CN114388102A - Diet recommendation method and device and electronic equipment - Google Patents

Abstract

The embodiment of the specification provides a diet recommendation method and device and electronic equipment. The method comprises the following steps: acquiring diet information uploaded by a user; inputting the diet information into the diet knowledge map, and acquiring diet basic information matched with the diet information in the diet knowledge map and diet basic information corresponding to the diet information under the diet label; inputting the diet basic information and the health information of the user into a prediction model for calculation to obtain a diet analysis result output by the prediction model; recommending a healthy diet plan to the user based on the diet analysis results.

Description

Diet recommendation method and device and electronic device

technical field

The embodiments of this specification relate to the field of computer technology, and in particular, to a method and apparatus for recommending a diet, and an electronic device.

Background technique

With the abundance of material life, people pay more and more attention to their physical health. As the final choice of medical means, more people need to prevent the occurrence of disease or the aggravation of the disease in daily life.

The health of the diet in daily life has a great impact on disease prevention.

However, for most ordinary people, they do not have the relevant professional knowledge to identify their own dietary status, so they cannot obtain a dietary plan that meets their own health needs.

SUMMARY OF THE INVENTION

A diet recommendation method, device, and electronic device provided by the embodiments of this specification are used to solve the problem that users cannot obtain a diet plan that meets their own health needs.

According to a first aspect of the embodiments of the present specification, a method for recommending a diet is provided. The method is applied to a diet management system, where the diet management system includes a diet knowledge graph for determining basic diet information, and the method includes:

Obtain dietary information uploaded by users;

Inputting the dietary information into the dietary knowledge graph, and obtaining basic dietary information that matches the dietary information in the dietary knowledge graph;

Inputting the basic dietary information and the health information of the user into a prediction model for calculation, and obtaining a dietary analysis result output by the prediction model;

A healthy diet plan is recommended to the user based on the diet analysis result.

Optionally, the obtaining dietary information uploaded by the user includes:

Obtain user-uploaded images containing food and beverages;

Based on the image recognition technology, the dietary information corresponding to the dietary meal is identified from the image.

Optionally, the dietary information includes dietary information obtained by the user scanning a graphic code on a dietary meal.

Optionally, recommending a healthy diet plan to the user based on the diet analysis result includes:

The diet analysis result is input into the deep knowledge perception network for calculation, and the healthy diet plan output by the deep knowledge perception network is recommended to the user.

Optionally, the healthy diet plan includes replacing unhealthy diet with healthy diet in the diet information uploaded by the user.

Optionally, the obtaining basic dietary information matching the dietary information in the dietary knowledge graph includes:

Obtain the dietary label to which the dietary information in the dietary knowledge graph belongs;

Obtain basic dietary information corresponding to the dietary information under the dietary label.

Optionally, the diet label includes at least one of category, attribute, nutrition, and theme; wherein, the category refers to the diet type to which the diet information belongs, and the attribute refers to the basic information of the diet information. The nutrition refers to the nutritional elements of the dietary information, and the topic refers to the therapeutic function of the dietary information.

Optionally, the diet type includes at least one of staple food, vegetables, fruits, and beverages; the basic information includes at least one of ingredients, cooking methods, tastes, meat and vegetables, and cuisines; the nutritional elements include protein , at least one of fat, vitamins, and calories; and the diet therapy function includes at least one of healthy meals, sugar control, weight loss, calcium supplementation, blood supplementation, and fat reduction.

Optionally, the user's health information includes user physical sign data in the user's health profile.

Optionally, the user sign data includes disease history.

Optionally, the prediction model includes a decision tree model.

According to a second aspect of the embodiments of the present specification, there is provided a diet recommendation device, which is applied to a diet management system, where the diet management system includes a diet knowledge graph for determining basic diet information, and the device includes:

an acquisition unit to acquire the dietary information uploaded by the user;

a matching unit, which inputs the dietary information into the dietary knowledge graph, and obtains basic dietary information that matches the dietary information in the dietary knowledge graph;

a calculation unit, which inputs the basic dietary information and the health information of the user into a prediction model for calculation, and obtains a dietary analysis result output by the prediction model;

A recommending unit, which recommends a healthy diet plan to the user based on the diet analysis result.

Optionally, the obtaining unit includes:

An image uploaded by the user including the food and drink is acquired, and based on the image recognition technology, the dietary information corresponding to the food and drink is identified from the image.

Optionally, the dietary information includes dietary information obtained by the user scanning a graphic code on a dietary meal.

