CN110837552B

CN110837552B - Diet information recommendation method and device

Info

Publication number: CN110837552B
Application number: CN201910943392.8A
Authority: CN
Inventors: 叶帅; 孙会业; 问志光; 杜振华; 叶孝璐; 邵帅; 马赞华
Original assignee: Koukouxiangchuan Beijing Network Technology Co ltd
Current assignee: Koukouxiangchuan Beijing Network Technology Co ltd
Priority date: 2019-09-30
Filing date: 2019-09-30
Publication date: 2022-12-09
Anticipated expiration: 2039-09-30
Also published as: CN110837552A

Abstract

The application discloses a diet information recommendation method and a device, wherein the method comprises the following steps: obtaining target original data; the target original data comprises at least one of user characteristic information of a target user, scene information corresponding to the target user and time factor information; obtaining a catering knowledge graph; according to the target original data and the catering knowledge map, at least one of target dish information matched with a target user, target merchant information corresponding to the target dish information and target dish information of the target dish information is obtained; obtaining diet recommendation information aiming at a target user according to at least one of target dish information, target merchant information and target menu information; and providing the diet recommendation information to the target user. By using the method, more targeted and more comprehensive diet recommendation information can be provided for the target user based on the user characteristic information, the scene information and the time factor information of the target user and in combination with the catering knowledge map.

Description

Diet information recommendation method and device

Technical Field

The application relates to the technical field of computers, in particular to a diet information recommendation method. The application also relates to a diet information recommending device and an electronic device. The application also relates to a catering knowledge graph creation method, a catering knowledge graph creation device and electronic equipment.

Background

With the development of e-commerce technology and the improvement of diet requirements of users, more and more life service platforms recommend diet information for users, and most of the existing diet recommendation modes perform diet information recommendation based on a single dimension or a small number of dimensions, for example, perform diet information recommendation based on preference information of users or perform diet information recommendation based on health conditions of users.

However, the knowledge system corresponding to the diet information recommendation process is complex, and there are many factors that can affect the diet information of the user, for example, diet principles adapted to different people are different, diet requirements corresponding to the same person in different scenes are different, and diet information corresponding to different times is different. Therefore, a single-dimension or a small number of dimensions cannot provide comprehensive, accurate and targeted diet recommendation information for a single user.

Disclosure of Invention

The application provides a diet information recommendation method, which aims to solve the problem that comprehensive, accurate and targeted diet recommendation information cannot be provided for a single user based on single dimensionality or a small number of dimensionalities. The application further provides a diet information recommending device and an electronic device. The application also provides a catering knowledge graph creating method and device and electronic equipment.

The application provides a diet information recommendation method, which comprises the following steps:

obtaining target original data; the target original data comprises at least one of user characteristic information of a target user, scene information corresponding to the target user and time factor information;

obtaining a catering knowledge map; the catering knowledge map comprises mapping relation information of original data and catering subject information, mapping relation information of the catering subject information and food material information, mapping relation information of the food material information and dish information, mapping relation information of the dish information and merchant information, and mapping relation information of the dish information and dish information;

according to the target original data and the catering knowledge graph, at least one of target dish information matched with the target user, target merchant information corresponding to the target dish information and target dish information of the target dish information is obtained;

obtaining diet recommendation information aiming at the target user according to at least one of the target dish information, the target merchant information and the target menu information;

and providing the diet recommendation information to the target user.

Optionally, the obtaining of the target dish information matched with the target user includes obtaining at least one of the following information:

first target dish information with normalized identification information;

second target dish information having diversified identification information; the first target dish information corresponds to the same dish as the second target dish information;

correspondingly, the obtaining of the target merchant information corresponding to the target dish information includes obtaining at least one of the following information:

first target merchant information corresponding to the first target dish information; second target merchant information corresponding to the second target dish information;

correspondingly, the obtaining of the target menu information of the target dish information comprises the following steps:

target menu information of the first target menu information or the second target menu information.

Optionally, the obtaining of the first target dish information having the normalized identification information and the second target dish information having the diversified identification information substantially the same as the first dish information includes:

first target dish information having a standard dish name and second target dish information having a non-standard dish name are obtained.

Optionally, the user characteristic information of the target user includes at least one of the following:

life stage information of the target user; taste preference information of the target user; health condition information of the target user; family condition information of the target user; group information to which the target user belongs; background information of the target user.

Optionally, the catering subject information includes at least one of the following:

holiday theme information; nursing subject information; pathology topic information; subject information of the group to which the user belongs.

Optionally, the scene information corresponding to the target user includes at least one of the following:

the position information of the target user; behavior information of the target user.

Optionally, the mapping relationship information between the food material information and the dish information includes: mapping relation information of the food material information and first dish information with the normalized identification information;

the mapping relation information of the dish information and the merchant information comprises: mapping relation information between the first dish information and first merchant information corresponding to the first dish information;

the mapping relation information of the dish information and the menu information comprises the following steps: and mapping relation information between the first dish information and the first menu information.

Optionally, the mapping relationship information between the food material information and the dish information further includes: mapping relation information between the food material information and second dish information with diversified identification information; the first dish information corresponds to the same dish as the second dish information;

the mapping relationship information between the dish information and the merchant information further comprises: mapping relation information between the second dish information and second merchant information corresponding to the second dish information;

the mapping relationship information between the dish information and the menu information further comprises: and mapping relation information of the second menu information and the first menu information.

Optionally, the catering knowledge graph further comprises:

mapping relation information of the first dish information and second dish information with diversified identification information; the first dish information corresponds to the same dish as the second dish information;

optionally, the target merchant information includes at least one of the following:

target merchant information providing a service of eating in store; target merchant information for providing take-away dining services.

Optionally, the obtaining diet recommendation information for the target user includes obtaining at least one of the following information:

the target dish information; providing target merchant information of the store-entering dining service aiming at the target dish information; providing target merchant information of takeaway meal service aiming at the target dish information;

cooking information including the target recipe information.

The application also provides a catering knowledge graph creating method, which comprises the following steps:

obtaining original data, wherein the original data comprises at least one of user characteristic information, scene information and time factor information;

obtaining catering subject information corresponding to the original data;

obtaining food material information associated with the catering subject information;

obtaining dish information containing the food material information;

acquiring merchant information corresponding to the dish information and menu information of the dish information;

establishing a mapping relation between the original data and the catering subject information, a mapping relation between the catering subject information and the food material information, a mapping relation between the food material information and the dish information, a mapping relation between the dish information and the merchant information, and a mapping relation between the dish information and the dish information to obtain a catering knowledge map.

