KR102122763B1 - Food recommendation system and method considering big data based constitution - Google Patents

Abstract

The present invention relates to a food recommendation system considering a physical constitution based on big data. The system comprises: a database including a physical constitution database and a collection database; a food recommendation device performing an association rule analysis based on the physical constitution data included in the physical constitution database, the collection data included in the collection database, and user information provided from a user terminal, and providing a plurality of recommended diet information generated in consideration of the user′s physical constitution; a kitchen monitoring device outputting the plurality of recommended diet information to a display unit provided in one area of a kitchen, collecting environmental information of food warehouses and kitchens using a plurality of sensors, and monitoring the condition of the food warehouses and the kitchens; and a user terminal providing user information corresponding to user input items provided in relation to the physical constitution to the food recommendation device.

Description

Food Recommendation System and Method Considering Big Data-Based Constitution {FOOD RECOMMENDATION SYSTEM AND METHOD CONSIDERING BIG DATA BASED CONSTITUTION}

The present invention relates to a food recommendation system and method in consideration of constitution based on big data.

Constitution, when observing a human being as a whole, it is possible to see features such as the shape and size of the body as well as facial expressions and movements. You can see the difference in the tendency to get sick, the ability to work, and the ability to withstand various internal and external conditions. Constitution is composed of three elements: body shape, aptitude, and personality. Body type is a characteristic of physique. Predisposition is a tendency characteristic of the body, and personality is a mental characteristic. Therefore, constitution is the whole body and organ tissue created by the action of genetic factors and the environment. It is the posture of the mind and body formed in the current environment. The above is the concept of constitution, but sometimes it is said that constitution is manifested in terms of body function.

Sasang constitution is divided into four types of constitution, such as burning, sun, yang, and noise, based on the size of the ledger, where the size of the ledger is the five organs (liver and phlegm, heart and small intestine. rain and stomach, lung and large intestine, and kidney) Bladder) refers to the difference in function strength. Eight constitutional medicine was based on Sasang constitution, but it is further subdivided into eight constitutions: Geumyang, Geumum, Taeum for Mokyang, Moumum, Soyang for soil, soil, noise for weeping, and masturbation.

Here, the commonality between Sasang constitution and 8 constitution is that each constitution inherently has long-term fruit and permission, and the difference is that Sasang constitution is classified based on the strongest and weakest of the five organs, but the eight constitution correlates with the five constitutions. All were considered.

According to constitutional medicine, the disease is caused by stronger and weaker books and weaker books depending on the size of each book. In other words, the disease does not occur only in weakness. Therefore, constitutional medicine aims to correct the imbalance of the tenon by strengthening the weak tenon and the strong tenon.

The constitutional diet has its own aura for each food, and it has an effect of strengthening or suppressing the function of each ledger. Through this, it is possible to control and balance the strength of the ledger to maximize disease prevention and improvement, health maintenance, and pharmacological activity.

However, there is a problem that it is difficult for an individual to easily access information about the beneficial and harmful effects of food according to the constitution and information such as the exact characteristics of the person's constitution.

In addition, it is necessary to provide information on the diet using this, since only beneficial and harmful food and medicines are listed.

The background technology of the present application is disclosed in Korean Patent Publication No. 10-2016-0000588.

The present application is intended to solve the problems of the prior art described above, and applies big data technology, and based on constitutional medicine, distinguishes individual constitutions and recommends a diet in which foods and medicines beneficial to the constitution are added. It is an object of the present invention to provide a food recommendation system and method in consideration of the constitution.

The present application is to solve the problems of the prior art described above, and aims to provide a food recommendation system and method capable of monitoring food recommendations and food materials in consideration of adult disease and constitution based on big data.

The present application is to solve the problems of the prior art described above, based on the data collected from the website, beneficial foods and medicines are added for each constitution, and harmful foods and medicines are reduced to prevent and improve the user's disease and maintain health The goal is to provide a food recommendation system and method capable of maximizing pharmacological activity and monitoring food recommendations and food ingredients.

The present application is intended to solve the problems of the prior art described above, and aims to provide a food recommendation system and method for continuously collecting user's diet data and recommending a diet beneficial to constitution.

The present application is to solve the above-described problems of the prior art, and aims to provide a food recommendation system and method for sensing and monitoring the kitchen environment based on information collected by using a plurality of sensors.

However, the technical problems to be achieved by the embodiments of the present application are not limited to the technical problems as described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, a food recommendation system considering a constitution based on big data according to an embodiment of the present application includes a constitution database and a collection database, a constitution data included in the constitution database, and A food recommendation device that performs a correlation rule analysis based on the collected data included in the collection database and the user information provided from the user terminal, and provides a plurality of recommended diet information generated in consideration of the user's constitution, an area of the kitchen Displaying the plurality of recommended diet information on the display unit provided in the kitchen, using a plurality of sensors to collect the environmental information of the food warehouse and kitchen, and monitor the condition of the food warehouse and kitchen related to the kitchen monitoring device and constitution It may include a user terminal for providing the user information corresponding to the provided user input item to the food recommendation device.

According to one embodiment of the present application, the food recommendation device comprises: a data collection unit that crawls a web page including keywords related to constitution and diet to collect unstructured data related to constitution, and user's constitution information and diet from the user terminal A user information collection unit for receiving user information including history information, a data analysis unit for performing association rule analysis between at least one of constitution data included in the constitution database and collection data included in the collection database, and the user information And a data providing unit that visualizes and provides a plurality of recommended diet information generated in consideration of the user's constitution with the user terminal, wherein the data analysis unit uses the analyzed result and the plurality of recommended diet information considering the user's constitution. Can generate

According to an embodiment of the present disclosure, the data collection unit collects collection data including keywords related to constitution and diet from content described in at least one website among news articles, SNS, blogs, and communities, and the database In the above, the collected data collected by the data collection unit may be stored in the collection database.

