WO2021120891A1 - Diet data generation method and device, and storage medium and electronic device - Google Patents

Abstract

A diet data generation method and device, and a storage medium and an electronic device. The method comprises: obtaining first label information and second label information corresponding to a target user, wherein the first label information refers to basic information related to the target user, and the second label information refers to information of the target user for a diet demand (S202); and determining target diet data from a nutrition database according to the first label information and the second label information, wherein the nutrition database comprises a nutrition ontology structure constructed on the basis of a knowledge graph, the nutrition ontology structure comprises an entity attribute and a relationship between entities, and the target diet data comprises at least one of the followings: data related to a target recipe and data related to a target food material (S204). The method solves the problem in the related art that a nutrition recommendation system is only oriented to special crowds or pushed nutrition data is not perfect.

Description

Method and device for generating diet data, storage medium and electronic device Technical field

This application relates to the field of pushing diet data, and specifically to a method and device for generating diet data, a storage medium, and an electronic device.

Background technique

The existing nutrition recommendation systems mainly include:

1. Food recommendation system for medical institutions: This system has certain advantages in practicability. Medical institutions combine the knowledge and experience of experts, according to the patient's physical condition, combined with the treatment characteristics of traditional Chinese medicine or Western medicine, to formulate nutritional rations for the patient in line with the condition. The foods issued by this type of system are generally more specific, and the recipes issued for most illnesses are the same.

2. Dietary nutrition catering system: This type of system customizes a diet plan for the user according to the relevant nutritional model by obtaining the user's personal information. The system generally regards nutrient intake balance as the basic requirement, and on this basis, recommends foods that meet the requirements as much as possible through linear programming or Gaussian principal element reduction method.

3. Public comment system: According to the different scores of different customers on the same food, the overall score of the food is calculated, so as to recommend the food with the highest score.

4. Personal dietary nutrition evaluation: This type of system uses different nutritional standard models (BFF method, DDP method, INQ method, etc.) to calculate and analyze the dietary structure by recording the dietary structure submitted by the user for a day or a period of time. And then its dietary nutrition score or propose further improvements.

However, the nutrition recommendation system of the existing scheme has the problem that it is only for special populations or the nutrition data that is pushed is not perfect, and it cannot realize the comprehensiveness and automation of generating or pushing diet data.

Summary of the invention

The embodiments of the present application provide a method and device for generating diet data, a storage medium, and an electronic device to at least solve the problem that the nutrition recommendation system in the related art is only for special populations or the nutrition data generated is not complete.

According to an embodiment of the present application, there is provided a method for generating diet data, including: acquiring first tag information and second tag information corresponding to a target user, wherein the first tag information refers to Basic information related to the user; the second label information refers to the information of the target user's dietary needs; the target diet data is determined from the nutrition database according to the first label information and the second label information; wherein , The nutrition database includes a nutrition ontology structure constructed based on a knowledge graph; the nutrition ontology structure includes: entity attributes, and relationships between entities and entities; and the target diet data includes at least one of the following: data related to the target recipe , Data related to the target ingredient.

According to another embodiment of the present application, there is provided a device for generating diet data, including: an acquisition module configured to acquire first tag information and second tag information corresponding to a target user, wherein the first tag information Refers to the basic information related to the target user; the second label information refers to the information of the target user’s dietary needs; the determining module is set to be based on the first label information and the second label information The target diet data is determined from the nutrition database; wherein, the nutrition database includes a nutrition ontology structure constructed based on a knowledge graph; the nutrition ontology structure includes entity attributes and the relationship between entities and entities; and the target diet data includes At least one of the following: data related to the target recipe, data related to the target ingredient.

According to another embodiment of the present application, there is also provided a storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps in any one of the foregoing method embodiments when running.

According to another embodiment of the present application, there is also provided an electronic device, including a memory and a processor, the memory is stored with a computer program, and the processor is configured to run the computer program to execute any of the above Steps in the method embodiment.

Through this application, the target diet data is determined from the nutrition database according to the first label information and the second label information of the target user. Since the target diet data is based on the nutrition database obtained by including the nutrition ontology structure constructed based on the knowledge graph, the nutrition The nutritional data in the database is more comprehensive and rich, and does not limit the target user group. Only the first label information and the second label information of the target user can generate the target diet data, which solves the problem that the nutrition recommendation system in the related technology is only oriented to The problem of insufficient nutrition data for special populations or pushes has achieved the comprehensiveness and automation of push diet data.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application, and do not constitute an improper limitation of the application. In the attached picture:

FIG. 1 is a block diagram of the hardware structure of a terminal of a method for generating diet data according to an embodiment of the present application;

Fig. 2 is a flowchart of a method for generating diet data according to an embodiment of the present application;

Fig. 3 is a structural block diagram of a device for generating diet data according to an embodiment of the present application;

Fig. 4 is an optional structural block diagram of a device for generating diet data according to an embodiment of the present application.

Detailed ways

Hereinafter, the application will be described in detail with reference to the drawings and in conjunction with the embodiments. It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other if there is no conflict.