Optionally, the obtaining of the dish information including the food material information includes:

obtaining first dish information containing the food material information and having normalized identification information and second dish information substantially identical to the first dish information and having diversified identification information;

correspondingly, the obtaining of the merchant information corresponding to the dish information and the menu information of the dish information includes:

obtaining first merchant information corresponding to the first dish information and second merchant information corresponding to the second dish information;

obtaining menu information of the first menu information or the second menu information;

correspondingly, the establishing of the mapping relationship between the dish information and the merchant information includes:

establishing a mapping relation between the first dish information and the first merchant information;

establishing a mapping relation between the second dish information and the second merchant information;

correspondingly, the establishing of the mapping relationship between the dish information and the recipe information includes:

and establishing a mapping relation between the first menu information and the second menu information and the menu information.

Optionally, the method further includes: and establishing a mapping relation between the first dish information and the second dish information.

Optionally, the method further includes: and establishing a mapping relation between the food material information and the second dish information.

Optionally, the obtaining first dish information containing the food material information and having normalized identification information and second dish information substantially identical to the first dish information and having diversified identification information includes:

obtaining information of alternative dishes;

performing word segmentation processing on the alternative dish information;

calculating a feature vector of the alternative dish information subjected to word segmentation; clustering calculation is carried out on the alternative dish information through a clustering algorithm to obtain first dish information;

calculating the vector space distance between the feature vector of the alternative dish information and the feature vector of the first dish information;

and determining the alternative dish information of which the vector space distance from the first dish information is smaller than a preset threshold value as second dish information.

Optionally, the clustering the alternative dish information through a clustering algorithm to obtain first dish information includes: and performing clustering calculation on the alternative dish information through a K-means clustering algorithm, and determining the alternative dish information of the central point as first dish information.

Optionally, the calculating a vector space distance between the feature vector of the alternative dish information and the feature vector of the first dish information includes: and calculating the vector space distance between the feature vector of the alternative dish information and the feature vector of the first dish information by adopting a vector space cosine similarity algorithm.

Optionally, the method further includes: and performing similarity filtering on at least one of the original data, the catering subject information, the food material information, the dish information and the menu information.

Optionally, the user characteristic information includes at least one of the following:

life stage information of the user; taste preference information of the user; health condition information of the user; family situation information of the user; group information to which the user belongs; background information of the user.

holiday theme information; nursing subject information; pathology topic information; subject information of a group to which the user belongs.

Optionally, the obtaining food material information associated with the catering subject information includes:

obtaining the correlation logic information of the catering subject information and the food material information;

and according to the association logic information, food material information associated with the catering subject information is obtained from the food material information.

Optionally, the establishing of the mapping relationship between the catering subject information and the food material information includes:

and establishing a mapping relation between the catering subject information and the food material information according to the correlation logic information of the catering subject information and the food material information.

Optionally, the obtaining of the catering subject information corresponding to the original data includes:

acquiring the associated logic information of the original data and the catering subject information;

and obtaining catering subject information corresponding to the original data according to the associated logic information.

Optionally, the establishing of the mapping relationship between the original data and the catering subject information includes:

and establishing a mapping relation between the original data and the catering subject information according to the associated logic information of the original data and the catering subject information.

The present application further provides a diet information recommendation device, including:

a target raw data obtaining unit for obtaining target raw data; the target original data comprises at least one of user characteristic information of a target user, scene information corresponding to the target user and time factor information;

the catering knowledge map obtaining unit is used for obtaining a catering knowledge map; the catering knowledge map comprises mapping relation information of original data and catering subject information, mapping relation information of the catering subject information and food material information, mapping relation information of the food material information and dish information, mapping relation information of the dish information and merchant information, and mapping relation information of the dish information and dish information;

the information obtaining unit is used for obtaining at least one of target dish information matched with the target user, target merchant information corresponding to the target dish information and target menu information of the target dish information according to the target original data and the catering knowledge map;

the diet recommendation information obtaining unit is used for obtaining diet recommendation information aiming at the target user according to at least one of the target dish information, the target merchant information and the target menu information;

and the diet recommendation information providing unit is used for providing the diet recommendation information to the target user.

The present application further provides an electronic device, comprising:

a processor; a memory for storing a diet information recommendation program that, when read and executed by the processor, performs the following:

according to the target original data and the catering knowledge map, at least one of target dish information matched with the target user, target merchant information corresponding to the target dish information and target dish information of the target dish information is obtained;

and providing the diet recommendation information to the target user.

The application also provides a catering knowledge graph creating device, which comprises:

the device comprises an original data obtaining unit, a processing unit and a processing unit, wherein the original data obtaining unit is used for obtaining original data, and the original data comprises at least one of user characteristic information, scene information and time factor information;

the catering subject information obtaining unit is used for obtaining catering subject information corresponding to the original data;

a food material information obtaining unit, configured to obtain food material information associated with the catering subject information;

a dish information obtaining unit for obtaining dish information including the food material information;

the system comprises a merchant information and menu information obtaining unit, a menu information obtaining unit and a menu information obtaining unit, wherein the merchant information and menu information obtaining unit is used for obtaining merchant information corresponding to the menu information and menu information of the menu information;

the catering knowledge graph obtaining unit is used for establishing a mapping relation between the original data and the catering subject information, a mapping relation between the catering subject information and the food material information, a mapping relation between the food material information and the dish information, a mapping relation between the dish information and the merchant information, and a mapping relation between the dish information and the dish information, so as to obtain the catering knowledge graph.

The present application further provides an electronic device, comprising:

a processor; a memory for storing a dining knowledge map creation program that, when read and executed by the processor, performs the following:

obtaining catering subject information corresponding to the original data;

obtaining dish information containing the food material information;

Compared with the prior art, the method has the following advantages:

according to the diet information recommendation method, target dish information matched with a target user, target merchant information corresponding to the target dish information and target dish information of the target dish information are obtained according to user characteristic information of the target user, scene information corresponding to the target user, time factor information and a diet knowledge map, diet recommendation information for the target user is obtained according to the information, and the diet recommendation information is provided for the target user. By using the method, more targeted and more accurate diet recommendation information can be provided for the target user based on multi-dimensional information such as user characteristic information, scene information, time factor information and the like of the target user in combination with the catering knowledge map. The problem that comprehensive, accurate and targeted diet recommendation information cannot be provided for a single user based on single dimensionality or a small number of dimensionalities in the prior art is effectively solved.

