KR102564996B1 - Method, device and system for providing user customized health functional food curation service based on artificial intelligence - Google Patents

Abstract

According to one embodiment, in the method for providing a user-customized health functional food curation service based on artificial intelligence, performed by an apparatus, blood type, constitution, age, preferred food, disease diagnosis, drug treatment, smoking, and drinking and providing a basic information input page for inputting basic information including whether or not to exercise to a first user terminal; obtaining basic information of the first user from the first user terminal when the basic information of the first user is input through the basic information input page; transmitting a request for consent to provide information on biometric information including body temperature, electrocardiogram, blood pressure, and body composition to the first user terminal; obtaining biometric information of the first user from a first wearable device worn on the body of the first user when consent to provide information on the biometric information of the first user is received from the first user terminal; Transmitting a request for consent to provide an image for a face image to the first user terminal; acquiring a first image generated by photographing the face of the first user from the first user terminal when photographing the face of the first user is performed using the camera of the first user terminal; The first image is compared with the pre-trained average face image of the first user, the mood and condition of the first user is analyzed, and based on the analysis result of the mood and condition of the first user, the first user's mood and condition are analyzed. generating user status information; generating health information of the first user by matching basic information of the first user, biometric information of the first user, and condition information of the first user; applying the health information of the first user to an artificial neural network and selecting a recommended health functional food for the first user based on an output of the artificial neural network; determining whether the first user has ever purchased the first food, based on a food purchase history of the first user, when the first food is selected as the first user's recommended health functional food; and providing recommendation information for recommending the first food to the first user terminal when it is determined that the first user has never purchased the first food. A method for providing a curation service is provided.

Description

AI-based user-customized health functional food curation service provision method, device, and system

The following embodiments relate to technologies for providing user-customized health functional food curation services based on artificial intelligence.

Pharmaceuticals refer to those used for treatment or prevention stored in pharmacies, etc., and health functional foods refer to foods manufactured using ingredients useful for human health promotion or health purposes.

Medicines include specialized medicines prescribed by doctors in hospitals and stored at pharmacies, and general medicines sold at pharmacies without a prescription.

There are many types of health functional foods, and since consumers have to consider many things in order to select such health functional foods, it is very difficult to find health functional foods that are suitable for them.

Therefore, there is an increasing demand for information on health functional foods that are suitable for users themselves, and research on related technologies is required.

Korean Patent Registration No. 10-2405676 Korean Patent Publication No. 10-2022-0152907 Korean Patent Publication No. 10-2022-0101876 Korean Patent Publication No. 10-2020-0117218

According to one embodiment, an object of the present invention is to provide a method, apparatus, and system for providing a user-customized health functional food curation service based on artificial intelligence.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned will be clearly understood from the description below.

According to one embodiment, in the method for providing a user-customized health functional food curation service based on artificial intelligence, performed by an apparatus, blood type, constitution, age, preferred food, disease diagnosis, drug treatment, smoking, and drinking and providing a basic information input page for inputting basic information including whether or not to exercise to a first user terminal; obtaining basic information of the first user from the first user terminal when the basic information of the first user is input through the basic information input page; transmitting a request for consent to provide information on biometric information including body temperature, electrocardiogram, blood pressure, and body composition to the first user terminal; obtaining biometric information of the first user from a first wearable device worn on the body of the first user when consent to provide information on the biometric information of the first user is received from the first user terminal; Transmitting a request for consent to provide an image for a face image to the first user terminal; acquiring a first image generated by photographing the face of the first user from the first user terminal when photographing the face of the first user is performed using the camera of the first user terminal; The first image is compared with the pre-trained average face image of the first user, the mood and condition of the first user is analyzed, and based on the analysis result of the mood and condition of the first user, the first user's mood and condition are analyzed. generating user status information; generating health information of the first user by matching basic information of the first user, biometric information of the first user, and condition information of the first user; applying the health information of the first user to an artificial neural network and selecting a recommended health functional food for the first user based on an output of the artificial neural network; determining whether the first user has ever purchased the first food, based on a food purchase history of the first user, when the first food is selected as the first user's recommended health functional food; and providing recommendation information for recommending the first food to the first user terminal when it is determined that the first user has never purchased the first food. A method for providing a curation service is provided.

The artificial intelligence-based user-customized health functional food curation service providing method, when it is confirmed that the first user has purchased the first food, based on the food purchase history of the first user, the first user checking a first number, which is the number of times the first food has been purchased; registering the first food as a health functional food consumed by the first user when it is confirmed that the first number is greater than a preset reference number; checking a first date, which is the last date the first food was purchased, and a first quantity, which is the number of first foods purchased on the first date, based on the food purchase history of the first user; calculating a second period by multiplying the first period by the first quantity when the intake period of the first food is determined to be the first period; and when it is determined that the first user has not additionally purchased the first food from the first date until the second period elapses, a notification message requiring additional purchase of the first food is sent to the first user. The step of transmitting to the terminal may be further included.

The artificial intelligence-based user-customized health functional food curation service providing method may include, when a plurality of foods are selected as recommended health functional foods for the first user, classifying the selected plurality of foods into a recommended food group; if it is confirmed that the recommended food group includes the food that the first user has purchased, excluding the food that the first user has purchased from the recommended food group; providing recommendation information recommending the first food to the first user terminal when it is determined that only the first food is included in the recommended food group; grouping users having a health condition similar to that of the first user based on the health information of the first user and classifying them into a first user group when it is determined that a plurality of foods are included in the recommended food group; ; Based on the food purchase history of each of the users included in the first user group, it is checked whether the users included in the first user group have ever purchased foods classified as the recommended food group, and the recommended food Calculating the number of purchasers and the number of purchases for each food included in the group; setting a first weight based on the number of purchasers and a second weight based on the number of purchases for each food included in the recommended food group; Calculating a recommendation score by adding the first weight and the second weight for each food included in the recommended food group; and providing recommendation information recommending the first food to the first user terminal when the food having the highest recommendation score among the foods included in the recommended food group is identified as the first food. there is.

According to one embodiment, by selecting a user's recommended health functional food based on the user's health information and providing recommendation information recommending the selected food, a user-customized health functional food is recommended to suit the user's health well. It has the effect of helping to check the information of functional food.

