KR102615749B1 - Method, device and system for providing diet management service and mental health care service using it and automated processing of user customized diet management consulting information creation using artificial intelligence model - Google Patents

Abstract

According to one embodiment, in the method of automatically processing the generation of customized diet management consulting information using an artificial intelligence model performed by a device and providing diet management services and mental health care services using the same, changes in the first user's body analyzing physical changes of the first user during a first predetermined period based on monitoring information; estimating the amount of physical change in the first period based on a result of analyzing the physical change of the first user during the first period; calculating a goal achievement rate in the first period based on the amount of physical change in the first period and a preset target value of the first user; setting the diet difficulty level of the first user to a first level based on the goal achievement rate of the first period; Confirming that the second period after the first period belongs to the first season, and confirming that the food category preferred by the first user is the first category; Generating first matching information by matching the first grade, the first season, and the first category; Generating a first input signal by encoding the first matching information; Inputting the first input signal to a first artificial intelligence model trained to select a recommended diet through analysis of diet difficulty, season, and preferred food category; When the recommended diet for the first user is selected through the first input signal, obtaining a first output signal representing the recommended diet for the first user from the first artificial intelligence model; Setting the recommended diet of the first user as a first diet based on the first output signal; generating first consulting information recommending the first diet as a customized diet for the first user during the second period; And providing a method for automatically processing the creation of user-tailored diet management consulting information using an artificial intelligence model and providing a diet management service and mental health care service using the same, including the step of transmitting the first consulting information to the first user terminal. do.

Description

Method, device, and system for automatically processing user-tailored diet management consulting information creation using an artificial intelligence model and providing diet management services and mental health care services using the same {METHOD, DEVICE AND SYSTEM FOR PROVIDING DIET MANAGEMENT SERVICE AND MENTAL HEALTH CARE SERVICE USING IT AND AUTOMATED PROCESSING OF USER CUSTOMIZED DIET MANAGEMENT CONSULTING INFORMATION CREATION USING ARTIFICIAL INTELLIGENCE MODEL}

The following embodiments relate to technology for automatically processing the creation of customized diet management consulting information using an artificial intelligence model and providing diet management services and mental health care services using this.

As modern society becomes increasingly westernized and industrialized, the number of people suffering from overweight or obesity is gradually increasing. Overweight or obesity is a serious problem for individuals that causes various diseases such as adult diseases, but it also causes enormous social costs to society, making it one of the serious social problems of modern times.

Therefore, in order to solve overweight or obesity, dieting is widely practiced to the extent that it is considered essential for modern people. Additionally, recently, as people's desire for beauty has increased, diet has been in the spotlight not only as a solution to overweight or obesity, but also as a means to maintain a beautiful body and health.

Dietary management is essential for such diets, but it is difficult for users to find diet information that suits them.

Therefore, there is a need for research and development on technology that can help users manage their diet by recommending a customized diet according to the user.

Additionally, because the probability of mental problems such as eating disorders, depression, and suicidal thoughts increases due to mental breakdown during dieting, the demand for services related to mental health care is increasing, and the implementation of related technologies is required.

Korean Patent Publication No. 10-2023-0109455 Korean Patent No. 10-2371787 Korean Patent No. 10-2459892 Korean Patent No. 10-2197102

According to one embodiment, the purpose is to use an artificial intelligence model to automatically process the creation of customized diet management consulting information and provide diet management services and mental health care services using this.

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

According to one embodiment, in the method of automatically processing the generation of customized diet management consulting information using an artificial intelligence model performed by a device and providing diet management services and mental health care services using the same, changes in the first user's body analyzing physical changes of the first user during a first predetermined period based on monitoring information; estimating the amount of physical change in the first period based on a result of analyzing the physical change of the first user during the first period; calculating a goal achievement rate in the first period based on the amount of physical change in the first period and a preset target value of the first user; setting the diet difficulty level of the first user to a first level based on the goal achievement rate of the first period; Confirming that the second period after the first period belongs to the first season, and confirming that the food category preferred by the first user is the first category; Generating first matching information by matching the first grade, the first season, and the first category; Generating a first input signal by encoding the first matching information; Inputting the first input signal to a first artificial intelligence model trained to select a recommended diet through analysis of diet difficulty, season, and preferred food category; When the recommended diet for the first user is selected through the first input signal, obtaining a first output signal representing the recommended diet for the first user from the first artificial intelligence model; Setting the recommended diet of the first user as a first diet based on the first output signal; generating first consulting information recommending the first diet as a customized diet for the first user during the second period; And providing a method for automatically processing the creation of user-tailored diet management consulting information using an artificial intelligence model and providing a diet management service and mental health care service using the same, including the step of transmitting the first consulting information to the first user terminal. do.

