Recipe recommendation method and device, storage medium and equipment
By obtaining and sorting the health parameter information of recipes and giving recipe health labels, the problem of neglecting health needs in the existing technology is solved, and more efficient and accurate recipe recommendations are achieved.
Patent Information
- Application Number
- CN202410622763.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-17
- Publication Date
- 2024-12-06
AI Technical Summary
The existing recipe recommendation methods ignore users' health needs and are unable to systematically and digitize the health attributes in the recipe, resulting in low recommendation efficiency and accuracy.
By obtaining recipe information, determine health parameter information, including condiments content and nutrient energy supply ratio, sorting and grading, giving recipes a healthy label, and recommending recipes based on the tags.
Improves the efficiency and accuracy of recipe recommendations, ensuring that users get recipe recommendations that meet their health needs.
Smart Images

Figure CN119088846A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a recipe recommendation method, device, storage medium and equipment. Background Art
[0002] With the development of technology, some application software or websites recommend recipes to users based on the preference tags pre-selected by the user, that is, matching the recipe tags with the preference tags pre-selected by the user and recommending the matched recipes to the user. For example, if the user marks that he likes Northeastern cuisine, then the application software or website will recommend the recipes in the recipe database that are also marked with the Northeastern cuisine tag to the user.
[0003] However, this method requires recipes to be labeled before they can be recommended, and this process is mostly done manually, which is not only time-consuming but also prone to errors. Moreover, such recipe recommendations often ignore the health needs of users and fail to systematically and digitally process the data on the health attributes of recipes, thus failing to recommend healthier recipes to users.
[0004] Therefore, how to make recipe recommendations based on user health needs to improve the efficiency and accuracy of recipe recommendations is an urgent problem to be solved. Summary of the invention
[0005] The present application provides a recipe recommendation method, device, storage medium and equipment to recommend recipes based on the health needs of users to improve the efficiency and accuracy of recipe recommendations.
[0006] This application adopts the following technical solutions:
[0007] The present application provides a recipe recommendation method, comprising:
[0008] Get recipe information for each recipe;
[0009] Determining health parameter information of each recipe according to the recipe information of each recipe, wherein the health parameter information is used to characterize information of each health attribute, and the information of each health attribute includes at least one of the content of condiments in each recipe and the energy supply ratio of nutrients in each recipe;
[0010] Sorting the recipes according to the health parameter information of the recipes to obtain a sorting result;
[0011] Determine the health level of each recipe according to the ranking result, and mark each recipe according to the health level to obtain a health label corresponding to each recipe;
[0012] According to the health label, recipes are recommended to the user.
[0013] This application sorts and divides each recipe into health levels according to the health parameter information of the recipe, and recommends recipes that are more suitable for the user's health according to the health labels corresponding to each recipe. It is more targeted and improves the efficiency and accuracy of recipe recommendations.
[0014] Optionally, the recipes are sorted according to the health parameter information of the recipes to obtain a sorting result, including:
[0015] Classifying the recipes according to preset recipe categories to obtain recipes under each recipe category;
[0016] For each recipe category, the recipes under the recipe category are sorted according to the health parameter information of each recipe under the recipe category to obtain the sorting result of each recipe under each recipe category.
[0017] In order to obtain more accurate health labels, the present application classifies each recipe and sorts each recipe under each recipe category. Optionally, the health level of each recipe is determined based on the sorting result, and each recipe is marked based on the health level to obtain a health label corresponding to each recipe, including:
[0018] According to the ranking results of each recipe under each recipe category, the health level of each recipe under each recipe category is determined respectively, and according to the health level of each recipe under each recipe category, each recipe under each recipe category is marked respectively to obtain the health label corresponding to each recipe under each recipe category.
[0019] This application is aimed at the sorting results of each recipe under each recipe category, and obtains the health label corresponding to each recipe under each recipe category.
[0020] Optionally, the recipes under the recipe category are sorted according to the health parameter information of the recipes under the recipe category, including:
[0021] For each health attribute in the health parameter information, the recipes under the recipe category are sorted according to the information of each recipe under the recipe category for the health attribute, so as to obtain the sorting result of each recipe under the recipe category for the health attribute.
[0022] This application can re-sort recipes under each recipe category according to each health attribute in the health parameter information.
[0023] Optionally, the ranking results of the recipes under each recipe category include ranking results of the recipes under each recipe category for each health attribute; according to the ranking results of the recipes under each recipe category, the health level of each recipe under each recipe category is determined respectively, and according to the health level of each recipe under each recipe category, each recipe under each recipe category is marked respectively to obtain the health label corresponding to each recipe under each recipe category, including:
[0024] For each health attribute in the health parameter information, according to the ranking results of each recipe under each recipe category for the health attribute, determine the health level of each recipe under each recipe category for the health attribute, and mark each recipe under each recipe category according to the health level of each recipe under each recipe category for the health attribute to obtain a health label for each recipe under each recipe category for the health attribute;
[0025] According to the health labels of each recipe under each recipe category for each health attribute, the health labels corresponding to each recipe under each recipe category are obtained.
[0026] This application can obtain the health label corresponding to each recipe under each recipe category according to the ranking results of each recipe under each recipe category for each health attribute.
[0027] Optionally, the recipes are sorted according to the health parameter information of the recipes to obtain a sorting result, including:
[0028] For each health attribute in the health parameter information, the recipes are sorted according to the information of the recipes for the health attribute to obtain a sorting result of the recipes for each health attribute.
[0029] The health parameter information of this application includes multiple health attributes, and each recipe needs to be sorted for each health attribute.