On the other hand, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
2 is a flowchart illustrating a process of generating health information of a user according to an exemplary embodiment.
3 is a flowchart illustrating a process of recommending a user-customized health functional food based on user's health information according to an embodiment.
4 is a flowchart illustrating a process of providing a notification service for additional purchase of health functional food consumed by a user according to an embodiment.
5 is a flowchart illustrating a process of recommending a user-customized health functional food when one food is included in a recommended food group according to an embodiment.
6 is a flowchart illustrating a process of recommending a user-customized health functional food when a plurality of foods are included in a recommended food group according to an embodiment.
7 is a flowchart illustrating a process of acquiring a first list that is a list of ingredients of a first food according to an embodiment.
8 is a flowchart illustrating a process of acquiring a second list that is a list of ingredients of a second food according to an embodiment.
9 is a flowchart illustrating a process of recommending an alternative health functional food according to an embodiment.
10 is a flowchart illustrating a process of providing information on recommended foods that can be supplemented according to an embodiment.
11 is a flowchart illustrating a process of providing a notification service for adjusting intake of health functional food according to an embodiment.
12 is a diagram for explaining learning of an artificial neural network according to an embodiment.
13 is an exemplary diagram of a configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

In an embodiment, an artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, a machine learns and judges on its own. The more the AI system is used, the higher the recognition rate and the more accurately the seller's taste can be understood, so the existing rule-based smart system is gradually being replaced by a deep learning-based AI system.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithm technology that classifies/learns the characteristics of input data by itself, and element technology is a technology that uses machine learning algorithms such as deep learning to mimic functions such as recognition and judgment of the human brain. It consists of technical fields such as understanding, inference/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology for recognizing and applying/processing human language/characters, including natural language processing, machine translation, dialogue systems, question and answering, voice recognition/synthesis, and the like. Visual understanding is a technology for recognizing and processing objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, space understanding, image improvement, and the like. Inference prediction is a technique of reasoning and predicting logically by judging information, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology for controlling the autonomous driving of a vehicle and the movement of a robot, and includes motion control (navigation, collision, driving), manipulation control (action control), and the like.

In general, in order to apply machine learning algorithms to real life, learning is performed in a trial and error method due to the nature of the basic methodology of machine learning. In particular, deep learning requires hundreds of thousands of iterations. It is impossible to execute this in an actual physical external environment, so instead, the actual physical external environment is virtually implemented on a computer and learning is performed through simulation.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to FIG. 1 , a system according to an embodiment may include a plurality of user terminals 100 and a device 200 capable of communicating with each other through a communication network.

First, a communication network may be configured regardless of its communication mode, such as wired or wireless, and may be implemented in various forms so that communication between servers and communication between servers and terminals is performed.

Each of the plurality of user terminals 100 may be implemented as a computing device having a communication function, and may be implemented as, for example, a mobile phone, desktop PC, laptop PC, tablet PC, smart phone, etc., but is not limited thereto. and may be implemented in various types of communication devices that can be connected to external servers.

The plurality of user terminals 100 are terminals used by users who want to receive a user-customized health functional food curation service, a first user terminal 110 used by a first user and a second terminal used by a second user. It may include a user terminal 120, a third user terminal 130 used by a third user, and the like.

Each of the plurality of user terminals 100 may be configured to perform all or part of an arithmetic function, a storage/reference function, an input/output function, and a control function of a normal computer. The plurality of user terminals 100 may be configured to communicate with the device 200 by wire or wireless.

Each of the plurality of user terminals 100 is connected to a web page operated by a person or organization that provides a service using the device 200, or is developed and distributed by a person or organization that provides a service using the device 200. An application may be installed. Each of the plurality of user terminals 100 may be linked with the device 200 through a web page or application.

Each of the plurality of user terminals 100 may access the device 200 through a web page or application provided by the device 200 .

Hereinafter, for convenience of description, the operation of the first user terminal 110 will be mainly described, but other user terminals such as the second user terminal 120 can perform the operation of the first user terminal 110 instead. am.

The device 200 may be a server owned by a person or organization that provides services using the device 200, may be a cloud server, or may be a peer-to-peer (p2p) set of distributed nodes. may be The device 200 may be configured to perform all or some of the arithmetic function, storage/reference function, input/output function, and control function of a normal computer. The device 200 may include one or more artificial neural networks that perform an inference function.

The device 200 may be configured to communicate with a plurality of user terminals 100 by wire or wirelessly, control the operation of each of the plurality of user terminals 100, and display certain information on the screen of each of the plurality of user terminals 100. You can control what is displayed.

The device 200 may be implemented as a server that provides a user-customized health functional food curation service, and may provide a platform service for health functional food curation.

Meanwhile, for convenience of explanation, FIG. 1 shows only the first user terminal 110, the second user terminal 120, and the third user terminal 130 among the plurality of user terminals 100, but the number of terminals is It can vary from case to case. As long as the processing capacity of the device 200 allows, the number of terminals is not particularly limited.

According to one embodiment, in providing a user-customized health functional food curation service, the device 200 selects a user-customized health functional food based on artificial intelligence and provides recommendation information recommending the selected food to the user. can be provided to

In the present invention, artificial intelligence (AI) means a technology that imitates human learning ability, reasoning ability, perception ability, etc., and implements it with a computer, and concepts such as machine learning and symbolic logic can include Machine learning (ML) is an algorithm technology that classifies or learns the characteristics of input data by itself. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the result of the analysis, and can make judgments or predictions based on the result of the learning. In addition, technologies that mimic the functions of the human brain, such as recognition and judgment, using machine learning algorithms, can also be understood as artificial intelligence. For example, technical fields such as linguistic understanding, visual understanding, inference/prediction, knowledge expression, and motion control may be included.

Machine learning may refer to processing that trains a neural network model using experience of processing data. Through machine learning, computer software could mean improving its own data processing capabilities. A neural network model is constructed by modeling a correlation between data, and the correlation may be expressed by a plurality of parameters. The neural network model derives a correlation between data by extracting and analyzing features from given data, and optimizing the parameters of the neural network model by repeating this process can be referred to as machine learning. For example, a neural network model may learn a mapping (correlation) between an input and an output with respect to data given as an input/output pair. Alternatively, even when only input data is given, the neural network model may learn the relationship by deriving a regularity between given data.

An artificial intelligence learning model or a neural network model may be designed to implement a human brain structure on a computer, and may include a plurality of network nodes having weights while simulating neurons of a human neural network. A plurality of network nodes may have a connection relationship between them by simulating synaptic activities of neurons that transmit and receive signals through synapses. In the artificial intelligence learning model, a plurality of network nodes can send and receive data according to a convolutional connection relationship while being located in layers of different depths. The artificial intelligence learning model may be, for example, an artificial neural network model, a convolutional neural network model (CNN), and the like. As an embodiment, the artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, Ada-boost , Perceptron, Genetic Programming, Clustering, etc. may be used.

Of these, CNNs are a type of multilayer perceptrons designed to use minimal preprocessing. A CNN consists of one or several convolution layers and general artificial neural network layers on top, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize the input data with a two-dimensional structure. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back-propagation. CNNs are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computational power, combined with algorithmic advances such as piecewise linear unit and dropout training, have greatly improved many computer vision tasks. With huge data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. To this end, a distributed, scalable implementation of deep neural networks can be used.

2 is a flowchart illustrating a process of generating health information of a user according to an exemplary embodiment.

Referring to FIG. 2 , first, in step S201 , the device 200 may receive a user-customized health functional food recommendation request from the first user terminal 110 . Here, the user-customized health functional food recommendation request is a request to recommend a customized health functional food that suits the user himself, and the first user selects a user-customized health functional food recommendation menu through the first user terminal 110. Upon selection, the first user terminal 110 may transmit a user-customized health functional food recommendation request to the device 200 .

