types.

[0043] In the present application, the allowable deviation heat is the difference range allowed between the heat of the initial recipe and the basic required heat. 1j , α 2j and α 3j The weight factors of the recommended degree indicators corresponding to the content of each nutrient component, the difference in the required quantity of each nutrient component, and the calorie quantity preset in the intelligent ordering database respectively represent the numerical values ​​of the influence of the content of each nutrient component, the difference in the required quantity of each nutrient component, and the calorie quantity on the recommended degree indicators of each initial recipe, and can be directly obtained from the intelligent ordering database when used. For example, a mapping set is formed by forming the content of each nutrient component and the weight factors of the recommended degree indicators corresponding to the content of each nutrient component preset in the intelligent ordering database, and the weight factors of the recommended degree indicators corresponding to a certain nutrient component content are obtained by inputting the mapping set according to the content of a certain nutrient component, wherein the mapping relationship is a many-to-one or one-to-one relationship, and the value range of the weight factor in the application of the present invention is between 0 and 1.

[0044] The weight factor of the recommended degree index corresponding to the content of each nutrient component is set to 0.5, the weight factor of the recommended degree index corresponding to the difference in the requirement of each nutrient component is set to 0.2, the weight factor of the recommended degree index corresponding to the heat is set to 0.3, the total requirement of the first nutrient component of a certain initial recipe is set to 50, the total requirement of the second nutrient component of the initial recipe is set to 80, the total requirement of the third nutrient component of the initial recipe is set to 60, the total requirement of the fourth nutrient component of the initial recipe is set to 100, the total requirement of the fifth nutrient component of the initial recipe is set to 10, the heat of the initial recipe is set to 350, the basic heat requirement is set to 300, the allowable deviation heat is set to 30, the number of nutrient types is set to 5, and the changes in the difference in the requirement of each nutrient component of the initial recipe under different nutrient content of the initial recipe are calculated, and the recommended degree index of the initial recipe is calculated. As shown in Table 1, the data table of the difference in the requirement of each nutrient component of a certain initial recipe based on the intelligent nutrition ordering system.

[0045] Table 1 Data table of the difference in nutritional requirements for an initial recipe based on the intelligent nutrition ordering system

[0046] i The i-th nutrient content The difference in nutrient requirement 1 50 0 2 100 0 3 55 5 4 80 20 5 15 0

[0047] The calculated recommendation index of the initial recipe is 0.977.

[0048] like Figure 2 As shown in FIG. 1 , it is a diagram showing the variation of the nutritional component requirements of a certain initial recipe based on the intelligent nutritional ordering system provided by the present invention. Figure 2 As can be seen from Table 1, the relationship between the difference in nutrient requirement, the total nutrient requirement and the content of each nutrient in the initial recipe is that when the total nutrient requirement is lower than the content of each nutrient, the nutrient requirement difference is marked as 0; when the total nutrient requirement is higher than or equal to the content of each nutrient, the nutrient requirement difference is marked as the difference between the total nutrient requirement and the content of the nutrient.

[0049] Furthermore, recipe recommendations are made based on the recommendation level index of each initial recipe, and the step of obtaining a nutritional recipe after selection by the service object includes: obtaining a recommendation level index threshold from the intelligent ordering database, comparing the recommendation level index of each initial recipe with the recommendation level index threshold, and if the recommendation level index of an initial recipe is greater than or equal to the recommendation level index threshold, marking the initial recipe as a recommended recipe, and counting the recommended recipes; sorting the recommended recipes in descending order according to the recommendation level index, and displaying and outputting them in turn for selection by the service object, and marking the recommended recipe selected by the service object as a nutritional recipe.

[0050] In the present application, the recommendation level index threshold is a critical value or dividing point for classifying whether a recipe is recommended or not, and is used in the present system to measure the recommendation level of each initial recipe to determine which recipes should be recommended to the service object. By comparing the recommendation level index of each initial recipe with the recommendation level index threshold, recipes that meet or exceed the standard can be screened out, which helps to exclude those options with low nutritional value. After browsing the recommended recipes, the service object can select one or more recipes as nutritional recipes according to his or her taste, nutritional needs or other personal preferences. This step ensures that the finalized recipe meets the actual needs of the service object.