According to an embodiment of the present application, the user information receiving unit receives user input information related to an evaluation item of recommended diet information, and the data analysis unit is a first user based on the evaluation item information on the recommended diet information When similar user information is input, the recommended diet information having an evaluation score equal to or greater than the reference value may be prioritized to generate the plurality of recommended diet information.

According to an embodiment of the present application, the data analysis unit, when provided with specific diet information from the user information collection unit, analyzes the specific diet information, and whether the user's constitution information included in the user information If the determination result is impossible, it is possible to generate replaceable food material information among the food material information included in the specific diet information.

According to an embodiment of the present application, the constitution database, constitution table, disease table, food material classification table, food material table, medicinal material table, member information table, member disease table, constitutional beneficial food and medicinal material table, harmful food material by constitution and It may include at least one of a medicinal table, a healthy diet table.

According to an embodiment of the present application, the data analysis unit, the artificial neural network and the collection built through learning to input a plurality of data included in the constitutional database and the collection database and output items related to dietary results for each constitution. Recommended diet information may be generated based on the user information.

According to an embodiment of the present application, the kitchen monitoring apparatus, when the environment information collection unit and the environmental information collection result for collecting the environmental information of the food warehouse and the kitchen using a plurality of sensors is not included in the preset reference value , It may include a control unit for controlling the driving of at least one of the plurality of kitchen devices provided in the food warehouse and the kitchen.

According to the exemplary embodiment of the present application, the kitchen monitoring device may further include a display unit provided in one area of the kitchen and outputting a plurality of recommended diet information provided from the food recommendation device.

According to one embodiment of the present application, a food recommendation method considering a constitution based on big data comprises: crawling a web page including keywords related to constitution and diet to collect unstructured data, and user's constitution information and diet from a user terminal Receiving user information including history information, performing association rule analysis between at least one of constitution data and collection data included in the database and the user information, and considering the constitution of the user using the analyzed result The method may include generating recommendation diet information and visualizing and providing the plurality of recommendation diet information to the user terminal.

The above-described problem solving means are merely exemplary and should not be construed as limiting the present application. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and detailed description of the invention.

According to the above-mentioned problem solving means of the present application, by recommending food by user's constitution based on big data, by adding beneficial foods and medicines and harmful foods and medicines according to an individual's constitution and disease and adding them to a diet, disease prevention And improving, maintaining health, and maximizing pharmacological activity.

However, the effects obtainable herein are not limited to the above-described effects, and other effects may exist.

1 is a schematic configuration diagram of a food recommendation system in consideration of constitution based on big data according to an embodiment of the present application.
2 is a schematic configuration diagram of a constitution database for a food recommendation system in consideration of constitution based on big data according to an embodiment of the present application.
3 is a schematic block diagram of a food recommendation apparatus for a food recommendation system considering a big data-based constitution according to an embodiment of the present application.
4 is a schematic block diagram of a kitchen monitoring apparatus for a food recommendation system considering a big data-based constitution according to an embodiment of the present application.
5 is a schematic flowchart of a food recommendation method considering a big data-based constitution according to an embodiment of the present application.

Hereinafter, embodiments of the present application will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present application pertains may easily practice. However, the present application may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present application in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

Throughout this specification, when a part is "connected" to another part, it is not only "directly connected", but also "electrically connected" or "indirectly connected" with another element in between. "It includes the case where it is.

Throughout the present specification, when a member is positioned on another member “on”, “on the top”, “top”, “bottom”, “bottom”, “bottom”, this means that one member is attached to another member. This includes cases where there is another member between the two members as well as when in contact.

Throughout this specification, when a part “includes” a certain component, it means that the component may further include other components, not to exclude other components, unless otherwise stated.

The present application recommends food (food) according to the constitution by using a database built by analyzing herbal and 8 constitutional information, and can detect and monitor the environment of the kitchen that stores and cooks food and medicines.

In addition, the present application provides information such as a person's body type, physical characteristics, and diseases, such as shepherds, shepherds, sheep, water, soil, and toe , Geumyang (金陽), Geumum (金陰) divided into eight constitutional characteristics to distinguish constitution, disease (distinguishable) disease prevention and improvement corresponding to the constitution, health maintenance, maximizing pharmacological benefits You may recommend a diet with food ingredients added.

In addition, the present application is equipped with a sensor for detecting temperature and humidity, flame flame, gas smoke in the kitchen cooking the recommended diet, it is possible to monitor the state of the kitchen based on the sensing results of the sensor.

Hereinafter, a food recommendation system considering a constitution based on big data according to an embodiment of the present application will be referred to as a food recommendation system for convenience of description. The food materials used hereinafter may mean food materials and food materials.

1 is a schematic configuration diagram of a food recommendation system in consideration of constitution based on big data according to an embodiment of the present application.

Referring to FIG. 1, the food recommendation system 1 may include a database 10, a food recommendation device 20, a kitchen monitoring device 30, and a user terminal 40. However, the food recommendation system 1 is not limited to this. For example, the food recommendation system 1 may be connected through a network such as a hospital server, a government office server, a restaurant server, a weather server, a school server (meal server), a service provider server, and the like.

According to one embodiment of the present application, the food recommendation system 1 is a system that recommends a diet for each constitution based on big data, and provides service management such as a general restaurant, a food service, a buffet, a food service provider, a gym, and a hospital. It can be used in companies that do.

In addition, the food recommendation system (1) distinguishes beneficial foods and medicines from harmful foods and medicines according to the user's constitutional disease, and is a healthy diet (recommended by adding or subtracting foods and medicines from the generally provided diet) Based on the diet information), it is possible to recommend a preferred diet to a member's diet history or a group having a similar diet tendency.