When a user-customized health functional food recommendation request is received from the first user terminal 110, the device 200 checks a first user account logged in to the first user terminal 110 to obtain first user information. can At this time, the device 200 checks the first user account logged in to the first user terminal 110, searches the user information stored in the database through the first user account, and obtains the first user information from the database. can Here, the first user information is user information about the first user, and may include personal information and personal information of the first user.

According to one embodiment, in order to provide a user-customized health functional food curation service, the user's health information is required, and the user's health information is based on the user's basic information, the user's biometric information, and the user's condition information. can be created

That is, when the first user is identified through the first user information, the device 200 provides the first user's basic information, the first user's biometric information, and After each state information of the first user is obtained or generated, health information of the first user may be generated based on the basic information of the first user, the biometric information of the first user, and the state information of the first user.

Hereinafter, a process of generating health information of the first user will be described in detail.

In step S202, when receiving a user-customized health functional food recommendation request from the first user terminal 110, the device 200 may check whether there is basic information of the first user, and the basic information of the first user is If it is confirmed that there is not yet, a basic information input page for inputting basic information may be provided to the first user terminal 110, and the basic information input page may be displayed on the screen of the first user terminal 110. Here, the basic information input page may include an interface for inputting basic information, and the basic information includes blood type, constitution, age, preferred food, disease diagnosis, drug treatment, smoking, drinking, exercise, etc. information may be included.

In step S203, when the basic information of the first user is input through the basic information input page provided to the first user terminal 110, the device 200 obtains the basic information of the first user from the first user terminal 110. can do.

That is, when the basic information input page is displayed on the screen of the first user terminal 110 and the first user inputs the basic information of the first user through the first user terminal 110, the device 200 first Basic information of the first user may be obtained from the user terminal 110 .

Meanwhile, in step S204, when receiving a user-customized health functional food recommendation request from the first user terminal 110, the device 200 may check whether there is biometric information of the first user, and may determine whether biometric information of the first user exists. If it is confirmed that there is no information yet, a request for consent to provide information on biometric information may be transmitted to the first user terminal 110, and a notification requesting consent to provide information on biometric information may be displayed on the screen of the first user terminal 110. A message may be displayed. Here, the biometric information may include information on body temperature, electrocardiogram, blood pressure, body composition, and the like.

In step S205 , the device 200 may receive permission to provide information on biometric information of the first user from the first user terminal 110 .

That is, after a notification message requesting consent to provide information on biometric information is displayed on the screen of the first user terminal 110, the first user selects consent to provide information on biometric information through the first user terminal 110. If so, the device 200 may receive permission to provide information on biometric information of the first user from the first user terminal 110 .

In step S206, the device 200 may obtain biometric information of the first user from the first wearable device worn on the body of the first user.

According to an embodiment, a plurality of wearable devices and the device 200 may be directly connected, each of the plurality of wearable devices is connected to the plurality of user terminals 100, and the plurality of user terminals 100 are connected to the device 200. , the plurality of wearable devices and the device 200 may be indirectly connected through the plurality of user terminals 100 . To this end, a plurality of wearable devices may have a corresponding relationship with a plurality of user terminals 100 . For example, while the first wearable device is connected to the first user terminal 110 , the first user terminal 110 may be connected to the device 200 .

Each of the plurality of wearable devices may be implemented in the form of an accessory such as glasses, a watch, or a ring, or a form of clothing such as clothes or underwear, but may be implemented in various types of devices according to embodiments, without being limited thereto.

Each of the plurality of wearable devices may collect and provide changes in the user's body in real time, and for this purpose, various sensors may be mounted. Here, the sensor may include a camera, a photoplethysmogram (PPG) sensor, an electrocardiogram (ECG) sensor, and the like, and other various sensors for measuring a user's biosignal may be included.

That is, when the consent to provide information on the first user's biometric information is received from the first user terminal 110, the device 200 identifies the first wearable device connected to the first user terminal 110, Biometric information of the first user may be obtained from the first wearable device. In this case, the first wearable device is worn on the body of the first user and may generate biometric information by measuring the body temperature, electrocardiogram, blood pressure, and body composition of the first user.

Meanwhile, in step S207, when receiving a user-customized health functional food recommendation request from the first user terminal 110, the device 200 may check whether or not there is state information of the first user, and determine the state of the first user. If it is confirmed that there is no information yet, a request for consent to provide information on the face image may be transmitted to the first user terminal 110, and a notification requesting consent to provide information on the face image may be displayed on the screen of the first user terminal 110. A message may be displayed.

In step S208, the device 200, when photographing the face of the first user using the camera of the first user terminal 110, captures and generates the face of the first user from the first user terminal 110. A first image may be obtained.

That is, when a notification message requesting consent to provide information about a facial image is displayed on the screen of the first user terminal 110 and the first user selects consent to the provision of facial image through the first user terminal 110 , The first user terminal 110 may perform a photograph of the first user's face using a camera, and may store an image generated by photographing the first user's face as a first image, and the device 200 may A first image may be obtained from the first user terminal 110 .

In step S209, the device 200 compares the first image with the average facial image of the first user, analyzes the mood and condition of the first user, and based on the analysis result of the mood and condition of the first user, 1 User status information can be created. To this end, the average face image of the first user may be learned in advance and stored in the database.

Specifically, after recognizing the face of the first user in the first image, the device 200 may recognize each part of the face of the first user recognized in the first image, such as eyes, nose, mouth, chin, and the like. , After recognizing the face of the first user from the average face image of the first user, each part of the face of the first user recognized from the average face image of the first user, such as eyes, nose, mouth, and chin, may be recognized. there is.

Thereafter, the apparatus 200 may analyze the mood and condition of the first user by comparing each part recognized in the first image with each part recognized in the average facial image of the first user. Here, the average face image of the first user is an image representing the first user's usual mood and normal condition, and the device 200 compares the first user's average face image with the first image as a standard. A current mood and condition of the first user may be analyzed. At this time, the current mood of the first user may be divided into joy, sadness, pleasure, anger, anxiety, etc. and analyzed, and the current condition of the first user may be classified into very good, good, normal, bad, very bad, and analyzed. It can be.

Thereafter, the apparatus 200 may generate state information of the first user based on an analysis result of the mood and condition of the first user. Here, the state information of the first user may include an analysis result of the first user's current mood and condition.

In step S210, the device 200 determines that the basic information of the first user, the biometric information of the first user, and the status information of the first user are present, respectively, the basic information of the first user, the biometric information of the first user, and the first user's biometric information. Health information of the first user may be generated by matching state information of the first user.

3 is a flowchart illustrating a process of recommending a user-customized health functional food based on user's health information according to an embodiment.

According to one embodiment, each step shown in FIG. 3 may be performed after each step shown in FIG. 2 is performed.

Referring to FIG. 3 , first, in step S301, the device 200 may apply health information of the first user to the artificial neural network. Here, the artificial neural network may be an algorithm that receives user's health information, analyzes health functional foods that may be recommended to the user, and outputs information on the recommended health functional foods. The artificial neural network may be learned through a method described later with reference to FIG. 12 .