Drawings

FIG. 1 is a flowchart of a diet information recommendation method provided in a first embodiment of the present application;

FIG. 2 is a flowchart of a restaurant knowledge graph creation method provided in a second embodiment of the present application;

FIG. 2-A is a schematic view of a restaurant knowledge graph provided in a second embodiment of the present application;

fig. 2-B is a schematic view of an association relationship among the subject information, the food material information and the dish information provided in the second embodiment of the present application;

fig. 3 is a block diagram of elements of a diet information recommendation device according to a third embodiment of the present application;

fig. 4 is a schematic logical structure diagram of an electronic device according to a fourth embodiment of the present application;

FIG. 5 is a block diagram of a restaurant knowledge map creation apparatus according to a fifth embodiment of the present application;

fig. 6 is a schematic logical structure diagram of an electronic device according to a sixth embodiment of the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit and scope of this application, and thus this application is not limited to the specific implementations disclosed below.

Aiming at a diet information recommendation scene in the field of life services, in order to improve the accuracy and pertinence of a diet information recommendation process, the application provides a diet information recommendation method, a diet information recommendation device corresponding to the method and electronic equipment, and also provides a diet knowledge map creation method, a diet knowledge map creation device corresponding to the method and electronic equipment. The following provides embodiments to explain the method, apparatus, and electronic device in detail.

A first embodiment of the present application provides a diet information recommendation method, an application subject of the method may be a back-end server of a catering service platform, fig. 1 is a flowchart of the diet information recommendation method provided in the first embodiment of the present application, and the method provided in this embodiment is described in detail below with reference to fig. 1. The following description refers to embodiments for the purpose of illustrating the principles of the methods, and is not intended to be limiting in actual use.

As shown in fig. 1, the diet information recommendation method provided in this embodiment includes the following steps:

and S101, obtaining target original data.

This step is used to obtain target raw data related to the target user, where the target raw data includes one or more of user characteristic information of the target user, scene information corresponding to the target user, and time factor information.

The user characteristic information of the target user may refer to one or more of life stage information of the target user, taste preference information of the target user, health condition information of the target user, family condition information of the target user, group information to which the target user belongs, background information of the target user, and the like.

The life stage information of the target user refers to stage information of the target user, such as young, middle-aged, pregnancy-preparing, pregnancy, baby-raising, marriage, old and the like; the taste preference information of the target user refers to taste information of light preference, vegetables, sweetmeats, hot and cold of the target user and the like; the health condition information of the target user refers to information on whether the target user suffers from diseases such as obesity, hypertension, hyperlipidemia and hyperglycemia and whether the target user is in an over-fatigue state, a sub-health state and the like; the family condition information of the target user refers to family member composition information of the target user, identity information of the target user in a family and other information; the group information to which the target user belongs refers to information of a group consisting of people having commonalities in some aspects with the target user, for example, information of a group consisting of people having the same hobbies or habits as the target user; the background information of the target user refers to home background information, education background information, work background information, etc. of the target user.

The scene information corresponding to the target user may refer to the location information of the target user and the behavior information of the target user, for example, the target user performs online shopping at home, and the target user moves outdoors.

The time factor information refers to information such as a current season, a current date, festival information corresponding to the current date, a time interval and a time point in a day, and for example, the current time is the mid-autumn festival, which is the time factor information. In this embodiment, the input data of the target user or the related data of the target user provided by the third-party network platform may be received, and the data may be collated to obtain the target original data.

And S102, obtaining a catering knowledge map.

The catering knowledge map is used for representing the corresponding relation of entities such as catering subject information, food material information, dish information, merchant information, menu information and the like in the catering field. In this embodiment, the restaurant knowledge map is a pre-created restaurant knowledge map, and outputs related dish information, merchant information and recipe data by using user characteristic information, scene information and time factor information as model input data. The food and beverage knowledge map comprises mapping relation information of original data and food and beverage subject information, mapping relation information of the food and beverage subject information and food material information, mapping relation information of the food material information and dish information, mapping relation information of the dish information and merchant information, and mapping relation information of the dish information and dish information.

In this embodiment, the raw data may refer to one or more of user characteristic information, scene information, and time factor information, and the catering subject information may refer to one or more of holiday subject information, nursing subject information, pathological subject information, and subject information of a group to which the user belongs.

In this embodiment, the mapping relationship information between the food material information and the dish information may be: mapping relationship information between the food material information and first dish information with normalized identification information, for example, mapping relationship information between the food material information and the first dish information which contains the food material information and has a standard name; the mapping relationship information between the dish information and the merchant information may be: mapping relationship information between the first dish information and the corresponding first merchant information, for example, mapping relationship information between the first dish information with the standard name and merchant information that can provide takeout service or restaurant-entering meal service for the first dish information; the mapping relationship information between the dish information and the menu information may be: and mapping relation information between the first dish information and the first menu information.

Since the same dish may correspond to different names, for example, stewed sirloin with tomato and stewed sirloin with tomato are the same dish with different names, in this embodiment, the mapping relationship information of the food material information and the dish information further includes: the food material information and the mapping relation information of the second dish information with diversified identification information, wherein the first dish information and the second dish information correspond to the same dish, the diversified identification information refers to a plurality of different names corresponding to the same dish, for example, the first dish information is stewed sirloin with tomatoes, and the second dish information is stewed sirloin with tomatoes.

Correspondingly, the mapping relationship information between the dish information and the merchant information further includes: mapping relation information between the second dish information and the corresponding second merchant information; the mapping relationship information between the dish information and the recipe information further includes: and mapping relation information between the second menu information and the first menu information.

In this embodiment, the food and beverage knowledge map may further include: and mapping relation information between the first dish information and the second dish information with diversified identification information.

S103, obtaining at least one of target dish information matched with a target user, target merchant information corresponding to the target dish information and target menu information of the target dish information according to the target original data and the catering knowledge map.