First, the terms in this embodiment are explained accordingly;

Diet pattern: The so-called diet pattern refers to the dietary structure. In short, it refers to our long-term stable eating habits, such as the Deshu diet (DASH), basic diet, Mediterranean diet, and ketogenic diet, which include the supply of ingredients. Energy percentage information, as well as the relationship between the number of meals and the energy supply of the ingredients.

Diet model: The diet model is based on the diet model, plus a series of restrictions, such as the number of meals and meal function ratio, diet preference, dietary contraindications, the function ratio of the three major nutrients, and the upper and lower limits of the intake of related nutrients ( Such as: sodium, dietary fiber, protein, fat and carbohydrates, etc.).

Semantic network: is a data structure used to store knowledge, that is, a graph-based data structure. The graph here can be a directed graph or an undirected graph.

Semantic Web: A network that describes things in a way that can be understood by computers.

Ontology: The concept of Ontology originates from the field of philosophy. It is defined in philosophy as "the systematic description of objective things in the world, that is, ontology". The ontology in philosophy is concerned with the abstract nature of objective reality. In the computer field, ontology can describe knowledge at the semantic level, and can be seen as a general conceptual model describing knowledge in a certain subject domain.

Entities: Entities are matters related to human health, including but not limited to food ingredients, recipes, nutrients, eating patterns, and diseases. In a preferred embodiment of the present application, the entities are food materials, recipes, nutrients, diet patterns, and diseases. Entities are the most basic elements in the knowledge graph, and different entities have different relationships.

It should be noted that the terms "first" and "second" in the specification and claims of the application and the above-mentioned drawings are used to distinguish similar objects, and not necessarily used to describe a specific sequence or sequence.

Example 1

The method embodiment provided in Embodiment 1 of the present application may be executed in a terminal, a computer terminal, or a similar computing device. Taking running on a terminal as an example, FIG. 1 is a hardware structure block diagram of a terminal in a method for generating diet data according to an embodiment of the present application. As shown in FIG. 1, the terminal 10 may include one or more (only one is shown in FIG. 1) processor 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) And the memory 104 for storing data. Optionally, the aforementioned terminal may also include a transmission device 106 and an input/output device 108 for communication functions. Those of ordinary skill in the art can understand that the structure shown in FIG. 1 is only for illustration, and does not limit the structure of the foregoing terminal. For example, the terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration from that shown in FIG.

The memory 104 may be used to store computer programs, for example, software programs and modules of application software, such as the computer programs corresponding to the method for generating diet data in the embodiments of the present application. The processor 102 runs the computer programs stored in the memory 104 to thereby Execute various functional applications and data processing, that is, realize the above-mentioned methods. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely provided with respect to the processor 102, and these remote memories may be connected to the terminal 10 via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by the communication provider of the terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC for short), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet in a wireless manner.

In this embodiment, a method for generating diet data running on the aforementioned terminal is provided. FIG. 2 is a flowchart of a method for generating diet data according to an embodiment of the present application. As shown in FIG. 2, the process includes the following steps:

Step S202: Acquire first tag information and second tag information corresponding to the target user, where the first tag information refers to basic information related to the target user itself; the second tag information refers to information about the target user's dietary needs;

Step S204: Determine the target diet data from the nutrition database according to the first label information and the second label information; wherein the nutrition database includes a nutrition ontology structure constructed based on the knowledge graph; the target diet data includes at least one of the following: related to the target recipe Data, data related to the target food;

It should be noted that the entity in this embodiment includes at least one of the following: ingredients, recipes, nutrients, diet patterns, and diseases; and the relationship between the entity and the entity includes at least one of the following: the relationship between the food and the recipe, The relationship between ingredients and nutrients, the relationship between diseases and ingredients, the relationship between diseases and recipes, the relationship between diseases and nutrients, the relationship between eating patterns and recipes.

Through the above steps S202 to S204, the target diet data is determined from the nutrition database according to the first label information and the second label information of the target user, because the target diet data is a nutrition database obtained from a nutrition ontology structure constructed based on a knowledge graph. , So that the nutrition data in the nutrition database is more comprehensive and rich, and does not limit the target user group, only the first label information and the second label information of the target user are needed to generate the corresponding target diet data, thereby solving the related technology The Chinese Nutrition Recommendation System is only oriented to special populations or the problem of insufficient nutrition data pushed, achieving the comprehensiveness and automation of pushing diet data.

Optionally, the method steps in this embodiment may further include: step S206, pushing the target diet data to the target user. That is to say, the target diet data can be pushed to the target user when the target diet data is generated, and the push method may be in the form of a message, or an email, or other methods.