On the other hand, big data is a technology that extracts value and analyzes results from data that includes large amounts of structured or even unstructured data sets that are not in the form of databases, beyond the capabilities of existing database management tools. The food recommendation system 1 may recommend a diet more suitable for the constitution of the member (user) by utilizing the big data.

According to one embodiment of the present application, the database 10 may include a constitutional database and a collection database. The constitutional database is divided into 8 types of constitutional medicine according to constitutional medicine: Geumyang, Geumum, Mokum, Soil, Toeum, Weeping, and Masturbation. Disease table that stores the characteristics of the 5 major diseases, including ingredients, food ingredients table that stores information such as the efficacy and characteristics of the medicine, herbal medicine table that stores information such as the efficacy and characteristics of the medicine, beneficial food materials classified by constitution, and Tables for storing medicinal materials, tables for storing harmful food and medicinal materials by constitution, tables for storing beneficial food and medicinal materials by disease, tables for storing harmful food and medicinal materials for different diseases, according to constitution and diseases It may include a table storing a diet (recipe) made by adding partially, a table storing information about a member's gender, age, and constitution. In addition, the collection database may include unstructured data collected from a website.

According to one embodiment of the present application, the food recommendation device 20 performs association rule analysis based on a plurality of tables included in the database 10 and user information provided from the user terminal 40, and the user's constitution. It is possible to provide a plurality of recommended diet information generated in consideration. In other words, the food recommendation device 20 may collect data related to constitution and diet from news, SNS blogs, and communities through a network. In addition, the food recommendation device 20 may determine a diet consumption propensity, such as a user's diet history and consumption form, based on the collected data. In addition, the food recommendation device 20 may analyze data using an association rule and grasp the correlation between the data. In addition, the food recommendation device 20 may visually process and output the integrated analysis result.

According to one embodiment of the present application, the kitchen monitoring device 30 outputs a plurality of recommended diet information on a display unit provided in one area of the kitchen, collects environmental information of the food warehouse and the kitchen using a plurality of sensors, and , You can monitor the condition of food warehouses and kitchens. The kitchen monitoring device 30 may collect temperature and humidity information, flame flame detection information, and gas smoke detection information sensed by a plurality of sensors, and determine whether or not a predetermined reference value is exceeded. In addition, the kitchen monitoring device 30 may generate a control signal that controls the operation of the kitchen device provided in the kitchen when the information collected from the plurality of sensors is greater than or equal to a preset reference value.

According to one embodiment of the present application, the food recommendation device 20 may provide a recommended diet menu to the user terminal 40. In addition, the kitchen monitoring device 30 may provide a kitchen monitoring management menu to the user terminal 40. For example, the application program provided by the food recommendation device 20 and the kitchen monitoring device 30 is downloaded and installed on the user terminal 40, and a recommended diet menu and a kitchen monitoring management menu may be provided through the installed application. have.

The food recommendation device 20 and the kitchen monitoring device 30 transmit and receive data, contents, and various communication signals to and from the user terminal 40 through a network, and all types of servers, terminals, or functions having data storage and processing functions. It may include a device.

The user terminal 40 is a device interworking with the food recommendation device 20 and the kitchen monitoring device 30 through the network 50, for example, a smartphone, a smart pad, and a tablet PC , Wearable devices, PCS (Personal Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, Wireless communication devices of all types, such as Code Division Multiple Access (CDMA)-2000, W-Code Division Multiple Access (W-CDMA), and Wireless Broadband Internet (Wibro) terminals, and fixed terminals such as desktop computers and smart TVs. .

The user terminal 40 is an example of a network 50 for sharing information between the food recommendation device 20 and the kitchen monitoring device 30 through the network 50, for example, a 3GPP (3rd Generation Partnership Project) network, LTE (Long) Term Evolution network, 5G network, World Interoperability for Microwave Access (WIMAX) network, Wired and wireless Internet, Local Area Network (LAN), Wireless Local Area Network (LAN), Wide Area Network (WAN), Personal (PAN) Area Network), a Bluetooth network, a Wifi network, a Near Field Communication (NFC) network, a satellite broadcasting network, an analog broadcasting network, a Digital Multimedia Broadcasting (DMB) network, and the like are not limited thereto.

Hereinafter, the database 10, the food recommendation device 20, and the kitchen monitoring device 30 will be described in more detail with reference to FIGS. 2 to 4.

2 is a schematic configuration diagram of a constitution database for a food recommendation system in consideration of constitution based on big data according to an embodiment of the present application.

According to one embodiment of the present application, the database 10 may include a constitutional database and a collection database. The constitution database may include structured data in a plurality of tables. The collection database may include data collected from posts posted on the website. The collection database may be big data. In other words, the collection database may include a large amount of structured data or unstructured data sets.

Referring to FIG. 2, the constitutional database included in the database 10 may include a plurality of tables. In a database, a table is a collection of data sets (values) arranged using a model of vertical and horizontal lines. Also, a table is a collection of data in a suitable form for quick reference. A table is a two-dimensional table that shows the structure of data, and is managed in the form of rows and columns. By specifying a key, you can quickly and easily find the desired data. The data of each row of the table is called a record, and each column is called a field.

Also, the database 10 may include a plurality of non-standardized data. In other words, the database 10 may include a database (eg, a constitution database, a collection database) for generating recommended diet information. Here, the non-standardized data is data that has not been standardized. As an example, the database 10 may include a constitutional database and a collection database. The constitutional database may be a database in which data collected in advance is classified in a table classified by each feature. The collection database may be a database storing unstructured data collected from a website in NoSQL format. Illustratively, the constitutional database can be a database that includes structured data. The collection database may be a database including unstructured data.

