KR102623723B1 - Method for providing customized health functional food recommendation service using artificial intelligence - Google Patents

Abstract

The present invention provides a method of providing a customized health functional food purchase recommendation service based on artificial intelligence, which uses artificial intelligence (AI) along with real-time data to create and provide segmented products, services, or content tailored to individual users. do. The recommendation service provision method of the present invention acquires the user's personal information, purchase purpose information, status information, taste information, experience information, and environmental information, and trains artificial intelligence with the above information to recommend health functional foods to the user. there is. The electronic device of the present invention can determine and record whether the user consumes health functional food using artificial intelligence from the video of the user consuming the health functional food, so that the guardian can easily determine whether the protected person has health functional food or not, and can improve health. You can increase the reliability of product reviews by using it as a means of verifying whether you have consumed functional foods.

Description

{Method for providing customized health functional food recommendation service using artificial intelligence}

The present invention relates to a method of providing a service that recommends necessary health functional foods to users based on artificial intelligence.

With the development of information and communication technology, the number of cases of purchasing health functional foods through online markets is increasing, and various online markets handling health functional foods are emerging. In the case of a service providing health functional foods through a conventional online market, categories are separated according to function and ingredient or health functional foods are sorted in order of highest rating so that users can more easily select the health functional foods they want. can be provided.

However, this method has limitations in recommending user-tailored health functional foods because it does not specifically consider an individual's genetic information, condition, and tastes, and does not have a function to effectively encourage users to write reviews, so it does not provide quality health functional food review data. It was difficult to secure.

Korean Patent Publication No. 10-1787030 Korean Patent Publication No. 10-2021-0136483

The technical task to be achieved by the present invention is to provide a method of providing an artificial intelligence-based customized health functional food purchase recommendation service by using artificial intelligence (AI) along with real-time data to create segmented products, services or content tailored to individual users. It is characterized by providing. The recommendation service provision method of the present invention acquires the user's personal information, purchase purpose information, status information, taste information, experience information, and environmental information, and trains artificial intelligence with the above information to recommend health functional foods to the user. there is. The problem to be solved by the present invention is not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

A method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment is performed by an electronic device, and includes the user's age, height, weight, constitution, location information, preferred food, drinking information, and smoking through a user terminal. Obtaining basic information of the user including information; Obtaining the user's biorhythm and normal body temperature information through the user terminal and receiving the user's health checkup information on the server; Determining the user's personal information based on the acquired user's basic information, the obtained user's biorhythm and normal body temperature information, and the received user's health checkup information and storing the user's personal information in a memory; Obtaining information on the user's purchase purpose regarding health functional foods through the user terminal; Obtaining user status information including the user's mood or condition through a user terminal; Obtaining user taste information including the formulation and taste of the user's preferred health functional food through a user terminal or server; Obtaining user experience information including the user's response to health functional food through a user terminal or server; Obtaining environmental information including current weather, temperature, and seasonal information using an external server; Using the personal information, the purchase purpose information, the status information, the taste information, the experience information, and the environment information, based on artificial intelligence, determining a health functional food to recommend to the user and an appropriate medication method; Presenting the health functional food determined to be recommended and the corresponding medication method through the user terminal, and receiving an order input from the user; Measuring the user's response to the health functional food ordered by the user through the user terminal; and generating user experience information from the measured user's responsiveness and transmitting it to the server, or updating existing experience information stored in the server from the user's responsiveness.

An electronic device according to one embodiment may include memory and a processor.

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, the health checkup information is provided to the user regarding one or more of diseases, nutrients, health management, eating habits, exercise ability, hair, skin, and personal characteristics. It includes genetic test results, and the genetic test results for the above diseases include one or more of stomach cancer, colon cancer, liver cancer, lung cancer, prostate cancer, thyroid cancer, head and neck cancer, esophageal cancer, breast cancer, cervical cancer, stroke, hyperlipidemia, and heart disease. Contains the user's genetic information regarding, and genetic test results regarding the above nutrients, vitamin C, vitamin D, coenzyme Q10, magnesium, zinc, iron stores, potassium, calcium, arginine, fatty acids, vitamin A, vitamin B6, vitamin B12 , containing the user's genetic information regarding metabolic capability for one or more nutrients from a group of nutrients including vitamin E, vitamin K, selenium, lutein, and zeaxanthin, and the genetic test results related to said health management are Contains the user's genetic information regarding health management of one or more of arthritis susceptibility, motion sickness, obesity, uric acid level, triglyceride concentration, body fat percentage, body mass index, cholesterol, blood sugar, blood pressure, bone mass, and abdominal obesity, and genetic testing regarding the eating habits. The results include the user's genetic information regarding one or more of appetite, satiety, sweet taste sensitivity, bitter taste sensitivity, and salty taste sensitivity, and the genetic test results regarding exercise ability include strength exercise fitness, aerobic exercise fitness, endurance exercise fitness, and muscle development. It includes the user's genetic information regarding one or more of the following: ability, sprinting ability, ankle injury risk, grip strength, and post-exercise recovery ability, and the genetic test results regarding the hair include one or more of male pattern baldness, hair thickness, gray hair, and alopecia areata. Contains the user's genetic information about, and the genetic test results about the skin include the user's genetic information about one or more of spots, freckles, pigmentation, acne, skin aging, skin inflammation, and tanning reaction after sun exposure; , the genetic test results regarding the personal characteristics may include the user's genetic information regarding one or more of alcohol metabolism, alcohol dependence, nicotine metabolism, nicotine dependence, caffeine metabolism, caffeine dependence, insomnia, sleep habit time, and morning person. there is.

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, the purchase purpose information includes memory improvement, tension relief, sleep quality improvement, cognitive ability improvement, fatigue improvement, stomach health/digestion function, and intestinal health. Health, liver health, improvement of body fat, promotion of calcium absorption, prostate health, female vaginal health, urinary tract health, improvement of urination function, improvement of sensitive skin condition, improvement of immune function, antioxidant, eye health, oral health, skin health, improvement of neutral fat in the blood. , improvement of blood cholesterol, blood pressure control, improvement of blood circulation, blood sugar control, menopausal health, joint bone health, improvement of muscle strength, improvement of exercise performance, child growth and development, sperm motility, increase in concentration, improvement of premenstrual condition and selection from the group consisting of nutrients. It may include one or more types.