In step S302, the device 200 may select the first user's recommended health functional food based on the output of the artificial neural network.

For example, the device 200 applies the health information of the first user to the artificial neural network, and as a result of checking the output of the artificial neural network, if the output value is confirmed to be 1, the first user's recommended health functional food is set as the first food. and if the output value is confirmed as 2, the health functional food recommended by the first user may be selected as the second food.

According to an embodiment, the artificial neural network may be trained to analyze health functional foods that may be recommended to the user through health information of the user. Through this, the artificial neural network may analyze and output health functional foods that may be recommended to the user in consideration of the user's health condition.

In step S303, if the first food is selected as the recommended health functional food for the first user, the device 200 determines whether the first user has ever purchased the first food based on the food purchase history of the first user. You can check. To this end, the database of the device 200 stores information on food purchase history classified by user, and the device 200 searches the information stored in the database to obtain the food purchase history of the first user, In the food purchase history of the first user, it may be determined whether a purchase history for the first food exists. Here, the food purchase history of the first user is composed of a list of when and how much food was purchased, and may include information such as the name of the purchased product, the date of purchase, and the amount of purchase. Purchase details may be checked first.

If it is confirmed in step S303 that the first user has purchased the first food, step S401 may be performed, and a detailed description related to this will be described later with reference to FIG. 4 .

If it is determined in step S303 that the first user has never purchased the first food, in step S304, the device 200 may provide recommendation information recommending the first food to the first user terminal 110 . Here, the recommendation information for recommending the first food may include information on main features, effects, ingredients, price, link to a purchase page, and the like of the first food.

4 is a flowchart illustrating a process of providing a notification service for additional purchase of health functional food consumed by a user according to an embodiment.

Referring to FIG. 4 , first, in step S401, if it is determined that the first user has purchased the first food, the first user selects the first food based on the food purchase history of the first user. A first number of times, which is the number of times food is purchased, may be checked. At this time, the device 200 determines the number of purchases of the first food by calculating the number of purchases of the first food within a preset period of time (eg, the last year) based on the food purchase history of the first user. can

In step S402, the device 200 may check whether the first number is greater than the reference number. Here, the reference number of times may be set differently according to embodiments.

If it is determined in step S402 that the first number of times is not greater than the reference number, returning to step S401, the device 200 acquires the first user's food purchase history again after a certain period of time has elapsed, and the newly acquired first Based on the user's food purchase history, the number of times the first user has purchased the first food may be checked again.

If it is confirmed in step S402 that the first number is greater than the reference number, in step S403, the device 200 may register the first food as a health functional food consumed by the first user. Here, the health functional food consumed by the first user may refer to health functional food consumed regularly and steadily by the first user.

In step S404, the device 200 determines a first date, which is the date of last purchase of the first food, and a first quantity, which is the number of first foods purchased on the first date, based on the food purchase history of the first user. can

For example, if it is confirmed through the food purchase history of the first user that 20 pieces of the first food were purchased on January 1st, 15 pieces on February 1st, and 20 pieces on March 1st, the device (200 ) may identify March 1st, the last purchase date of the first food, as the first date, and 20 items purchased on March 1st as the first quantity.

In step S405, the device 200 may identify the intake period of the first food as the first period. At this time, the device 200 may confirm a recommended intake period of the first food based on the product information on the first food, and then identify the confirmed intake period as the first period.

For example, if the first food consists of 30 tablets and the intake method is determined to be consumed one tablet per day for one month, the device 200 sets the intake period of one month as the first food. period can be checked.

In step S406, the device 200 may calculate the second period by multiplying the first period by the first quantity.

For example, when the first period is 1 month and the first quantity is 3, the device 200 calculates 3, which is a value obtained by multiplying the first period and the first quantity, and uses the calculated 3 to convert 3 months to a second quantity. It can be set as a period.

In step S407, the device 200 may check whether the first user additionally purchases the first food until the second period elapses from the first date.

For example, when the first date is March 1 and the second period is 3 months, the device 200 provides the first user with the first food from March 1 to June 1, after 3 months have elapsed. You can check whether or not to purchase additionally. At this time, the device 200 periodically obtains the first user's food purchase history, and based on the periodically obtained first user's food purchase history, determines whether the first user additionally purchases the first food. can

If it is confirmed in step S407 that the first user has additionally purchased the first food before the second period elapses from the first date, the process returns to step S404, and the device 200 returns to the first user after a certain period of time has elapsed. The food purchase history of the user may be acquired again, and based on the newly acquired food purchase history of the first user, the last purchase date and quantity of the first food may be confirmed.

If it is determined in step S407 that the first user has not additionally purchased the first food from the first date until the second period elapses, in step S408, the device 200 notifies the user of the need to additionally purchase the first food. A message may be transmitted to the first user terminal 110 . Here, the additional purchase necessity notification message for the first food is a notification message informing that additional purchase is required for the first food product, and includes a first date, a second date, which is a date when a second period has elapsed from the first date, and a second date. It can include information about days left until the 2nd date, etc.

5 is a flowchart illustrating a process of recommending a user-customized health functional food when one food is included in a recommended food group according to an embodiment.

According to one embodiment, each step shown in FIG. 5 may be performed after step S302 is performed.

Referring to FIG. 5 , first, in step S501, when a plurality of foods are selected as recommended health functional foods for the first user, the device 200 may classify the selected plurality of foods into a recommended food group.

For example, the artificial neural network analyzes health functional foods that may be recommended to the first user based on the health information of the first user, and as a result, the first food, the second food, and the third food are the first user's recommended health function. food, and the device 200 determines that the first food, the second food, and the third food are selected as the first user's recommended health functional food based on the output of the artificial neural network, the first user Since a plurality of foods are selected as recommended health functional foods, the first, second, and third foods selected as recommended health foods of the first user may be classified as a recommended food group.

In step S502, the device 200 may check whether the recommended food group includes food that the first user has purchased.

Specifically, the device 200 checks whether there is a purchase history for each of the foods included in the recommended food group based on the food purchase history of the first user, and determines whether the first user has ever purchased a food in the recommended food group. You can check whether food is included or not.

For example, when the recommended food group includes first food and second food, and the first user's food purchase history includes the second food purchase history, the device 200 assigns the recommended food group to the recommended food group. It can be confirmed that the second food that the first user has purchased is included.

If it is confirmed in step S502 that the food that the first user has purchased is included in the recommended food group, in step S503, the device 200 may exclude the food that the first user has purchased from the recommended food group. there is.

For example, if it is confirmed that the first user has purchased the second food among the foods included in the recommended food group, the device 200 may exclude the second food from the recommended food group.

In step S502, if it is confirmed that the recommended food group does not include the food that the first user has purchased, the recommended food group inevitably includes a plurality of foods, and it is determined that the recommended food group includes a plurality of foods. If confirmed, step S601 may be performed. A detailed description related to this will be described later with reference to FIG. 6 .

In step S504, the device 200 may check whether one food is included in the recommended food group.