As an example, the database 10 may include a plurality of tables including numerical data, character data, image data, and the like. Unstructured data, unstructured data, and unstructured data may refer to information that does not have a predefined data model or is not organized in a predefined manner. Unstructured data may mean unstructured data having different shapes and structures, such as pictures, images, and documents, unlike numeric data having a certain standard or shape. As another example, the database 10 may classify and store the unstructured data collected by the food recommendation device 20 into each table. In addition, the database 10 may store and store a plurality of recommended diet information generated by the food recommendation device 20. In addition, the database 10 may table and store user information provided from the user terminal 40. In addition, the database 10 may store the collected data collected by the food recommendation device 20 as a table.

In addition, the database 10 may include a constitutional database. Constitution table 111, disease table 112, food material classification table 113, food material table 114, medicine table 115, member information table 116, member disease table 117, beneficial food materials for each constitution and It may include at least one of the medicinal material table 118, harmful food ingredients and medicinal materials table 119, and a healthy diet table 120. As an example, each table may include a primary key. The primary key is a key selected from candidate keys. A NULL value cannot be entered, and an attribute selected as the primary key cannot have the same value. Hereinafter, items of a column and a field included in each of a plurality of tables may be primary keys of the corresponding table.

According to one embodiment of the present application, the constitution table 111 may be a table having a constitution name, a constitution ID, and a book size for each constitution as a column or a field. In other words, the constitution table 111 may include data (information) about the characteristics of the constitution, such as the constitution name, the constitution ID, and the number of books per constitution. For example, the constitution name field of the constitution table 111 may be divided into Taeum, Sun, Soyang, and Noise. In addition, the sieving name field of the sieving table 111 may be divided into eight sieving characteristics: shepherd, shepherd, weeping, masturbation, soil, toeum, geumyang, and geumum.

In addition, the disease table 112 may be a table in which a disease name, a disease ID, and an age group having a large number of diseases are columns and fields. In other words, the disease table 112 may include data (information) about the characteristics of the disease, such as the disease name, the disease ID, and the age of the disease. As an example, the disease table 112 may be a table storing characteristics for five diseases including adult disease, hypertension, diabetes, cerebrovascular disease, and myocardial infarction.

In addition, the food material classification table 113 may be a table having a food material classification name, a food material classification ID, and a food material ID as a column or a field. In other words, the food material classification table 113 may include data (information) about the characteristics of the food material, such as the food material classification name, the food material classification ID, and the food material ID. As an example, the food material classification table 113 may be a table that stores food material classification data (information) about whether it is a vegetable or a fruit.

In addition, the food material table 114 may be a table of food material name, food material ID, food material classification ID, and food material efficacy as columns and fields. In other words, the food material table 114 may include characteristic data (information) of the food material, such as the food material name, the food material ID, the food material classification ID, and the food material efficacy.

In addition, the medicinal material table 115 may be a table that uses the medicinal material name, the medicinal material ID, and the efficacy of the medicinal material as a column or field. In other words, the medicine table 115 may include data (information) about the characteristics of the medicine, such as the medicine name, the medicine ID, and the efficacy of the medicine.

In addition, the member information table 116 may be a table in which an individual's gender, age, constitution, and member ID are columns and fields. In other words, the member table 116 may include member data (information) such as an individual's gender, age, constitution, and member ID.

In addition, the member disease table 117 may be a table in which a disease ID of a member in a member ID included in the member ID included in the member table 116 is a column or field. . In other words, the member disease table 117 may include data (information) of diseases the member has, such as disease ID.

In addition, the beneficial food material and medicinal material table 118 may be a table having a constitution ID, a food material ID, and a medicine ID as a column or a field. In other words, the beneficial food material and medicinal material table for each constitution may include data (information) for classifying the beneficial food material for each constitution and the beneficial drug for each constitution.

In addition, the harmful food materials and medicinal materials table 119 may be a table having a constitution ID, a food material ID, and a medicine ID as a column or a field. In other words, the harmful food ingredients and medicinal materials table 119 may include data (information) that classifies harmful food materials by physique and harmful medicinal materials by constitution.

In addition, the healthy diet table 120 may be a table having a diet name, a diet ID, a food material ID, and a medicine ID as columns and fields. In other words, the healthy diet table 120 may include old data (information) of a diet in which beneficial foods and medicines are added in consideration of constitution and disease.

According to one embodiment of the present application, the collection database may include unstructured data collected by crawling a web page including a specific keyword in the data collection unit 21 of the food recommendation device 20.

3 is a schematic block diagram of a food recommendation apparatus for a food recommendation system considering a big data-based constitution according to an embodiment of the present application.

According to one embodiment of the present application, the food recommendation device 20 may include a data collection unit 21, a user information collection unit 22, a data analysis unit 23, and a data providing unit 24. However, the configuration of the food recommendation device 20 is not limited to this.

According to one embodiment of the present application, the data collection unit 21 may collect unstructured data related to constitution by crawling a web page including keywords related to constitution and diet. In other words, the data collection unit 21 may collect collection data including keywords related to constitution and diet from content described in at least one website among news articles, SNS, blogs, and communities. Crawling may mean collecting content existing on the web. The data collection unit 21 can import an HTML page, parse HTML/CSS, and the like, and extract only necessary data. Also, the data collection unit 21 may store the collected collection data in a collection database included in the database 10. As an example, the collection database may be NoSQL. The data collection unit 21 may collect structured and unstructured data from various sources.

For example, keywords related to constitution may include words (keywords) related to four constitutions: Taeum, Sun, Soyang, and Noise. In addition, keywords related to constitution, Mokyang (陽阳), Mokum (木陰), Suyang (水陽), masturbation (水陰), soil (土阳), Toeum (土陰), Geumyang (金陽), Geumum Eight constitutional characteristics related to (金陰) can include words (keywords). Keywords related to diet include animal protein, vegetable protein, carbohydrates (grains), oil (oil), root vegetables (root vegetables), vegetables (leaves, stem vegetables), herbs and seasonings, seaweeds, fruits, medicinal herbs, beverages, preferences It may include words (keywords) related to food. However, the constitution and diet and related keywords are not limited thereto.