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, the status information includes the user's blood pressure, electrocardiogram, blood oxygen saturation, blood sugar, body odor test, breath odor test, saliva test, and recent travel distance. , sunlight exposure, facial condition score, concentration score, stress score, fatigue score, amount of alcohol, drinking time, recent sleep quality, and recent sleep time, and the breath odor test is based on the breath smell of the user terminal. It is measured using a measuring instrument, and is measured based on the concentration of sulfur compounds. The facial condition score is obtained by photographing the user's face with the camera of the user terminal, and using the captured facial image of the user to learn in advance using artificial intelligence. It is obtained by comparing the face image according to the user's health status, and the concentration score, stress score, and fatigue score are the game score obtained while the user plays the attention game installed on the user terminal and the camera of the user terminal while playing the attention game. It may be measured based on the moving body visual acuity score measured by.

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, the dosage form information included in the taste information includes tablet, capsule, pill, granule, selected from the group consisting of powder, liquid, flake, paste, syrup, gel, jelly, bar, and film. There is one or more types, and the taste information included in the taste information is one type selected from the group consisting of tasteless, apple taste, grape taste, lemon taste, grapefruit taste, chocolate taste, strawberry taste, melon taste, caramel taste, and banana taste. It may be more than that.

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, the personal information, the purchase purpose information, the status information, the taste information, the experience information, and the environmental information are collected based on artificial intelligence. The step of determining a health functional food to be recommended to a user and a method of taking the corresponding medication includes using a first input signal based on the personal information, the purchase purpose information, the status information, the preference information, the experience information, and the environmental information. Generating the generated first input signal to a first neural network - the first neural network includes training personal information, training purchase purpose information, training status information, training preference information, training experience information, training Generating a first output signal by applying environmental information, first output signals, and information previously learned based on training recommended health functional food and medication method information; And generating a recommended health functional food and information on a medication method corresponding to the recommended health functional food based on the first output signal, wherein the recommended health functional food and information on a medication method appropriate for the recommended health functional food include the training personal information and the purpose of purchasing the training. Information, the training status information, the training preference information, the training experience information, and the training environment information respectively correspond to recommended health functional foods and corresponding medication method information, and the first output signals are the training First training input signals generated based on personal information, the training purchase purpose information, the training status information, the training taste information, the training experience information, and the training environment information are connected to the first neural network. These are output signals generated by applying to, and the first neural network is learned by minimizing training errors generated based on differences in the first output signals and the training recommended health functional food and the corresponding medication method information. You can.

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, the step of measuring the user's responsiveness to the health functional food ordered by the user through the user terminal includes the user's state before consuming the health functional food. re-measuring information; Re-measuring the user's condition information after consuming the health functional food; It may include a step of determining the user's responsiveness by identifying numerically improved and worsened elements after ingestion of the recommended health functional food.

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, after receiving an order from a user, a video of the user consuming the ordered health functional food is captured through the camera of the user terminal, It may further include the step of analyzing the captured video with artificial intelligence installed on the server to determine whether the user has consumed health functional foods, and storing the user's intake of health functional foods in memory.

In the method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, after the step of determining the health functional food to be recommended to the user and the appropriate medication method, the personal information, the purchase purpose information, and the status The information management department receives, stores, and manages the information, the taste information, the experience information, the environmental information, the health functional food determined correspondingly, and the corresponding medication method, from the user terminal, and provides blockchain-based distributed identity authentication. It may include an additional step of managing it using MS Decentralized identity (DID).

In a method of providing an artificial intelligence-based customized health functional food recommendation service according to an embodiment, after the step of storing the user's health functional food intake in a memory, the user's health functional food intake record stored in the memory is stored in the information management unit. It may receive, store, and manage the information, but may additionally include the step of managing it using a blockchain-based distributed identity authentication method (MS Decentralized identity (DID)).

The electronic device according to one embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the above-described methods.

According to one embodiment, the electronic device recommends a product that matches the user's personal characteristics by considering the user's genes, purchase purpose, condition, and taste, and may also reflect the user's experience with the product in the product recommendation for the next purchase.

According to one embodiment, an electronic device provides recommended health functional foods and corresponding medication methods based on an artificial intelligence learning model to determine in advance whether the user may cause an allergic reaction to the medicine he or she is taking or whether an allergic reaction may occur due to the characteristics of the user's body. This can protect the user's health.

The electronic device according to one embodiment can determine and record whether the user consumes health functional food using artificial intelligence from the video of the user consuming the health functional food, so that the guardian can easily determine whether the protected person has health functional food. , you can increase the reliability of product reviews by using it as a means of verifying whether you have consumed health functional foods.

Figure 1 is a diagram illustrating a system for providing an artificial intelligence-based customized health functional food purchase recommendation service according to an embodiment.
Figure 2 is an exemplary diagram of the configuration of an electronic device according to an embodiment.
Figure 3 shows a flowchart of a method of providing an artificial intelligence-based customized health functional food purchase recommendation service according to an embodiment.
Figure 4 is a diagram for explaining learning of an artificial neural network according to an embodiment.
Figure 5 illustrates a process for inputting a user's purchase purpose information according to an embodiment.
Figure 6 illustrates a process for receiving user status information according to an embodiment.
Figure 7 illustrates a process for receiving user taste information according to an embodiment.

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

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from another component. For example, a first component may be named a second component, and similarly, the second component may also be named a first component.

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected or connected to the other component, but that other components may exist in between.

The terms used in the examples are for descriptive purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the embodiments belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In addition, when describing with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiments, if it is determined that detailed descriptions of related known technologies may unnecessarily obscure the gist of the embodiments, the detailed descriptions are omitted.

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.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, it is a system in which machines learn and make decisions on their own. As artificial intelligence systems are used, their recognition rates improve and they can more accurately understand user preferences, and existing rule-based smart systems are gradually being replaced by deep learning-based artificial intelligence systems.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithmic technology that classifies/learns the characteristics of input data on its own, and elemental technology is a technology that utilizes machine learning algorithms such as deep learning to mimic the functions of the human brain such as recognition and judgment, including linguistic understanding and visual It consists of technical areas such as understanding, reasoning/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology that recognizes and applies/processes human language/characters and includes natural language processing, machine translation, conversation systems, question and answer, and voice recognition/synthesis. Visual understanding is a technology that recognizes and processes objects as if they were human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image improvement. Inferential prediction is a technology that judges information to make logical inferences and predictions, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendations. 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 that controls the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), operation control (behavior control), etc.

Generally, in order to apply machine learning algorithms to real life, learning is performed using 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.