After the user characteristic information of the target user, the scene information corresponding to the target user, the time factor information and the catering knowledge map are obtained in the steps, the steps are used for obtaining one or more of target dish information matched with the target user, target merchant information corresponding to the target dish information, target dish information of the target dish information and the like according to the obtained information.

Obtaining the target dish information matched with the target user refers to obtaining at least one of the following information: first target dish information with normalized identification information; and the first target dish information corresponds to the same dish as the second target dish information. In this embodiment, the two target dish information are obtained simultaneously, that is, the first target dish information with the standard dish name and the second target dish information with the non-standard dish name are obtained, for example, the first target dish information with the standard dish name is stewed sirloin with tomato, and the second target dish information with the non-standard dish name is stewed sirloin with tomato.

Correspondingly, the obtaining of the target merchant information corresponding to the target dish information means obtaining at least one of the following information: the first target merchant information and the second target merchant information can be both target merchant information for providing in-store dining service or target merchant information for providing take-out dining service; obtaining target menu information of the target dish information, which means: and acquiring target menu information of the first target menu information or the second target menu information, wherein the first target menu information and the second target menu information correspond to the same target menu information.

And S104, obtaining diet recommendation information aiming at the target user according to at least one of the target dish information, the target merchant information and the target menu information.

After the target dish information, the target merchant information and the target menu information are obtained in the above steps, the step is used for obtaining diet recommendation information for the target user according to at least one of the obtained target dish information, the obtained target merchant information and the obtained target menu information.

In this embodiment, the diet recommendation information for the target user may be one or more of the target dish information, target merchant information providing in-store dining service for the target dish information, target merchant information providing take-away dining service for the target dish information, and target menu information corresponding to the target dish information, and the diet recommendation information may further include image information or text description information of the above information.

And S105, providing the diet recommendation information to the target user.

The step is used for providing the diet recommendation information obtained in the step for the target user, for example, sending the diet recommendation information to a terminal used by the target user.

According to the diet information recommendation method provided by the embodiment, target dish information matched with a target user, target merchant information corresponding to the target dish information and target dish information of the target dish information are obtained according to user characteristic information of the target user, scene information and time factor information corresponding to the target user and a diet knowledge map, diet recommendation information for the target user is obtained according to the information, and the diet recommendation information is provided for the target user. By using the method, more targeted and more accurate diet recommendation information can be provided for the target user based on multi-dimensional information such as user characteristic information, scene information, time factor information and the like of the target user in combination with the catering knowledge map. The problem that comprehensive, accurate and targeted diet recommendation information cannot be provided for a single user based on single dimensionality or a small number of dimensionalities in the prior art is effectively solved.

Corresponding to the diet information recommendation method provided in the first embodiment of the present application, a second embodiment of the present application provides a restaurant knowledge graph creation method, as shown in fig. 2, the restaurant knowledge graph creation method provided in this embodiment includes the following steps:

s201, obtaining original data.

This step is used to obtain raw data, which contains one or more of user characteristic information, scene information, and time factor information.

The user characteristic information may refer to one or more of life stage information of the user, taste preference information of the user, health condition information of the user, family condition information of the user, group information of the user, user background information and the like.

The life stage information of the user refers to the stage information of the user, such as young, middle-aged, pregnancy preparation, pregnancy, baby raising, marriage, old and the like; the taste preference information of the user refers to taste information such as light preference, vegetables, sweetmeats, spicy taste, hot taste, cold taste and the like of the user; the health condition information of the user refers to information on whether the user suffers from diseases such as obesity, hypertension, hyperlipidemia and hyperglycemia and information on whether the user is in a fatigue state, a sub-health state and the like; the family condition information of the user refers to information such as family member composition information of the user, identity of the user in a family and the like; the group information to which the user belongs refers to information of a group composed of people having commonalities in some aspects, for example, group information composed of people having the same hobbies or the same habits; the user's context information refers to the user's home context information, education context information, work context information, and the like.

The context information may refer to location information where the user is located and user behavior information, for example, online shopping behavior information of the user, behavior information of the user moving outdoors.

The time factor information refers to information such as season, date, holiday information corresponding to the date, time interval and time point in a day, for example, the current time is the mid-autumn festival, and the mid-autumn festival is the time factor information.

In this embodiment, the user characteristic information, the scene information, and the time factor information from the third-party network platform may be aggregated and sorted to obtain the original information.

And S202, obtaining catering subject information corresponding to the original data.

The step is used for obtaining catering subject information corresponding to the original data. The catering subject information can be one or more of holiday subject information, nursing subject information, pathological subject information and subject information of groups to which the user belongs.

The holiday theme information refers to theme information with a specific holiday as a dining background, such as midautumn theme information and afternoon theme information. The nursing subject information refers to subject information with the body of the nursing user as the background of dining, such as hair-nourishing subject information, beauty-maintaining and young-keeping subject information, kidney-nourishing subject information, eye-care subject information, and good sleep subject information. The pathological topic information refers to topic information on the background of eating for treating or preventing diseases, such as diabetes topic information and obesity topic information. The subject information of the group refers to subject information with information of the same hobbies or the same living habits of the users as the dining background, such as body-building subject information, donkey-friend subject information and the like.

In the embodiment, the catering subject information corresponding to the original data is obtained, and firstly, the correlation logic information between the original data and the catering subject information is obtained, and then the catering subject information corresponding to the original data is obtained according to the correlation logic information. The association logic information refers to causal relationship information between information such as user characteristic information, scenario information, and time factor information, and holiday theme information, nursing theme information, pathological theme information, and user group theme information, for example, if the user taste preference information is spicy, the scenario information corresponding to the user is office overtime, and the time factor information is late night, which indicates that the user needs skin care, liver protection, or kidney care, the theme information corresponding to the user may be the nursing theme information. For another example, if the current time is before or after the mid-autumn festival, the theme information corresponding to the current time may be the mid-autumn festival theme information.

S203, food material information associated with the catering subject information is obtained.

After the catering subject information is obtained in the above step, the step is used for obtaining the food material information associated with the catering subject information.

The food material information associated with the catering topic information means that the efficacy or the composition of the food material information is matched with the holiday topic information, the nursing topic information, the pathological topic information and the topic information of the group to which the user belongs, for example, for a good sleep topic in the nursing topic information, the food material information matched with the good sleep topic can be white radish, kelp, corn, green soy bean and the like. For another example, for the beauty maintaining and young keeping topic information in the nursing topic information, the food material information matched with the beauty maintaining and young keeping topic information may be black beans, chinese yams and the like.