[0030] Optionally, determining the health level of each recipe according to the ranking result, and marking each recipe according to the health level to obtain a health label corresponding to each recipe, including:
[0031] For each health attribute in the health parameter information, according to the ranking result of each recipe for the health attribute, determine the health level of each recipe for the health attribute, and mark each recipe according to the health level of each recipe for the health attribute to obtain a health label of each recipe for the health attribute;
[0032] According to the health labels of the recipes for the health attributes, the health labels corresponding to the recipes are obtained.
[0033] The present application sorts each recipe according to each health attribute, and then obtains a health label for each recipe for each health attribute. Therefore, the present application can divide each recipe according to multiple health attributes to obtain more diversified health labels.
[0034] Optionally, the recipe information of each recipe includes the number of people eating and total health parameter information;
[0035] Determining health parameter information of each recipe according to the recipe information of each recipe includes:
[0036] The per capita health parameter information of each recipe is determined according to the number of consumers and the total health parameter information in the recipe information of each recipe, as the health parameter information of each recipe.
[0037] This application takes into account that the number of consumers corresponding to each recipe is different. In order to unify the classification standards, the total health parameter information can be calculated first to obtain the per capita health parameter information.
[0038] Optionally, based on the health label, a recipe is recommended to the user, including:
[0039] Acquire the health preference information that the user is concerned about;
[0040] Recommending recipes to the user based on the health label and the health preference information.
[0041] This application further screens recipes based on the health preference information of the user, obtains recipes that meet the health information of the user, and recommends them to the user.
[0042] Optionally, based on the health label, a recipe is recommended to the user, including:
[0043] Determine the recipe category selected by the user as the target recipe category;
[0044] According to the target recipe category, determine each recipe under the target recipe category;
[0045] Recipes are recommended to the user based on the health labels corresponding to the recipes under the target recipe category.
[0046] In order to improve the user experience, this application can obtain the recipe category selected by the user, and then recommend recipes under the recipe category selected by the user.
[0047] Optionally, based on the health label, a recipe is recommended to the user, including:
[0048] Acquire the health preference information of the user and the recipe category selected by the user;
[0049] Determining the recipe category selected by the user as a target recipe category;
[0050] According to the target recipe category, determine each recipe under the target recipe category;
[0051] According to the health label of each recipe under the target recipe category and the health preference information, the recipes under the target recipe category are recommended to the user.
[0052] This application can recommend suitable recipes to users based on health preference information and the recipe categories required by users.
[0053] Optionally, based on the health label, a recipe is recommended to the user, including:
[0054] According to the health labels, recipes are recommended to the user in descending order of the health levels of the recipes.
[0055] This application can recommend recipes to users in order of health level from high to low, so that users can see recipes with higher health levels first.
[0056] The present application provides a recipe recommendation device, comprising:
[0057] The acquisition module is used to obtain the recipe information of each recipe;
[0058] a determination module, configured to determine health parameter information of each recipe according to recipe information of each recipe, wherein the health parameter information is information used to characterize each health attribute, and the information of each health attribute includes at least one of the content of condiments in each recipe and the energy supply ratio of nutrients in each recipe;
[0059] A sorting module, used for sorting the recipes according to the health parameter information of the recipes to obtain a sorting result;
[0060] a marking module, used to determine the health level of each recipe according to the sorting result, and mark each recipe according to the health level to obtain a health label corresponding to each recipe;
[0061] The recommendation module is used to recommend recipes to users based on the health tags.
[0062] The present application provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned recipe recommendation method is implemented.
[0063] The present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned recipe recommendation method when executing the program.
[0064] At least one of the above technical solutions adopted in this application can achieve the following beneficial effects:
[0065] In the recipe recommendation method provided by the present application, the recipe information of each recipe is first obtained, and the health parameter information of each recipe is determined based on the recipe information. According to the health parameter information of each recipe, each recipe is sorted to obtain a sorting result. Then, according to the sorting result, the health level of each recipe is determined, and according to the health level, each recipe is marked to obtain a health label corresponding to each recipe. Finally, according to the health label, the recipe is recommended to the user. The present application can sort the recipes according to the health parameter information in the recipe information, divide the health level for the recipes according to the sorting results, and recommend recipes according to the divided health levels, thereby improving the efficiency and accuracy of recipe recommendations.
[0066] It can be seen from the above method that in this application, each recipe is classified into a health level through health parameter information, and then recipes are recommended to users through the obtained health labels. This method allows users to quickly find recipes that meet their health needs, and while meeting the health needs of users, it also further improves the efficiency of recipe recommendations. BRIEF DESCRIPTION OF THE DRAWINGS
[0067] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the specification of the present application. The illustrative embodiments and descriptions of the specification of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0068] Figure 1 A schematic diagram of a recipe recommendation method provided in this application;
[0069] Figure 2A to Figure 2D A schematic diagram of dividing health labels according to four health attributes provided in this application;
[0070] Figure 3 A schematic diagram of a recipe recommendation device provided in this application;
[0071] Figure 4 A method corresponding to the present application Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION
[0072] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0073] With the development of technology, some current applications or websites recommend recipes based on user preferences. Specifically, recipes are tagged and tagged with tags that match the recipe. For example, if the recipe has a tag of Northeastern cuisine, and the user's favorite tags include Northeastern cuisine, then when the user searches for recipes, the application or website will give priority to recommending recipes with the Northeastern cuisine tag.
[0074] It can be seen that current recipes are often recommended based on the user's own preferences. When a user wants to choose a recipe that matches his or her health condition, he or she needs to check the recipe information in the recipes recommended based on the user's own preferences one by one to find a recipe that matches his or her health condition. Therefore, this method is inefficient in recommending recipes.