In the present invention, artificial intelligence (AI) refers to technology that imitates human learning ability, reasoning ability, perception ability, etc. and implements this with a computer, and includes concepts such as machine learning and symbolic logic. may include. Machine Learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the results of the analysis, and makes judgments or predictions based on the results of the learning. Additionally, technologies that mimic the functions of the human brain, such as cognition and judgment, using machine learning algorithms can also be understood as the category of artificial intelligence. For example, technical fields such as verbal understanding, visual understanding, reasoning/prediction, knowledge representation, and motion control may be included.

Machine learning can refer to the process of training a neural network model using experience processing data. Machine learning can mean that computer software improves its own data processing capabilities. A neural network model is built by modeling the correlation between data, and the correlation can be expressed by a plurality of parameters. A neural network model extracts and analyzes features from given data to derive correlations between data. Repeating this process to optimize the parameters of the neural network model can be called machine learning. For example, a neural network model can learn the mapping (correlation) between input and output for data given as input-output pairs. Alternatively, a neural network model may learn the relationships by deriving regularities between given data even when only input data is given.

An artificial intelligence learning model or neural network model may be designed to implement the human brain structure on a computer, and may include a plurality of network nodes with weights that simulate neurons of a human neural network. A plurality of network nodes may have a connection relationship with each other by simulating the synaptic activity of neurons in which neurons exchange signals through synapses. In an artificial intelligence learning model, multiple network nodes are located in layers of different depths and can exchange data according to convolutional connection relationships. The artificial intelligence learning model may be, for example, an artificial neural network model (Artificial Neural Network), a convolution neural network (CNN) model, etc. As an example, an 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, and Ada-boost. , Perceptron, Genetic Programming, Clustering, etc. can be used.

Among them, CNN is a type of multilayer perceptrons designed to use minimal preprocessing. CNN consists of one or several convolution layers and general artificial neural network layers on top of them, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize 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 have the advantage of being easier to train and using fewer parameters than other feedforward neural network techniques.

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 led to significant improvements in many computer vision tasks. For extremely large 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. For this purpose, distributed, scalable implementations of deep neural networks can be used.

Current Internet technology is useful for sharing neutral information. However, there are significant limitations in sharing information containing value. In reality, the information that contains the most important value can be said to be information about ‘identity (ID).’ However, if an individual's identity information is copied by another person, the existence of a specific individual can be copied infinitely in the Internet environment. The replica can arbitrarily control the original's financial accounts and use public services. To prevent such situations from occurring, a certificate guaranteed by a 'trusted third party (TTP)' is required to share identity information in a conventional Internet environment. However, these certificates are inconvenient and inconvenient in issuing and using them, and even if they are used, there is still a possibility of identity data being leaked or stolen.

On the other hand, dAPP, which supports identity verification (ID) based on blockchain, can solve the above-mentioned problems. In other words, personal information can be prevented from being distorted, and information leakage problems can be eliminated because identity can be authenticated without entrusting all personal information to the user. Additionally, individuals may have the authority to control their own identity information. In the Internet environment, identity authentication is essential to receive apps that require ‘purchasing power’, financial services, and government services. However, existing identity authentication was slow, risky of exposure, and inefficient. However, using decentralized identities (DIDs), it is possible to open a bank account, sign up for Facebook, and receive government services in just a few seconds. User effort and time can be reduced and costs can be reduced. Against this background, the demand for decentralized identity authentication is expected to increase.

Meanwhile, as the market for early prediction and diagnosis of diseases blooms, drug prescriptions and life services tailored to the characteristics of each individual's genome are expected to begin. Therefore, the need for a system that provides genetic information portal, payment, and compensation services is emerging.

In other words, the blockchain-based health data management system according to an embodiment of the present invention receives and stores user health data including genetic information or health checkups from the user terminal, and stores and manages user information and user health data using blockchain-based When a request for user health data is received from an information management department managed by MS Decentralized identity (DID) and health data demand organizations, some of the user health data managed by the information management department is extracted and provided. A payment processing unit that receives compensation in the form of electronic money for providing user health data information from institutions that study and demand the health data, and pays compensation in the form of electronic money to the user who provided the user health data. It can be included.

Meanwhile, the method of operating the blockchain-based health data management system is for the information management department to receive and store user health data including at least one of genetic information or health checkup from the user terminal, and to store and manage the user information and user health data through the blockchain. Management step based on MS Decentralized identity (DID) method, when the information provider receives a request for user health data from a health data demand organization, extracts and provides some of the user health data stored and managed. The stage and payment processing department receives compensation for providing user health data information from the health data demand agency in the form of electronic money, and pays compensation for providing user health data to the user who provided the user health data in the form of electronic money. Includes steps.

According to the present invention, the rapidly growing personal genome prediction/diagnosis service is provided through a portal system, and personal health big data such as genome, medical diagnosis information, and social data is provided, thereby valuing personal genetic testing costs and diagnosis costs. can relieve the burden. In particular, by providing compensation through self-issued blockchain-based virtual currency, it not only resolves the inconvenience in issuing and using public certificates, but also reduces concerns about identity data leakage and theft crimes. The health data management system according to an embodiment of the present invention uploads personal health big data from individuals. And as compensation for this, for example, electronic money is paid. In other words, individuals can acquire electronic money by valuing their health big data. At this time, health big data may include genome, i.e. genetic information, medical-related information, and social data.

In one embodiment, the health data management system can convert personal health data into metadata and store it based on blockchain. Individual users can undergo genetic testing to obtain genetic information (DNA, RNA, epigenetic variation, genetic mutation, gene group, and entire genome). In addition, genotyping and association information related to genes can be stored and managed by uploading the test result data to the portal.

The health data management system according to one embodiment can convert personal health data into big data and store it reliably. The health data management system can provide stored personal health data, that is, big data, to organizations that need it through purchase or viewing functions. Here, the demand organization may be one of pharmaceutical companies, medical device companies, insurance companies, food/cosmetics companies, research institutes, schools, and bio companies. However, it is not limited to this.

Additionally, the health data management system can recommend solutions optimized for individuals based on big data including personal health data. For example, solutions may include health supplements, cosmetics, customized supplements or medications, and medical institution information. However, this limitation is interpreted to include various information necessary for health management. In addition to simply providing information, it is also possible to provide a user interface that connects to a local shopping mall and leads to purchases.