In step S504, when it is determined that not one food but a plurality of foods are included in the recommended food group, step S601 may be performed. A detailed description related to this will be described later with reference to FIG. 6 .

If it is determined in step S504 that one food is included in the recommended food group, in step S505, the device 200 may determine that only one first food is included in the recommended food group.

In step S506 , if it is determined that only one first food is included in the recommended food group, the device 200 may provide recommendation information recommending the first food to the first user terminal 110 .

6 is a flowchart illustrating a process of recommending a user-customized health functional food when a plurality of foods are included in a recommended food group according to an embodiment.

Referring to FIG. 6 , first, in step S601, if it is confirmed that a plurality of foods are included in the recommended food group, the device 200 determines a health condition similar to that of the first user based on health information of the first user. By grouping the users who have the device, it may be classified as a first user group.

For example, the device 200 identifies basic information of the first user based on the health information of the first user, and then selects users having a similar health status to that of the first user based on the basic information of the first user. Users who can be classified into the first user group and have a similar health condition to the first user based on the first user's biometric information after checking the first user's biometric information based on the first user's health information After selecting and classifying them into a first user group, based on the first user's health information, after checking the first user's condition information, a health condition similar to that of the first user is determined based on the first user's condition information. It is possible to select and classify the users having a first user group.

In step S602, the apparatus 200 determines whether the users included in the first user group have ever purchased foods classified as a recommended food group, based on the food purchase history of each of the users included in the first user group. After confirmation, the number of purchasers and the number of purchases may be calculated for each food included in the recommended food group.

For example, a first user, a second user, and a third user are classified as a first user group, a recommended food group includes first food, second food, and third food, and the food of the first user. The purchase history includes a purchase history of purchasing the first food twice and purchasing the second food three times, and the second user's food purchase history includes purchasing the first food twice and purchasing the second food three times. When one purchase history is included, and the third user's food purchase history includes a purchase history of purchasing the first food twice and purchasing the third food three times, the device 200 purchases the first food. As a result of checking the current status, since the first user has purchased the first food twice, the second user has purchased the first food twice, and the third user has purchased the first food twice, the number of purchases of the first food The number can be calculated as 3 and the number of purchases of the first food can be calculated as 6 times.

In step S603, the apparatus 200 may set a first weight based on the number of purchasers and set a second weight based on the number of purchases for each food included in the recommended food group. In this case, the first weight may be set to a higher value as the number of purchasers increases, and the second weight may be set to a higher value as the number of purchases increases.

For example, when the number of purchasers of the first food is 5 and the number of purchasers of the second food is 6, the apparatus 200 sets the first weight of the first food to 1.1 and sets the first weight of the second food to 1.1. Can be set to 1.2.

In addition, when the number of purchases of the first food is 5 times and the number of purchases of the second food is 6, the apparatus 200 sets the second weight of the first food to 1.1 and sets the second weight of the second food to 1.2. can be set

In step S604, the apparatus 200 may calculate a recommendation score by adding a first weight and a second weight for each food included in the recommended food group.

For example, when the first weight of the first food is 1.1 and the first weight of the first food is 1.2, the apparatus 200 sets the recommendation score of the first food to 230 through 2.3, which is the sum of 1.1 and 1.2. In this way, each recommendation score can be calculated for each identification included in the recommended food group.

In step S605, the device 200 may identify a food having the highest recommendation score among foods included in the recommended food group as the first food.

That is, when each recommendation score is calculated for each food included in the recommended food group, the apparatus 200 compares the calculated recommendation scores for each food and identifies the food with the highest recommendation score as the first food.

In step S606, if the food with the highest recommendation score among the foods included in the recommended food group is identified as the first food, the device 200 provides recommendation information recommending the first food to the first user terminal 110. can

7 is a flowchart illustrating a process of acquiring a first list that is a list of ingredients of a first food according to an embodiment.

According to one embodiment, each step shown in FIG. 7 may be performed after each step shown in FIG. 3 is performed.

Referring to FIG. 7 , first, in step S701, the device 200 may periodically receive biometric information of the first user from the first wearable device. Here, the first wearable device is worn on the body of the first user and may generate biometric information by measuring heart rate, oxygen saturation, body temperature, electrocardiogram, blood pressure, and body composition of the first user.

That is, the device 200 may receive the first user's biometric information from the first wearable device worn on the first user's body for each preset period. For example, the device 200 may receive biometric information of the first user once every 10 seconds from the first wearable device. Here, the biometric information may include measurement values obtained by measuring heart rate, oxygen saturation, body temperature, electrocardiogram, blood pressure, and body composition.

In step S702, the device 200 may confirm that the first food is input as the health functional food consumed by the first user at the first time.

Specifically, the first user may input information on the first food through the first wearable device at a first point in time, and through the first user terminal 110 connected to the first wearable device at a first point in time. Information on the first food may be input, and when the device 200 receives the information on the first food from the first wearable device or the first user terminal 110, the information consumed by the first user at the first time It may be confirmed that the first food is input as the health functional food. Here, the information on the first food may include information about the category, name, and first point of view of the first food.

In step S703, when the first food is input as the health functional food consumed by the first user at the first time, the device 200 retrieves the biometric information of the first user received at time 1-1, which is before the first time. It can be classified as first biometric information.

That is, in a state in which the device 200 periodically receives the biometric information of the first user from the first wearable device, when it is confirmed that the first food is input as the health functional food consumed by the first user at the first time, , Biometric information of the first user received at point 1-1, which is before the first point in time, may be classified as first biometric information.

In step S704, when the first food is input as the health functional food consumed by the first user at the first time, the device 200 converts the biometric information of the first user received at 1-2 points in time after the first point in time. It can be classified as second biometric information.

That is, in a state in which the device 200 periodically receives the biometric information of the first user from the first wearable device, when it is confirmed that the first food is input as the health functional food consumed by the first user at the first time, , Biometric information of the first user received at points 1-2 after the first point of time may be classified as second biometric information.

In step S705, the device 200 may compare the first biometric information and the second biometric information.

In step S706, the device 200 may determine whether or not there is an abnormality in the body of the first user as a result of comparing the first biometric information and the second biometric information. In this case, the device 200 may determine whether there is an abnormality in the body of the first user through an increase in heart rate, decrease in oxygen saturation, increase in blood pressure, and the like. That is, the device 200 may determine abnormalities in different ways according to the type of biometric information.

If it is determined that there is no abnormality in the body of the first user in step S706, the apparatus 200 may continue to periodically receive the biometric information of the first user from the first wearable device, returning to step S701.

If it is determined in step S706 that there is something wrong with the body of the first user, in step S707, the device 200 may obtain a first list that is a list of ingredients of the first food.

Specifically, in the database of the device 200, a list of ingredients included in each health functional food is stored separately for each health functional food, and the device 200 searches the ingredient list stored in the database to obtain the ingredients of the first food A first list, which is a list, may be obtained.

8 is a flowchart illustrating a process of acquiring a second list that is a list of ingredients of a second food according to an embodiment.