[0075] Based on this, the present application provides a recipe recommendation method, which obtains the recipe information of each recipe, and determines the health parameter information of each recipe based on the recipe information. According to the health parameter information of each recipe, each recipe is sorted to obtain a sorting result. Then, according to the sorting result, the health level of each recipe is determined, and according to the health level, each recipe is marked to obtain a health label corresponding to each recipe. Finally, according to the health label, the recipe is recommended to the user. The present application can sort the recipes according to the health parameter information in the recipe information, divide the health level for the recipes according to the sorting results, and recommend recipes according to the divided health levels, thereby improving the efficiency and accuracy of recipe recommendations.
[0076] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0077] Figure 1 A schematic diagram of a recipe recommendation method provided in this application, comprising the following steps:
[0078] S101: Obtain recipe information of each recipe.
[0079] In this application, a recipe recommendation method can be divided into two parts. The first is to determine the health label of each recipe, and then recommend recipes to users based on the health label. Among them, the execution subject for determining the health label of each recipe can be a terminal device such as a tablet computer, a laptop computer, a mobile phone, and of course, it can also be a server. For the sake of ease of description, this application only takes the server as an example to illustrate the part of determining the health label in a recipe recommendation method provided in this application.
[0080] The preset recipe database includes multiple recipes, which can be preset by the business party or uploaded by different users. Each recipe records rich recipe information, including: recipe name, main ingredient amount, side ingredient amount, number of diners, nutrient information, etc. The server obtains the recipe information of each recipe from the preset recipe database, so as to determine the health label of each recipe based on the recipe information.
[0081] S102: Determine the health parameter information of each recipe according to the recipe information of each recipe.
[0082] The server determines health parameter information of each recipe based on the recipe information of each recipe, wherein the health parameter information is used to characterize information of each health attribute, and the information of each health attribute includes at least one of the content of seasoning in each recipe and the energy supply ratio of nutrients in each recipe.
[0083] For example, the content of condiments in the information of various health attributes may refer to the salt (Na) content, edible oil content, added sugar content, etc., and the energy supply ratio of nutrients in the information of various health attributes may refer to the energy supply ratio of fat, protein, carbohydrates, etc. These health attribute information are the basis of nutritional meal matching and are also important indicators for evaluating whether the dietary structure is reasonable. Through these health attribute information, it is possible to better judge which recipes are more suitable for recommendation to users.
[0084] The recipe information of each recipe may include the number of people eating and total health parameter information. The health parameter information here may directly refer to the total health parameter information.
[0085] Of course, because the number of people corresponding to each recipe may be different, in order to unify the sorting criteria, the server may first process the total health parameter information. Specifically, for each recipe, the server determines the per capita health parameter information of the recipe based on the number of people in the recipe information of the recipe and the total health parameter information in the recipe information of the recipe, as the health parameter information of the recipe.
[0086] S103: Sort the recipes according to the health parameter information of the recipes to obtain a sorting result.
[0087] The server sorts each recipe according to the health parameter information of each recipe to obtain a sorting result. For example, if the salt content in the health parameter information is sorted, when the health parameter information refers to the per capita health parameter information, for each recipe, the per capita salt content is obtained according to the total salt content of the recipe and the number of people who consume it, as the health parameter information determined according to the recipe information. Then, the recipes are sorted according to the per capita salt content of each recipe to obtain a sorting result for the salt content.
[0088] S104: Determine the health level of each recipe according to the ranking result, and mark each recipe according to the health level to obtain a health label corresponding to each recipe.
[0089] When making recommendations based on all recipes, the server determines the health level of each recipe based on the ranking results of each recipe, and further labels each recipe based on the health level of each recipe to obtain a health label corresponding to each recipe. The health label is used to characterize the health level of each recipe. For each recipe, the higher the ranking position of the recipe in the ranking results, the higher the health level of the recipe. Conversely, the lower the ranking position of the recipe in the ranking results, the lower the health level of the recipe.
[0090] In actual applications, each recipe can be divided into multiple categories, and the ranking results of each recipe under each category may be slightly different from the ranking results of all recipes. Therefore, for different categories, the server can obtain the health labels corresponding to each recipe under the category. Specifically, for each recipe category, the server determines the health level of each recipe under the recipe category based on the ranking results of each recipe under the recipe category, and marks each recipe under the recipe category based on the health level of each recipe under the recipe category to obtain the health labels corresponding to each recipe under each recipe category, thereby obtaining the health levels corresponding to all recipes.
[0091] It should be noted that the health parameter information includes information on multiple health attributes. The server sorts and marks the health level of each recipe for each health attribute to obtain a health label corresponding to each health attribute.
[0092] Specifically, for each health attribute in the health parameter information, the server can sort each recipe according to the information of each recipe for the health attribute, obtain the sorting result of each recipe for the health attribute, and thus obtain the sorting result of each recipe for each health attribute. Further, for each health attribute in the health parameter information, the server determines the health level of each recipe for the health attribute according to the sorting result of each recipe for the health attribute, and marks each recipe according to the health level of each recipe for the health attribute, so as to obtain the health label of each recipe for the health attribute.
[0093] That is to say, if the health parameter information includes only one health attribute, then the server will only get one sorting result, and the health label corresponding to the sorting result will also be only one. If the health parameter information includes multiple health attributes, then for each health attribute, the server can get the sorting result for the health attribute, and then get the health label for each health attribute.
[0094] For example, when the health parameter information contains information about four health attributes, three of which may be salt (Na) content, cooking oil content, and added sugar content, and the other health attribute may be fat energy supply ratio, the server classifies the health level of each recipe according to the information about the four health attributes, which may be divided into four health levels, and the health labels corresponding to the four health levels are A, B, C, and D. Figure 2A to Figure 2D shown.