The method of automatically processing the generation of user-tailored diet management consulting information using the artificial intelligence model and providing diet management services and mental health care services using the same includes, after the step of transmitting the first consulting information to the first user terminal, the first Analyzing a change in the body of the first user during the second period based on monitoring information about the change in the body of the first user; estimating the amount of physical change in the second period based on a result of analyzing the physical change of the first user during the second period; calculating a goal achievement rate in the second period based on the amount of physical change in the second period and the target value of the first user; If it is confirmed that the goal achievement rate of the second period is higher than the goal achievement rate of the first period, checking the remaining value remaining up to the target value of the first user; If the remaining value is confirmed to be greater than a preset standard value, maintaining the diet difficulty level of the first user at the first level; If the remaining value is confirmed to be less than the reference value, changing the difficulty level of the first user's diet to a second level that is easier than the first level; If it is confirmed that the goal achievement rate of the second period is lower than the goal achievement rate of the first period, changing the diet difficulty level of the first user to a third level that is more difficult than the first level; confirming that a third period after the second period belongs to a second season; When the first user's diet difficulty level is maintained at the first level, second matching information is generated by matching the first grade, the second season, and the first category, and the first user's diet difficulty level is When changed to the second grade, second matching information is generated by matching the second grade, the second season, and the first category, and when the diet difficulty of the first user is changed to the third grade, the first user's diet difficulty level is changed to the third grade. Generating second matching information by matching 3 grades, the second season, and the first category; Generating a second input signal by encoding the second matching information; Inputting the second input signal to the first artificial intelligence model; When the recommended diet for the first user is selected through the second input signal, obtaining a second output signal representing the recommended diet for the first user from the first artificial intelligence model; setting the recommended diet of the first user as a second diet based on the second output signal; generating second consulting information recommending the second diet as a customized diet for the first user during the third period; And it may further include transmitting the second consulting information to the first user terminal.

The method of automatically processing the creation of customized diet management consulting information using the artificial intelligence model and providing diet management services and mental health care services using the same is such that the goal achievement rate in the second period is lower than the goal achievement rate in the first period. If confirmed, determining that a mental health check of the first user is necessary; Containing at least one of the first user's posting upload history, the first user's location movement history, the first user's music listening history, the first user's video viewing history, and the first user's post viewing history collecting activity data of the first user; extracting activity details performed during the second period from the activity data of the first user as first activity data; Analyzing activity keywords indicating an activity state during the second period based on the first activity data; Based on the activity keyword, diagnosing whether there is a problem with the first user's mental health according to a preset classification standard; And when it is diagnosed that the first user has a first type of mental health problem, it may further include transmitting a notification message recommending consultation for the first type of problem to the first user terminal. .

According to one embodiment, there is an effect of helping users manage their diet by providing consulting information that recommends a user's customized diet using an artificial intelligence model.

Additionally, according to one embodiment, by providing a mental health care service, there is an effect of helping to manage the mental state of a user who is managing a diet.

Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned can 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.
Figure 2 is a flow chart to explain the process of providing a diet management service using an artificial intelligence model according to an embodiment.
Figures 3 and 4 are flowcharts illustrating a process for providing consulting information that adjusts a user's recommended diet by tracking consulting results according to an embodiment.
Figure 5 is a flowchart for explaining the process of providing mental health care services according to an embodiment.
Figure 6 is a flowchart for explaining the process of analyzing changes in the user's body according to one embodiment.
Figure 7 is a flowchart for explaining the process of estimating calorie intake and adding it to total calorie intake according to one embodiment.
Figure 8 is a flow chart for explaining the process of estimating the user's calorie intake by confirming the actual amount eaten according to one embodiment.
Figure 9 is an exemplary diagram of the configuration of a device 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.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, 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.

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.

In an embodiment, 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, recognition rates improve and sellers' tastes can be more accurately understood, 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 mimics the functions of the human brain such as cognition and judgment by utilizing machine learning algorithms such as deep learning, 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 like 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.

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 devices 200 that can communicate with each other through a communication network.

First, a communication network can be configured regardless of the communication mode, such as wired or wireless, and can be implemented in various forms to enable communication between servers and between servers and terminals.

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

The plurality of user terminals 100 are terminals used by users who wish to receive customized diet management services, including a first user terminal 110 used by the first user, and a second user terminal used by the second user ( 120), etc. may be included.

Each of the plurality of user terminals 100 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. A plurality of user terminals 100 may be configured to communicate with the device 200 in a wired or wireless manner.