In addition, it should be noted that the nutrition database in this embodiment is used to define the attributes of entities in the nutrition ontology structure and the relationships between entities and entities. Specifically, in an optional implementation of this embodiment, nutrition data is obtained through the following method steps:

Step S102, constructing the nutrition ontology structure based on the knowledge graph, wherein the nutrition ontology structure includes: entity attributes and the relationship between the entities and the entities;

For this step S102, it should be noted that, in this embodiment, it is a dietary nutrition database established based on the knowledge graph technology, wherein, based on the knowledge graph ontology construction technology, a bottom-up and top-down hybrid method is used to construct the nutrition database. The ontology structure of the domain;

Among them, the ontology structure includes five types of entities, namely: food, recipes, nutrients, diet patterns, and diseases) and six types of relationships, namely: the relationship between food and recipe, the relationship between food and nutrients, the relationship between disease and food The relationship between the disease, the relationship between the disease and the recipe, the relationship between the disease and the nutrient, the relationship between the diet pattern and the recipe, and the attributes related to the entity (such as definition, Chinese and English name, characteristics, source, etc.) and The relationship between entities has been fully defined to facilitate the continuous update of the subsequent database.

Among them, the structured definition of entities can comprehensively define these five categories of entities and the relationship between entities and entities by integrating resources such as nutrition experts, books, and the Web. In addition, the entity definition is similar to the upper-level architecture. In this example, the entity definition is carried out in accordance with the principle of defining the entity as complete as possible, so that subsequent database updates only need to be filled with data and do not need to move the basic part. The nutrition database in the prior art does not fully cover these 5 categories of entities and 6 categories of relationships. Most of them are ingredients, recipes, and nutrients. A few include ingredients, recipes, nutrients, and diseases, which are not complete enough. .

Step S104, obtaining corresponding nutritional data according to the entity attributes in the nutritional ontology structure and the relationship between the entities and the entities, and uniformly naming the obtained nutritional data to obtain standard structured nutritional data;

For this step S104, it should be noted that related information such as food materials, recipes, nutrients, and diseases can be obtained based on the web crawler, and the obtained original data can be defined according to entities, relationships between entities and their attributes. In a preferred embodiment, in order to better obtain the corresponding nutrition data according to the entity attribute in the nutrition ontology structure and the relationship between the entity and the entity, under the guidance of the principle of cleaning loyal to the source data, the data of each source Knowledge is structured and reorganized, and finally a consistent structure is obtained, so as to solve the problems of entity attributes and confusion of entity and entity relationship due to the different emphasis, form or expression of the content of different sources, because the content of different sources is not focused. The same, for example, for a certain food material, Mint.net has aliases, nutrient content, etc.; Nutritional Foods website has characteristics, English name, nutrient content, etc., and even if there are nutrient content in the two sources, there are differences, such as Mint. There is iron content and no zinc content, while the Nutrition Food Network has zinc content. That is, it is necessary to consider the similarities and differences of different sources, and integrate different sources to make them consistent.

In a preferred embodiment, after routine data cleaning and structuring, in order to meet the storage requirements, the data needs to be further standardized, because each food website has its own set of naming rules, plus the difference in food materials It is called, food ingredients have their real names and aliases, and there is a large amount of data obtained from the heterogeneous information of food ingredients. Based on this, the entity alignment technology is used to normalize the heterogeneous information of food ingredients, and the process is as follows:

Step S11, for the normalization process between the long-name food entities, tf-idf (term frequency-inverse document frequency) is used to calculate the cos similarity (cosine similarity) of the pair of two entities;

Step S12, for the normalization processing between the food entities of the long name and the short name, preferably, word2vec and char2vec are trained using wiki, Baidu Encyclopedia data set, etc., to calculate the cos similarity of the two entity pairs, more preferably Yes, in order to obtain more comprehensive and accurate data, use the wiki data set;

Step S13, for the normalization process between the food entities of the short name, the character (char) and the word (word) are respectively the basic features, and the jaccard similarity and dice similarity of the pair of entities are calculated;

Step S14, using the method of constructing an index, perform preliminary clustering of the entity pairs with similarity score>0.5; in a specific embodiment, any one of the jaccard similarity and dice similarity of the two entity pairs calculated in step S13 If the similarity is greater than 0.5, preliminary clustering is performed.

Step S15, in order to enhance the granularity of the clustering, a gradient threshold clustering method is used

Among them, the method of gradient threshold clustering is that the cos similarity, the jaccard similarity and the dice similarity will be within the range of 0.5-1 respectively, and the similarity interval of 0.01-0.2 will be continuously increased recursively within the range of 0.5-1. Automatic classification is completed. The classification is completed. Entity alignment, fusion of the results of cos similarity, jaccard similarity and dice similarity, the entity groups of the preliminary clustering are grouped in detail, so as to realize the alignment of the entities and obtain the final result. Preferably, the similarity interval of 0.05 is continuously increased and recursively.

Through the above steps S11 to S15, the food corresponding to each ingredient ID is unique, and there will be no different foods whose IDs are the same, which may cause confusion in subsequent recommendations. In this embodiment, those with more than 10 characters are regarded as long-name food entities, and those with less than or equal to 10 characters are regarded as short-name food entities. Of course, different numbers of characters can be used to define long or short name entities according to actual needs. For example, 8 characters, 12 characters, etc.