[0051] Furthermore, the service object selects the dish to be replaced from the nutritional menu, and the service object selects the dish to be replaced from the nutritional menu, and marks the dish as the dish to be replaced, and obtains the same type of dish as the dish to be replaced, and marks them as each similar dish.

[0052] In the present application, after determining the nutritional menu, the service recipient may find that one of the dishes does not meet his or her taste, allergen requirements, dietary taboos, or simply wants to try different dishes. In order to let the system or service personnel understand the service recipient's replacement intention, the service recipient will mark the selected dish as a dish to be replaced, so that the system can clearly know which dish needs to be replaced and provide corresponding replacement options accordingly. After determining the dish to be replaced, the system will match similar dishes from the smart ordering database as replacement options based on the type attributes of the dish. These similar dishes should be able to meet the basic needs of the service recipient, and at the same time have certain differences and selectivity in taste, nutrition, etc. By allowing the service recipient to select and replace dishes in the nutritional menu, the system can more accurately meet the personalized needs of the service recipient, thereby improving their dining experience.

[0053] Furthermore, the step of replacing dishes according to the nutritional similarity evaluation values ​​of each similar dish includes: sorting each similar dish in order from large to small according to the nutritional similarity evaluation values ​​of each similar dish, and displaying and outputting them in sequence for the service object to choose, marking the dish selected by the service object as a replacement dish, and performing dish replacement.

[0054] In the present invention application, after obtaining similar dishes of the dish to be replaced, the system will calculate the similarity between each similar dish and the dish to be replaced in terms of nutritional ingredients, give an evaluation value, and sort them in order starting from the one with the highest nutritional similarity. Through the sorting service object, the nutritional similarity between each similar dish and the dish to be replaced can be clearly seen, so as to make a more wise choice. By replacing based on the nutritional similarity evaluation value, it can be ensured that the replaced dish is similar to or better than the dish to be replaced in terms of nutritional ingredients, thereby maintaining the overall balance of the nutritional recipe.

[0055] Furthermore, the step of analyzing and obtaining nutritional similarity evaluation values ​​of similar dishes includes: obtaining the content of each nutrient component of the dish to be replaced and the content of each nutrient component of similar dishes; subtracting the content of each nutrient component of each similar dish from the content of each nutrient component of the dish to be replaced, performing a ratio operation on the absolute value of the difference and the allowable deviation content of each nutrient component preset in the intelligent ordering database, and obtaining the nutritional similarity evaluation value of similar dishes through logarithmic processing.

[0056] In the present application, the nutritional similarity assessment value of each similar dish is a comprehensive indicator for measuring the similarity of the nutritional components of different dishes. In actual application, it is also necessary to use professional nutritional analysis software or database to comprehensively consider the differences in cooking methods, raw material ratios, processing methods, etc. of different dishes, resulting in different nutritional similarity assessment values.

[0057] The steps of obtaining the calories of each dish of the same type and analyzing and obtaining the nutritional similarity evaluation value of each dish of the same type include:

[0058]

[0059] In the formula, ζ k N represents the nutritional similarity evaluation value of the kth similar dish, 3x Indicates the xth nutrient content of the dish to be replaced, N kx represents the xth nutrient content of the kth dish of the same type, △N x Indicates the allowable deviation content of the xth nutrient component, Q 1k represents the calories of the kth dish of the same type, Q( D Indicates the calories of the dish to be replaced, △Q( D ) represents the allowable deviation calories preset in the smart ordering database, x is the number of each nutrient type, x=1,2,3..., M, M is the number of nutrient types, k is the number of dishes of the same type, k=1,2,3,..., m, m is the number of dishes of the same type.