Each of the plurality of user terminals 100 is connected to a web page operated by a person or organization providing services using the device 200, or is developed and distributed by a person or organization providing services using the device 200. An application can be installed. Each of the plurality of user terminals 100 may be linked to 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 explanation, the operation of the first user terminal 110 will be mainly described, but of course, 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 its own server owned by a person or organization that provides services using the device 200, a cloud server, or a p2p (peer-to-peer) set of distributed nodes. It may be possible. The device 200 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The device 200 may be equipped with at least one artificial intelligence model that performs an inference function.

The device 200 may be configured to communicate wired or wirelessly with a plurality of user terminals 100, 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 whether to display it or not.

The device 200 is implemented as a server that automatically processes the creation of consulting information for diet management customized to the user and provides diet management services and mental health care services using this, forming a platform for diet management services and mental health care services. can be provided.

Meanwhile, for convenience of explanation, only the first user terminal 110 and the second user terminal 120 are shown in FIG. 1 among the plurality of user terminals 100, but the number of terminals may vary depending on the embodiment. . As long as the processing capacity of the device 200 allows, the number of terminals is not particularly limited.

According to one embodiment, the device 200 may utilize artificial intelligence to select a recommended diet for the user and, through this, provide consulting information recommending a customized diet for the user. A detailed description regarding this will be provided later with reference to FIG. 2 .

Additionally, after providing consulting information, the device 200 tracks the consulting results to select a recommended diet for the user and, through this, provides consulting information adjusting the user's recommended diet. A detailed description related to this will be described later with reference to FIGS. 3 and 4.

Additionally, in order to manage the mental health of users who are on a diet, the device 200 can diagnose whether there is a problem with the user's mental health and, through this, provide mental health care services to the user. A detailed description regarding this will be provided later with reference to FIG. 5 .

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 artificial 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.

Figure 2 is a flow chart to explain the process of providing a diet management service using an artificial intelligence model according to an embodiment.

Referring to FIG. 2 , first, in step S201, the device 200 may analyze changes in the first user's body during a first period based on monitoring information about changes in the first user's body. Here, the first period is a predetermined period and may be set differently depending on the embodiment.

According to one embodiment, the monitoring information on changes in the first user's body is information monitored on how the first user's body has changed, and may be obtained from the first user terminal 110.

Monitoring information on physical changes of the first user may include details of calories consumed by the first user, details of calories consumed by the first user, details of the first user's physical condition, etc.

The first user's intake calorie history is a history indicating when and how many calories the first user consumed, and may consist of a list of information about the food eaten, calories consumed, intake time, etc., and the first user can eat the food. If the calorie intake is manually entered each time, the calorie intake may be added to the first user's calorie intake history each time the calorie intake is entered, and if the calorie intake is estimated by analysis of a photo of food, the calorie intake may be estimated. Each time may be added to the first user's calorie intake history.

The calorie consumption history of the first user is a history indicating when and how many calories the first user consumed, and may consist of a list of information about the exercise performed, calories burned, exercise time, etc., and the first user is exercising. If the calories burned are manually entered each time the calories burned are entered, they can be added to the first user's calories burned history, and if the calories burned are estimated by analyzing the type of exercise performed by the user, the calories burned are Each time an estimate is made, it may be added to the first user's calories burned history.

The body condition details of the first user are details indicating the body condition of the first user, and may consist of a list of information about the body condition such as the first user's height, weight, muscle mass, and body fat percentage, and the first user may be If the measurement result is manually entered each time the condition is measured, it may be added to the body condition history of the first user each time the measurement result is entered, and the meter that measured the body condition of the first user and the first user terminal ( If 110) is connected, each time the first user measures the physical condition, the measurement result may be automatically added to the first user's physical condition history.

That is, the first user terminal 110 may continuously accumulate and update the added information for each of the first user's calorie intake details, the first user's consumed calories details, and the first user's physical condition details, and the first user terminal 110 may continuously accumulate and update the added information. Based on the 1 user's calorie intake history, the first user's consumed calorie history, and the first user's physical condition history, monitoring information about the first user's body change may be generated, and the device 200 may generate monitoring information about the first user's body change. Monitoring information on physical changes of the first user may be received from the terminal 110, and based on the received monitoring information on physical changes of the first user, the physical changes of the first user may be analyzed during the first period. .

For example, the device 200 analyzes how the first user's body change has changed during a first period based on monitoring information about the first user's body change, and maintains the status quo of the first user's body change. It can be checked as one of weight loss, weight gain, muscle mass loss, and muscle mass increase. In the case of weight loss, check how much weight was lost during the first period. If it is weight gain, check how much weight was gained during the first period. In the case of a decrease in muscle mass, it is possible to check how much the muscle mass was reduced during the first period, and in the case of an increase in muscle mass, it is possible to check how much the muscle mass was increased during the first period.