It should be noted that, in order to facilitate the continuous update of the subsequent database, the structure of the data before storage can be: for entities, such as food, ensure that each record of the source file before storage corresponds to an ID; for the import of relational data The library ensures that each record corresponds to a specific relationship between two entities (such as the content relationship between spinach and cellulose). Under the premise of ensuring that a record has an entity ID, if the defined field is in an array format, another file is used to save the related data of the field, and a new ID is created for the field at the same time. Each line of the file is recorded as the new ID Corresponding to the subject ID. If the array is nested in the array, another file is used to save the data, and a new ID is created for the nested field. Each line of the file is recorded as the nested field ID and the nested field ID Correspondingly, and so on, the same is true for relational data processing.

In a preferred embodiment, in a relational database, a record is equivalent to a row in an Excel table. For an entity, a specific food has a specific ID. For a relationship between two entities, one record corresponds to a certain relationship. For example, the content relationship between spinach and cellulose is one record, and the content relationship between spinach and vitamin A is another record. This way, on the one hand, it facilitates the writing of warehousing programs, and on the other hand, it facilitates subsequent database updates, that is, only the parts that need to be updated are updated without affecting the whole, which can reduce the inherent drawbacks of relational database updates to a certain extent.

In a specific application scenario, the data format of the standard structured nutrition data is JSON (JavaScript Object Notation) format. In order to facilitate the subsequent development of the library program, internally developed scripts are used to convert the ontology JSON format into Python objects in batches. Conducive to processing in Python language. For fields with nested arrays, the dictionary key-value pair method is adopted, and the layered links are finally associated with the subject ID. Finally, the structured data is imported into MongoDB, MySQL and other databases in batches according to the designed ontology structure. The MongoDB database is preferred, and the final entry is There are 8835 food material records, 56 nutrient records and 10416 recipe records behind the library. The relevant data can also be continuously updated and accumulated.

Step S106: Import the standard structured nutrition data into the nutrition database according to the nutrition ontology structure.

That is to say, in this embodiment, a general import format is defined for the ontology and relational entity structure. Knowledge information within the scope of any source can be converted into this format and then stored in a unified database, thus laying a foundation for importing more third-party similar libraries.

In an optional implementation of this embodiment, the method of determining the target diet data from the nutrition database based on the first label information and the second label information involved in step S202 may further be:

Step S202-11: Select a target diet pattern from a plurality of diet patterns in the nutrition database, where the target diet pattern includes: information on the energy supply ratio of ingredients, the relationship between the number of meals and the energy supply of the ingredients

Step S202-12: Determine the nutrient requirement per unit time required by the target user according to the first label information and the second label information;

Step S202-13: Determine the target diet data from the nutrition database according to the nutrient requirements.

In addition, before the target diet data is determined from the nutrition database according to the nutrient requirements, the target diet pattern can be selected from a plurality of diet patterns in the nutrition database, where the target diet pattern includes: the energy supply ratio of the ingredients Information, as well as the relationship between the number of meals and the energy provided by the ingredients; after selecting the diet mode, the relevant parameters of the diet model can be set, such as the number of meals and the ratio of meals, diet preferences, dietary taboos, and three major nutrient functions Setting the upper and lower limits of the ratio and related nutrient intake (such as sodium, dietary fiber, protein, fat and carbohydrates, etc.). The setting of diet model parameters makes the final recipes and ingredients more suitable for the user’s personalization. demand.

It should be noted that the diet model involved in this embodiment may be a basic diet model, a DASH diet model, a Mediterranean diet model, a Vegan diet model, a ketogenic diet model and other diet modules. The following will illustrate this application with a basic diet model;

The structuring of the diet pattern is mainly based on the basic nutrition (the ratio of the three major nutrients) as the starting point for the dietitian. According to the recommended foods and servings of different diet patterns, firstly, determine the weight and calories of each type of ingredient; secondly, calculate the difference The number and weight of each type of food required by people with energy requirements; finally, the basic diet is structured.

Calculate the proportion and number of servings of each type of ingredient under different energy levels to obtain the ratio of the energy supply of the ingredients as shown in Table 1, and the proportion of each ingredient in different meals to obtain the number of meals and the ratio of energy supply. 2 shown. Different diet patterns have their own unique diet structure. According to the dietary structure of the basic diet pattern and the DASH diet pattern, the energy supply ratio and the number of meals and the energy supply ratio of the two diet patterns can be finally calculated.

Table 1: The proportion of energy supplied by food ingredients (basic diet model)

It should be noted that the numbers in the second column Num indicate the number of servings of the ingredients of each category, and the following columns in the second column indicate the ingredients of each category under different energy levels (1400KJ, 1800KJ...) The proportion of each column is approximately equal to 1.

group	breakfast	lunch	dinner
Cereals and Potatoes | Refined Grains	0	0.52	0.48
Cereals and potatoes|whole grains and mixed beans	0.46	0.54	0
Cereals and Tubers| Tubers	1	0	0
Vegetables|Other Vegetables	0	0	1
Vegetables | Dark Vegetables	0	1	0
fruit	1	0	0
Livestock and poultry meat and eggs	0	1	0
Aquatic products	0	0	1
Milk and its products	1	0	0
Soybean and its products	0	0.8	0.2
Nuts, seeds	1	0	0
Cooking oil	0	0.5	0.5

Table 2: Meal number and energy supply ratio table (basic diet model)

It should be noted that the numbers in Table 2 represent the proportions of different types of ingredients in different meals.