[0060] Furthermore, the step of evaluating and providing feedback on the replacement result includes: marking the nutritional recipe after the dish is replaced as the recipe to be evaluated, obtaining the critical nutritional similarity evaluation value from the intelligent ordering database, and calculating the recommendation degree index of the recipe to be evaluated, and obtaining the nutritional value evaluation value of the recipe to be evaluated through comprehensive analysis based on the nutritional similarity evaluation value between the replaced dish and the dish to be replaced and the recommendation degree index of the recipe to be evaluated; obtaining the nutritional value evaluation threshold from the intelligent ordering database, and if the nutritional value evaluation value of the recipe to be evaluated is greater than or equal to the nutritional value evaluation threshold, waiting for the service object to confirm and completing the ordering operation; if the nutritional value evaluation value of the recipe to be evaluated is less than the nutritional value evaluation threshold, issuing a nutritional demand warning and providing a recommended dish addition operation.

[0061] In the present application, the recommendation index of the menu to be evaluated is obtained according to the calculation formula of the recommendation index of each initial menu. The nutritional value evaluation threshold is obtained from the intelligent ordering database. If the nutritional value evaluation value of the menu to be evaluated is greater than or equal to the nutritional value evaluation threshold, it means that the replaced menu has reached the standard set by the system in terms of comprehensive performance, so the system will show it to the user and wait for the user to confirm whether it is satisfied. If the user confirms, the ordering operation is completed; if the nutritional value evaluation value of the menu to be evaluated is less than the nutritional value evaluation threshold, it indicates that the replaced menu fails to meet the recommended standard of the system in some aspects. At this time, the system will trigger the nutritional demand early warning mechanism to remind the user that the menu may not meet its specific nutritional needs. At the same time, the system will also provide a recommended dish operation, that is, it is recommended that the user add some dishes to improve the overall nutritional balance or taste matching. Through the automated evaluation and feedback mechanism, users can quickly obtain ordering suggestions that meet their nutritional needs without manually calculating or comparing the nutritional components of various dishes, thereby improving the convenience and satisfaction of dining.

[0062] The step of obtaining the nutritional value evaluation value of the recipe to be evaluated includes:

[0063]

[0064] In the formula, ξU represents the nutritional value evaluation value of the recipe to be evaluated, β1 represents the nutritional value evaluation value weight factor corresponding to the nutritional similarity evaluation value, β2 represents the nutritional value evaluation value weight factor corresponding to the recommendation degree index, ζ1 represents the nutritional similarity evaluation value between the replacement dish and the dish to be replaced, ζ0 represents the critical nutritional similarity evaluation value, ξ1 represents the recommendation degree index of the recipe to be evaluated, and ξ0 represents the recommendation degree index threshold.

[0065] In the present application, the nutritional similarity evaluation value between the replacement dish and the dish to be replaced is extracted from the nutritional similarity evaluation value of each similar dish. β1 and β2 are the nutritional value evaluation value weight factors corresponding to the nutritional similarity evaluation value and the recommendation degree index preset in the intelligent ordering database, respectively, which respectively represent the numerical values ​​of the degree of influence of the nutritional similarity evaluation value and the recommendation degree index on the nutritional value evaluation value, and can be directly obtained from the intelligent ordering database when used. For example, the nutritional similarity evaluation value and the nutritional value evaluation value weight factors corresponding to each nutritional similarity evaluation value preset in the intelligent ordering database form a mapping set, and the nutritional value evaluation value weight factor corresponding to a certain nutritional similarity evaluation value is obtained according to the input mapping set of the nutritional similarity evaluation value, wherein the mapping relationship is a many-to-one or one-to-one relationship, and the value range of the weight factor in the present application is between 0 and 1.

[0066] Second, as Figure 3The figure shows a flow chart of the intelligent nutrition ordering method. The intelligent nutrition ordering method adopts any intelligent nutrition ordering system of the first aspect, including:

[0067] Obtain the basic data of the service object and the number of each type of dishes required, count the dishes that can be provided and mark them as target dishes, and collect the nutrient content and calories of each target dish; obtain the total amount of nutrient requirements and basic calorie requirements according to the basic data of the service object, match the menus according to the number of each type of dishes required, obtain each initial menu, obtain the recommendation level index of each initial menu according to the nutrient content and calories of each target dish, recommend menus according to the recommendation level index of each initial menu, and obtain the nutritional menu after selection by the service object; the service object selects the dish to be replaced from the nutritional menu, obtains the nutrient content of each similar dish, analyzes to obtain the nutritional similarity evaluation value of each similar dish, replaces the dish according to the nutritional similarity evaluation value of each similar dish, and evaluates and feedbacks the replacement result.