According to one embodiment, based on monitoring information on physical changes of the first user, the calorie intake of the first user during the first period and the calorie consumption of the first user during the first period are confirmed, and through this, the first user Changes in the user's body can be analyzed. A detailed description regarding this will be provided later with reference to FIG. 6 .

In step S202, the device 200 may estimate the amount of physical change in the first period based on a result of analyzing the physical change of the first user during the first period.

For example, if the physical change of the first user during the first period is confirmed to be the status quo, the device 200 may estimate the amount of physical change in the first period as 0, and the physical change of the first user during the first period may be estimated as 0. If the body change in the first period is confirmed to be a 1kg weight loss, the amount of physical change in the first period can be estimated as a 1kg weight loss, and if the physical change of the first user during the first period is confirmed to be a 1kg weight gain, the amount of physical change in the first period can be estimated as the body weight. It can be estimated as an increase of 1kg, and if the physical change of the first user during the first period is confirmed to be a decrease in muscle mass by 1kg, the amount of physical change in the first period can be estimated as a decrease in muscle mass by 1kg, and the physical change of the first user during the first period can be estimated as a decrease of 1kg in muscle mass. If the physical change is confirmed as an increase in muscle mass by 1kg, the amount of physical change in the first period can be estimated as an increase in muscle mass by 1kg.

In step S203, the device 200 may calculate the goal achievement rate in the first period based on the amount of physical change in the first period and the target value of the first user. Here, the first user's target value may be preset and registered by the first user.

For example, if the amount of physical change in the first period is estimated to be 1 kg weight loss, and the first user's target value is set to 10 kg weight loss, the device 200 compares the 1 kg weight loss and the 10 kg weight loss, The goal achievement rate for period 1 can be calculated as 10%.

In addition, when the amount of physical change in the first period is estimated to be 1 kg weight gain and the first user's target value is set to 10 kg weight loss, the device 200 compares the 1 kg weight gain and the 10 kg weight loss, and The goal achievement rate can be calculated as -10%.

In step S204, the device 200 may set the diet difficulty level of the first user to the first level based on the goal achievement rate of the first period. At this time, the device 200 may set the first grade to a level that is more difficult as the goal achievement rate in the first period is lower.

For example, if the goal achievement rate in the first period is 50% or more, the device 200 sets the diet difficulty level of the first user to grade 1, which is the easiest level, and if the goal achievement rate in the first period is 0% or more and 50%. If it is less than %, the first user's diet difficulty can be set to level 2, and if the goal achievement rate in the first period is less than 0%, the first user's diet difficulty can be set to level 3.

In step S205, the device 200 may confirm that the second period after the first period belongs to the first season. At this time, the second period may be set to the same period as the first period. For example, if the first period is January, the second period may be set to February, and if the second period is set to February, The first season can be identified as winter.

In step S206, the device 200 may identify the food category preferred by the first user as the first category. At this time, food categories can be divided into Korean, Japanese, Chinese, Western, etc., stew, stir-fry, seasoned, etc. In addition, food categories can be divided based on various criteria.

Based on the first user information, the device 200 may check the food category preferred by the first user and confirm that the food category preferred by the first user is the first category. Here, the first user information may be obtained through a database or the first user terminal 110.

In step S207, the device 200 may generate first matching information by matching the first grade, first season, and first category.

In step S208, the device 200 may generate a first input signal by encoding the first matching information.

Specifically, in order to use the first matching information as input to an artificial intelligence model, the device 200 may perform normal information processing on the first matching information and generate a first input signal.

In step S209, the device 200 may input a first input signal to the first artificial intelligence model learned in advance. Here, the first artificial intelligence model may be trained to select a recommended diet through analysis of diet difficulty, season, and preferred food category.

The first artificial intelligence model receives an input signal generated by encoding matching information matching diet difficulty, season, and preferred food category, then selects the user's recommended diet through the input signal, and produces an output signal representing the selected result. It may be an algorithm that outputs .

In other words, the first artificial intelligence model analyzes which foods would be good for the user to eat, considering diet difficulty, season, and preferred food category, generates a recommended diet based on the analyzed results, and outputs representing the generated recommended diet. A signal can be output.

In step S210, when the recommended diet for the first user is selected through the first input signal, the device 200 may obtain a first output signal representing the recommended diet for the first user from the first artificial intelligence model.

For example, when the device 200 inputs a first input signal to the first artificial intelligence model, the first user's recommended diet is the first food for breakfast, the second food for lunch, and the recommended diet for the first user through the first input signal. If it is selected to eat the third food, a first output signal representing (first food, second food, third food) can be obtained from the first artificial intelligence model. At this time, the first user's recommended diet may be selected as what foods to eat for breakfast, lunch, and dinner for each day during a predetermined period.