Optionally, the recommendation unit includes:

The diet analysis result is input into the deep knowledge perception network for calculation, and the healthy diet plan output by the deep knowledge perception network is recommended to the user.

Optionally, the healthy diet plan includes replacing unhealthy diet with healthy diet in the diet information uploaded by the user.

Optionally, the matching unit includes:

a first matching subunit, which inputs the dietary information into the dietary knowledge graph, and obtains a dietary label to which the dietary information in the dietary knowledge graph belongs;

The second matching subunit acquires basic dietary information corresponding to the dietary information under the dietary label.

Optionally, the diet label includes at least one of category, attribute, nutrition, and theme; wherein, the category refers to the diet type to which the diet information belongs, and the attribute refers to the basic information of the diet information. The nutrition refers to the nutritional elements of the dietary information, and the topic refers to the therapeutic function of the dietary information.

Optionally, the diet type includes at least one of staple food, vegetables, fruits, and beverages; the basic information includes at least one of ingredients, cooking methods, tastes, meat and vegetables, and cuisines; the nutritional elements include protein , at least one of fat, vitamins, and calories; and the diet therapy function includes at least one of healthy meals, sugar control, weight loss, calcium supplementation, blood supplementation, and fat reduction.

Optionally, the user's health information includes user physical sign data in the user's health profile.

Optionally, the user sign data includes disease history.

Optionally, the prediction model includes a decision tree model.

According to a third aspect of the embodiments of the present specification, an electronic device is provided, including:

processor;

memory for storing processor-executable instructions;

Wherein, the processor is configured to any one of the above-mentioned diet recommendation methods.

The embodiments of this specification provide a diet recommendation scheme. By constructing a diet knowledge graph, the diet information uploaded by the user can be analyzed in a targeted manner, and a diet scheme that meets the user's health needs can be recommended in combination with the user's health information.

Description of drawings

1 is a flowchart of a method for recommending a diet provided by an embodiment of the present specification;

2 is a schematic diagram of a diet label provided by an embodiment of the present specification;

3 is a schematic diagram of a dietary knowledge graph provided by an embodiment of this specification;

4 is a schematic diagram of dietary analysis and dietary recommendation provided by an embodiment of the present specification;

FIG. 5 is a hardware structure diagram of a diet recommendation device provided by an embodiment of the present specification;

FIG. 6 is a module of a diet recommendation device provided by an embodiment of the present specification.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this specification. Rather, they are merely examples of apparatus and methods consistent with some aspects of this specification as recited in the appended claims.

The terms used in this specification are for the purpose of describing particular embodiments only and are not intended to limit the specification. As used in this specification and the appended claims, the singular forms "a," "the," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information, without departing from the scope of the present specification. Depending on the context, the word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determining."

The following describes an embodiment of the diet recommendation method provided by the present specification with reference to FIG. 1, which is applied to a diet management system, where the diet management system includes a diet knowledge map for determining basic diet information, and the method includes:

Step 210: Obtain the dietary information uploaded by the user;

Step 220: Input the dietary information into the dietary knowledge graph, and obtain a dietary label to which the dietary information in the dietary knowledge graph belongs, and basic dietary information corresponding to the dietary information under the dietary label;

Step 230: Input the basic dietary information and the health information of the user into a prediction model for calculation, and obtain a dietary analysis result output by the prediction model;

Step 240: Recommend a healthy diet plan to the user based on the diet analysis result.

In this specification, the above-mentioned diet management system refers to any form of machine or machine cluster for managing a diet plan.

For example, in practical applications, the above-mentioned diet management system may specifically be a machine or cluster deployed in the cloud for diet recommendation.

In the present specification, the above-mentioned diet management system includes a diet knowledge graph for determining diet basic information.

For example, in practical applications, the above-mentioned diet management system stores a diet knowledge map used to determine basic dietary information in a database in the background. The above-mentioned diet management system can also provide users with diet through web pages or docked APP software. Recommended service. For example, after the user accesses the above-mentioned diet management system through the terminal held by the user, the above-mentioned diet management system can interact with the client terminal held by the user, including the above-mentioned user uploading diet information through the operation interface displayed by the client terminal.

In an exemplary embodiment, the above step 210 to obtain the dietary information uploaded by the user may include:

Obtain user-uploaded images containing food and beverages;

Based on the image recognition technology, the dietary information corresponding to the dietary meal is identified from the image.