According to one embodiment, each step shown in FIG. 8 may be performed after each step shown in FIG. 7 is performed.

Referring to FIG. 8 , first, in step S801, after acquiring the first list, the device 200 may continuously and periodically receive biometric information of the first user from the first wearable device.

In step S802, the device 200 may confirm that the second food is input as the health functional food consumed by the first user at the second time point.

Specifically, the first user may input information on the second food through the first wearable device at a second point of view, and at the second point of view through the first user terminal 110 connected to the first wearable device. Information on the second food may be input, and when the device 200 receives the information on the second food from the first wearable device or the first user terminal 110, the first user consumes information at a second point in time. It may be confirmed that the second food is input as the health functional food. Here, the information on the second food may include information about the category, name, and second point of view of the second food.

In step S803, when the second food is input as the health functional food consumed by the first user at the second time, the device 200 retrieves the biometric information of the first user received at the time 2-1, which is before the second time. It can be classified as third biometric information.

That is, in the state in which the device 200 periodically receives the first user's biometric information from the first wearable device, if it is confirmed that the second food is input as the health functional food consumed by the first user at a second time point, , Biometric information of the first user received at point 2-1 prior to the second point in time may be classified as third biometric information.

In step S804, when the second food is input as the health functional food consumed by the first user at the second time, the device 200 converts the biometric information of the first user received at the 2-2 point in time after the second point in time. It can be classified as fourth biometric information.

That is, in the state in which the device 200 periodically receives the first user's biometric information from the first wearable device, if it is confirmed that the second food is input as the health functional food consumed by the first user at a second time point, , Biometric information of the first user received at point 2-2 after the second point in time may be classified as fourth biometric information.

In step S805, the device 200 may compare the third biometric information and the fourth biometric information.

In step S806, the device 200 may determine whether there is an abnormality in the body of the first user as a result of comparing the third biometric information and the fourth biometric information. In this case, the device 200 may determine whether there is an abnormality in the body of the first user through an increase in heart rate, decrease in oxygen saturation, increase in blood pressure, and the like. That is, the device 200 may determine abnormalities in different ways according to the type of biometric information.

If it is determined that there is no abnormality in the body of the first user in step S806, the apparatus 200 may continue to periodically receive the biometric information of the first user from the first wearable device, returning to step S801.

If it is determined in step S806 that there is something wrong with the body of the first user, in step S807, the device 200 may obtain a second list that is a list of ingredients of the second food.

Specifically, in the database of the device 200, a list of ingredients included in each health functional food is stored separately for each health functional food, and the device 200 searches the ingredient list stored in the database to obtain ingredients of the second food A second list that is a list may be obtained.

9 is a flowchart illustrating a process of recommending an alternative health functional food according to an embodiment.

According to one embodiment, each step shown in FIG. 9 may be performed after each step shown in FIG. 8 is performed.

Referring to FIG. 9 , first, in step S901, the apparatus 200 compares the first biometric information and the second biometric information, and if it is determined that there is something wrong with the body of the first user, the list of ingredients of the first food A first list may be obtained.

In step S902, the apparatus 200 may obtain a second list, which is a list of ingredients of the second food, when it is determined that the body of the first user has an abnormality as a result of comparing the third biometric information and the fourth biometric information. there is.

In step S903, the device 200 may compare the first list and the second list.

In step S904, the device 200 may determine whether there is an ingredient overlapping in each of the first list and the second list as a result of comparing the first list and the second list.

If it is determined in step S904 that there are no overlapping components, returning to step S801, the device 200 may continue to periodically receive the biometric information of the first user from the first wearable device.

In step S904, if it is confirmed that there is an ingredient that is included redundantly, and if the ingredient that is included redundantly is identified as the first ingredient, in step S905, the device 200 selects the first ingredient as a component that the first user should take with care. can be set to

That is, as a result of comparing the first list and the second list, the device 200 may select the first ingredient as an ingredient that the first user should take with caution when it is confirmed that the first ingredient is included in duplicate. .

In step S906, the device 200 may create a third list by deleting the first component after combining the first list and the second list.

For example, when the first list includes the first component and the second component, and the second list includes the first component and the third component, the device 200 configures the first list and the second list. It is possible to create a combined list including the first component, the second component and the third component by combining, and a third list including the second component and the third component can be generated by deleting the first component from the combined list. there is.

In step S907, the apparatus 200 may identify the third food as a health functional food containing the most ingredients included in the third list without containing the first ingredient.

That is, the apparatus 200 determines which food is a health functional food that does not contain the first ingredient and contains the most ingredients included in the third list, based on the list of ingredients classified for each health functional food. Thus, it can be confirmed that the third food contains most of the ingredients included in the third list without the first ingredient.

In step S908 , the apparatus 200 may provide recommendation information for recommending the third food as a health functional food replacing the first food and the second food to the first user terminal 110 . Here, the recommendation information recommending the third food may include information on the main features, effects, ingredients, price, link to the purchase page, etc. of the third food, and a comparison table of ingredients between the third food and the first food, It may further include a component comparison table between the third food and the second food.

10 is a flowchart illustrating a process of providing information on recommended foods that can be supplemented according to an embodiment.

According to one embodiment, each step shown in FIG. 10 may be performed after each step shown in FIG. 3 is performed.

Referring to FIG. 10 , first, in step S1001, the device 200 includes nutrient information of the first food and the amount of body fat, moisture, blood sugar, protein, mineral, calcium, bone density, and muscle mass of the first user. Based on the information on the body composition of the first user, information on the current nutrient state of the first user and the nutrient state expected to change when the first user consumes the first food may be provided to the first user terminal 110 . .

That is, the device 200 may display the current nutrient state of the first user and the nutrient state of the user expected to change when consuming the recommended food, based on the nutrient information of the recommended food and the current body composition information of the first user. .

In step S1002, the device 200 transmits to the first user terminal a guide notification asking the first user whether to eat food at a designated time, and measures the body composition of the first user before eating the first food. measurement results can be obtained.

That is, the device 200 displays a guide asking the first user whether or not to eat food at a designated time, and based on the first user's intake of food, the first user's body fat amount, water content, blood sugar level, protein, mineral content, calcium, When the bone density and muscle mass are measured, a first measurement result generated by measuring the body composition of the first user may be obtained.

In step S1003, when the first measurement result is obtained, the device 200 retransmits a guide notification asking the first user whether to eat food to the first user terminal, and measures the body composition of the first user after eating the first food. Thus, the generated second measurement result may be obtained.

That is, the apparatus 200 displays again a guide asking the first user whether to eat food after a certain amount of time has elapsed from the time of obtaining the first measurement result, and based on the fact that the first user has eaten the food, the first user 200 displays the guide again. When the amount of body fat, moisture, blood sugar, protein, mineral, calcium, bone density, and muscle mass are measured, a second measurement result generated by measuring the body composition of the first user may be obtained.

In step S1004, the device 200 displays information about the body composition of the first user measured before and after eating the first food on the screen of the first user terminal 110 based on the first measurement result and the second measurement result. can be controlled to be displayed.