In other words, the first artificial intelligence model allows the user to select which foods to eat for breakfast, lunch, and dinner for each day through input signals, generates a recommended diet by collecting the selected foods, and generates an output signal representing the generated recommended diet. Can be printed. To this end, the first artificial intelligence model allows the user to select a food and generate a recommended diet based on food information classified by grade, food information classified by season, food information classified by category, etc. stored in the database. It may be in a pre-trained state to analyze whether

The learning device in which learning of the first artificial intelligence model is performed may be the same device as the device 200 that selects a recommended diet through analysis of diet difficulty, season, and preferred food category using the learned first artificial intelligence model, or may be a separate device. It may be a device of Below, the process by which the first artificial intelligence model is learned is explained.

First, the learning device can generate input based on matching information that matches diet difficulty, season, and preferred food categories.

Specifically, the learning device may perform a preprocessing process on matching information that matches diet difficulty, season, and preferred food categories. The pre-processed matching information can be used as an input to the first artificial intelligence model, or the input can be generated through normal processing to remove unnecessary information.

Next, the learning device can apply input to the first artificial intelligence model. The first artificial intelligence model may be an artificial neural network learned according to reinforcement learning. The first artificial intelligence model may be a Q-Network, DQN (Depp Q-Network), or relational network (RL) structure suitable for outputting abstract inference through reinforcement learning.

The first artificial intelligence model learned according to reinforcement learning can be updated and optimized by reflecting the evaluation of various rewards.

For example, for the first reward, the more difficult the level of diet difficulty is, the higher the reward value can be when selecting a recommended diet by including diet foods in the menu, and for the second reward, the reward value can be increased by including seasonal foods in the menu and selecting a recommended diet. If selected, the reward value can be increased, and as a third reward, the reward value can be increased if a recommended diet is selected by including foods belonging to the preferred food category in the diet.

Next, the learning device may obtain an output from the first artificial intelligence model. At this time, the output of the first artificial intelligence model may be information indicating the user's recommended diet. In other words, the first artificial intelligence model can select the user's recommended diet by analyzing matching information that matches diet difficulty, season, and preferred food categories, and output information about the selected recommended diet. At this time, information about the recommended diet may include information indicating what food to eat for breakfast, lunch, and dinner during a predetermined period.

Next, the learning device may evaluate the output of the first artificial intelligence model and pay a reward.

For example, the learning device awards more first rewards when the recommended diet is selected by including diet foods in the menu as the diet difficulty level becomes more difficult, and second rewards are awarded when the recommended diet is selected by including seasonal foods appropriate for the season in the menu. If you award a lot of rewards and select a recommended diet by including foods belonging to the preferred food category in the diet, you can award a lot of third rewards.

Next, the learning device may update the first artificial intelligence model based on the evaluation.

Specifically, the learning device determines actions to be taken in specific states so that the expected value of the sum of rewards is maximized in an environment where the first artificial intelligence model analyzes changes in the user's body. The first artificial intelligence model can be updated through the process of optimizing the policy that determines actions.

For example, the learning device matches the first grade, first season, and first category, and if there is no problem with the result of selecting the first user's recommended diet based on the first matching information, the learning device selects the first user's recommended diet. Generate a first learning signal indicating that there is no problem with the selected result, apply the first learning signal to the first artificial intelligence model, and input signals having similar values to the first grade, first season, and first category. When is input, the first artificial intelligence model can be updated through a process of training the first artificial intelligence model to select a recommended diet similar to the first user's recommended diet.

Meanwhile, the process of optimizing the policy can be accomplished through estimating the maximum 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 can be done through stochastic gradient descent (SGD), etc. The process of optimizing the policy is not limited to this, and various optimization algorithms used in reinforcement learning can be used.

The learning device can gradually update the first artificial intelligence model by repeating the learning process of the first artificial intelligence model described above. Through this, the learning device can learn the first artificial intelligence model that selects and outputs the user's recommended diet.

That is, when selecting a user's recommended diet, the learning device can learn the first artificial intelligence model by reflecting reinforcement learning through the first to third rewards, etc. and adjusting the analysis standard.

In step S211, the device 200 may set the recommended diet of the first user as the first diet based on the first output signal.

That is, when the first output signal representing the recommended diet of the first user is obtained, the device 200 determines what foods the first user should eat for breakfast, lunch, and dinner during the second period, based on the first output signal. After confirmation, the first diet can be set based on the confirmed foods.