For example, in practical applications, a user may use a camera device (eg, a camera) mounted on the above-mentioned terminal to capture images including food and drink items, and then upload the captured images to the food and beverage management system. The diet management system can identify the diet information corresponding to the diet meal from the received image based on the image recognition technology.

In the present specification, the above-mentioned dietary information may include the names of dietary items. For example, rice, milk, eggs, noodles, vegetables, fish, meat, etc.

In this specification, the above-mentioned image recognition technology may be based on an image recognition model constructed by a convolutional neural network (Convolutional Neural Networks, CNN) algorithm.

In an exemplary embodiment, the above-mentioned dietary information includes dietary information obtained by the user by scanning a graphic code on a dietary item.

In this example, instead of uploading an image, the user scans the graphic code sprayed on the food and drink through the scanning device (such as a code scanner, camera, etc.) mounted on the terminal, so as to obtain the dietary information of the food and drink, and then upload the dietary information Give the above diet management system.

In this specification, the above-mentioned graphic codes may include barcodes or two-dimensional codes.

After introducing the above dietary information, let's introduce the knowledge graph in this manual. In order to facilitate understanding, here is a brief introduction to the knowledge graph, which is an information technology that maps human cognition of the objective world to the computer world. Taking objects in the objective world as entities in the computer world, and using the attributes of objects in the objective world or the relationships between objects as entity attributes or relationships between entities in the computer world, it is used to describe objects and objects in the objective world through the computer world. properties and object relationships.

At the time of implementation, the core of the knowledge graph is a triple: entity (Entity), attribute (Attribute) and relationship (Relation); the attributes of objects in the objective world or the relationship between objects can be expressed as <entity, relationship , entity> or <entity, attribute, attribute value>.

For example: "The protein content of milk is 3.5g/100ml" This is human cognition. In the computer world, when describing the triplet of the knowledge graph, you can use the triplet <milk, protein, 3.5g/ml >Expression; wherein, "milk" is an entity, "protein" represents the entity attribute of the "milk" entity, and "3.5g/ml" represents the attribute value of the "protein" entity attribute.

Therefore, by constructing massive triple data of knowledge graph, human cognition can be formed into massive data knowledge graph data in the computer world, and the knowledge graph data can be stored by graph database. , please refer to the technical description of graph database, which will not be repeated here.

In this specification, the dietary knowledge graph refers to the above entity attributes as diet labels, and the attribute values as diet basic information.

In an exemplary embodiment, the above-mentioned diet label includes at least one of categories, attributes, nutrition, and topics;

The above category refers to the type of diet to which the dietary information belongs, the above attribute refers to the basic information of the dietary information, the above element refers to the nutritional element of the dietary information, and the above topic refers to the therapeutic function of the dietary information.

Please refer to FIG. 2, which is a schematic diagram of a diet label provided by an embodiment of the present specification.

In this example, the above diet tags can be divided into four categories: category, attribute, nutrition, and topic, and each tag is also subdivided into many sub-tags.

For example, the type of diet represented by the category label in FIG. 2 may include staple food, vegetables, fruits, drinks, dishes, etc.; the basic information represented by the attribute label may include ingredients, cooking methods, tastes, meat and vegetables, cuisine, etc.; the nutrition label indicates The nutritional elements can include protein, fat, vitamins, calories, GI (Glycemic Index, glycemic index), GL (Glycemic Load, glycemic load), etc; Calcium, blood replenishment, fat loss, etc.

It should be noted that there is a certain correlation between the above diet labels; in general, according to different categories of diet information, the attributes of the corresponding diet information will also be different; and the attributes of the diet will further affect the nutrition of the diet; The attributes and nutrition of the diet are ultimately the basis for determining the theme.

In addition, the data source of the above-mentioned dietary knowledge graph can be obtained from public channels, such as recipes, scientific knowledge or the Internet; it can also be gradually improved during the operation of the system.

For example, the above-mentioned diet information corresponding to the diet meal is identified from the image based on the image recognition technology, or the diet information uploaded by the user scanning the graphic code on the diet meal can be recorded as the diet information in the diet knowledge map For the missing basic dietary information, it can be manually annotated and updated to the knowledge map, or automatically obtained from public channels based on related algorithms to update the knowledge map.

In an exemplary embodiment, obtaining basic dietary information in the dietary knowledge graph that matches the dietary information in step 220 includes:

Obtain the dietary label to which the dietary information in the dietary knowledge graph belongs, and further acquire basic dietary information corresponding to the dietary information under the dietary label.