In this embodiment, food material information associated with the catering subject information is obtained, and at first, associated logic information of the catering subject information and the food material information needs to be obtained, and then according to the associated logic information, food material information associated with the catering subject information is obtained. For example, an association relationship is established by using the efficacy of the food material information and the effect achieved by the catering topic information, the effect achieved by the catering topic information and the efficacy of the food material information are association logic information of the catering topic information and the food material information, and the food material information meeting the above efficacies is food material information associated with the catering topic information.

And S204, obtaining dish information containing the food material information.

After the food material information associated with the catering subject information is obtained in the above step, the step is used for obtaining dish information containing the food material information. For example, the food material information is tomatoes, and the dish information containing the food material information may be tomato-fried eggs, tomato-stewed sirloin, and the like.

In this embodiment, the obtaining of the dish information including the food material information specifically includes: the method comprises the steps of obtaining first dish information containing the food material information and having normalized identification information and second dish information having diversified identification information substantially the same as the first dish information, namely obtaining first dish information having standard dish names and second dish information having non-standard dish names, wherein the first dish information having the standard dish names is tomato stewed sirloin and tomato fried eggs, and the second dish information having the non-standard dish names is tomato stewed sirloin and tomato fried eggs.

In this embodiment, the obtaining of the first dish information having the normalized identification information and the second dish information having the diversified identification information substantially the same as the first dish information, which include the food material information, includes the following steps:

obtaining alternative dish information, for example, randomly obtaining a predetermined amount of dish information as alternative dish information, such as tomato fried eggs, tomato stewed sirloin, and the like; performing word segmentation on the alternative dish information, for example, segmenting tomato stewed sirloin into tomato, stewed sirloin and sirloin; calculating a feature vector of the candidate dish information subjected to word segmentation, for example, calculating the feature vector of the candidate dish information by using a word2vec algorithm, for example, the feature vector of the stewed sirloin with tomatoes is X (1, 0, 1), and the feature vector of the stewed sirloin with tomatoes is Y (0, 1); performing clustering calculation on the alternative dish information through a clustering algorithm to obtain first dish information, for example, performing clustering calculation on the alternative dish information through a K-means clustering algorithm, and determining the alternative dish information corresponding to the central point as the first dish information, for example, determining the stewed sirloin with tomatoes and fried eggs with tomatoes as the first dish information; calculating a vector space distance between the feature vector of the remaining alternative dish information and the feature vector of the first dish information, for example, calculating the vector space distance between the feature vector of the remaining alternative dish information and the feature vector of the first dish information by using a vector space cosine similarity algorithm; and determining the remaining alternative dish information with the vector space distance from the first dish information smaller than a preset threshold value as second dish information.

And S205, acquiring merchant information corresponding to the dish information and menu information of the dish information.

After the dish information is obtained in the above steps, the step is used for obtaining merchant information and menu information of the dish information containing the dish information.

In this embodiment, obtaining merchant information and menu information of the dish information corresponding to the dish information includes: and acquiring first merchant information corresponding to the first dish information and second merchant information corresponding to the second dish information, wherein the merchant information can be merchant information for providing a service of eating in store aiming at the dish information or merchant information for providing a service of taking out meals aiming at the dish information. And acquiring menu information of the first menu information or the second menu information, wherein the first menu information and the second menu information correspond to the same menu information.

It should be noted that, after the original data, the catering subject information, the food material information, the dish information, and the recipe information are obtained in the above steps, similarity filtering needs to be performed on at least one of the original data, the catering subject information, the food material information, the dish information, and the recipe information. For example, the similarity of the above information is calculated by using the euclidean distance algorithm, and information with high similarity is filtered.

S206, establishing a mapping relation between the original data and the catering subject information, a mapping relation between the catering subject information and the food material information, a mapping relation between the food material information and the dish information, a mapping relation between the dish information and the merchant information, and a mapping relation between the dish information and the menu information, and obtaining the catering knowledge map.

After the original data, the catering subject information, the food material information, the dish information and the menu information are obtained in the steps, the steps are used for sequentially establishing mapping relations among the information to generate a catering knowledge graph.

In this embodiment, the step of establishing the mapping relationship between the original data and the catering subject information refers to establishing the mapping relationship between the original data and the catering subject information according to the associated logic information of the original data and the catering subject information. The step of establishing the mapping relation between the catering subject information and the food material information refers to establishing the mapping relation between the catering subject information and the food material information according to the association logic information of the catering subject information and the food material information.

Establishing a mapping relation between the dish information and the merchant information, comprising the following steps: establishing a mapping relation between the first dish information and the first merchant information, and establishing a mapping relation between the second dish information and the second merchant information; correspondingly, the step of establishing the mapping relation between the dish information and the menu information refers to respectively establishing the mapping relation between the first dish information and the menu information and the mapping relation between the second dish information and the menu information.

It should be noted that a mapping relationship between the first dish information and the second dish information may also be established, in this case, one first dish information corresponds to a plurality of second dish information, and establishing a mapping relationship between the dish information and the merchant information means only establishing a mapping relationship between the second dish information and the second merchant information.

In addition, in this embodiment, a mapping relationship between the food material information and the second dish information may also be established.

As shown in fig. 2-a, fig. 2-a is a schematic diagram of the finally created dining knowledge graph of the present embodiment.

As shown in fig. 2-B, fig. 2-B is a schematic diagram of the association relationship among the topic information, the food material information and the dish information, and in fig. 2-B, for the topic information of good sleep, the efficacy of the food material information is associated by the topic, for example, the food material corresponding to the topic of good sleep is corn, kelp, white radish, green soy bean, etc., and the dish information (standard dish) having a standard name is associated by the food material information, for example, the standard dish corresponding to white radish is sirloin, clear-fried white radish, white radish stewed chicken, etc.

As shown in fig. 2-a, the catering knowledge graph provided in this embodiment establishes a N: N correspondence with an existing merchant data engine (one standard dish belongs to multiple merchants, and one merchant includes multiple standard dishes), establishes 1: and establishing a relation of N to N with a menu data engine (one standard menu corresponds to a plurality of menu information, and one menu information corresponds to a plurality of standard menus). The incidence relation from the theme information to the food material information, from the food material information to the standard dish information, from the standard dish information to the merchant information, from the standard dish to the non-standard dish and from the standard dish to the menu information is realized. By searching through the catering knowledge graph, the association relationship among the subject information, the food material information, the standard menu information, the non-standard menu information, the merchant information and the menu information can be inquired.