In step S212, the device 200 may generate first consulting information recommending the first diet as the first user's customized diet for the second period. Here, the first consulting information may include information indicating what food the first user eats for breakfast, lunch, and dinner during the second period.

In step S213, the device 200 may transmit first consulting information to the first user terminal 110.

Figures 3 and 4 are flowcharts illustrating a process for providing consulting information that adjusts a user's recommended diet by tracking consulting results 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, and each step shown in FIG. 4 may be performed after each step shown in FIG. 3 is performed. can be performed.

Referring to FIG. 3 , first, in step S301, the device 200 may analyze changes in the body of the first user during a second period based on monitoring information about changes in the body of the first user.

In step S302, the device 200 may estimate the amount of physical change in the second period based on a result of analyzing the physical change of the first user during the second period.

In step S303, the device 200 may calculate the goal achievement rate in the second period based on the amount of physical change in the second period and the first user's goal value.

In step S304, the device 200 may check whether the goal achievement rate of the second period is higher than the goal achievement rate of the first period.

If it is confirmed in step S304 that the goal achievement rate of the second period is higher than the goal achievement rate of the first period, in step S305, the device 200 may check the remaining value up to the first user's goal.

For example, if the first user's goal is to reduce body weight from 70 kg to 60 kg, the first user's goal value may be set to 10 kg weight loss, and the device 200 may determine that the body change in the first period is 1 kg body weight. If a decrease is estimated, the goal achievement rate in the first period is calculated as 10%, and if the body change in the second period is estimated to be a 2kg weight loss, the goal achievement rate in the second period is calculated as 20%, and then from the first period, the goal achievement rate is calculated as 20%. The amount of physical change until the second period can be estimated as a total weight loss of 3kg, and by comparing the 3kg weight loss and the 10kg weight loss, the remaining value remaining up to the first user's target can be confirmed to be 7kg.

In step S306, the device 200 can check whether the remaining value is greater than the reference value. Here, the reference value may be set differently depending on the embodiment.

If the remaining value is confirmed to be greater than the reference value in step S306, the device 200 may maintain the first user's diet difficulty level at the first level in step S307.

In other words, if the device 200 confirms that the target achievement rate of the first period is higher than the target achievement rate of the second period and the remaining value is greater than the reference value, the recommended diet is sufficiently effective, but there is still a lot left to reach the target value, so the remaining value is greater than the reference value. 1 The user's diet difficulty level can be maintained at the existing first level.

If the remaining value is confirmed to be less than the reference value in step S306, the difficulty level of the first user's diet may be changed to a second level that is easier than the first level in step S308.

For example, if the first user's diet difficulty level is set to level 3, the device 200 may change the first user's diet level of difficulty from level 3 to level 2.

In other words, if the device 200 determines that the goal achievement rate of the first period is higher than the goal achievement rate of the second period and the remaining value is less than the reference value, the recommended diet is effective enough and there is not much left to reach the target value, so the 1 The user's diet difficulty level can be changed from the existing level to an easier level.

Meanwhile, if it is confirmed in step S304 that the goal achievement rate of the second period is lower than the goal achievement rate of the first period, in step S309, the device 200 adjusts the difficulty level of the first user's diet to a third level that is more difficult than the first level. It can be changed to .

For example, if the first user's diet difficulty level is set to level 1, the device 200 may change the first user's diet difficulty level from level 1 to level 2.

That is, if the device 200 determines that the goal achievement rate of the first period is lower than the goal achievement rate of the second period, the recommended diet has no effect, and the difficulty level of the first user's diet is graded from the existing level to a more difficult level. It can be changed to .

After any one of steps S307, S308, and S309 is performed, in step S401, the device 200 may confirm that the third period after the second period belongs to the second season. At this time, the third period may be set to the same period as the first period and the second period. For example, if the first period is January and the second period is February, the third period may be set to March. And, if the third period is set to March, the second season can be confirmed as spring.

In step S402, when the first user's diet difficulty level is maintained at the first level, the device 200 may generate second matching information by matching the first level, the second season, and the first category.

In step S403, when the first user's diet difficulty level changes to the second level, the device 200 may generate second matching information by matching the second level, the second season, and the first category.

In step S404, when the first user's diet difficulty level changes to the third level, the device 200 may generate second matching information by matching the third level, the second season, and the first category.

In step S405, the device 200 may generate a second input signal by encoding the second matching information.

In step S406, the device 200 may input a second input signal to the first artificial intelligence model.

In step S407, when the recommended diet for the first user is selected through the second input signal, the device 200 may obtain a second output signal representing the recommended diet for the first user from the first artificial intelligence model.

In step S408, the device 200 may set the first user's recommended diet as the second diet based on the second output signal.