That is, the device 200 may display the amount of body fat, moisture, blood sugar, protein, mineral, calcium, bone density, and muscle mass of the first user measured before and after consumption of the recommended food together on the display.

In step S1005, the device 200 controls elements that are numerically improved after eating the first food to be displayed on the screen of the first user terminal 110, and the numerical value changes in an unintended direction after eating the first food. Elements may be analyzed, and information on other recommended foods capable of compensating for elements whose numerical values change in an unintended direction after eating the first food may be controlled to be displayed on the screen of the first user terminal 110 .

That is, the device 200 displays elements that are numerically improved after consumption of the recommended food, analyzes factors whose numerical value has changed in an unintended direction after consumption of the recommended food, and analyzes factors in which the numerical value has changed in an unintended direction after consumption of the recommended food. Other recommended foods that can compensate for the factors whose values have changed can be displayed together.

11 is a flowchart illustrating a process of providing a notification service for adjusting intake of health functional food according to an embodiment.

Referring to FIG. 11 , first, in step S1101, the device 200 may transmit a request for input of information about the type of health functional food that the first user is ingesting and the ingestion start point to the first user terminal 110. there is.

In step S1102, the device 200 obtains dosage information including the total amount and per serving of the first food consumed by the first user, based on the type of health functional food consumed by the first user. can

That is, the device 200 determines the total amount and per serving of the health functional food consumed by the first user based on the type of health functional food consumed by the first user from the external server or the first user terminal 110 . It is possible to receive dosage information including.

In step S1103, the device 200 may determine the standard remaining amount of the first food by using the dosage information based on the fact that the specified period from the start of intake of the first food that the first user is ingesting has exceeded.

In step S1104 , the device 200 may transmit a photographing request of the first food to the first user terminal 110 .

In step S1105 , the device 200 may determine the actual remaining amount of the first food based on the image of the first food photographed through the first user terminal 110 .

In step S1106, the device 200 may check whether the actual remaining amount of the first food is within the reference range. Here, the reference range may be set through a standard remaining capacity.

If it is determined in step S1106 that the actual remaining amount of the first food is out of the reference range, in step S1107, the device 200 may determine whether the actual remaining amount of the first food is greater than the maximum value of the reference range.

If it is confirmed in step S1107 that the actual remaining capacity of the first food is greater than the maximum value of the reference range, in step S1108, the device 200 transmits information instructing the first food to be increased per serving to the first user terminal. (110).

That is, when the actual remaining amount of the first food exceeds a specified level compared to the standard remaining amount, the device 200 transmits information instructing the first user terminal 110 to increase the intake amount per serving of the first food. ) can be provided.

If it is confirmed in step S1107 that the actual remaining capacity of the first food is smaller than the maximum value of the standard range, the actual remaining capacity of the first food is out of the standard range, so that the actual remaining capacity of the first food is smaller than the minimum value of the standard range. and if the actual remaining capacity of the first food is determined to be smaller than the minimum value of the reference range, in step S1109, the device 200 transmits information instructing to reduce the intake per serving of the first food to the first food. It may be provided to the user terminal 110 .

That is, when the actual remaining amount of the first food is less than a specified level compared to the standard remaining amount, the device 200 transmits information instructing the first user terminal 110 to reduce the intake amount per serving of the first food. ) can be provided.

12 is a diagram for explaining learning of an artificial neural network according to an embodiment.

According to one embodiment, the artificial neural network may be an algorithm that receives user's health information, analyzes health functional foods that are likely to be recommended to the user, and outputs information on the recommended health functional foods.

The learning device where the artificial neural network is learned may be the same device as the device 200 that provides a user-customized health functional food curation service, or may be a separate device. Hereinafter, a process of learning an artificial neural network will be described.

First, in step S1201, the learning device may generate an input to be input to the artificial neural network. In this case, the learning device may generate an input based on the health information of the user to input to the artificial neural network.

Specifically, the learning device may perform a process of pre-processing the user's health information. The pre-processed health information of the user may be used as an input of the artificial neural network, or the input of the artificial neural network may be generated through a normal process of removing unnecessary information.

In step S1202, the learning device may apply the input to the artificial neural network.

The artificial neural network may be an artificial neural network that is trained according to reinforcement learning. The artificial neural network may be a Q-Network, a Depp Q-Network (DQN), or a relational network (RL) structure suitable for outputting abstract inference through reinforcement learning.

An artificial neural network trained by reinforcement learning may be updated and optimized by reflecting evaluations on various rewards. For example, the artificial neural network may be updated and optimized through first and second compensation.

For example, the first reward may increase as the user selects a health functional food containing an ingredient beneficial to the user's health as a recommended food according to the user's health condition, and the second reward may increase according to the user's health condition. It can be higher if you do not select health functional foods that contain ingredients that are not beneficial to your health as recommended foods.

In step S1203, the learning device may obtain an output from the artificial neural network.

The output of the artificial neural network may be information on recommended food, which is a health functional food recommended to the user. In this case, the artificial neural network may select health functional foods that may be recommended to the user through the user's health information and output information on the recommended foods.

In step S1204, the learning device may evaluate the output of the artificial neural network and provide a reward.

Evaluation of the output of the artificial neural network may be divided into first and second rewards. According to the user's health condition, the learning device provides more first rewards as the health functional food containing ingredients beneficial to the user's health is selected as the recommended food, and according to the user's health condition, the user's health benefit The more the second reward is awarded, the more the health functional food containing the undesirable ingredient is selected as the recommended food.

In step S1205, the learning device may update the artificial neural network based on the evaluation.

In an environment in which an artificial neural network selects health functional foods that are recommended to a user, the learning device takes action in specific states so that the expectation of the sum of rewards is maximized. ), the artificial neural network can be updated through the process of optimizing the policy that determines the

For example, if there is a problem with the selection of the first food as a health functional food to be recommended to the first user, the learning device provides first learning data including information indicating that there is a problem with the selection of the first food. and applying the first learning data to the artificial neural network to learn the artificial neural network so that the first food is not selected as a recommended health functional food for a user having a health condition similar to that of the first user. can be updated.

Meanwhile, the process of optimizing the policy may be performed through a process of estimating the maximum value of the expected value of the sum of rewards or the maximum value of the Q-function, or estimating the minimum value of the loss function of the Q-function. Estimation of the minimum value of the loss function may be performed through stochastic gradient descent (SGD) or the like. The process of optimizing the policy is not limited thereto, and various optimization algorithms used in reinforcement learning may be used.

The learning device may gradually update the artificial neural network by repeating the learning process of the artificial neural network as described above.

Specifically, in selecting health functional foods to be recommended to the user, the learning device selects the health functional food to be recommended to the user in consideration of the health condition of the user, and then uses an artificial neural network that outputs information on the selected recommended food. can be learned

That is, when the learning device analyzes health functional foods that are recommended to the user through the user's health information, the artificial neural network is trained by reflecting reinforcement learning through the first and second rewards and adjusting the analysis criteria. can

13 is an exemplary diagram of a configuration of a device according to an embodiment.