The information management department receives and stores user health data including at least one of genetic information, health checkup, and prescription from the user terminal, and provides user information and user health data with blockchain-based decentralized identity authentication (MS Decentralized identity (DID). )) method. MS Decentralized identity (DID) is a blockchain-based electronic identity authentication technology that stores personal information on the user's terminal, that is, on the user's terminal, and allows users to select and submit only the information needed for authentication.

The majority of companies and organizations store and manage personal information in a central system. However, in decentralized identity verification, individuals can directly manage their personal information. Additionally, in a centralized system, when hacking occurs, there is a risk of personal information being leaked on a large scale, and there have been cases where companies secretly use personal information to make profits. However, in distributed identity authentication, individuals become the entities that manage their personal information, and the information is stored in a decentralized manner on each individual's user terminal. By using distributed identity authentication, there is no need to provide all personal information when authenticating to use the service, and only the necessary information can be selected and provided. In other words, decentralized identity verification, also called 'Self Sovereign Identity', simply retrieves previously authenticated information without the need to log in or authenticate each time. Therefore, the inconvenience of having to take photos of ID cards or enter information one by one is reduced.

The user's genetic (genome) data is uploaded one-time by the information management department, but medical-related information such as health checkup results and prescriptions and social data are information that is continuously uploaded over time, so the information management department uploads the personal health data. It is desirable to manage them to ensure continuity by continuously uploading them. When a request for user health data is received from an organization requesting health data, the information provision department extracts and provides some of the user health data managed by the information management department. Organizations requiring health data may be one of pharmaceutical companies, medical device companies, insurance companies, food and cosmetics companies, research institutes, and schools. However, it is not limited to this and is interpreted to encompass all institutions, companies, and organizations that require genetic information or user health-related information.

The health data management system according to one embodiment uses blockchain-based distributed identity authentication (MS Decentralized identity (DID)) to strengthen the security of the user's personal email address and ID. In one embodiment, while sharing personal health big data, the data owner is anonymized, and the network address of the genome portal provided by the health data management system is treated as an encrypted identifier unrelated to personal information.

Therefore, purchasers of health data are limited to transparent people whose identities are confirmed in the health data management system, and all transaction records are permanently stored in the genome portal blockchain provided by the health data management system.

At this time, the user's health data request from the health data requesting agency may include filtering criteria information for the health data. For example, it includes filtering criteria such as the user's gender or age or if the user has a specific disease. The information provision unit extracts and provides user health data that meets the filtering criteria included in the user health data request from the health data requesting agency.

Accordingly, the health data management system can provide a customized search engine that provides genetic information with weights applied according to the user's health and genetic information. The payment processing department receives compensation in the form of electronic money for providing user health data information from health data demand organizations, and pays compensation in the form of electronic money to users who provide user health data. Accordingly, genetic testing can be provided free of charge or the cost of testing can be discounted for members who provide (share) personal health checkup information, i.e. health data.

Figure 1 is a diagram illustrating a system for providing an artificial intelligence-based customized health functional food purchase recommendation service according to an embodiment.

As shown in Figure 1 , the artificial intelligence-based customized health functional food purchase recommendation service providing system includes a plurality of user terminals (100, 200, 300??), a network 400, a server 500, and an external server 600. ) may include. The server 500 may include multiple artificial intelligence systems for performing machine learning algorithms. According to one embodiment, a plurality of user terminals (100, 200, 300??), a server 500, and an external server 600 may be connected to communicate with each other through the network 400.

The network 400 can perform wireless or wired communication between a plurality of user terminals (100, 200, 300??), a server 500, and an external server 600. For example, networks include long-term evolution (LTE), LTE Advanced (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), Wireless BroadBand (WiBro), wireless fidelity (WiFi), and Bluetooth ( Wireless communication can be performed using methods such as Bluetooth), NFC (near field communication), GPS (Global Positioning System), or GNSS (global navigation satellite system). For example, the network 400 is configured to perform wired communication according to a method such as universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 232 (RS-232), or plain old telephone service (POTS). You may.

Figure 2 is an exemplary diagram of the configuration of an electronic device according to an embodiment.

The electronic device 500 according to one embodiment may include a processor 530 and a memory 540, and some of the illustrated components may be omitted or replaced. The electronic device 500 according to one embodiment may be a server or a terminal. According to one embodiment, the processor 530 is a component capable of performing operations or data processing related to control and/or communication of each component of the electronic device 500, and may be composed of one or more processors. The memory 540 may store information related to the above-described method or store a program implementing the above-described method. Memory 540 may be volatile memory or non-volatile memory. The memory 540 can store various file data, and the stored file data can be updated according to the operation of the processor 530.

According to one embodiment, the processor 530 can execute a program and control the device 500. The code of the program executed by the processor 530 may be stored in the memory 540. Operations of the processor 530 may be performed by loading instructions stored in the memory 540. The electronic device 500 is connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and can exchange data.

According to one embodiment, the processor 530 provides a guide for entering the user's basic information, including the user's blood type, age, height, weight, constitution, location information, preferred food, drinking information, and smoking information, , Obtain the user's biorhythm and the user's usual body temperature information on the health application, receive the user's health checkup information on the server, obtain the user's basic information, the acquired user's biorhythm and usual body temperature information, and the received user The user's personal information can be determined based on the health examination information and stored in the memory 540. The processor 530 acquires information on the user's purchase purpose regarding health functional foods, obtains user status information including the user's mood or condition, and obtains information on the user's status including the user's preferred health functional food formulation and taste. Obtaining the user's taste information, obtaining the user's experience information including the user's response to health functional foods, obtaining environmental information including the current weather, temperature, and seasonal information, and based on artificial intelligence, the personal information, The purchase purpose information, the status information, the taste information, the experience information, and the environment information can be used to determine a health functional food to recommend to the user and an appropriate medication method. The processor 530 presents the health functional food determined to be recommended and the corresponding medication method, receives an order from the user, measures the user's response to the health functional food ordered by the user, and measures the user's response to the measured health functional food. The user's experience information can be generated from the responsiveness and the experience information can be updated.