In step S409, the device 200 may generate second consulting information recommending the second diet as the first user's customized diet for the third period. Here, the second consulting information may include information indicating what food the first user eats for breakfast, lunch, and dinner during the third period.

In step S410, the device 200 may transmit the second consulting information to the first user terminal 110.

Figure 5 is a flowchart for explaining the process of providing mental health care services according to an embodiment.

Referring to FIG. 5, first, in step S501, if it is confirmed that the goal achievement rate of the second period is lower than the goal achievement rate of the first period, the device 200 may determine that a mental health check of the first user is necessary. there is.

In step S502, the device 200 records at least one of the first user's posting upload history, the first user's location movement history, the first user's music listening history, the first user's video viewing history, and the first user's posting viewing history. Activity data of the first user, including one, may be collected.

The device 200 may collect activity data of the first user through various techniques such as crawling and big data collection.

Specifically, the device 200 is linked to an SNS server, can collect the first user's posting upload history from the SNS server, and tracks the location movement of the first user from the first user terminal 110 to the recorded location. Movement history can be collected, linked to the music service providing server, and the first user's music listening history can be collected from the music service providing server. Linked to the video service providing server, the first user can be linked to the video service providing server. The video viewing history can be collected, and by linking with the bulletin board service providing server, the first user's posting viewing history can be collected from the bulletin board service providing server.

In step S503, the device 200 may extract activity details performed during the second period from the activity data of the first user as first activity data.

That is, the device 200 may check the activity details of the first user by date based on the activity data of the first user and then extract the activity details performed during the second period as the first activity data.

Specifically, the device 200 may extract post upload details during a second period from the post upload details of the first user, and extract location movement details during a second period from the first user's location movement details. Music listening history during a second period can be extracted from the first user's music listening history, video viewing history during a second period can be extracted from the first user's video viewing history, and the first user's video viewing history can be extracted from the first user's music listening history during a second period. The post view details for the second period can be extracted from the post view details.

In step S504, the device 200 may analyze an activity keyword indicating an activity state during the second period based on the first activity data.

Specifically, based on the first activity data, the device 200 includes upload post history during the second period, location movement history during the second period, music listening history during the second period, and video viewing during the second period. By checking at least one of the history and the post view history during the second period, activity keywords indicating the activity state during the second period can be analyzed.

For example, the device 200 may check the hashtags registered in posts uploaded during the second period based on the uploaded post history during the second period and analyze the confirmed hashtags as activity keywords. .

In addition, the device 200 confirms the places visited during the second period based on the location movement history during the second period, confirms the place category of what the confirmed place does, and performs activities in the confirmed place category. It can be analyzed by keyword. Here, the place category can be classified into home, restaurant, department store, theater, etc.

In addition, based on the music listening history during the second period, the device 200 confirms the music listened to during the second period, determines the music category of which genre of music the listened to music is, and selects the confirmed music category. It can be analyzed by activity keywords. Here, the music category can be classified into ballad, dance, trot, etc.

In addition, based on the video viewing history during the second period, the device 200 confirms the video watched during the second period, determines the genre of the video and the video category of the video watched, and selects the confirmed video category. It can be analyzed by activity keywords. Here, video categories can be classified into romance, action, thriller, comedy, etc.

In addition, the device 200 checks the posts viewed during the second period based on the post view history during the second period, determines which bulletin board the confirmed post was posted on, and selects the confirmed bulletin board as an activity keyword. It can be analyzed as: Here, bulletin boards can be classified into consultation, health, beauty, humor, etc.

In step S505, the device 200 may diagnose whether there is a problem with the first user's mental health according to a preset classification standard based on the activity keyword. For this purpose, problem keywords are set for each type of mental health problem, and through comparison between problem keywords and activity keywords, it is possible to diagnose whether there is a problem with mental health. Here, mental health problems are problems caused by diet, and can be divided into various types such as eating disorders, depression, and suicidal impulses.

That is, the device 200 compares activity keywords with problem keywords set for each type, and when a certain number of matching keywords between a specific type of problem keyword and an activity keyword are confirmed, it is diagnosed as having a problem of that type. You can.

For example, the device 200 may diagnose that there is a first type of problem if it is confirmed that three or more keywords match as a result of comparing the activity keyword and the first type of problem keyword.

In step S506, if it is diagnosed that the first user has a first type of mental health problem, the device 200 may transmit a notification message recommending consultation for the first type of problem to the first user terminal. Here, the notification message may include information about a counseling center where counseling is available for the first type of problem.

Figure 6 is a flowchart for explaining the process of analyzing changes in the user's body according to one embodiment.