Please refer to FIG. 3 , which is a schematic diagram of a dietary knowledge graph provided by an embodiment of the present specification.

In Figure 3, the dietary information input into the dietary knowledge graph is mutton soba, and the category tag that matches the mutton soba in the dietary knowledge graph is obtained as a dish, and the basic dietary information corresponding to the mutton soba under the dish is: pasta.

Similarly, the attribute tags matching mutton soba in the dietary knowledge map are meat and vegetables, ingredients and cooking methods; further, the basic dietary information corresponding to mutton soba under meat and vegetables is meat; under ingredients, it corresponds to mutton soba. The basic dietary information of mutton and soba is mutton and soba; the basic dietary information corresponding to mutton soba under the cooking mode is boiled.

The nutrition labels matching mutton soba in the dietary knowledge map are calorie, GI, GE, fat, vitamin, protein; the basic dietary information corresponding to mutton soba under further calories is 1200 kcal; The corresponding basic dietary information is 59; the basic dietary information corresponding to mutton buckwheat noodles under GL is 11.3; the basic dietary information corresponding to mutton soba under GL is 5.41; the basic dietary information corresponding to mutton buckwheat noodles under vitamin The information is 1.47; the basic dietary information corresponding to mutton soba under protein is 9.52;

The subject tag matching the mutton soba in the dietary knowledge map is a healthy meal; the basic dietary information corresponding to the mutton soba under the further healthy meal is diabetes.

It should be noted that the labels and numerical values in FIG. 3 are only examples, especially the numerical values may deviate from the actual ones, and it can be understood that the examples do not specifically limit the embodiments provided in this specification.

In an exemplary embodiment, after the basic dietary information is obtained, the basic dietary information and the user's health information may be further input into a prediction model for calculation to obtain a dietary analysis result output by the prediction model. .

In practical applications, the user's health information may include the user's sign data in the user's health profile. For example, the physical examination report generated after the user's physical examination.

The following description will be given in conjunction with the schematic diagram of the dietary analysis and dietary recommendation described in FIG. 4 .

As can be seen in FIG. 4 , the above-mentioned user sign data may at least include the user's disease history. In addition, the user's basic physical information such as age, weight, height, etc. may also be included.

In the implementation process, basic dietary information (as shown in Figure 4, calorie 338 kcal, subject of sugar control and fat reduction, GI34), and the user's health information (as shown in Figure 4, age 60, weight 45kg, height 170cm, history of diabetes) was input into the prediction model for calculation, and the result of dietary analysis was: not suitable for people with diabetes.

Wherein, the above-mentioned prediction model may include a decision tree (Decision Tree) shown in FIG. 4 . By inputting the basic dietary information and the user's health information into the decision tree, since the decision tree calculates it, it can finally be displayed in the form of data, for example, the dietary analysis results can be output in the form of a score system and a hierarchical system.

Combining again with Fig. 4, in Fig. 4, the output of several different forms (in points, color green light yellow light red light, grade A/B/C) is exemplified.

In the example in the form of scores, the decision tree calculates the input basic dietary information and the user's health information, and can calculate a score that reflects the health of the diet; if the score is between 100 and 70, it means that the dietary information corresponds to If the score is between 70 and 50, it means that the user can only eat a small amount; if the score is lower than 50, it means that the user cannot eat it.

By applying the above embodiment, it is possible to carry out a diet analysis based on the basic dietary information in combination with the user's health information, to obtain whether the user's diet meets the actual health needs of the user.

In an exemplary embodiment, after the dietary analysis result is determined, a healthy dietary plan may be recommended to the user based on the dietary analysis result.

In this specification, a healthy diet plan can be recommended to the user based on the diet analysis result in combination with the recommendation algorithm.

The following description will be given in conjunction with the schematic diagram of the dietary analysis and dietary recommendation described in FIG. 4 .

As can be seen in FIG. 4 , the above recommendation algorithm may adopt the DKN algorithm (Deep Knowledge-Aware Network, deep knowledge awareness network).

Specifically, the diet analysis result may be input into a deep knowledge perception network for calculation, and a healthy diet plan output by the deep knowledge perception network is recommended to the user.

As shown in FIG. 4 , the recommended diet plan includes diet content that conforms to the user’s health information. For example, since the user suffers from diabetes, the recommended food to the user is tofu, and the reason for the recommendation is that tofu is suitable for people with diabetes; for example, due to the user’s weight The weight reaches 85kg, so the recommended food to the user is beef, and the reason for the recommendation is that beef is suitable for people who lose fat; and because the user is 60 years old, the food recommended to the user is pumpkin soup, and the reason for the recommendation is that pumpkin soup is suitable for people over 60 years old. crowd. It can be seen that the dietary plans recommended to the user are all healthy dietary content that meets the user's health needs.