[0095] Figure 2A to Figure 2D This is a schematic diagram of dividing health labels according to four health attributes provided in this application.
[0096] from Figure 2AIt can be seen that when the health attribute information includes salt content, in addition to directly classifying by salt content, it can also be assisted by the ratio between salt content (in mg) and total energy (in kcal). Its health label can be marked as: in the sorting results for salt content, the recipes ranked at [0,25%] (for example, 100 recipes, the top 25 recipes in the ranking belong to [0,25%]) have a health label of A for salt content; for recipes ranked at (25,50%], further determine whether the ratio between the salt content and the total energy of the recipe is not greater than 1. If If yes, the recipe's health label for salt content is A, otherwise the recipe's health label for salt content is B; for recipes at the sorting position (50,75%], further determine whether the ratio of the recipe's salt content to total energy is not greater than 1. If so, the recipe's health label for salt content is A, otherwise the recipe's health label for salt content is C; for recipes at the sorting position (75,100%], further determine whether the ratio of the recipe's salt content to total energy is not greater than 1. If so, the recipe's health label for salt content is A, otherwise the recipe's health label for salt content is D.
[0097] The server can also directly sort the recipes according to the salt content (in mg) from small to large to obtain the sorting results of each recipe for salt content. The healthy label for salt content can be marked as follows: in the sorting results for salt content, the recipes at the sorting position [0,25%] have a healthy label A for salt content; the recipes at the sorting position (25,50%] have a healthy label B for salt content; the recipes at the sorting position (50,75%] have a healthy label C for salt content; the recipes at the sorting position (75,100%] have a healthy label D for salt content.
[0098] from Figure 2B It can be seen that when the information of health attributes includes edible oil content, the health label for edible oil content can be marked as follows: in the sorting results for edible oil content, the recipes at the sorting position [0,25%] have a health label A for edible oil content; the recipes at the sorting position (25,50%] have a health label B for edible oil content; the recipes at the sorting position (50,75%] have a health label C for edible oil content; the recipes at the sorting position (75,100%] have a health label D for edible oil content.
[0099] from Figure 2CIt can be seen that when the information of health attributes includes the added sugar content, the health label for the added sugar content can be marked as follows: in the sorting results for the added sugar content, the recipes at the sorting position [0,25%] have a health label A for the added sugar content; the recipes at the sorting position (25,50%] have a health label B for the added sugar content; the recipes at the sorting position (50,75%] have a health label C for the added sugar content; the recipes at the sorting position (75,100%] have a health label D for the added sugar content.
[0100] from Figure 2D It can be seen that when the health attribute information includes the fat energy supply ratio, for each recipe, when the fat energy supply ratio of the recipe belongs to [0,30%], the health label of the recipe for the fat energy supply ratio is A; when the fat energy supply ratio of the recipe belongs to (30,50%], the health label of the recipe for the fat energy supply ratio is B; when the fat energy supply ratio of the recipe belongs to (50,75%], the health label of the recipe for the fat energy supply ratio is C; when the fat energy supply ratio of the recipe belongs to (75,100%], the health label of the recipe for the fat energy supply ratio is D.
[0101] Based on the health label for salt content, the health label for cooking oil content, the health label for added sugar content, and the health label for fat energy supply ratio, the server obtains the health labels for health parameter information of each recipe, which can be recorded as [A, B, C, D], [B, B, A, D], etc., where the four positions represent the health labels for the four health attributes respectively.
[0102] It should be noted that the server can divide each recipe into four health levels, or it can divide each recipe into three health levels, or five health levels. The percentage values used for dividing the health levels for the sorting positions can also be changed to meet the effect that can be achieved in this application. For example, when dividing each recipe into four health levels, you can use [0, 25%], (25, 50%], (50, 75%], (75, 100%] as the division criteria, or you can use [0, 30%], (30, 50%], (50, 75%], (75, 100%] as the division criteria.
[0103] S105: Recommending recipes to the user based on the health label.
[0104] The above content illustrates the process of the server determining the health label of each recipe, and the server can store the determined health label of each recipe, and then recommend recipes to users based on the health label. This process can be completed by the terminal device used by the user or the client installed on the terminal device interacting with the server. Specifically, the client can send a request to the server based on the user's selection operation, and the server returns the recipes that meet the user's needs to the client based on the request sent by the client, and the client then recommends the recipes that meet the user's needs to the user. Among them, the client mentioned here can be an application software, a mini-program, etc.
[0105] The client recommends recipes to users based on the health tags of the health parameter information and in descending order of the health level of each recipe.
[0106] Continuing with the above example, if the health attribute information includes salt (Na) content, edible oil content, added sugar content, and fat energy supply ratio, the health label for each recipe is in the form of [A, B, C, D], [B, B, A, D], etc. It can be seen that there are health labels for four health attributes, and the health label for each health attribute can be one of A, B, C, and D.
[0107] On this basis, the present application provides a method for recommending recipes to users based on health labels. For each recipe, when the health labels for the four health attributes in the health labels corresponding to the recipe do not contain A or B, no recommendation will be made (that is, when the health labels for the four health attributes in the health labels corresponding to the recipe are all composed of C or D, no recommendation will be made), such as [C, C, C, D], [C, D, C, D].
[0108] The client recommends recipes that contain at least one A or B in the health tag in the order of the most A in the health tag, that is, 4A>3A>2A>A (when the health tag contains 4 A's, it is recommended first, followed by 3 A's, then 2 A's, and finally 1 A), and then recommends recipes in the order of the most B's in the health tag, that is, 4B>3B>2B>B (when the health tag contains 4 B's, it is recommended first, followed by 3 B's, then 2 B's, and finally 1 B).