According to one embodiment, the health checkup information includes the results of the user's genetic test for one or more of diseases, nutrients, health care, eating habits, exercise ability, hair, skin, and personal characteristics, and genetic testing for the disease. The results include the user's genetic information regarding one or more of stomach cancer, colon cancer, liver cancer, lung cancer, prostate cancer, thyroid cancer, head and neck cancer, esophageal cancer, breast cancer, cervical cancer, stroke, hyperlipidemia, and heart disease, and genes related to the nutrients. Test results include vitamin C, vitamin D, coenzyme Q10, magnesium, zinc, iron stores, potassium, calcium, arginine, fatty acids, vitamin A, vitamin B6, vitamin B12, vitamin E, vitamin K, selenium, lutein, and zeaxanthin. It includes the user's genetic information regarding metabolic capability for one or more nutrients from the group of nutrients, and the genetic test results related to health management include susceptibility to degenerative arthritis, motion sickness, obesity, uric acid level, neutral fat concentration, and body fat percentage. , includes the user's genetic information regarding health management of one or more of body mass index, cholesterol, blood sugar, blood pressure, bone mass, and abdominal obesity, and the genetic test results regarding the eating habits include appetite, satiety, sweet taste sensitivity, bitter taste sensitivity, and salty taste sensitivity. It includes one or more genetic information of the user, and the genetic test results regarding the exercise ability include fitness for strength exercise, suitability for aerobic exercise, suitability for endurance exercise, muscle development ability, sprint ability, ankle injury risk, grip strength, and post-exercise recovery. Genetic information about the user regarding one or more of the abilities, and the genetic test results about the hair include genetic information about the user about one or more of male pattern baldness, hair thickness, gray hair, and alopecia areata, and Genes about the skin The test results include the user's genetic information regarding one or more of spots, freckles, pigmentation, acne, skin aging, skin inflammation, and tanning reaction after sun exposure, and the genetic test results related to the personal characteristics include alcohol metabolism and alcohol dependence. , may include the user's genetic information regarding one or more of nicotine metabolism, nicotine dependence, caffeine metabolism, caffeine dependence, insomnia, sleep habit time, and morning person.

The processor 530 captures the user's face using a camera, and provides user status information including the user's mood or condition based on a comparison result between the captured user's face image and the user's pre-learned average face image. can be obtained.

According to one embodiment, after the step of receiving an order from the user, the processor 530 of the server determines whether the user has consumed the health functional food from the video of the user consuming the ordered health functional food captured through the camera of the user terminal. is determined based on artificial intelligence, and whether the user consumes health functional foods can be stored in memory.

Once it becomes possible to authenticate whether a user consumes health functional foods based on artificial intelligence, trustworthy product reviews can be written based on this. Specifically, when a user who has actually consumed a health functional food writes a product review, a certification mark for consuming a health functional food can be displayed, and rewards such as points and virtual currency can be provided to users who have obtained the certification mark. can be provided.

If it becomes possible to verify whether a user consumes health functional foods based on artificial intelligence, the guardian can check whether the protected person consumes health functional foods based on this.

According to one embodiment, the processor 530 receives the user's genotype information, genetic information, and the user's diet information and calculates the user's obesity risk, including the user's obesity risk, the type of the user's last purchase, and the purchased product. A list of at least one recommended product is determined based on the amount and search history, and based on the fact that the product that the user expressed an intention to purchase is not included in the list of recommended products, the product that the user expressed an intention to purchase is selected by the user. Information indicating that the product may not be suitable for the user may be displayed, and information on the purchase amount or consumption cycle of the recommended product may be displayed based on the fact that the product for which the user has expressed an intention to purchase is included in the list of recommended products.

According to one embodiment, the processor 530 determines the target weight or recommended weight based on the user's weight, height, gender, age, muscle mass, and basal metabolic rate, and achieves the target weight or recommended weight through user input. Determine the goal achievement period for the user, determine the type and amount of food suitable for the user based on the user's preferred food, the user's constitution, the target weight, the recommended weight, and the goal achievement period, and determine the type of food suitable for the user and information on intake amount can be displayed to the user.

According to one embodiment, the processor 530 determines a health functional food to recommend to the user and a corresponding medication method based on the user's personal information, the user's status information, and the environmental information, and determines the recommended health functional food. Based on nutrient information and the current user's body fat, moisture, blood sugar, protein, mineral, calcium, bone density, and muscle mass information, the user's current nutrient status and the user's nutrient status expected to change when consuming the recommended health functional food are displayed. , displays a guide asking the user whether to consume health functional foods at a specified time, and measures the user's body fat, moisture, blood sugar, protein, minerals, calcium, bone density, and muscle mass based on the user's previous intake of health functional foods. After a certain period of time, a guide asking the user whether to consume health functional foods is displayed again, and the user's body fat, moisture, blood sugar, protein, minerals, calcium, bone density, and muscle mass are measured based on the user's intake of health functional foods. , the user's body fat, moisture, blood sugar, protein, minerals, calcium, bone density, and muscle mass measured before and after consumption of recommended health functional foods can be displayed together on the display.

According to one embodiment, the processor 530 receives data about the drug the user is currently taking, or receives the user's medication history or prescription record from the server, and receives the user's body fat amount, water content, blood sugar level, protein, minerals, and calcium. , determines the components that can be lost from the user's body due to the drug being taken with respect to bone density and muscle mass, based on the user's personal information, the user's condition information, and whether it is impossible to use it in combination with the drug the user is currently taking. Determine a recommended health functional food to supplement the ingredients that may be lost, display information about the recommended health functional food and the drug the user is taking, and mix the recommended health functional food and the drug the user is taking. Whether this is possible can be determined through an artificial intelligence learning model.

According to one embodiment, the artificial intelligence learning model groups data including ingredient information for drugs, nutrient information for food, and information on reactions to human allergic ingredients into a specified number of clusters and learns them using an average algorithm, The user enters information about the medicine he or she is taking and information about the recommended health functional food and determines the likelihood of causing an allergic reaction in numerical terms. If the likelihood of causing an allergic reaction exceeds a specified level, the recommended product is considered dangerous. Information indicating that this can be done can be displayed, and other products that can be mixed with the medicine the user is taking can be recommended, taking into account the price, nutrients, and texture of the recommended product.

According to one embodiment, there will be no limitation to the calculation and data processing functions that the processor 530 can implement on the electronic device, but the purchase recommendation function of artificial intelligence-based customized health functional food will be described below.

Figure 3 shows a flowchart of a method of providing an artificial intelligence-based customized health functional food purchase recommendation service according to an embodiment.