Further, in an optional implementation manner of this embodiment, the method of determining the target diet data from the nutrition database according to the nutrient demand involved in the above step S202-13 may further include:

Steps S202-131, allocating the required amount of nutrients to different meals in a unit time according to a preset ratio;

Steps S202-132, according to the nutrient requirements for different meals, determine the recipes corresponding to different meals per unit time from the candidate recipes.

For the method involved in the above step S202-13, in specific application scenarios, it can be: First, calculate the daily energy required and the conversion ratio between energy and the three major energy supply nutrients (carbohydrate, protein, fat) , And then calculate the daily demand of the three major energy supply nutrients of the target user. The calculation process is as follows:

First, calculate the Active Metabolic Rate (Active Metabolic Rate, referred to as AMR). Table 3 shows the corresponding relationship between the amount of exercise and the estimated value of the Active Metabolic Rate, as shown in Table 3.

table 3

In addition, the corresponding relationship between the estimated value of active metabolic rate (MET) and AMR is as follows: (1) In the case of MET<=1.4, AMR=0; (2) In the case of 1.4<MET<=1.69, AMR=1 ; (2) In the case of 1.69<MET<=2.59, AMR=2; (3) in the case of MET>2.59, AMR=3.

Second, calculate the basal metabolic rate (Basal Metabolic Rate, referred to as BMR), and calculate the corresponding BMR based on gender (weight, height, and age correspond to weight (kg), height (cm), and age (years)):

Male BMR=13.397*weight+4.799*height-5.677*age+88.362

Female BMR=9.247*weight+3.098*height-4.33*age+447.593

Then, calculate the daily required energy (kCal), where the daily required energy value (Energy)=BMR*(1.2+AMR*0.175); according to the preset energy supply ratio of the three major nutrients, such as carbon water: protein: Fat=5.5:2:2.5 to obtain the corresponding nutrient energy; then through the conversion ratio between energy and the three major energy supply nutrients, their respective quality requirements are obtained. The energy conversion ratio (Energy to gram) of carbohydrates, protein and fat is 4:4:9. That is, each gram of carbohydrates and protein produce heat 4kCal, and each gram of fat produces 9kCal.

Finally, according to the preset energy supply ratio of each meal, the user's daily energy and the three major energy supply nutrient requirements are allocated to different meals in proportion. Filter specific candidate recipes in the recipe library according to the tag information of the target user (eliminate allergens; select a custom diet mode, such as DASH diet mode or basic diet mode; select specific meal recipes, such as breakfast recipes, etc.), and randomly select candidate recipes to fill in For different meals, according to the daily energy required by the user and the requirements of the three major energy-supplying nutrients, combined with the dietary energy and the content of the three major energy-supplying nutrients (in units of 100 grams), the over-determined linear equations are solved to obtain the Choose the recipe size, and finally get the daily recipe list.

The recipe portion calculation process is:

A_1*x+B_1*y+C_1*z=total_energy (total energy)

A_2*x+B_2*y+C_2*z=total_carbohydrates (total carbohydrates)

A_3*x+B_3*y+C_3*z=total_protein

A_4*x+B_4*y+C_4*z=total_fat (total fat)

Among them, A, B, C: respectively refer to: carbohydrate, protein, vitamin/mineral; "1" refers to energy (kCal); "2" refers to carbohydrate content (g); "3" refers to protein Content (g); "4" refers to fat content (g). It should be noted that the content is the content per hundred grams of the recipe (kCal; g).

In addition, x, y, and z are the respective portions of the three recipes obtained by solving the overdetermined linear equations, where x is the portion of A (carbohydrate-based recipe) obtained by solving the equation; y is the portion obtained by solving the equation The amount of B (protein-based recipe); z is the amount of C (vitamin/mineral-based recipe) obtained by solving the equation.

In addition, if any of the following conditions are not met, the random selection process is repeated until the set number of iterations ends: a. The amount of the recipe exceeds the generally defined amount (can be preset, such as 0.5 to 1.5); b. The recipe is not "dry" ", "dilute" collocation; c. The content of other nutrients in the daily diet does not meet the requirements (can be preset, such as the cellulose content is greater than 25g).

In yet another optional implementation manner of this embodiment, the method of determining target diet data from the nutrition database according to the nutrient requirements involved in step S203-13 may further include:

Steps S202-133, determining the required amount of food by using the nutrient demand and the functional proportion information of the food;

Steps S202-134, according to the relationship between the number of meals and the energy supply of the ingredients, the required amount of ingredients is allocated to different meals per unit time, and the ingredients corresponding to the different meals are obtained.

Regarding the methods involved in the above step S202-13, in a specific application scenario, it may also be: First, according to the daily energy required and the proportion of the energy supplied by the ingredients, the energy supplied by each ingredient group is calculated. Secondly, select specific candidate ingredients in the food library based on the label information of the target user (for example, eliminate allergens, etc.), randomly select the ingredients, and calculate the required amount of ingredients based on the energy of the ingredients and the content of the three major energy-supplying nutrients (in units of 100 grams) .