[0109] For example, if there are the following five recipes, and their health labels are [A, C, C, D], [B, A, C, D], [A, A, B, D], [A, B, B, B], and [C, A, A, B], the client will recommend these five recipes to the user in the order of [C, A, A, B], [A, A, B, D], [A, B, B, B], [B, A, C, D], and [A, C, C, D].
[0110] It should be noted that in actual applications, the server may first classify all recipes according to preset recipe categories to obtain recipes under each category. For example, each recipe may be divided into five categories, namely staple food, meat, vegetables, desserts, and beverages. For each recipe category, the server determines the health level of each recipe under the recipe category based on the sorting results of each recipe under the recipe category, and marks each recipe under the recipe category based on the health level of each recipe under the recipe category to obtain the health label corresponding to each recipe under the recipe category, thereby obtaining the health label corresponding to each recipe under each recipe category, and then obtaining the health label corresponding to all recipes.
[0111] It should also be noted that when sorting the recipes under each recipe category, the health parameter information thereof may also include multiple health attributes. Specifically, for each health attribute in the health parameter information, the server sorts the recipes under the recipe category according to the information of the health attribute of the recipes under the recipe category, so as to obtain the sorting result of the recipes under the recipe category for the health attribute, thereby obtaining the sorting result of the recipes under each recipe category for each health attribute.
[0112] Furthermore, for each health attribute in the health parameter information, the server determines the health level of each recipe under each recipe category for the health attribute according to the sorting results of each recipe under each recipe category for the health attribute, and marks each recipe under each recipe category according to the health level of each recipe under each recipe category for the health attribute to obtain a health label for each recipe under each recipe category for the health attribute. The server obtains the health label corresponding to each recipe under each recipe category based on the health label of each recipe under each recipe category for each health attribute.
[0113] On this basis, when making recipe recommendations, the client can also make recommendations based on the recipe category selected by the user. Specifically, the client can send the recipe category selected by the user as the target recipe category to the server, and the server can determine the recipes under the target recipe category and return the health tags corresponding to the recipes under the target recipe category to the client. Then, the client can recommend recipes under the target recipe category to the user based on the health tags corresponding to the recipes under the target recipe category. This method allows recipes of different categories to be compared only with recipes of the same category to obtain more accurate recommendation results.
[0114] From the above content, it can be seen that there are two ways to determine the health labels of each recipe in this application. One is to sort all recipes, and the other is to classify each recipe and sort each recipe under each category separately. In either case, the user can get recipe recommendations for the recipe category by selecting the recipe category, but when making recommendations based on health labels determined in different ways, the recommendation results may be inconsistent.
[0115] For example, for a recipe, the health label corresponding to the ranking result of the recipe in all recipes may be [B, A, C, B], while the health label corresponding to the ranking result of the recipe in each recipe under the recipe category to which it belongs may be [A, A, B, B]. It can be seen that under different ranking methods, the health label corresponding to each recipe may be inconsistent. Therefore, when the client makes recommendations based on the recipe category selected by the user, the recommendation results may also be inconsistent.
[0116] In order to better meet the health needs of users, the client can also set some options about health preference information for users to choose, such as: less salt, less oil, less sugar. The client obtains the health preference information that users are concerned about, and recommends it to users based on the health preference information that users are concerned about and the health labels corresponding to each recipe. The health labels corresponding to each recipe here can be obtained by sorting all recipes, or by sorting each recipe under different recipe categories.
[0117] When a user selects a health preference information, such as less salt. Less salt corresponds to a health label for salt content. Then, when the client recommends recipes to the user based on the health label, only recipes with health labels A or B for salt content are recommended (recipes with health labels C and D for salt content are not recommended), and the recommendations are made in the order of A and then B for salt content. In the case of the same level of health labels for salt content, A is given priority display among the other three health attributes, followed by B, and then C.
[0118] For example, there are three recipes with health labels [C, A, A, B], [A, A, B, D], and [A, B, B, B] respectively. Then, the client will recommend the recipes to the user in the order of [A, A, B, D] and [A, B, B, B]. The recipe with the health label [C, A, A, B] is not recommended because its health label for salt content is C, which does not meet the recommendation requirements.
[0119] When the user selects two health preference information, such as less salt and less oil. Less salt corresponds to the health label for salt content, and less oil corresponds to the health label for edible oil content. Then, when the client recommends recipes based on health labels, only recipes with health labels A or B for salt content and A or B for edible oil content are recommended (recipes with health labels C or D for either health attribute in the health labels for salt content or edible oil content are not recommended), and recommendations are made from the most to the least number of A in the health labels for salt content and the health labels for edible oil content (AA>AB=BA>BB). When the health labels for salt content and edible oil content are of the same level, the health labels A for the other two health attributes are given priority display, followed by B with more priority display, and then C with more priority display.
[0120] For example, there are four recipes with health labels of [A, A, A, B], [A, D, B, D], [A, B, B, B], and [A, B, C, B]. Then, the client will recommend the recipes to the user in the order of [A, A, A, B], [A, B, B, B], and [A, B, C, B]. The recipe with the health label of [A, D, B, D] is not recommended because its health label for edible oil content is D, which does not meet the recommendation requirements.
[0121] When the user selects three health information, such as less salt, less oil, and less sugar. Less salt corresponds to a health label for salt content, less oil corresponds to a health label for edible oil content, and less sugar corresponds to a health label for added sugar content. Then, when the client recommends recipes based on health labels, only recipes with health labels A or B for salt content, A or B for edible oil content, and A or B for added sugar content are recommended (recipes with health labels C or D for any of the health attributes in the health labels for salt content, edible oil content, and added sugar content are not recommended), and are recommended from most to least according to the number of A in the health labels for salt content, edible oil content, and added sugar content (AAA>AAB=ABA=BAA>ABB=BAB=BBA>BBB). When the health labels for salt content, edible oil content, and added sugar content are of the same level, the health label for the remaining health attribute is A, which is displayed first, followed by B, and then C.