Although the process steps, method steps, algorithms, etc. are depicted in a sequential order in the flow chart of FIG. 3 , such processes, methods, and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods and algorithms described in various embodiments of the invention do not need to be performed in the order described herein. Additionally, although some steps are described as being performed asynchronously, in other embodiments, some such steps may be performed concurrently. Additionally, the illustration of a process by depiction in the drawings does not mean that the illustrated process excludes other variations and modifications thereto, and that any of the illustrated process or steps thereof may be incorporated into any of the various embodiments of the invention. It does not imply that more than one is required, nor does it imply that the illustrated process is preferred.

In operation S201, the processor (eg, processor 530 in FIG. 2) may receive the user's personal information. According to one embodiment, the processor 530 may receive the user's basic information including the user's age, height, weight, constitution, location information, preferred food, drinking information, and smoking information, and may use the health application (100, 200) , 300 ??), the user's biorhythm and the user's usual body temperature information may be acquired, and the user's health checkup information may be received on the server and stored in the memory (e.g., memory 540 in FIG. 2).

In operation S202, the processor 530 may receive the user's purchase purpose information. According to one embodiment, the processor 530 improves memory, relieves tension, improves sleep quality, improves cognitive ability, improves fatigue, stomach health/digestion function, intestinal health, liver health, improves body fat, promotes calcium absorption, prostate health, Women's vaginal health, urinary tract health, improvement of urination function, improvement of sensitive skin condition, improvement of immune function, antioxidant, eye health, oral health, skin health, improvement of blood neutral fat, improvement of blood cholesterol, blood pressure control, improvement of blood circulation, blood sugar control, menopause Purchase purpose information includes one or more selected from the group consisting of health, joint bone health, muscle strength improvement, exercise performance improvement, child growth and development, sperm motility, increased concentration, improvement of premenstrual condition, and nutrients, and memory It can be stored on (540).

In operation S203, the processor 530 may obtain user status information. According to one embodiment, the processor 530 records the user's blood pressure, electrocardiogram, blood oxygen saturation, blood sugar, recent distance traveled, amount of sunlight exposure, facial condition score, concentration score, stress score, fatigue score, amount of alcohol consumed, time of drinking, and recent sleep. The time can be received as status information and stored on the memory 540. According to one embodiment, the facial condition score is obtained by photographing the user's face with a camera and comparing the captured facial image of the user with a facial image for each health state of the user learned in advance using artificial intelligence, and the concentration The score, stress score, and fatigue score are measured based on the game score obtained by the user while playing the attention game installed on the user terminal and the moving body visual acuity score measured while playing the attention game, and these can be stored in the memory 540. there is.

In operation S204, the processor 530 may obtain user taste information including the formulation and taste of the health functional food. According to one embodiment, the processor 530 stores tablet, capsule, pill, granule, powder, liquid, flake, and paste as formulation information. At least one selected from the group consisting of paste, syrup, gel, jelly, bar, and film is obtained as taste information, and taste information such as tasteless and apple is obtained. One or more types selected from the group consisting of taste, grape, lemon, grapefruit, chocolate, strawberry, melon, caramel, and banana flavors can be acquired as taste information and stored in the memory 540. there is.

In operation S205, the processor 530 may obtain user experience information including responsiveness to the health functional food. According to one embodiment, the processor 530 newly acquires the user's experience information through the user terminal (100, 200, 300??) or acquires the experience information stored on the memory 540 of the server 500. You can.

In operation S206, the processor 530 may obtain environmental information including current weather, temperature, and season information. According to one embodiment, the processor 530 may store the environment information on the memory 540.

In operation S207, the processor 530 may use personal information, purchase purpose information, status information, taste information, experience information, and environmental information based on artificial intelligence to determine a health functional food to recommend to the user and an appropriate medication method. According to one embodiment, the processor 530 includes training personal information, training purchase purpose information, training status information, training preference information, training experience information, training environment information, output signals, and training recommended health functions. Recommendations are made from input signals generated based on personal information entered by the user, purchase purpose information, status information, taste information, experience information, and environmental information using a neural network previously learned based on food and corresponding medication method information. Health functional food information can be generated. According to one embodiment, the processor 530 can train the neural network in a way to minimize training errors generated based on differences between the output signals and the training recommended health functional food and the corresponding medication method information. there is.

In operation S208, the processor 530 can present the health functional food determined to be recommended and the corresponding medication method, and receive an order from the user. According to one embodiment, the processor 530 may store the order entered by the user on the memory 540.

In operation S209, the processor 530 may measure the user's response to the health functional food ordered by the user. According to one embodiment, the processor 530 determines the numerically improved factors after consuming the recommended health functional food based on the user's body fat, water content, blood sugar level, protein, minerals, calcium, bone density, and muscle mass measured before and after consuming the health functional food. The user's responsiveness can be determined by identifying and deteriorating factors, and these can be stored in the memory 540. According to one embodiment, the processor 530 can determine the level of responsiveness by identifying changes in the user's state information before and after consuming the measured health functional food, and store them in the memory 540.

In operation S210, the processor 530 may generate user experience information from the measured user's responsiveness and transmit it to the server 500, or update existing experience information stored in the server 500 from the user's responsiveness. . According to one embodiment, the processor 530 may store the newly created user's responsiveness in the memory 540.

Figure 4 is a diagram for explaining learning of a neural network according to an embodiment.

As shown in FIG. 4 , the learning device can learn the neural network 515 based on information received from a plurality of user terminals (100, 200, 300??). According to one embodiment, the learning device may be a separate entity from the server 500, but is not limited thereto.

The neural network 515 includes an input layer through which training samples (input data 510) are input and an output layer through which training outputs are output, and there is a connection between the training outputs (predicted values 520) and labels (correct answer data). Can be learned based on differences. Here, labels are defined based on items corresponding to training data. The neural network 515 is connected to a group of a plurality of nodes, and is defined by weights between connected nodes and an activation function that activates the nodes.

The learning device may learn the neural network 515 using a gradient descent (GD) technique or a stochastic gradient descent (SGD) technique. The learning device can use a loss function designed by the outputs and labels of the neural network.

The learning device can calculate the training error using a predefined loss function. The loss function may be predefined with a label, output, and parameter as input variables, where the parameter may be set by weights in the neural network 515. For example, the loss function may be designed in the form of MSE (Mean Square Error), entropy, etc., and various techniques or methods may be employed in embodiments in which the loss function is designed.

The learning device can use the backpropagation technique to find weights that affect the training error. Here, the weights are relationships between nodes in the neural network 515. The learning device can use the SGD technique using labels and outputs to optimize the weights found through the backpropagation technique. For example, the learning device can update the weights of the loss function defined based on the labels, outputs, and weights using the SGD technique.