In addition, the data collection unit 21 generates a URL based on keywords related to constitution and diet, and uses the generated URL to search for a site posted on the web. Then, an HTML file containing the searched side list and content body is fetched from the web. In addition, the data collection unit 21 performs encoding for Hangul support, extracts text data including specific keywords (keywords related to constitution and diet) among HTML file contents, and generates the extracted text data in txt format And save. In other words, the data collection unit 21 may obtain content information including keywords from the web based on keywords related to constitution and diet. Also, the data collection unit 21 may crawl a web page including keywords related to constitution and diet based on the content information. The data collection unit 21 may generate a URL including keywords related to constitution and diet and transmit it to the web, and receive an HTML file including search results from the web.

Meanwhile, the data analysis unit 23 may preprocess the crawled web page based on a predefined dictionary word. The preset dictionary word is a word including keywords related to constitution and diet, and may be a word arbitrarily designated by the user. The data analysis unit 23 may classify content text data that includes a preset word and content text data that does not contain a preset word. Also, the data analysis unit 23 may remove a preset removal text element from content text data including a preset predefined word.

According to another embodiment of the present disclosure, the user information collection unit 22 may receive keyword information related to constitution and diet from the user terminal 40. The data collection unit 21 obtains website information including keywords related to constitution and diet from the web based on keyword information related to constitution and diet, which is user input information received from the user information collection unit 22, and the web A web page included in a website may be crawled based on the site information. The data analysis unit 23 may perform text data analysis included in the crawled web page.

According to one embodiment of the present application, the user information collection unit 22 may receive user information including the user's constitution information and diet history information from the user terminal 40. The user information may include user constitution information, diet history information, consumption form, and diet consumption propensity information. In addition, the user information may include the user's age, gender, occupation, pregnancy status, smoking status, drinking status, disease history, drug information during taking, and allergy information. For example, the user's constitutional information may include Sasangin, Saeumin, Soyangin, and Soinin. In addition, the user's constitution information may include constitutional characteristic information classified into eight types: Geumyang, Geumum, Mokyang, Mokum, Soil, Toum, Weeping, and Masturbation. Further, the diet history information may include food and medicine information contained in food consumed by the user (member) every time. In addition, the diet history information may include information on the type and amount of food consumed by the user (member). In addition, the user information is member information, and may include information about a member's gender, age, constitution, illness, recently consumed food, and preferred food.

In addition, the user information collection unit 22 may receive user information from a hospital server, an oriental medicine server, a office server, a restaurant server, a weather server, a school server (meal server), and a service provider server connected through a network. User information collection unit 22 By collecting user information not provided from the user terminal 40 from various servers, it is possible to provide recommended diet information more suitable for the user's constitution.

The data analysis unit 23 may analyze the user's constitution based on the user information collected by the user information collection unit 22. For example, the data providing unit 24 may provide input items related to a user's constitution. The user information collection unit 22 may receive an input item related to the user's constitution. The data analysis unit 23 may analyze the user's constitution based on the input items related to the user's constitution. For example, input items related to the user's constitution include physique classification items, appearance and skeleton classification items, appearance development items, gait items, face color classification items, eye classification items, chest classification items, and skin classification items. can do. The data analysis unit 23 analyzes the user's constitution based on the collected user information, and thus can perform a more accurate constitution analysis than the user's constitution information provided to the user.

In addition, the user information collecting unit 22 may collect the user's SNS, card payment history, location information, etc. from the user terminal 40 when user information above a preset reference value is not received from the user terminal 40. . The data analysis unit 23 may analyze the user's diet history, consumption form, and dietary consumption propensity based on the user's SNS, card payment history, and location information collected by the user information collection unit 22. In other words, when the user information received from the user terminal 40 is insufficient, the user information collection unit 22 may generate user information using information collectable from the user terminal 40. For example, the data analysis unit 23 may analyze the user's diet history by analyzing at least one of posts, photos, and videos of the user's SNS, and generate diet history information. In addition, the data analysis unit 23 may derive consumption type and diet consumption propensity information based on the user's card payment history information. In addition, the data analysis unit 23 may generate diet history information such as a user's diet history and consumption form, based on GPS information collected from the user terminal 40. When the GPS information collected from the user terminal 40 is collected for a predetermined time or more (a time when the user stays at a specific restaurant and eats), the data analysis unit 23 based on the information, the user's diet history and consumption form You can generate information such as diet history.

According to one embodiment of the present application, the data analysis unit 23 may perform association rule analysis between at least one of constitution data included in the constitution database and collection data included in the collection database and user information. In addition, the data analysis unit 23 may generate a plurality of recommended diet information in consideration of the user's constitution using the analyzed result. For example, the data analysis unit 23 may perform association rule analysis that analyzes a relationship between diets based on collected data such as an individual's diet history. The data analysis unit 23 may grasp the mutual relationship between the plurality of data based on the user's constitution, and group them into groups of similar tendencies to generate a plurality of recommended diet information. In other words, the data analysis unit 23 may generate a plurality of recommended diet information in consideration of taste and constitution information similar to a user.

Association rule learning is a rule-based machine learning method for discovering relationships between variables in a large database. Association rules are expressed as X=>Y. For example, if the association rule between constitutions is {Geumyang, Geumum}=>{Sunin}, the user of the constitution of {Geumyang, Geumum} may be interpreted as the Suninin rule.

For example, the recommended diet information may include recipe information composed of beneficial (beneficial) food ingredients ingested by users of the Geumyang constitution. For example, the beneficial (beneficial) food materials consumed by users of Geumyang Constitution are all sea fish, crab, shellfish, rice, barley, buckwheat, red beans, mung beans, wormwood, cucumber, eggplant, cabbage, cabbage, lettuce, and other blues. Vegetables, fern, salted fish, glucose, cocoa, chocolate, banana, strawberry, peach, cherry, persimmon, melon, quince, ice, acidic water, glucose injection, and the like. The recommended diet information may provide a recipe using sea fish, which is a beneficial food material consumed by users of the Geumyang constitution.