The process of calculating the amount of ingredients is:

Food_amount=total_energy*Food_ratio/Num/Food_energy

Among them, Food_ratio refers to the energy ratio of food ingredients (for example, 0.23, available in Table 1). The table look-up method is to lock the food group according to the category of the food, that is, the Group in Table 1; lock the nearest energy level (such as 2000kCal) according to total_energy; the corresponding energy ratio under the two conditions is the Food_ratio used in the formula. total_energy*Food_ratio is the energy supply of each food ingredient group; Num refers to the number of portions corresponding to the food ingredient group, corresponding to NUM in the energy supply ratio of the food ingredient in Table 1; Food_energy refers to the content per hundred grams of the food (kCal); amount refers to the formula Solve for the amount of the ingredient.

Finally, according to the number of meals and the energy supply ratio in Table 1 and Table 2, randomly selected ingredients are allocated to different meals, and finally a list of daily ingredients is obtained.

In addition, it should be noted that the presentation of the diet data generation method in this embodiment on the client side may be: the target user uploads his own first tag information and second tag information, and then selects the existing diet pattern structure according to his own Actually need to customize the diet model, and then set a series of related parameters related to the diet model (such as the number of meals and the energy ratio of meals, diet preference, dietary contraindications, the energy supply ratio of the three major nutrients, and related nutrients such as sodium and dietary fiber , Protein, fat, or carbon water intake upper and lower limits, etc.), upload it to the back-end, interact with the front-end and back-end through API (Application Programming Interface), and finally return to the user a complete diet plan, including ingredients and recipe. The target user can also click to view the specific nutrient information of a certain ingredient. If the information is biased or some nutrient information is blank, the user can correct, edit and supplement it online. The revised information will be stored in the nutrition knowledge base next time. Can be called.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is Better implementation. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to enable a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the method described in each embodiment of the present application.

Example 2

In this embodiment, a device for generating diet data is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementations, and those that have been described will not be repeated. As used below, the term "module" can implement a combination of software and/or hardware with predetermined functions. Although the devices described in the following embodiments are preferably implemented by software, implementation by hardware or a combination of software and hardware is also possible and conceived.

Fig. 3 is a structural block diagram of a device for generating diet data according to an embodiment of the present application. As shown in Fig. 3, the device includes: an acquisition module 32 configured to acquire first tag information and second tag information corresponding to a target user, Among them, the first label information refers to the basic information related to the target user; the second label information refers to the information of the target user’s dietary needs; the determining module 34 is configured to obtain information from the nutrition database according to the first label information and the second label information. The target diet data is determined in the database; wherein the nutrition database includes a nutrition ontology structure constructed based on the knowledge graph; the nutrition ontology structure includes: entity attributes and the relationship between entities and entities; the target diet data includes at least one of the following: related to the target recipe Data, data related to the target ingredient.

In an alternative implementation of this embodiment, the nutrition database may be obtained in the following manner: before obtaining the first label information and the second label information corresponding to the target user, the nutrition ontology structure is constructed based on the knowledge graph; according to the nutrition ontology The entity attributes in the structure and the relationship between the entity and the entity obtain the corresponding nutrition data, and the obtained nutrition data is named uniformly to obtain the standard structured nutrition data; the standard structured nutrition data is imported and obtained according to the nutrition ontology structure Nutritional data.

It should be noted that the entity in this embodiment includes at least one of the following: ingredients, recipes, nutrients, eating patterns, and diseases. The relationship between the entity and the entity includes at least one of the following: the relationship between the food and the recipe, the relationship between the food and the nutrient, the relationship between the disease and the food, the relationship between the disease and the recipe, the relationship between the disease and the nutrient The relationship between dietary patterns and recipes.

Optionally, the determining module 34 in this embodiment may further include: a selection unit configured to select a target diet pattern from a plurality of diet patterns in the nutrition database, wherein the nutritional information in the target diet pattern includes: The relationship between the energy supply ratio information of the ingredients, the number of meals and the energy supply of the ingredients; the first determining unit is set to determine the nutrient needs of the target user per unit time according to the first label information and the second label information The second determination unit is configured to determine the target diet data from the nutrition database according to the nutrient requirements.

In addition, the determination module further includes: a second selection unit configured to select the target diet model from a plurality of diet models in the nutrition database before determining the target diet data from the nutrition database according to the nutrient requirements, wherein the diet The information of the model includes: the number of meals and the proportion of energy provided by meals, eating habits, the energy supply ratio of nutrients, or the upper and lower limits of nutrient intake.

Wherein, the second determining unit may further include: a first distribution subunit, configured to distribute nutrient requirements to different meals within a unit time according to a preset ratio; and the first determining subunit is configured to distribute according to different meals The required nutrient requirements determine the recipes corresponding to different meals per unit time from the candidate recipes.

In addition, the second determining unit may further include: a second determining subunit, configured to determine the required amount of ingredients based on the nutrient demand and the functional proportion information of the ingredients; the second allocating subunit, set to dine according to the food The relationship between the number and the energy supply of the ingredients allocates the required amount of ingredients to different meals per unit time, and obtains the ingredients corresponding to the different meals.