According to one embodiment, the learning device includes training personal information, training purchase purpose information, training status information, training preference information, training experience information, and/or training environment information and training recommended health functional foods corresponding thereto. and obtain information on how to take medication accordingly, and generate a first input signal 510 based on the personal information, training purchase purpose information, training status information, training taste information, and/or training experience information, , the generated first input signal 510 is applied to the first neural network 515 to generate first output signals 520 corresponding to the first objects, and the first output signal 520 and the training recommendation are generated. The first neural network can be trained using health functional foods and corresponding medication method information (correct answer data).

According to one embodiment, the recommended health functional food and the corresponding medication method information include values corresponding to one or more of personal information, purchase purpose information, status information, taste information, experience information, and environmental information. have According to one embodiment, there is recommended health functional food and corresponding medication method information corresponding to each of personal information, purchase purpose information, status information, taste information, experience information, and environmental information.

According to one embodiment, the learning device may obtain first training outputs by applying the first training information to the neural network 515. The learning device may learn the neural network 515 based on the first training outputs and first labels (correct answer data). The learning device calculates first training errors corresponding to the first training outputs and learns the algorithm of the neural network 515 by optimizing the connection relationship of nodes in the neural network 515 to minimize the first training errors. You can. The server 500 can extract recommended health functional foods and information on medication methods appropriate for them using the first neural network on which learning has been completed. According to one embodiment, the first training information is one or more of personal information, purchase purpose information, status information, taste information, experience information, and environmental information, and the first label (correct answer data) is the first training information. 1 This may be information on recommended health functional foods and corresponding medication methods corresponding to the training information.

According to one embodiment, the neural network 515 trained with the first training information and the first label (correct answer data) may be further trained with the second training information and the second label (correct answer data). According to one embodiment, the second training information is one or more of personal information, purchase purpose information, status information, taste information, experience information, and environmental information, and the second label (correct answer data) is the first 2 This may be information on recommended health functional foods and corresponding medication methods corresponding to the training information. According to one embodiment, the neural network 515 trained with the first training information and the first label (correct answer data) can be subjected to additional learning from additional training information and additional labels, and the training information and labels are secured and the number of learning is performed. is not limited.

Figures 5 to 7 illustrate the process of receiving user information.

According to Figure 5 , electronic devices improve memory, relieve tension, improve sleep quality, improve cognitive ability, improve fatigue, stomach health/digestion function, intestinal health, liver health, improve body fat, promote calcium absorption, prostate health, and women's vaginal health. , urinary tract health, improvement of urination function, improvement of sensitive skin condition, improvement of immune function, antioxidant, eye health, oral health, skin health, improvement of blood neutral fat, improvement of blood cholesterol, blood pressure control, improvement of blood circulation, blood sugar control, menopausal health, joints. Information on the user's purchase purpose can be entered, including one or more items selected from the group consisting of bone health, muscle strength improvement, exercise performance improvement, child growth and development, sperm motility, increased concentration, improvement of premenstrual condition, and nutrients.

According to FIG. 6 , the electronic device may determine the concentration score, stress score, and fatigue score by using the game score obtained while the user plays the attention game installed on the user terminal and the moving body vision score measured while playing the attention game. If the game score becomes lower than average while playing the attention game, or if the movement of the body measured by the camera slows down while playing the game, the concentration score, stress score, and fatigue score may be determined to be low.

According to Figure 7 , the electronic device displays tablet, capsule, pill, granule, powder, liquid, flake, and paste as dosage form information. , it is one or more types selected from the group consisting of syrup, gel, jelly, bar, and film, and taste information includes tasteless, apple, grape, lemon, Taste information can be determined by receiving input from the user of one or more flavors selected from the group consisting of grapefruit flavor, chocolate flavor, strawberry flavor, melon flavor, caramel flavor, and banana flavor.

According to one embodiment, the operation of determining a health functional food to recommend to the user based on the user's personal information, the user's status information, and the environmental information receives data about the drug the user is currently taking, or receives data from the server. Receiving a user's medication history or prescription record; Determining ingredients that can be lost from the user's body due to the drug being taken with respect to the user's body fat content, water content, blood sugar level, protein, minerals, calcium, bone density, and muscle mass; An operation of determining a recommended health functional food to supplement the ingredients that may be lost based on the user's personal information, the user's condition information, and whether it cannot be used in combination with the drug the user is currently taking; And further comprising an operation of displaying information about the recommended health functional food and the medicine the user is taking, and determining whether the recommended health functional food and the medicine the user is taking can be mixed using an artificial intelligence learning model. can do.

The artificial intelligence learning model groups data including drug ingredient information, food nutrient information, and human reaction information to allergic ingredients into a specified number of clusters, learns using an average algorithm, and determines the drug the user is taking. Information on the above and the recommended health functional food is entered, the possibility of causing an allergic reaction is determined numerically, and if the possibility of causing an allergic reaction exceeds a specified level, an indication is given that the recommended product may be dangerous. information is displayed, and other products that can be mixed with the medicine the user is taking can be recommended, taking into account the price, nutrients, and texture of the recommended product.

The embodiments described above may be implemented with 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, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

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., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of 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 optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. 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 these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

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

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

100: Terminal (smart shoes)
200: Terminal (smartphone)
300: Terminal (smart watch)
400: Network
500: Server
510: input data
515: Neural Network
520: predicted value
530: processor
540: Memory
600: external server

Claims (6)