Device 200 according to an embodiment includes a processor 210 and a memory 220 . The processor 210 may include at least one device described above with reference to FIGS. 1 to 12 or may perform at least one method described above with reference to FIGS. 1 to 12 . A person or organization using the device 200 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 12 .

The memory 220 may store information related to the methods described above or may store a program in which the methods described below are implemented. Memory 220 may be volatile memory or non-volatile memory.

The processor 210 may execute a program and control the device 200 . Program codes executed by the processor 210 may be stored in the memory 220 . The device 200 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data through wired/wireless communication.

Apparatus 200 may be used to train an artificial neural network or to use a trained artificial neural network. The memory 220 may include a learning or learned artificial neural network. The processor 210 may learn or execute an artificial neural network algorithm stored in the memory 220 . The learning device for learning the artificial neural network and the device 200 using the learned artificial neural network may be the same or separate.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable 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 and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially 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 codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (3)

In the artificial intelligence-based user-customized health functional food curation service provided method performed by the device,
Providing a basic information input page for inputting basic information including blood type, constitution, age, preferred food, disease diagnosis, drug treatment, smoking, drinking, and exercise to a first user terminal;
obtaining basic information of the first user from the first user terminal when the basic information of the first user is input through the basic information input page;
transmitting a request for consent to provide information on biometric information including body temperature, electrocardiogram, blood pressure, and body composition to the first user terminal;
obtaining biometric information of the first user from a first wearable device worn on the body of the first user when consent to provide information on the biometric information of the first user is received from the first user terminal;
Transmitting a request for consent to provide an image for a face image to the first user terminal;
acquiring a first image generated by photographing the face of the first user from the first user terminal when photographing the face of the first user is performed using the camera of the first user terminal;
The first image is compared with the pre-trained average face image of the first user, the mood and condition of the first user is analyzed, and based on the analysis result of the mood and condition of the first user, the first user's mood and condition are analyzed. generating user status information;
generating health information of the first user by matching basic information of the first user, biometric information of the first user, and condition information of the first user;
applying the health information of the first user to an artificial neural network and selecting a recommended health functional food for the first user based on an output of the artificial neural network;
determining whether the first user has ever purchased the first food, based on a food purchase history of the first user, when the first food is selected as the first user's recommended health functional food;
providing recommendation information recommending the first food to the first user terminal when it is confirmed that the first user has never purchased the first food;
When the first food is input as the health functional food consumed by the first user at the first time point, the biometric information of the first user received at time point 1-1 before the first time point is used as the first biometric information. dividing the biometric information of the first user, which is received at a time point 1-2 after the first time point, into second biometric information;
comparing the first biometric information and the second biometric information to determine whether or not there is an abnormality in the body of the first user;
obtaining a first list, which is a list of ingredients of the first food, when it is determined that the first user's body has an abnormality as a result of comparing the first biometric information and the second biometric information;
When information on the second food is input through the first wearable device or the first user terminal at a second point in time and the information on the second food is received from the first wearable device or the first user terminal, It is confirmed that the second food is input as the health functional food consumed by the first user at the second time point, and the biometric information of the first user received at the time point 2-1 before the second time point is determined. 3 classifying biometric information, and classifying biometric information of the first user received at a point in time 2-2 after the second point in time into fourth biometric information;
comparing the third biometric information and the fourth biometric information to determine whether or not there is an abnormality in the body of the first user;
obtaining a second list, which is a list of ingredients of the second food, when it is determined that the body of the first user has an abnormality as a result of comparing the third and fourth biometric information;
setting the first ingredient as an ingredient that the first user should take with caution when it is determined that the first ingredient is included in duplicate as a result of comparing the first list and the second list;
generating a third list by deleting the first component after combining the first list and the second list; and
If the third food is identified as a health functional food that does not contain the first ingredient and contains the most ingredients included in the third list, the health function that replaces the first food and the second food Providing recommendation information for recommending the third food as food to the first user terminal;
After the step of providing recommendation information recommending the first food to the first user terminal,
Based on the nutrient information of the first food and the information about the body composition of the first user including the amount of body fat, water, blood sugar, protein, mineral, calcium, bone density and muscle mass of the current first user, providing information about the nutrient state of the first user and the nutrient state of the first user, which is expected to change when the first food is consumed, to the first user terminal;
At a designated time, a guide notification asking the first user whether to consume food is transmitted to the first user terminal, and a first measurement result generated by measuring the body composition of the first user before eating the first food is obtained step;
When the first measurement result is obtained, a guide notification asking the first user whether to consume food is retransmitted to the first user terminal, and the body composition of the first user is measured after eating the first food. 2 obtaining measurement results;
controlling information about the body composition of the first user measured before and after eating the first food to be displayed on a screen of the first user terminal based on the first measurement result and the second measurement result; and
Elements that are numerically improved after ingestion of the first food are controlled to be displayed on the screen of the first user terminal, elements whose numerical values are changed in an unintended direction after ingestion of the first food are analyzed, and Further comprising the step of controlling information on other recommended foods that can compensate for an element whose numerical value has changed in an unintended direction after eating the food is displayed on the screen of the first user terminal,
A method for providing user-customized health functional food curation service based on artificial intelligence. According to claim 1,
When it is confirmed that the first user has purchased the first food, based on the food purchase history of the first user, determining a first number of times, which is the number of times the first user has purchased the first food step;
registering the first food as a health functional food consumed by the first user when it is confirmed that the first number is greater than a preset reference number;
checking a first date, which is the last date the first food was purchased, and a first quantity, which is the number of first foods purchased on the first date, based on the food purchase history of the first user;
calculating a second period by multiplying the first period by the first quantity when the intake period of the first food is determined to be the first period; and
If it is determined that the first user has not additionally purchased the first food from the first date until the second period elapses, an additional purchase notification message for the first food is sent to the first user terminal. Further comprising the step of transmitting to,
A method for providing user-customized health functional food curation service based on artificial intelligence. According to claim 1,
classifying the selected plurality of foods into recommended food groups when a plurality of foods are selected as the recommended health functional foods of the first user;
if it is confirmed that the recommended food group includes the food that the first user has purchased, excluding the food that the first user has purchased from the recommended food group;
providing recommendation information recommending the first food to the first user terminal when it is determined that only the first food is included in the recommended food group;
grouping users having a health condition similar to that of the first user based on the health information of the first user and classifying them into a first user group when it is determined that a plurality of foods are included in the recommended food group; ;
Based on the food purchase history of each of the users included in the first user group, it is checked whether the users included in the first user group have ever purchased foods classified as the recommended food group, and the recommended food Calculating the number of purchasers and the number of purchases for each food included in the group;
setting a first weight based on the number of purchasers and a second weight based on the number of purchases for each food included in the recommended food group;
Calculating a recommendation score by adding the first weight and the second weight for each food included in the recommended food group; and
When a food having the highest recommendation score among foods included in the recommended food group is identified as the first food, providing recommendation information recommending the first food to the first user terminal,
A method for providing user-customized health functional food curation service based on artificial intelligence.