Analysis of association rules performed by the data analysis unit 23 may be performed by applying at least one of the Apriori algorithm, FP growrh algorithm, and DHP algorithm, but is not limited thereto, and various association rules developed or developed in the future Analysis algorithms can be applied.

In addition, the data analysis unit 23 may build an artificial neural network through learning that inputs a plurality of data included in the constitution database and the collection database and outputs items related to diet results for each constitution. In addition, the data analysis unit 23 may generate recommended diet information by inputting the user information collected by the user information collection unit 22 into the constructed artificial neural network. The data analysis unit 23 artificially through learning to input the unstructured data collected by crawling a web page from the structured data and the data collection unit 21 included in the constitutional database, and output items related to dietary results for each constitution. You can build neural networks. In addition, the data analysis unit 23 may update and build an artificial neural network using big data. Here, the big data may be data collected by the data collection unit 21. For example, the artificial neural network may be a deep learning neural network, but is not limited thereto, and various neural network systems developed or developed in the future may be applied.

For example, the data analysis unit 23 calculates a plurality of data (for example, constitutional data and collected data) included in the constitutional database and the collection database, based on a non-supervised learning-based clustering algorithm, and generates a group pattern having a similar tendency. can do. Unsupervised learning refers to an algorithm that analyzes or clusters data itself, rather than constructing learning data. The data analysis unit 23 may calculate a group pattern by clustering based on a clustering algorithm. For example, a logistic regression algorithm, a random forest algorithm, a support vector machine (SVM) algorithm, a decision algorithm, and a clustering algorithm may be used as the clustering algorithm for unsupervised learning.

In addition, in addition to the above-described algorithm, the data analysis unit 23 may also use cluster algorithms such as Extra Tree algorithm, XG Boost algorithm and Deep Learning algorithm, K-means clustering algorithm, SOM (Self-Organizing-Maps) algorithm EM & Canopy algorithm. Can conduct unsupervised learning. The Random Forest algorithm is an algorithm in which numerous Decision Trees form a Forest and averages each prediction result as one result variable. The SVM algorithm determines the classification to which the data belongs by classifying the boundary of the largest width in the distribution space of the data. It is a non-stochastic algorithm. The Extra Tree algorithm is similar to the Random forest, but is faster than the Random forest, and the XGBoost algorithm is a boost algorithm that applies the result of the XGBoost Tree to the next tree if the Tree of the Random Forest is independent. Deep Learning Algorithm is an algorithm that learns by adjusting the effect of variable patterns on results based on a multi-layered neural network. In addition, the K-means clustering algorithm is a traditional classification technique that iteratively subdivides the target group into K clusters based on the average value (similarity) of the distance, and the SOM algorithm weights the input pattern of the training set based on the artificial neural network. It is a technique of learning and clustering. In addition, the EM & Canopy algorithm refers to a technique of updating and clustering parameter values through an iterative process from the maximum likelihood with a given initial value.

In addition, the data analysis unit 23 may generate a plurality of recommended diet information based on the user input information received from the user information collection unit 22. For example, the user information collection unit 22 may receive user input information related to an evaluation item of recommended diet information. For example, the evaluation item of the recommended diet information may be an item including satisfaction, normal, and dissatisfaction. The user information collection unit 22 may receive user input information that has been evaluated by the user who selected at least one of the plurality of recommended diet information generated by the data analysis unit 23. The data analysis unit 23 may assign 3 points, 2 points, and 1 point to items including each satisfaction, normal, and dissatisfaction, and calculate an evaluation score of the recommended diet. In addition, the data analysis unit 23, based on the evaluation item scores for the recommended diet information, when the user information similar to the first user is input, prioritizes the recommended diet information whose evaluation score is greater than or equal to the reference value, and the plurality of recommended diet information Can generate For example, when the data analysis unit 23 inputs second user information similar to the first user (for example, a woman, a constrictor, and a cucumber allergy), an evaluation score among recommended diet information provided to the first user The first recommendation diet information that is greater than or equal to the reference value may be given with priority.

In addition, the data analysis unit 23 may analyze specific diet information when receiving specific diet information from the user information collection unit 22, and the data analysis unit 23 includes constitution information of the user included in the user information It is possible to determine whether the suitability is with and if the determination result is impossible, it is possible to generate replaceable food material information among food material information included in specific diet information. For example, the specific diet information may be information generated when a user cooks and eats food or visits a restaurant. The user information collection unit 22 may receive the first specific diet information from the user terminal 40. The first specific diet information may include a recipe using meat, cabbage, and other green vegetables. The data analysis unit 23 may determine whether the user's constitution information included in the user information is suitable for the first specific diet information. The data analysis unit 23 may determine that the user's constitution information included in the user information is a Geumyang constitution, and may generate food material information to replace meat meat with sea fish among the food material information included in the first specific diet information.

In addition, the data analysis unit 23 may perform analysis of association rules between the collected content text data and preset predefined words. The preset dictionary word is a word including keywords related to constitution and diet, and may be a word arbitrarily designated by the user. For example, the data analysis unit 23 may perform analysis of association rules with the collected content text data when the preset predefined words are Taein, Taeumin, Soyangin, and Soumin. As a result of the analysis of the association rules of the data analysis unit 23, in the case of the sun, text data related to the development of the upper part of the chest, the thick neck and the large head, the strong eyes, and the lower part of the waist and lower back are included. It can be understood that content text data is mainly collected. However, the above-described example is only one embodiment, and more various embodiments may exist.