[0068] In summary, the present invention application collects basic data, counts dish information, matches nutritional needs, matches initial recipes, recommends the best recipes, supports dish substitutions, and collects feedback to tailor nutritionally balanced dish combinations for users. This effectively solves the problem in the prior art that the ordering system recommends dishes based more on the user's historical taste preferences, but these dishes may not cover all the nutrients needed by the body, resulting in unbalanced diet for users, thereby increasing health risks.

[0069] Those skilled in the art will appreciate that the embodiments of the present invention application can be provided as methods, systems, or computer program products. Therefore, the present invention application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present invention application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0070] The present invention application is described with reference to the flowcharts and / or block diagrams of the systems, devices (systems), and computer program products according to the embodiments of the present invention application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0073] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. Intelligent nutrition ordering system, characterized by: include: Data acquisition module, recipe screening module, recipe selection module and intelligent ordering database; The data acquisition module is used to obtain basic data of service objects and the number of demands for various dishes, count the dishes that can be provided and mark them as target dishes, and collect the nutritional content and calories of each target dish; The recipe screening module is used to obtain the total amount of each nutrient component requirement and the basic calorie requirement according to the basic data of the service object, match the recipes according to the number of each type of dish required, obtain each initial recipe, process the recommendation level index of each initial recipe according to the nutrient component content and calorie of each target dish, and recommend recipes according to the recommendation level index of each initial recipe, and obtain the nutritious recipe after the service object selects; The dish replacement module is used for the service object to select the dish to be replaced from the nutritional menu, obtain the content of each nutrient component of each similar dish, analyze and obtain the nutritional similarity evaluation value of each similar dish, replace the dish according to the nutritional similarity evaluation value of each similar dish, and evaluate and feedback the replacement result.

2. The intelligent nutritional ordering system as claimed in claim 1, characterized in that: The step of obtaining the total amount of each nutrient component requirement and the basic calorie requirement according to the basic data of the service object includes: The basic data of the service objects include the basal metabolic rate of each service object, the age of each service object and the number of service objects; Matching the basal metabolic rate of each service object with the required calories corresponding to each basal metabolic rate interval preset in the intelligent ordering database to obtain the basal calorie requirement of each service object; Matching the age of each service object with the required amount of each nutrient component corresponding to each age range preset in the intelligent ordering database to obtain the required amount of each nutrient component of each service object; The calorie requirement of each service object and the nutrient requirement of each service object are summed up respectively to obtain the basic calorie requirement and the total requirement of each nutrient component.

3. The intelligent nutritional ordering system as claimed in claim 1, characterized in that: The step of obtaining the recommendation index of each initial recipe according to the nutrient content and calorie of each target dish comprises: According to the content of each nutrient component of each target dish in each initial recipe and the calorie of each target dish, summing calculation is performed to obtain the content of each nutrient component of each initial recipe and the calorie of each initial recipe; Subtract the total amount of each nutrient required from the content of each nutrient in each initial recipe to obtain the difference in the nutrient required; Compare each nutrient requirement difference with zero. If a nutrient requirement difference is less than zero, set the nutrient requirement difference to zero. If a nutrient requirement difference is greater than or equal to zero, retain the original value of the nutrient requirement difference. Comprehensive analysis was performed to obtain the recommendation level index of each initial recipe.

4. The intelligent nutritional ordering system as claimed in claim 3, characterized in that: The method for obtaining the recommendation index of each initial recipe is as follows: In the formula, ξ j represents the recommendation index of the jth initial recipe, α 1j represents the weight factor of the recommended degree index corresponding to the j-th nutrient content, α 2j represents the weight factor of the recommended degree index corresponding to the j-th nutrient requirement difference, α 3j Indicates the weight factor of the recommendation index corresponding to the jth calorie, N 2(ij) represents the nutrient content of the i-th initial recipe, N 1(ij) N represents the difference in nutrient requirement of the i-th initial recipe, 0(i) represents the total amount of nutrient required for the i-th nutrient, Q 1(j) represents the calories of the jth initial recipe, Q0 represents the basic required calories, ΔQ represents the allowable deviation calories preset in the smart ordering database, where j is the initial recipe number, j=1, 2, 3, ..., N, N is the number of initial recipes, i is the nutrient type number, i=1, 2, 3, ..., n, n is the number of nutrient types.