The third embodiment of the present application further provides a diet information recommending apparatus, since the apparatus embodiment is substantially similar to the method embodiment, and therefore, the description is relatively simple, and the details of the related technical features can be found in the corresponding description of the method embodiment provided above, and the following description of the apparatus embodiment is only illustrative.

Referring to fig. 3, to understand the embodiment, fig. 3 is a block diagram of a unit of the apparatus provided in the embodiment, and as shown in fig. 3, the apparatus provided in the embodiment includes:

a target raw data obtaining unit 301 for obtaining target raw data; the target original data comprises at least one of user characteristic information of a target user, scene information corresponding to the target user and time factor information;

the catering knowledge map obtaining unit 302 is used for obtaining a catering knowledge map; the food and beverage knowledge map comprises mapping relation information of original data and food and beverage theme information, mapping relation information of the food and beverage theme information and food material information, mapping relation information of the food material information and dish information, mapping relation information of the dish information and merchant information, and mapping relation information of the dish information and dish information;

an information obtaining unit 303, configured to obtain at least one of target dish information matched with the target user, target merchant information corresponding to the target dish information, and target menu information of the target dish information according to the target original data and the catering knowledge graph;

a diet recommendation information obtaining unit 304, configured to obtain diet recommendation information for the target user according to at least one of the target dish information, the target merchant information, and the target recipe information;

a diet recommendation information providing unit 305, configured to provide the diet recommendation information to the target user.

Optionally, the obtaining of the target dish information matched with the target user includes obtaining at least one of the following information: first target dish information with normalized identification information; second target dish information having diversified identification information; the first target dish information corresponds to the same dish as the second target dish information;

correspondingly, the obtaining of the target merchant information corresponding to the target dish information includes obtaining at least one of the following information: first target merchant information corresponding to the first target dish information; second target merchant information corresponding to the second target dish information;

correspondingly, the obtaining of the target menu information of the target dish information includes:

Optionally, the catering subject information includes at least one of the following: holiday theme information; nursing subject information; pathology topic information; subject information of the group to which the user belongs.

position information of the target user; behavior information of the target user.

the mapping relation information of the dish information and the merchant information comprises the following steps: mapping relation information between the first dish information and corresponding first merchant information;

Optionally, the catering knowledge graph further comprises:

target merchant information providing a service of eating in store; target merchant information that provides take-away dining services.

Optionally, the obtaining diet recommendation information for the target user includes obtaining at least one of the following information: the target dish information; providing target merchant information of the store-entering dining service aiming at the target dish information; providing target merchant information of takeout meal service aiming at the target dish information; cooking information including the target recipe information.

In the above embodiments, a diet information recommendation method and a diet information recommendation apparatus are provided, and in addition, a fourth embodiment of the present application further provides an electronic device, which is basically similar to the method embodiment and therefore is relatively simple to describe, and please refer to the corresponding description of the method embodiment for the details of the related technical features, and the following description of the embodiment of the electronic device is only illustrative. The embodiment of the electronic equipment is as follows:

please refer to fig. 4 for understanding the present embodiment, fig. 4 is a schematic diagram of a logic structure of the electronic device provided in the present embodiment. As shown in fig. 4, the electronic apparatus includes: a processor 401; a memory 402;

the memory 402 is used for storing a diet information recommendation program, and when the program is read and executed by the processor, the program performs the following operations:

obtaining a catering knowledge graph; the food and beverage knowledge map comprises mapping relation information of original data and food and beverage theme information, mapping relation information of the food and beverage theme information and food material information, mapping relation information of the food material information and dish information, mapping relation information of the dish information and merchant information, and mapping relation information of the dish information and dish information;

providing the diet recommendation information to the target user.

first target dish information with normalized identification information;

the mapping relation information of the dish information and the menu information comprises: and mapping relation information between the first dish information and the first menu information.

the mapping relation information of the dish information and the menu information further comprises: and mapping relation information of the second menu information and the first menu information.

Optionally, the food and beverage knowledge map further comprises:

The fifth embodiment of the present application further provides a restaurant knowledge graph creating device, which is basically similar to the method embodiment, so that the description is relatively simple, and the details of the related technical features need to be referred to the corresponding description of the method embodiment, and the following description of the device embodiment is only illustrative.

Referring to fig. 5, to understand the embodiment, fig. 5 is a block diagram of a unit of the apparatus provided in the embodiment, and as shown in fig. 5, the apparatus provided in the embodiment includes:

a raw data obtaining unit 501, configured to obtain raw data, where the raw data includes at least one of user characteristic information, scene information, and time factor information;

a catering subject information obtaining unit 502, configured to obtain catering subject information corresponding to the original data;

a food material information obtaining unit 503, configured to obtain food material information associated with the catering subject information;

a dish information obtaining unit 504 for obtaining dish information including the food material information;

a merchant information and menu information obtaining unit 505, configured to obtain merchant information corresponding to the menu information and menu information of the menu information;

a catering knowledge graph obtaining unit 506, configured to establish a mapping relationship between the original data and the catering subject information, a mapping relationship between the catering subject information and the food material information, a mapping relationship between the food material information and the dish information, a mapping relationship between the dish information and the merchant information, and a mapping relationship between the dish information and the dish information, so as to obtain a catering knowledge graph.

correspondingly, the obtaining of the merchant information corresponding to the dish information and the menu information of the dish information includes: obtaining first merchant information corresponding to the first dish information and second merchant information corresponding to the second dish information; obtaining menu information of the first menu information or the second menu information;

and establishing a mapping relation between the first dish information and the second dish information and the menu information.

Optionally, the obtaining first dish information containing the food material information and having normalized identification information and second dish information substantially identical to the first dish information and having diversified identification information includes: obtaining information of alternative dishes; performing word segmentation processing on the alternative dish information; calculating a feature vector of the alternative dish information subjected to word segmentation processing; clustering calculation is carried out on the alternative dish information through a clustering algorithm to obtain first dish information; calculating the vector space distance between the feature vector of the alternative dish information and the feature vector of the first dish information; and determining the alternative dish information of which the vector space distance from the first dish information is smaller than a preset threshold value as second dish information.

life stage information of the user; taste preference information of the user; health condition information of the user; family condition information of the user; group information to which the user belongs; background information of the user.

obtaining the correlation logic information of the catering subject information and the food material information; and according to the association logic information, food material information associated with the catering subject information is obtained from the food material information.