According to one embodiment of the present application, the data providing unit 24 may visualize and provide a plurality of recommended diet information generated in consideration of the user's constitution with the user terminal 40. The data providing unit 24 may help to set detailed values for generating recommended diet information by providing the information visualized by the GUI to the user terminal 40. In addition, the data providing unit 24 may output the generated plurality of recommended diet information in a graph and tag cloud. The data providing unit 24 may graphically output the result of the association rule analysis analyzed by the data analysis unit 23. The data analysis unit 23 may provide the result of the analysis in association with the identifier of the result of the association rule analysis, and the data providing unit 24 may provide the result of the association rule analysis to the user terminal 40.

4 is a schematic block diagram of a kitchen monitoring apparatus for a food recommendation system considering a big data-based constitution according to an embodiment of the present application.

Referring to FIG. 4, the kitchen monitoring device 30 may include a display unit 31, an environment information collection unit 32, and a control unit 33. However, the kitchen monitoring device 30 is not limited thereto. For example, the kitchen monitoring device 30 is a determination unit (not shown) for determining food and drug information included in the recommended diet information provided from the food recommendation device 20 and food and drug information provided in one area of the kitchen. City).

According to an embodiment of the present application, the display unit 31 is provided in one area of the kitchen and may output a plurality of recommended diet information provided from the food recommendation device. The display unit 31 includes a PDP (Plasma Display Panel), an LCD (Liquid Crystal Display), a thin film liquid crystal display (TFT-LCD, Thin Film Transistor LCD), and an LED (Light) that can display various information such as images or images. It may mean a flat panel display device such as an emitting diode (OLED), an organic LED (OLED), a retina display, and a dynamic scattering display panel, but is not limited thereto. By outputting a plurality of recommended diet information provided from the food recommendation device through the display unit 31, a user can process food more easily. The recommended diet information may include a food recipe (recipe).

According to an embodiment of the present application, the environmental information collection unit 32 may collect environmental information of a food warehouse and a kitchen using a plurality of sensors. The environment information collection unit 32 may provide information collected from a plurality of sensors to the display unit 31. Also, the environment information collection unit 32 may provide information collected from a plurality of sensors to the user terminal 40. For example, the plurality of sensors may include a temperature sensor, a humidity sensor, a flame flame sensor, a gas smoke sensor, an image acquisition sensor, and the like. The temperature and humidity sensor can measure the temperature and humidity of food warehouses and kitchens where food materials are stored. The flame flame detection sensor can detect a fire using infrared rays. In addition, the gas detection sensor is a sensor that detects harmful gas, and can detect combustible gas and smoke such as city gas, carbon monoxide, hydrogen, LPG, butane, methane, and alcohol.

In addition, the environment information collection unit 32 may provide a sensing unit sensed result from a plurality of sensors to the display unit 31. Sensing results detected from a plurality of sensors may include temperature and humidity data of food warehouses and kitchens that store food and medicines, infrared wavelength data by heat radiation derived from a flame, and harmful gas data information. In other words, the display unit 31 can display (output) temperature and humidity data of food warehouses and kitchens storing food materials and medicines, infrared wavelength data by heat radiation derived from a flame, and detection amount of harmful gas data. have.

According to one embodiment of the present application, when the collection result of the environmental information collection unit 32 is not included in the preset reference value, the control unit 33 may include at least one kitchen among a plurality of kitchen devices provided in the food warehouse and the kitchen. It is possible to generate a control signal to control the driving of the device. For example, when the temperature of the food warehouse equipped with food and medicine materials is not included in a preset reference value (for example, 5 degrees or less in the refrigerator compartment and 18 degrees or less in the freezer compartment), the control unit 33 is a kitchen device (eg For example, a control signal for controlling the operation of the refrigerator compartment or the freezer compartment may be generated. In addition, when the harmful gas data in the kitchen is greater than or equal to a preset reference value, the control unit 33 may generate a control signal that controls the driving of the kitchen device (eg, a ventilator) for circulating air.

According to another embodiment of the present application, the determination unit (not shown) may determine the similarity between food and medicine provided in a specific area based on the recommended diet information provided to the data providing unit 23. For example, a specific area may be an area capable of obtaining image information from the display unit 31. The display unit 31 may generate food materials provided by the user for cooking as image information using a photographing device (camera). The determination unit (not shown) may use the image information to determine whether or not the food materials included in the recommended diet information match, and if the food materials do not match, may recommend replaceable food materials.

According to an embodiment of the present application, the food recommendation device 20 may query information of a user (member) stored in the database 10. The member information inquiry may include information about a member's gender, age, constitution, illness, recently consumed food, and preferred food. The food recommendation device 20 may query the constitution information stored in the constitution database. The constitutional information inquiry may include information about beneficial ingredients and medicinal materials, harmful food ingredients and medicinal materials for a member's constitution. The food recommendation device 20 may recommend food customized for a member based on member information. In other words, the food recommendation device 20 may generate recommended diet information. The customized food recommendation (recommended diet information) may include three or more foods excluding recently consumed foods and foods harmful to the member's constitution among the food types preferred by the member. The food recommendation device 20 provides customized food information (recommended diet information) to the user terminal 40, and the user provides at least one food information (recommended diet information) among a plurality of customized food information (recommended diet information). You can choose. In other words, the user may select a food or recipe to be provided from among a plurality of customized food information (recommended diet information). The food recommendation device 20 may delete harmful food ingredients of the user's constitution based on the user's selection information. The food recommendation device 20 may query beneficial food materials that can replace the deleted harmful food materials. The search for food materials that can be replaced may refer to food materials that can replace the taste and aroma of food materials and medicines. The food recommendation device 20 may determine whether the replaceable foodstuff is a foodstuff beneficial to the member. The food recommendation device 20 may add the beneficial foodstuff to the customized food information selected by the user, provide food to which the beneficial foodstuff and medicine are added to the user terminal 40, or provide a recipe (cooking method) for the food. have.

Hereinafter, based on the details described above, the operation flow of the present application will be briefly described.