[0122] For example, there are four recipes with health labels [A, A, A, B], [A, A, B, D], [A, B, B, B], and [A, B, C, B]. Then, the client will recommend the recipes to the user in the order of [A, A, A, B], [A, A, B, D], and [A, B, B, B]. The recipe with the health label [A, B, C, B] is not recommended because its health label for added sugar is C, which does not meet the recommendation requirements.
[0123] Of course, the client can also recommend recipes based on the user's health preference information and the recipe category selected by the user. Specifically, the client obtains the health preference information that the user is concerned about and the recipe category selected by the user, takes the recipe category selected by the user as the target recipe category, and recommends recipes under the target recipe category to the user based on the health preference information that the user is concerned about and the health tags of each recipe under the target recipe category.
[0124] When the client makes recommendations based on the health tags of each recipe, it can use the health tags obtained by sorting all the recipes together, or it can use the health tags obtained by sorting the recipes under the target recipe category.
[0125] For example, when the client makes recipe recommendations based on both the user's health preference information and the recipe category selected by the user, one of the methods is to make recommendations based on the health tags obtained by sorting all the recipes together. Specifically, the client can send the recipe category selected by the user as the target recipe category to the server, and the server can determine the recipes under the target recipe category, and return the health tags corresponding to the recipes under the target recipe category to the client. The client can then make recommendations based on the health tags corresponding to the recipes under the target recipe category and the user's health preference information, that is, recommend recipes with health tags such as A or B corresponding to the user's health preference information under the target recipe category.
[0126] The other is to make recommendations based on the health labels obtained by sorting the recipes under each recipe category, which includes two methods. The server has pre-sorted the recipes under each recipe category as described above to obtain the health labels of each recipe under each recipe category. The client can send the recipe category selected by the user as the target recipe category to the server, and the server can determine the recipes under the target recipe category, and return the health labels corresponding to the recipes under the target recipe category to the client. Then the client can make recommendations based on the health labels corresponding to the recipes under the target recipe category in combination with the user's health preference information, that is, recommend recipes with health labels corresponding to the user's health preference information under the target recipe category, such as A or B; or the client first sends the recipe category selected by the user as the target recipe category to the server, and the server re-sorts the recipes under the target recipe category to obtain the health labels of each recipe under the target recipe category, and then returns the health labels corresponding to the recipes under the target recipe category to the client. Then the client can make recommendations based on the health labels corresponding to the recipes under the target recipe category in combination with the user's health preference information, that is, recommend recipes with health labels corresponding to the user's health preference information under the target recipe category, such as A or B.
[0127] In order to better explain this application as a whole, a complete recipe is used as an example. The basic information of this recipe is:
[0128] Recipe Name: Sweet and Sour Spare Ribs
[0129] Main ingredients: 500 grams of pork ribs
[0130] Ingredients: 10g ginger; 50g rock sugar; 50g balsamic vinegar; 50g cooking wine; 25g light soy sauce; 5g dark soy sauce; 1g cooked white sesame seeds (appropriate amount)
[0131] Servings: 4 people
[0132] Nutritional information: Calories 1736.86 kcal, protein 88.04 g (protein energy supply ratio 32.0%), fat 127.04 g (fat energy supply ratio 46.0%), carbohydrates 60.53 g (carbohydrate energy supply ratio 22.0%), sodium 2135.21 mg
[0133] Recipe category: Meat.
[0134] The server first obtains the information of each health attribute in the health parameter information:
[0135] 1. Obtain salt content: 2135.21 mg;
[0136] 2. Get the edible oil content: 0 grams;
[0137] 3. Get the added sugar content: 50 grams;
[0138] 4. Obtain energy supply ratio from fat: 46%.
[0139] Furthermore, the server calculates the average health parameter information:
[0140] 1. The average salt content per person is 2135.21 mg / 4 = 533.80 mg; the ratio between salt content and total energy is Na / total energy = 2135.21 mg / 1736.86 kcal = 1.23
[0141] 2. Per capita edible oil content: 0 g / 4 = 0 g
[0142] 3. Added sugar content per person: 50g / 4=12.5g
[0143] Next, the server sorts all recipes in the recipe database according to the per capita salt content, per capita edible oil content, and per capita added sugar content, and obtains the sorting results for per capita salt content, per capita edible oil content, and per capita added sugar content:
[0144] 1. If the per capita salt content of the recipe is in the (25%, 50%] position in the ranking results for per capita salt content, and Na / total energy>1, then the health label corresponding to the per capita salt content is B;
[0145] 2. If the per capita edible oil content of the recipe is in the (0%, 25%] position in the ranking results for per capita edible oil content, the health label corresponding to the per capita edible oil content is A;
[0146] 3. If the per capita added sugar content of the recipe is in the (50%, 75%] position in the sorting results for per capita added sugar content, the health label corresponding to the per capita added sugar content is C;
[0147] 4. The fat energy supply ratio of this recipe is 46%, which belongs to the (25%, 50%] range, so the health label corresponding to the fat energy supply ratio is B.
[0148] Then, the health label of this sweet and sour pork ribs recipe for health parameter information is [B, A, C, B].
[0149] When the user does not select a recipe category, the sweet and sour pork ribs recipe is a recipe with only one A, and not all four health tags are C or D. It can be recommended to the user. The client can make recommendations in the order of the number of A in the health tags of each recipe from most to least (4A>3A>2A>A).