Using the above example, since the DKN algorithm is a recommendation algorithm suitable for knowledge graphs, the DKN algorithm used in this specification can quickly calculate the recommended healthy diet plan based on the dietary knowledge graph. Compared with the general recommendation algorithm processing higher efficiency.

In an exemplary embodiment, the above-mentioned healthy diet plan includes replacing unhealthy diet with healthy diet in the diet information uploaded by the user.

In practical applications, the unhealthy diet in the user's current diet content is replaced with a healthy diet, so that the user can more reasonably match the diet that meets the health requirements, reducing the cost of the user's diet management; for users with chronic diseases, it can be Effectively improve the ability of diet correction, so as to achieve the purpose of disease prevention.

Corresponding to the foregoing embodiments of the dietary recommendation method, the present specification also provides embodiments of the dietary recommendation device. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by reading the corresponding computer program in the non-volatile memory into the memory through the processor of the device where it is located. From the perspective of hardware, as shown in FIG. 5 , a hardware structure diagram of the equipment where the diet recommendation device is located in this specification, in addition to the processor, network interface, memory and non-volatile memory shown in FIG. In the example, the device where the device is located usually recommends actual functions according to the diet, and may also include other hardware, which will not be repeated here.

Please refer to FIG. 6 , which is a block diagram of a diet recommendation device provided in an embodiment of the present specification. The device corresponds to the embodiment shown in FIG. 1 and is applied to a diet management system. The diet management system includes basic information for determining diet. The dietary knowledge graph, the device includes:

The obtaining unit 310 obtains the dietary information uploaded by the user;

A matching unit 320, which inputs the dietary information into the dietary knowledge graph, and obtains basic dietary information that matches the dietary information in the dietary knowledge graph;

The calculation unit 330 inputs the basic dietary information and the health information of the user into a prediction model for calculation, and obtains a dietary analysis result output by the prediction model;

The recommending unit 340 recommends a healthy diet plan to the user based on the diet analysis result.

In an exemplary embodiment, the obtaining unit 310 includes:

An image uploaded by the user including the food and drink is acquired, and based on the image recognition technology, the dietary information corresponding to the food and drink is identified from the image.

In an exemplary embodiment, the dietary information includes dietary information obtained by the user scanning a graphic code on a dietary item.

In an exemplary embodiment, the recommending unit 340 includes:

The diet analysis result is input into the deep knowledge perception network for calculation, and the healthy diet plan output by the deep knowledge perception network is recommended to the user.

In an exemplary embodiment, the healthy diet plan includes replacing unhealthy diets with healthy diets in the diet information uploaded by the user.

In an exemplary embodiment, the matching unit 320 includes:

a first matching subunit, which inputs the dietary information into the dietary knowledge graph, and obtains a dietary label to which the dietary information in the dietary knowledge graph belongs;

The second matching subunit acquires basic dietary information corresponding to the dietary information under the dietary label.

In an exemplary embodiment, the diet label includes at least one of category, attribute, nutrition, and theme; wherein, the category refers to the diet type to which the diet information belongs, and the attribute refers to the diet information The basic information of , the nutrition refers to the nutritional elements of the dietary information, and the subject refers to the therapeutic function of the dietary information.

In an exemplary embodiment, the diet type includes at least one of staple food, vegetables, fruits, and beverages; the basic information includes at least one of ingredients, cooking methods, tastes, meat and vegetables, and cuisines; The nutritional elements include at least one of protein, fat, vitamins, and calories; and the therapeutic function includes at least one of healthy meals, sugar control, weight loss, calcium supplementation, blood supplementation, and fat reduction.

In an exemplary embodiment, the user's health information includes user vitals data in the user's health profile.

In an exemplary embodiment, the user sign data includes disease history.

In an exemplary embodiment, the predictive model includes a decision tree model.

The systems, devices, modules or units described in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media player, navigation device, email sending and receiving device, game control desktop, tablet, wearable device, or a combination of any of these devices.

For details of the implementation process of the functions and functions of each unit in the above device, please refer to the implementation process of the corresponding steps in the above method, which will not be repeated here.