In the above embodiments, a restaurant knowledge graph creation method and a restaurant knowledge graph creation apparatus are provided, and in addition, a sixth embodiment of the present application also provides an electronic device, which is basically similar to the method embodiment and therefore is relatively simple to describe, and the details of the relevant technical features may be obtained by referring to the corresponding description of the method embodiment provided above, and the following description of the electronic device embodiment is only illustrative. The embodiment of the electronic equipment is as follows:

please refer to fig. 6 for understanding the present embodiment, fig. 6 is a schematic diagram of a logic structure of the electronic device according to the present embodiment. As shown in fig. 6, the electronic apparatus includes: a processor 601; a memory 602;

the memory 602 is configured to store a catering knowledge graph creation program, and when the program is read and executed by the processor, the program performs the following operations:

obtaining catering subject information corresponding to the original data;

obtaining dish information containing the food material information;

correspondingly, the establishing of the mapping relationship between the dish information and the merchant information comprises the following steps:

correspondingly, the establishing of the mapping relationship between the dish information and the menu information comprises the following steps:

Optionally, the method further includes:

and establishing a mapping relation between the first dish information and the second dish information.

Optionally, the method further includes:

and establishing a mapping relation between the food material information and the second dish information.

Optionally, the obtaining first menu information containing the food material information and having normalized identification information and second menu information substantially identical to the first menu information and having diversified identification information includes:

obtaining information of alternative dishes; performing word segmentation processing on the alternative dish information; calculating a feature vector of the alternative dish information subjected to word segmentation processing; clustering calculation is carried out on the alternative dish information through a clustering algorithm to obtain first dish information; calculating the vector space distance between the feature vector of the alternative dish information and the feature vector of the first dish information; and determining the alternative dish information of which the vector space distance from the first dish information is smaller than a preset threshold value as second dish information.

Optionally, the performing cluster calculation on the alternative dish information through a clustering algorithm to obtain first dish information includes: and performing clustering calculation on the alternative dish information through a K-means clustering algorithm, and determining the alternative dish information of the central point as first dish information.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

1. Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.

2. As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.

Claims

1. A diet information recommendation method is applied to a back-end server of a diet service platform, and comprises the following steps:

obtaining target original data; the target original data comprises at least one of user characteristic information of a target user, scene information corresponding to the target user and time factor information, the user characteristic information of the target user comprises group information to which the target user belongs, the scene information corresponding to the target user comprises position information of the target user and behavior information of the target user, and the time factor information comprises holiday information corresponding to a current date;

obtaining a catering knowledge graph, wherein the catering knowledge graph is a knowledge graph in the catering field; the catering knowledge map comprises mapping relation information of original data and catering subject information, mapping relation information of the catering subject information and food material information, mapping relation information of the food material information and dish information, mapping relation information of the dish information and merchant information and mapping relation information of the dish information and dish information, wherein the mapping relation information of the original data and the catering subject information is causal relation information between the original data and the catering subject information, the catering subject information comprises holiday subject information and one or more of group subject information to which a user belongs, the holiday subject information comprises subject information with a specific holiday as a dining background, and the group subject information to which the user belongs comprises subject information with the same hobby information or the same living habit information as the dining background;

obtaining diet recommendation information aiming at the target user according to at least one of the target dish information, the target merchant information and the target menu information, wherein the diet recommendation information aiming at the target user comprises the target merchant information, and the target merchant information is target merchant information providing store-in dining service aiming at the target dish information or target merchant information providing take-out dining service aiming at the target dish information;

and providing the diet recommendation information to a terminal used by the target user.

2. The method of claim 1, wherein obtaining the target dish information matching the target user comprises obtaining at least one of:

first target dish information with normalized identification information;

correspondingly, the obtaining of the target merchant information corresponding to the target dish information comprises obtaining at least one of the following information:

3. The method of claim 2, wherein obtaining a first target dish information having normalized identification information and a second target dish information having diversified identification information substantially identical to the first dish information comprises:

4. The method of claim 1, wherein the user characteristic information of the target user comprises at least one of:

life stage information of the target user;

taste preference information of the target user;

health condition information of the target user;

family condition information of the target user;

group information to which the target user belongs;

background information of the target user.

5. The method of claim 1, wherein the dining topic information further comprises at least one of:

nursing subject information;

pathological subject information.

6. The method of claim 1, wherein the mapping relationship information between the food material information and the dish information comprises: mapping relation information of the food material information and first dish information with the normalized identification information;

7. The method of claim 6, wherein the mapping relationship information between the food material information and the dish information further comprises: mapping relation information between the food material information and second dish information with diversified identification information; the first dish information corresponds to the same dish as the second dish information;

the mapping relationship information between the dish information and the menu information further comprises: and mapping relation information between the second dish information and the first menu information.

8. The method of claim 6, wherein the dining knowledgegraph further comprises:

mapping relation information of the first dish information and second dish information with diversified identification information; the first dish information and the second dish information correspond to the same dish.

9. The method of claim 1, wherein the target merchant information comprises at least one of:

target merchant information providing a service of eating in store;

target merchant information that provides take-away dining services.

10. The method of claim 1, wherein the obtaining dietary recommendation information for the target user comprises obtaining at least one of:

the target dish information;

providing target merchant information of store-entering dining service aiming at the target dish information;

providing target merchant information of takeout meal service aiming at the target dish information;

cooking information including the target recipe information.

11. A catering knowledge graph creation method is characterized by comprising the following steps:

obtaining original data, wherein the original data comprises at least one of user characteristic information, scene information and time factor information, the user characteristic information of a target user comprises group information to which the target user belongs, the scene information corresponding to the target user comprises position information of the target user and behavior information of the target user, and the time factor information comprises holiday information corresponding to a current date;

obtaining catering subject information corresponding to the original data;

obtaining dish information containing the food material information;

establishing a mapping relation between the original data and the catering subject information, a mapping relation between the catering subject information and the food material information, a mapping relation between the food material information and the dish information, a mapping relation between the dish information and the merchant information, and a mapping relation between the dish information and the menu information, and obtaining a catering knowledge map, wherein the mapping relation information between the original data and the catering subject information is causal relation information between the original data and the catering subject information, the catering subject information comprises holiday subject information and one or more of group subject information to which a user belongs, the holiday subject information comprises subject information with a specific holiday as a dining background, and the group subject information to which the user belongs comprises subject information with the same preference information or the same living habit information of the user as the dining background.