[0150] When the user selects health preference information (less salt, less oil, less sugar), if the user selects less salt, according to the sweet and sour pork ribs recipe, the health label corresponding to less salt is B, and it can be recommended, but the recommendation order is after the recipe with the health label corresponding to less salt is A; when the user selects less salt and less oil, according to the sweet and sour pork ribs recipe, the health label corresponding to less salt and less oil is BA, and it can be recommended, but the recommendation order is after the recipe with the health label corresponding to less salt and less oil is AA, and in front of the recipe with the health label corresponding to less salt and less oil is BB; when the user selects less salt, less oil, less sugar, according to the sweet and sour pork ribs recipe, the health label corresponding to less salt, less oil and less sugar is BAC, it is not recommended.
[0151] If the user selects a meat recipe, the server can first filter out all recipes classified as meat in the recipe database. The sweet and sour pork ribs recipe is a recipe with only one A, and not all four health tags are C or D. It can be recommended to the user. Specifically, the client can make recommendations in the order of the number of A in the health tags of each recipe under meat (4A>3A>2A>A).
[0152] If the user selects a meat recipe and is interested in the low-salt tag, the server can first filter out all recipes in the recipe database that are classified as meat. The sweet and sour pork ribs recipe has a low-salt health tag of B and can be recommended, but the recommendation order is after the recipe with a low-salt health tag of A.
[0153] When determining the health label of the sweet and sour pork ribs recipe for health parameter information, it is not determined according to the ranking of the recipe category in which it is located. Therefore, when determining the health label of the sweet and sour pork ribs recipe for health parameter information, it can also be classified according to the recipe category. The sweet and sour pork ribs recipe belongs to a meat recipe. According to the per capita salt content, per capita cooking oil content, and per capita added sugar content in the meat recipe, the recipes of the recipe category of meat are sorted and the health levels are determined, and the health label of the sweet and sour pork ribs is [A, A, B, B]. Then recommend according to the above recommendation method, such as recommending according to the order of the number of A contained in the health label of each recipe from most to least, selecting the corresponding health label for recommendation according to the health preference information of the user (such as less salt), first determining the target recipe category and then recommending according to the number of A contained in the health label or combining the health preference information of the user, etc.
[0154] Of course, when the user selects the recommendation of meat recipes, the server can also first filter out all recipes classified as meat in the recipe database, and re-sort the filtered meat recipes according to the per capita salt content, per capita cooking oil content, and per capita added sugar content. The server regenerates the health label of the sweet and sour spareribs recipe based on the sorting result. If the health label of the sweet and sour spareribs regenerated in the meat recipe is [A, A, B, B], the client recommends the sweet and sour spareribs recipe to the user, such as recommending it in order of the number of A in the health labels of each recipe from most to least, and selecting the corresponding health label for recommendation based on the health preference information that the user is concerned about (such as less salt).
[0155] In the present application, the server quickly grades each recipe based on the health parameter information in the recipe, obtains a health label for each recipe based on the health parameter information, and determines which recipes should be recommended to users and which recipes are not suitable for recommendation based on the health labels, and recommends them to users in a specific order. In this way, the recipes that users see first are relatively healthier recipes, and the efficiency of recipe recommendations is further improved.
[0156] In addition, the present application can also recommend recipes that are more in line with the user's own health based on the health preference information that the user pays attention to and selects. For example, if the user expects the recommended recipe to be low in oil and salt, then the client can select recipes with higher levels in the health tags corresponding to low in oil and salt and recommend them to the user.
[0157] Furthermore, because the evaluation criteria for recipes corresponding to each category may be inconsistent, in order to make the recommended recipes more accurate, users can also select a recipe category. Under the recipes corresponding to the recipe category selected by the user, all recipes corresponding to the recipe category will be reprocessed (sorted, labeled, etc.) to obtain more accurate health labels and recommend recipes to users based on the health labels.
[0158] The health parameter information in the present application may be composed of information on a variety of health attributes. Therefore, when recommending recipes, the client may filter the recipes based on a variety of health attributes for evaluating whether the recipes are healthy or not, so as to recommend more reasonable recipes to users.
[0159] Moreover, in this application, since the number of people consuming different recipes is different, in order to unify the standards for sorting, this application calculates the total health parameter information to obtain per capita health parameter information (that is, the health parameter information when the number of people consuming the recipe is one person).
[0160] The above are one or more recipe recommendation methods implemented in this application. Based on the same idea, this application also provides a corresponding recipe recommendation device, such as Figure 3 shown.
[0161] Figure 3 A schematic diagram of a recipe recommendation device provided for this application includes:
[0162] An acquisition module 301 is used to acquire recipe information of each recipe;
[0163] A determination module 302 is used to determine health parameter information of each recipe according to the recipe information of each recipe, wherein the health parameter information is information used to characterize each health attribute, and the information of each health attribute includes at least one of the content of condiments in each recipe and the energy supply ratio of nutrients in each recipe;
[0164] A sorting module 303 is used to sort the recipes according to the health parameter information of the recipes to obtain a sorting result;
[0165] A marking module 304 is used to determine the health level of each recipe according to the sorting result, and mark each recipe according to the health level to obtain a health label corresponding to each recipe;
[0166] The recommendation module 305 is used to recommend recipes to the user based on the health label.
[0167] The present application also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A recipe recommendation method provided.
[0168] This application also provides Figure 4 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 4 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, this application does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0169] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.
[0170] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.
[0171] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0172] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0173] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0174] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present 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 1 A device that provides the functions specified in a block or multiple blocks.
[0175] 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.
[0176] 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.
[0177] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0178] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0179] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0180] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0181] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may 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.