Fig. 4 is an optional structural block diagram of a device for generating diet data according to an embodiment of the present application. As shown in Fig. 4, the device includes a pushing device 42 configured to push target nutritional data to a user.

It should be noted that each of the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following manner, but not limited to this: the above modules are all located in the same processor; or, the above modules can be combined in any combination. The forms are located in different processors.

Example 3

The embodiment of the present application also provides a storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps in any one of the foregoing method embodiments when running.

Optionally, in this embodiment, the aforementioned storage medium may be configured to store a computer program for executing the following steps:

S1. Acquire first tag information and second tag information corresponding to the target user, where the first tag information refers to basic information related to the target user itself; the second tag information refers to information about the target user's dietary needs;

S2. Determine the target diet data from the nutrition database according to the first label information and the second label information; wherein the nutrition database includes a nutritional ontology structure constructed based on the knowledge graph; the target diet data includes at least one of the following: Data, data related to the target ingredient.

Optionally, in this embodiment, the foregoing storage medium may include, but is not limited to: U disk, Read-Only Memory (Read-Only Memory, ROM for short), Random Access Memory (Random Access Memory, RAM for short), Various media that can store computer programs, such as mobile hard disks, magnetic disks, or optical disks.

The embodiment of the present application also provides an electronic device, including a memory and a processor, the memory is stored with a computer program, and the processor is configured to run the computer program to execute the steps in any of the foregoing method embodiments.

Optionally, the aforementioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the aforementioned processor, and the input-output device is connected to the aforementioned processor.

Optionally, in this embodiment, the foregoing processor may be configured to execute the following steps through a computer program:

S1. Acquire first tag information and second tag information corresponding to the target user, where the first tag information refers to basic information related to the target user itself; the second tag information refers to information about the target user's dietary needs;

S2. Determine the target diet data from the nutrition database according to the first label information and the second label information; wherein the nutrition database includes a nutritional ontology structure constructed based on the knowledge graph; the target diet data includes at least one of the following: Data, data related to the target ingredient.

Optionally, for specific examples in this embodiment, reference may be made to the examples described in the above-mentioned embodiments and optional implementation manners, and details are not described herein again in this embodiment.

Obviously, those skilled in the art should understand that the above-mentioned modules or steps of this application can be implemented by a general computing device, and they can be concentrated on a single computing device or distributed in a network composed of multiple computing devices. Above, alternatively, they can be implemented with program codes executable by a computing device, so that they can be stored in a storage device for execution by the computing device, and in some cases, they can be executed in a different order than here. Perform the steps shown or described, or fabricate them into individual integrated circuit modules respectively, or fabricate multiple modules or steps of them into a single integrated circuit module for implementation. In this way, this application is not limited to any specific combination of hardware and software.

The above descriptions are only preferred embodiments of the application, and are not intended to limit the application. For those skilled in the art, the application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the principles of this application shall be included in the protection scope of this application.

Industrial applicability

Through this application, the target diet data is determined from the nutrition database according to the first label information and the second label information of the target user. Since the target diet data is based on the nutrition database obtained by including the nutrition ontology structure constructed based on the knowledge graph, the nutrition The nutritional data in the database is more comprehensive and rich, and does not limit the target user group. Only the first label information and the second label information of the target user can generate the target diet data, which solves the problem that the nutrition recommendation system in the related technology is only oriented to The problem of insufficient nutrition data for special populations or pushes has achieved the comprehensiveness and automation of push diet data.

Claims (20)

1. A method for generating diet data includes:

   Acquire first tag information and second tag information corresponding to the target user, where the first tag information refers to basic information related to the target user itself; the second tag information refers to the target user’s Information on dietary requirements;

   The target diet data is determined from the nutrition database according to the first label information and the second label information; wherein the nutrition database includes a nutrition ontology structure constructed based on a knowledge graph; the nutrition ontology structure includes entity attributes, The relationship between the entity and the entity; the target diet data includes at least one of the following: data related to the target recipe and data related to the target food material.
2. The method according to claim 1, wherein the nutrition database is used to define the attributes of entities in the nutrition ontology structure and the relationships between entities and entities.
3. The method according to claim 1, wherein the nutrition database is obtained in the following manner:

   Constructing the nutritional ontology structure based on the knowledge map;

   Obtaining corresponding nutritional data according to the entity attributes in the nutritional ontology structure and the relationship between the entity and the entity, and uniformly naming the obtained nutritional data to obtain standard structured nutritional data;

   Import the standard structured nutritional data according to the nutritional ontology structure to obtain the nutritional database.
4. The method of claim 3, wherein:

   The entity includes at least one of the following: ingredients, recipes, nutrients, diet patterns, and diseases;

   The relationship between the entity and the entity includes at least one of the following: the relationship between the food material and the recipe, the relationship between the food material and the nutrient, the disease and the food material The relationship between the disease, the relationship between the disease and the diet, the relationship between the disease and the nutrient, the relationship between the diet pattern and the diet.
5. The method according to claim 1, wherein determining the target diet data from a nutrition database according to the first label information and the second label information comprises:

   The target eating pattern is selected according to a plurality of eating patterns in the nutrition database, wherein the target eating pattern includes: information on the proportion of energy supplied by the ingredients, the relationship between the number of meals and the energy supplied by the ingredients;

   Determining the required amount of nutrients required by the target user per unit time according to the first label information and the second label information;

   The target diet data is determined from the nutrition database according to the required amount of the nutrient.
6. The method of claim 5, wherein before determining the target diet data from the nutrition database according to the nutrient requirements, further comprising selecting a target diet model from a plurality of diet models in the nutrition database Wherein, the information of the diet model includes: the number of meals and the energy supply ratio information of the meals, eating habits, nutrient energy supply ratio, or upper and lower limits of nutrient intake.
7. The method according to claim 6, wherein determining the target diet data from the nutrition database according to the nutrient requirement comprises:

   Allocating the required amount of nutrients to different meals in a unit time according to a preset ratio;

   According to the nutrient requirements of different meals, the recipes corresponding to different meals per unit time are determined from the candidate recipes.
8. The method according to claim 6, wherein determining the target diet data from the nutrition database according to the nutrient requirement comprises:

   Determining the amount of food required by the information on the required amount of nutrients and the functional proportion of the food;

   According to the relationship between the number of meals and the energy supply of the ingredients, the required amount of ingredients is allocated to different meals per unit time, and the ingredients corresponding to the different meals are obtained.
9. The method according to any one of claims 1 to 8, wherein the method further comprises:

   Push the target diet data to the target user.
10. A device for generating diet data includes:

    The acquiring module is configured to acquire first tag information and second tag information corresponding to the target user, where the first tag information refers to basic information related to the target user itself; the second tag information refers to Information about the dietary needs of the target user;

    The determining module is configured to determine target diet data from a nutrition database according to the first label information and the second label information; wherein the nutrition database includes a nutrition ontology structure constructed based on a knowledge graph; the nutrition ontology structure Including: entity attributes, the relationship between the entity and the entity; the target diet data includes at least one of the following: data related to the target recipe and data related to the target food.
11. The device according to claim 10, wherein the nutrition database is used to define the attributes of entities in the nutrition ontology structure and the relationships between entities and entities.
12. The device according to claim 10, wherein the nutrition database is obtained in the following manner:

    Before acquiring the first label information and the second label information corresponding to the target user, construct the nutrition ontology structure based on the knowledge graph;

    Obtaining corresponding nutritional data according to the entity attributes in the nutritional ontology structure and the relationship between the entity and the entity, and uniformly naming the obtained nutritional data to obtain standard structured nutritional data;

    Import the standard structured nutritional data according to the nutritional ontology structure to obtain the nutritional database.
13. The device according to claim 11, wherein:

    The entity includes at least one of the following: ingredients, recipes, nutrients, diet patterns, and diseases;

    The relationship between the entity and the entity includes at least one of the following: the relationship between the food material and the recipe, the relationship between the food material and the nutrient, the disease and the food material The relationship between the disease, the relationship between the disease and the diet, the relationship between the disease and the nutrient, the relationship between the diet pattern and the diet.
14. The device according to claim 10, wherein the determining module comprises:

    The first selection unit is configured to select a target diet pattern from a plurality of diet patterns in the nutrition database, wherein the nutritional information in the target diet pattern includes: information on the energy supply ratio of ingredients, the number of meals and the amount of ingredients provided Relationship between energy

    The first determining unit is configured to determine the required amount of nutrients required by the target user per unit time according to the first label information and the second label information;

    The second determining unit is configured to determine the target diet data from the nutrition database according to the nutrient demand.
15. The device according to claim 14, wherein the determining module further comprises: a second selection unit configured to determine the target diet data from the nutrition database according to the nutrient requirement, before the nutrition The target diet model is selected from a plurality of diet models in the database, wherein the information of the diet model includes: the number of meals and the energy supply ratio information of meals, eating habits, nutrient energy supply ratio, or upper and lower limits of nutrient intake.
16. The device according to claim 15, wherein the second determining unit comprises:

    The first distribution subunit is configured to distribute the nutrient requirements to different meals in a unit time according to a preset ratio;

    The first determining subunit is configured to determine the recipes corresponding to different meals in a unit time from the candidate recipes according to the nutrient requirements of different meals.
17. The device according to claim 15, wherein the second determining unit comprises:

    The second determining subunit is configured to determine the required amount of food material by determining the required amount of the nutrient and the functional proportion information of the food material;

    The second allocation subunit is configured to allocate the required amount of food material to different meals per unit time according to the relationship between the number of meals and the energy supply of the food materials, so as to obtain the food materials corresponding to the different meals.
18. The device according to any one of claims 10 to 17, wherein the device further comprises:

    The push module is configured to push the target diet data to the target user.
19. A storage medium in which a computer program is stored, wherein the computer program is configured to execute the method described in any one of claims 1 to 9 when running.
20. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of claims 1 to 9.

Images