5. The intelligent nutritional ordering system as claimed in claim 1, characterized in that: The step of recommending a recipe based on the recommendation level index of each initial recipe and obtaining a nutritious recipe after selection by the service object includes: Obtaining a recommendation index threshold from the intelligent ordering database, comparing the recommendation index of each initial recipe with the recommendation index threshold respectively, if the recommendation index of an initial recipe is greater than or equal to the recommendation index threshold, marking the initial recipe as a recommended recipe, and counting each recommended recipe; The recommended recipes are sorted in descending order according to the recommendation degree index, and are displayed and output in sequence for selection by the service object, and the recommended recipe selected by the service object is marked as a nutritious recipe.

6. The intelligent nutritional ordering system as claimed in claim 1, characterized in that: The service object selects the dish to be replaced from the nutritional menu, the service object selects the dish to be replaced from the nutritional menu, and marks the dish as the dish to be replaced, and obtains the same kind of dishes as the dish to be replaced, and marks them as each similar dish.

7. The intelligent nutritional ordering system as claimed in claim 1, characterized in that: The step of replacing dishes according to the nutritional similarity evaluation values ​​of dishes of the same type includes: According to the nutritional similarity evaluation values ​​of each similar dish, each similar dish is sorted in order from large to small, and the output is displayed in sequence for the service object to choose, and the dish selected by the service object is marked as a replacement dish, and the dish is replaced.

8. The intelligent nutritional ordering system as claimed in claim 7, characterized in that: The step of analyzing and obtaining the nutritional similarity evaluation value of each similar dish comprises: Obtaining the nutritional content of the dish to be replaced and the nutritional content of similar dishes; The nutritional content of each similar dish is subtracted from the nutritional content of the dish to be replaced, and the absolute value of the difference is ratioed with the allowable deviation content of each nutritional component preset in the intelligent ordering database. After logarithmic processing, the nutritional similarity assessment value of each similar dish is obtained.

9. The intelligent nutritional ordering system as claimed in claim 1, characterized in that: The step of providing evaluation feedback on the replacement result comprises: The nutritional recipe after the dish is replaced is marked as a recipe to be evaluated, the critical nutritional similarity evaluation value is obtained from the intelligent ordering database, and the recommendation index of the recipe to be evaluated is calculated, and the nutritional value evaluation value of the recipe to be evaluated is obtained through comprehensive analysis based on the nutritional similarity evaluation value between the replaced dish and the dish to be replaced and the recommendation index of the recipe to be evaluated; Obtaining a nutritional value evaluation threshold from the intelligent ordering database, and if the nutritional value evaluation value of the menu to be evaluated is greater than or equal to the nutritional value evaluation threshold, waiting for confirmation by the service object to complete the ordering operation; If the nutritional value assessment value of the recipe to be evaluated is less than the nutritional value assessment threshold, a nutritional demand warning will be issued and a recommended dish addition operation will be provided.

10. An intelligent nutritional ordering method, applied to the intelligent nutritional ordering system according to any one of claims 1 to 9, characterized in that: include: Obtain basic data of service objects and the number of requests for various dishes, count and mark the dishes that can be provided as target dishes, and collect the nutritional content and calories of each target dish; According to the basic data of the service object, the total amount of each nutrient component requirement and the basic calorie requirement are obtained, and the menus are matched according to the number of each type of dishes required to obtain each initial menu. According to the nutrient content and calorie of each target dish, the recommendation degree index of each initial menu is obtained, and the menu is recommended according to the recommendation degree index of each initial menu, and the nutritious menu is obtained after the service object selects it; The service recipient selects dishes to be replaced from the nutrition menu, obtains the content of each nutrient component of each similar dish, analyzes and obtains the nutritional similarity assessment value of each similar dish, replaces the dishes according to the nutritional similarity assessment value of each similar dish, and provides evaluation feedback on the replacement results.

Images