For the apparatus embodiments, since they basically correspond to the method embodiments, reference may be made to the partial descriptions of the method embodiments for related parts. The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed over multiple network elements. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in this specification. Those of ordinary skill in the art can understand and implement it without creative effort.

Figure 6 above describes the internal functional modules and structural schematic diagrams of the diet recommendation device, and its substantial executive body can be an electronic device, including:

processor;

memory for storing processor-executable instructions;

Wherein, the processor is configured to execute any of the above embodiments of the dietary recommendation method.

In the above embodiments of the electronic device, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, CPU for short), or other general-purpose processors, digital signal processors (English: Digital Signal Processor) , referred to as: DSP), application specific integrated circuit (English: Application Specific Integrated Circuit, referred to as: ASIC) and so on. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., and the aforementioned memory can be a read-only memory (English: read-only memory, abbreviation: ROM), random access memory (English: read-only memory, abbreviation: ROM), random access memory (English : random access memory, referred to as: RAM), flash memory, hard disk or solid state disk. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the electronic device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments.

Other embodiments of this specification will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This description is intended to cover any variations, uses, or adaptations of this specification that follow the general principles of this specification and include common knowledge or conventional techniques in the art not disclosed in this specification . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the specification being indicated by the following claims.

It should be understood that this specification is not limited to the precise structures described above and illustrated in the accompanying drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of this specification is limited only by the appended claims.

Claims (13)

1. A dietary recommendation method, the method is applied to a dietary management system, the dietary management system comprising a dietary knowledge graph for determining basic dietary information, the method comprising: Obtain dietary information uploaded by users; Inputting the dietary information into the dietary knowledge graph, and obtaining basic dietary information that matches the dietary information in the dietary knowledge graph; Inputting the basic dietary information and the health information of the user into a prediction model for calculation, and obtaining a dietary analysis result output by the prediction model; A healthy diet plan is recommended to the user based on the diet analysis result. 2. The method according to claim 1, wherein the obtaining dietary information uploaded by the user comprises: Obtain user-uploaded images containing food and beverages; Based on the image recognition technology, the dietary information corresponding to the dietary meal is identified from the image. 3. The method according to claim 1, wherein the dietary information comprises dietary information obtained by the user scanning a graphic code on a dietary item. 4. The method of claim 1, wherein recommending a healthy diet plan to the user based on the diet analysis result, comprising: The diet analysis result is input into the deep knowledge perception network for calculation, and the healthy diet plan output by the deep knowledge perception network is recommended to the user. 5. The method of claim 1 or 4, wherein the healthy diet plan comprises replacing unhealthy diets with healthy diets in the diet information uploaded by the user. 6. The method according to claim 1, wherein the acquiring basic dietary information matched with the dietary information in the dietary knowledge graph comprises: Obtain the dietary label to which the dietary information in the dietary knowledge graph belongs; Obtain basic dietary information corresponding to the dietary information under the dietary label. 7. The method according to claim 6, wherein the diet label includes at least one of categories, attributes, nutrition, and topics; wherein, the category refers to the diet type to which the diet information belongs, and the attribute refers to The basic information of the dietary information, the nutrition refers to the nutritional elements of the dietary information, and the topic refers to the therapeutic function of the dietary information. 8 . The method according to claim 7 , wherein the diet type includes at least one of staple food, vegetables, fruits, and beverages; and the basic information includes at least one of ingredients, cooking methods, tastes, meat and vegetables, and cuisines. 9 . ; the nutrient elements include at least one of protein, fat, vitamins, and calories; and the therapeutic function includes at least one of healthy meals, sugar control, weight loss, calcium supplementation, blood supplementation, and fat reduction. 9. The method of claim 1, the user's health information comprising user vital data in a user's health profile. 10. The method of claim 9, the user sign data comprising disease history. 11. The method of claim 1, the predictive model comprising a decision tree model. 12. A diet recommendation device, the device being applied to a diet management system, the diet management system comprising a diet knowledge graph for determining basic diet information, the device comprising: an acquisition unit to acquire the dietary information uploaded by the user; a matching unit, which inputs the dietary information into the dietary knowledge graph, and obtains basic dietary information that matches the dietary information in the dietary knowledge graph; a calculation unit, which inputs the basic dietary information and the health information of the user into a prediction model for calculation, and obtains a dietary analysis result output by the prediction model; A recommending unit, which recommends a healthy diet plan to the user based on the diet analysis result. 13. An electronic device comprising: processor; memory for storing processor-executable instructions; wherein the processor is configured to perform the method of any of the preceding claims 1-11.

Images