12. The method of claim 11, wherein the obtaining the dish information including the food material information comprises:

13. The method of claim 12, further comprising:

14. The method of claim 12, further comprising:

15. The method of claim 12, wherein obtaining a first recipe information having normalized identification information that includes the food material information and a second recipe information having diversified identification information that is substantially the same as the first recipe information comprises:

obtaining information of alternative dishes;

performing word segmentation processing on the alternative dish information;

calculating a feature vector of the alternative dish information subjected to word segmentation processing; clustering calculation is carried out on the alternative dish information through a clustering algorithm to obtain first dish information;

16. The method of claim 15, wherein the clustering the alternative dish information by the clustering algorithm to obtain the first dish information comprises:

and performing clustering calculation on the alternative dish information through a K-means clustering algorithm, and determining the alternative dish information of the central point as first dish information.

17. The method of claim 15, wherein calculating the vector space distance between the feature vector of the alternative dish information and the feature vector of the first dish information comprises:

and calculating the vector space distance between the feature vector of the alternative dish information and the feature vector of the first dish information by adopting a vector space cosine similarity algorithm.

18. The method of claim 11, further comprising:

and performing similarity filtering processing on at least one of the original data, the catering subject information, the food material information, the dish information and the menu information.

19. The method of claim 11, wherein the user characteristic information comprises at least one of:

life stage information of the user;

taste preference information of the user;

health condition information of the user;

family condition information of the user;

group information to which the user belongs;

context information of the user.

20. The method of claim 11, wherein the dining topic information comprises at least one of:

nursing subject information;

pathological subject information.

21. The method of claim 11, wherein the obtaining food material information associated with the catering subject information comprises:

obtaining the association logic information of the catering subject information and the food material information;

and obtaining food material information associated with the catering subject information according to the associated logic information.

22. The method of claim 21, wherein the establishing the mapping relationship between the catering subject information and the food material information comprises:

23. The method of claim 11, wherein obtaining catering subject information corresponding to the raw data comprises:

obtaining the correlation logic information of the original data and the catering subject information;

24. The method of claim 23, wherein the establishing a mapping relationship between the raw data and the dining topic information comprises:

25. A diet information recommendation device characterized by comprising:

a target original data obtaining unit for obtaining target original data; the target original data comprises at least one of user characteristic information of a target user, scene information corresponding to the target user and time factor information, the user characteristic information of the target user comprises group information to which the target user belongs, the scene information corresponding to the target user comprises position information of the target user and behavior information of the target user, and the time factor information comprises holiday information corresponding to a current date;

the catering knowledge map obtaining unit is used for obtaining a catering knowledge map, and the catering knowledge map is a knowledge map in the catering field; the catering knowledge graph comprises mapping relation information of original data and catering subject information, mapping relation information of the catering subject information and food material information, mapping relation information of the food material information and dish material information, mapping relation information of the dish material information and merchant information, and mapping relation information of the dish material information and dish material information, wherein the mapping relation information of the original data and the catering subject information is causal relation information between the original data and the catering subject information, the catering subject information comprises one or more of holiday subject information and subject information of a group to which a user belongs, the holiday subject information comprises subject information taking a specific holiday as a dining background, and the subject information of the group to which the user belongs comprises subject information taking the same hobby information or the same living habit information of the user as the dining background;

a diet recommendation information obtaining unit, configured to obtain diet recommendation information for the target user according to at least one of the target dish information, the target merchant information, and the target menu information, where the diet recommendation information for the target user includes the target merchant information, and the target merchant information is target merchant information providing a service for eating by entering a store for the target dish information or target merchant information providing a service for taking out of the store for the target dish information;

and the diet recommendation information providing unit is used for providing the diet recommendation information to a terminal used by the target user.

26. An electronic device, comprising:

a processor;

a memory for storing a diet information recommendation program that, when read and executed by the processor, performs the following:

obtaining a catering knowledge graph, wherein the catering knowledge graph is a knowledge graph in the catering field; the catering knowledge map comprises mapping relation information of original data and catering subject information, mapping relation information of the catering subject information and food material information, mapping relation information of the food material information and dish information, mapping relation information of the dish information and merchant information, and mapping relation information of the dish information and dish information, wherein the mapping relation information of the original data and the catering subject information is causal relation information between the original data and the catering subject information, the catering subject information comprises holiday subject information and one or more of group subject information to which a user belongs, the holiday subject information comprises subject information with a specific holiday as a dining background, and the group subject information to which the user belongs comprises subject information with the same hobby information or the same living habit information as the dining background;

27. A catering knowledge map creation device is characterized by comprising:

the system comprises an original data obtaining unit, a data processing unit and a data processing unit, wherein the original data comprises at least one of user characteristic information, scene information and time factor information, the user characteristic information of a target user comprises group information to which the target user belongs, the scene information corresponding to the target user comprises position information of the target user and behavior information of the target user, and the time factor information comprises holiday information corresponding to a current date;

the catering knowledge map obtaining unit is used for establishing a mapping relation between the original data and the catering subject information, a mapping relation between the catering subject information and the food material information, a mapping relation between the food material information and the dish information, a mapping relation between the dish information and the merchant information, and a mapping relation between the dish information and the dish information to obtain the catering knowledge map, wherein the mapping relation information between the original data and the catering subject information is causal relation information between the original data and the catering subject information, the catering subject information comprises one or more of holiday subject information and subject information of a group to which a user belongs, the holiday subject information comprises subject information taking a specific holiday as a dining background, and the subject information of the group to which the user belongs comprises subject information taking the same hobby-day information or the same living habit information of the user as a dining background.

28. An electronic device, comprising:

a processor;

a memory for storing a dining knowledge map creation program that, when read and executed by the processor, performs the following:

obtaining catering subject information corresponding to the original data;

obtaining dish information containing the food material information;