5 is an operation flowchart for a food recommendation method considering a big data-based constitution according to an embodiment of the present application.

The food recommendation method considering the constitution based on the big data shown in FIG. 5 may be performed by the food recommendation device 20 described above. Therefore, even if omitted, the description of the food recommendation device 20 may be equally applied to the description of the food recommendation method considering the big data-based constitution.

In step S501, the food recommendation device 20 may collect unstructured data by crawling a web page including keywords related to constitution and diet.

In step S502, the food recommendation device 20 may receive user information including user's constitution information and diet history information from the user terminal 40.

In step S503, the food recommendation device 20 may perform association rule analysis between at least one of constitution data and collection data included in the database 10 and the user information.

In step S504, the food recommendation device 20 may generate a plurality of recommended diet information in consideration of the user's constitution using the analyzed result.

In step S505, the food recommendation device 20 may provide the user terminal 40 by visualizing and providing a plurality of recommended diet information.

In the above description, steps S501 to S506 may be further divided into additional steps or combined into fewer steps, depending on the implementation herein. In addition, some steps may be omitted if necessary, and the order between the steps may be changed.

The food recommendation method considering a constitution based on big data according to an embodiment of the present application may be implemented in a form of program instructions that can be executed through various computer means and may be recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, or the like alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and available to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, and magnetic media such as floptical disks. Includes hardware devices specifically configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language code that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa.

In addition, the above-described food recommendation method considering the constitution of the big data may be implemented in the form of a computer program or application executed by a computer stored in a recording medium.

The above description of the present application is for illustrative purposes, and those skilled in the art to which the present application pertains will understand that it is possible to easily modify to other specific forms without changing the technical spirit or essential features of the present application. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present application is indicated by the claims below, rather than the detailed description, and it should be interpreted that all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof are included in the scope of the present application.

1: Food recommendation system
10: database
20: food recommendation device
30: kitchen monitoring device
40: user terminal

Claims (10)

In the food recommendation system considering the constitution of the big data,
A database including a sieving database and a collection database;
Analyze association rules based on the constitution data included in the constitution database and the collected data included in the collection database and user information provided from a user terminal, and provide a plurality of recommended diet information generated in consideration of the user's constitution Food recommendation device;
A kitchen monitoring device that outputs the plurality of recommended diet information on a display unit provided in one area of a kitchen, collects environmental information of a food warehouse and a kitchen using a plurality of sensors, and monitors the state of the food warehouse and the kitchen ; And
A user terminal that provides user information corresponding to a user input item provided in connection with constitution to the food recommendation device,
Including,
The food recommendation device,
A data collection unit crawling a web page including keywords related to constitution and diet to collect unstructured data related to constitution;
A user information collection unit for receiving user information including user's constitution information and diet history information from the user terminal;
A data analysis unit performing analysis of association rules between at least one of constitution data included in the constitution database and collection data included in the collection database and the user information; And
Data provision unit to visualize and provide a plurality of recommended diet information generated in consideration of the user's constitution with the user terminal,
Including,
The user information collection unit,
If the user information above a preset reference value is not received, collects the user's SNS, card payment details and location information from the user's terminal,
The data analysis unit,
Based on the user's SNS, card payment history and location information, analyzes the user's diet history, consumption patterns, and diet consumption propensity, and uses the analyzed results to generate a plurality of recommended diet information in consideration of the user's constitution,
To generate recommended diet information by inputting the user information collected in an artificial neural network constructed through learning that inputs a plurality of data included in the constitution database and the collection database and outputs items related to diet results for each constitution. ,
The artificial neural network,
Based on the unsupervised learning-based clustering algorithm, a group pattern having a similar tendency is calculated, wherein the clustering algorithm includes a logistic regression algorithm, a random forest algorithm, a support vector machine (SVM) algorithm, a decision algorithm, and a clustering algorithm,
The kitchen monitoring device,
A judging unit for judging the similarity between the food material information included in the recommended diet information provided to the data providing unit and the image information generated by photographing food materials provided in a specific area to prepare the recommended diet; And
A display unit provided in one area of the kitchen and outputting a plurality of recommended diet information provided from the food recommendation device,
Including,
The display unit,
The image material of the food material provided in a specific area is generated using a photographing device using the food material provided by the user for cooking,
The determination unit,
The food recommendation system is to determine the similarity between the image information and the food material information included in the recommended diet information, and to recommend alternative food materials when the food materials do not match. delete According to claim 1,
The data collection unit,
Collecting data including keywords related to constitution and diet from content described on at least one website among news articles, SNS, blogs, and communities,
The database,
Food collection system that stores the collected data collected by the data collection unit in the collection database. According to claim 1,
The user information receiving unit,
Receiving user input information related to the evaluation item of the recommended diet information,
The data analysis unit,
When the user information similar to the first user is input based on the evaluation item information on the recommended diet information, the recommendation diet information having an evaluation score equal to or greater than a reference value is given priority to generate the plurality of recommended diet information. Recommendation system. According to claim 1,
The data analysis unit,
When specific diet information is provided from the user information collection unit, analyzes the specific diet information, determines whether the user's constitutional information included in the user information is appropriate,
When the determination result is impossible, the food recommendation system is to generate replaceable foodstuff information among foodstuff information included in the specific diet information. According to claim 1,
The constitution database,
Constitution table, disease table, food material classification table, food material table, medicine table, member information table, member disease table, constitutional beneficial food and medicine table, constitutional harmful food and medicine table, health diet table , Food recommendation system. delete According to claim 1,
The kitchen monitoring device,
An environmental information collection unit for collecting environmental information of the food warehouse and kitchen using a plurality of sensors; And
If the environmental information collection result is not included in the preset reference value, a control unit for generating a control signal for controlling the operation of at least one of the plurality of kitchen devices provided in the food warehouse and kitchen,
That includes, food recommendation system. delete delete

Images