[0182] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0183] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0184] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A recipe recommendation method, characterized in that: include: Get recipe information for each recipe; Determining health parameter information of each recipe according to the recipe information of each recipe, wherein the health parameter information is information used to characterize each health attribute, and the information of each health attribute includes at least one of the content of condiments in each recipe and the energy supply ratio of nutrients in each recipe; Sorting the recipes according to the health parameter information of the recipes to obtain a sorting result; Determine the health level of each recipe according to the ranking result, and mark each recipe according to the health level to obtain a health label corresponding to each recipe; According to the health label, recipes are recommended to the user.
2. The method according to claim 1, characterized in that According to the health parameter information of each recipe, the recipes are sorted to obtain a sorting result, including: Classifying the recipes according to preset recipe categories to obtain recipes under each recipe category; For each recipe category, the recipes under the recipe category are sorted according to the health parameter information of each recipe under the recipe category to obtain the sorting result of each recipe under each recipe category.
3. The method according to claim 2, characterized in that Determining the health level of each recipe according to the ranking result, and marking each recipe according to the health level to obtain a health label corresponding to each recipe, including: According to the ranking results of each recipe under each recipe category, the health level of each recipe under each recipe category is determined respectively, and according to the health level of each recipe under each recipe category, each recipe under each recipe category is marked respectively to obtain the health label corresponding to each recipe under each recipe category.
4. The method according to claim 3, characterized in that According to the health parameter information of each recipe under the recipe category, the recipes under the recipe category are sorted, including: For each health attribute in the health parameter information, the recipes under the recipe category are sorted according to the information of each recipe under the recipe category for the health attribute, so as to obtain the sorting result of each recipe under the recipe category for each health attribute.
5. The method according to claim 4, characterized in that The ranking results of the recipes under each recipe category include ranking results of the recipes under each recipe category for each health attribute; According to the ranking results of each recipe under each recipe category, the health level of each recipe under each recipe category is determined respectively, and according to the health level of each recipe under each recipe category, each recipe under each recipe category is marked respectively to obtain the health label corresponding to each recipe under each recipe category, including: For each health attribute in the health parameter information, according to the ranking results of each recipe under each recipe category for the health attribute, determine the health level of each recipe under each recipe category for the health attribute, and mark each recipe under each recipe category according to the health level of each recipe under each recipe category for the health attribute to obtain a health label for each recipe under each recipe category for the health attribute; According to the health labels of each recipe under each recipe category for each health attribute, the health labels corresponding to each recipe under each recipe category are obtained.
6. The method according to claim 1, characterized in that According to the health parameter information of each recipe, the recipes are sorted to obtain a sorting result, including: For each health attribute in the health parameter information, the recipes are sorted according to the information of the recipes for the health attribute to obtain a sorting result of the recipes for each health attribute.
7. The method according to claim 6, characterized in that Determining the health level of each recipe according to the ranking result, and marking each recipe according to the health level to obtain a health label corresponding to each recipe, including: For each health attribute in the health parameter information, according to the ranking result of each recipe for the health attribute, determine the health level of each recipe for the health attribute, and mark each recipe according to the health level of each recipe for the health attribute to obtain a health label of each recipe for the health attribute; According to the health labels of the recipes for the health attributes, the health labels corresponding to the recipes are obtained.
8. The method according to any one of claims 1 to 7, characterized in that: The recipe information of each recipe includes the number of people eating and total health parameter information; Determining health parameter information of each recipe according to the recipe information of each recipe includes: The per capita health parameter information of each recipe is determined according to the number of consumers and the total health parameter information in the recipe information of each recipe, as the health parameter information of each recipe.
9. The method according to any one of claims 1 to 7, characterized in that: According to the health label, recipes are recommended to the user, including: Acquire the health preference information that the user is concerned about; Recommending recipes to the user based on the health label and the health preference information.
10. The method according to any one of claims 1 to 7, characterized in that: According to the health label, recipes are recommended to the user, including: Obtaining the recipe category selected by the user and determining it as the target recipe category; According to the target recipe category, determine each recipe under the target recipe category; Recipes are recommended to the user based on the health labels corresponding to the recipes under the target recipe category.
11. The method according to any one of claims 1 to 7, characterized in that: According to the health label, recipes are recommended to the user, including: Acquire the health preference information of the user and the recipe category selected by the user; Determining the recipe category selected by the user as a target recipe category; According to the target recipe category, determine each recipe under the target recipe category; According to the health labels of the recipes under the target recipe category and the health preference information, the recipes under the target recipe category are recommended to the user.
12. The method according to any one of claims 1 to 7, characterized in that: According to the health label, recipes are recommended to the user, including: According to the health labels, recipes are recommended to the user in descending order of the health levels of the recipes.
13. A recipe recommendation device, characterized in that: include: The acquisition module is used to obtain the recipe information of each recipe; a determination module, configured to determine health parameter information of each recipe according to recipe information of each recipe, wherein the health parameter information is information used to characterize each health attribute, and the information of each health attribute includes at least one of the content of condiments in each recipe and the energy supply ratio of nutrients in each recipe; A sorting module, used for sorting the recipes according to the health parameter information of the recipes to obtain a sorting result; a marking module, used to determine the health level of each recipe according to the sorting result, and mark each recipe according to the health level to obtain a health label corresponding to each recipe; The recommendation module is used to recommend recipes to users based on the health tags.
14. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.
15. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 12 is implemented.
Citation Information
Patent Citations
Electronic device and method for carrying out individual catering recommendation by means of electronic device
CN102054117A
Recipe recommendation method for patients with chronic diseases
CN111081347A
Recipe recommendation method and device, electronic equipment and storage medium
CN112786154A
Purification Apparatusfor 3D Printer
KR1020240162728A