In a method performed by an electronic device to provide an artificial intelligence-based customized health functional food recommendation service,
Obtaining the user's basic information including the user's age, height, weight, constitution, location information, preferred food, drinking information, and smoking information through the user terminal;
Obtaining the user's biorhythm and normal body temperature information through the user terminal and receiving the user's health checkup information on the server;
Determining the user's personal information based on the acquired user's basic information, the obtained user's biorhythm and normal body temperature information, and the received user's health checkup information and storing the user's personal information in a memory;
Obtaining information on the user's purchase purpose regarding health functional foods through the user terminal;
Obtaining user status information including the user's mood or condition through a user terminal;
Obtaining user taste information including the formulation and taste of the user's preferred health functional food through a user terminal or server;
Obtaining user experience information including the user's response to health functional food through a user terminal or server;
Obtaining environmental information including current weather, temperature, and seasonal information using an external server;
Using the personal information, the purchase purpose information, the status information, the taste information, the experience information, and the environment information, based on artificial intelligence, determining a health functional food to recommend to the user and an appropriate medication method;
Presenting the health functional food determined to be recommended and the corresponding medication method through the user terminal, and receiving an order from the user;
Measuring the user's response to the health functional food ordered by the user through the user terminal; and
Generating user experience information from the measured user's responsiveness and transmitting it to the server, or updating existing experience information stored in the server from the user's responsiveness,
After the step of receiving an order from the user, a video of the user consuming the ordered health functional food is captured through the camera of the user terminal, and the captured video is analyzed by artificial intelligence installed on the server to determine whether the user has consumed the health functional food. It further includes the step of determining and storing in memory whether the user consumes health functional foods,
The step of measuring the user's responsiveness to the health functional food ordered by the user through the user terminal includes re-measuring the user's status information before consuming the health functional food; Re-measuring the user's condition information after consuming the health functional food; And a step of determining the user's responsiveness by identifying numerically improved and worsened elements after consumption of the recommended health functional food,
The status information includes the user's blood pressure, electrocardiogram, blood oxygen saturation, blood sugar, body odor test, breath odor test, saliva test, recent travel distance, amount of sunlight exposure, facial condition score, concentration score, stress score, fatigue score, amount of alcohol, and time of drinking. , is determined from one or more types selected from recent sleep quality and recent sleep time,
The breath odor test is measured using a breath odor meter in the user terminal, and is measured based on the concentration of sulfur compounds. The facial condition score is obtained by photographing the user's face with the camera of the user terminal, and capturing the user's face in the photograph. It is obtained by comparing the image with facial images for each user's health status that have been learned in advance using artificial intelligence.
The concentration score, stress score and fatigue score are measured based on the game score obtained by the user while playing the attention game installed on the user terminal and the moving body vision score measured by the camera of the user terminal while playing the attention game,
Based on the artificial intelligence, the step of determining a health functional food to recommend to the user and an appropriate medication method using the personal information, the purchase purpose information, the status information, the taste information, the experience information, and the environmental information
A first input signal is generated based on the personal information, the purchase purpose information, the status information, the taste information, the experience information, and the environment information, and the generated first input signal is connected to a first neural network - the first 1 The neural network includes training personal information, training purchase purpose information, training status information, training preference information, training experience information, training environment information, first output signals, and training recommended health functional foods and corresponding medication. generating a first output signal by applying a previously learned method based on the method information; and
It includes the step of generating recommended health functional foods and information on medication methods appropriate for them based on the first output signal,
The recommended health functional food and the corresponding medication method information are included in the training personal information, the training purchase purpose information, the training status information, the training preference information, the training experience information, and the training environment information. This is information on the corresponding recommended health functional foods and how to take them,
The first output signals are first training signals generated based on the training personal information, the training purchase purpose information, the training status information, the training preference information, the training experience information, and the training environment information. Input signals are output signals generated by applying the first neural network,
The first neural network is trained to update weights to minimize training errors generated based on differences between the first output signals and the training recommended health functional food and the corresponding medication method information,
After the step of determining the health functional food to be recommended to the user and the appropriate medication method, the personal information, the purchase purpose information, the status information, the taste information, the experience information, and the environmental information and the health function determined accordingly. A step in which the information management department receives, stores, and manages health data including information on food, appropriate medication methods, and weights from the user terminal, and manages it using a blockchain-based distributed identity authentication method (MS Decentralized identity (DID)). Additionally includes,
After the step of storing in memory whether the user consumes health functional food, the information management unit receives and stores and manages the user's health functional food intake record stored in the memory, using a blockchain-based decentralized identity authentication method (MS Decentralized identity). (DID)), and additionally includes a management step,
In managing updated weights and health functional food intake records using a blockchain-based distributed identity authentication method, a video of the user consuming the ordered health functional food is recorded through the camera of the user terminal, and the captured video is stored on the server. Analyzing with installed artificial intelligence, it is determined whether the user has consumed the health functional food, and only if the facial condition score and the moving body vision score are improved before and after consuming the health functional food, information regarding the weight and intake record is requested. A method of providing an artificial intelligence-based customized health functional food recommendation service, wherein a reward is paid to the user while providing it to the institution, and the reward is a user trust score, certification mark, and virtual currency. The method of claim 1, wherein the health checkup information includes the user's genetic test results regarding one or more of diseases, nutrients, health care, eating habits, exercise ability, hair, skin, and personal characteristics,
The genetic test results for the above diseases include the user's genetic information regarding one or more of stomach cancer, colon cancer, liver cancer, lung cancer, prostate cancer, thyroid cancer, head and neck cancer, esophageal cancer, breast cancer, cervical cancer, stroke, hyperlipidemia, and heart disease. ,
Genetic test results for the above nutrients include vitamin C, vitamin D, coenzyme Q10, magnesium, zinc, iron stores, potassium, calcium, arginine, fatty acids, vitamin A, vitamin B6, vitamin B12, vitamin E, vitamin K, selenium, and lutein. and the user's genetic information regarding metabolic capability for one or more nutrients from the group of nutrients including zeaxanthin,
The genetic test results related to health management include the user's genetic information related to one or more of the following: susceptibility to degenerative arthritis, motion sickness, obesity, uric acid level, neutral fat concentration, body fat percentage, body mass index, cholesterol, blood sugar, blood pressure, bone mass, and abdominal obesity. Including,
The genetic test results related to the eating habits include the user's genetic information regarding one or more of appetite, satiety, sweet taste sensitivity, bitter taste sensitivity, and salty taste sensitivity,
The genetic test results related to the exercise ability include the user's genetic information regarding one or more of the following: fitness for strength exercise, fitness for aerobic exercise, fitness for endurance exercise, muscle development ability, short-distance sprinting ability, ankle injury risk, grip strength, and post-exercise recovery ability. do,
The genetic test results regarding the hair include the user's genetic information regarding one or more of male pattern baldness, hair thickness, gray hair, and alopecia areata,
The genetic test results for the skin include the user's genetic information regarding one or more of spots, freckles, pigmentation, acne, skin aging, skin inflammation, and tanning reaction after sun exposure,
The genetic test results regarding the personal characteristics are artificial, including the user's genetic information regarding one or more of alcohol metabolism, alcohol dependence, nicotine metabolism, nicotine dependence, caffeine metabolism, caffeine dependence, insomnia, sleep habit time, and morning person. A method of providing intelligence-based customized health functional food recommendation service. delete delete delete delete