Referring to FIG. 6 , first, in step S601, the device 200 may collect the calorie intake of the first user during the first period and calculate the total calorie intake of the first period. Here, if the first user's calorie intake is entered every time the first user eats food, the input calorie intake can be added to the first user's calorie intake history, and the calorie intake can be calculated by analyzing the photo of the food. Once estimated, the estimated calorie intake may be added to the first user's calorie intake history. A detailed explanation of the process of estimating calorie intake by analyzing photos of food will be described later with reference to FIG. 7.

That is, the device 200 obtains the calorie intake details of the first user from the first user terminal 110 and determines the calories consumed by the first user during the first period based on the calorie intake details of the first user. And, by collecting the confirmed calories, the total calorie intake for the first period can be calculated.

In step S602, the device 200 may calculate the active metabolic rate of the first period by collecting calories consumed by the first user during the first period. Here, if the first user inputs the calories burned every time the first user performs exercise, the input calories burned can be added to the first user's calories burned, and the calories burned can be consumed by analyzing the type of exercise performed by the user. Once the calories are estimated, the estimated calories burned may be added to the first user's calories burned history.

That is, the device 200 obtains the details of calories consumed by the first user from the first user terminal 110 and determines the calories consumed by the first user during the first period based on the details of calories consumed by the first user. And, by collecting the confirmed calories, the active metabolic rate of the first period can be calculated.

In step S603, the device 200 may calculate the basal metabolic rate of the first user based on the first user's gender, age, weight, and height. At this time, the device 200 may check the gender, age, weight, and height of the first user based on the first user information and calculate the basal metabolic rate of the first user. Here, the first user information may be obtained through a database or the first user terminal 110.

When calculating the basal metabolic rate of the first user, the device 200 may calculate the basal metabolic rate of the first user through various known methods, such as the Harris Benedict equation and the Miffin Sategel equation.

In step S604, the device 200 may generate third matching information by matching the total calorie intake of the first period, the active metabolic rate of the first period, and the basal metabolic rate of the first user.

In step S605, the device 200 may generate a third input signal by encoding the third matching information.

Specifically, in order to use the third matching information as an input to an artificial intelligence model, the device 200 may perform normal information processing on the third matching information and generate a third input signal.

In step S606, the device 200 may input a third input signal to the pre-trained second artificial intelligence model. Here, the second artificial intelligence model may be trained to identify physical changes through analysis of total calorie intake, active metabolic rate, and basal metabolic rate.

The second artificial intelligence model receives an input signal generated by encoding matching information matching total calorie intake, active metabolic rate, and basal metabolic rate, then analyzes the user's body changes through the input signal, and outputs the analysis result. It may be an algorithm that outputs a signal.

In other words, the second artificial intelligence model can predict and analyze how the user's body will change by considering total calorie intake, active metabolic rate, and basal metabolic rate, and output an output signal representing the analyzed result.

In step S607, when the change in the first user's body is identified through the third input signal, the device 200 may obtain a third output signal representing the change in the first user's body from the second artificial intelligence model.

For example, the device 200 inputs a third input signal to the second artificial intelligence model, and when the change in the first user's body is analyzed as weight loss through the third input signal, the device 200 determines the weight loss from the second artificial intelligence model. A third output signal indicating an increase in muscle mass can be obtained, and when the physical change of the first user is analyzed as an increase in muscle mass through the third input signal, a third output signal indicating an increase in muscle mass can be obtained from the second artificial intelligence model. . At this time, the third output signal may include information indicating how much the body weight will be reduced when the first user's physical change is analyzed as a weight loss, and when the first user's physical change is analyzed as an increase in muscle mass, the third output signal may include information indicating how much the body weight will be reduced. It may contain information indicating how much muscle mass will be increased.

In other words, the second artificial intelligence model can identify changes in the user's body through input signals and output an output signal representing the identified body changes. To this end, the second artificial intelligence model may be pre-trained to analyze how the user's body has changed based on body change information classified by situation stored in the database.

The learning device in which learning of the second artificial intelligence model is performed may be the same device as the device 200 that determines physical changes by analyzing total calorie intake, active metabolic rate, and basal metabolic rate using the learned second artificial intelligence model, It may be a separate device. Below, the process by which the second artificial intelligence model is learned is explained.

First, the learning device can generate input based on matching information that matches total calorie intake, active metabolic rate, and basal metabolic rate.

Specifically, the learning device may perform a preprocessing process on matching information that matches total calorie intake, active metabolic rate, and basal metabolic rate. The pre-processed matching information can be used as is as an input to the second artificial intelligence model, or the input can be generated through normal processing to remove unnecessary information.

Next, the learning device can apply input to the second artificial intelligence model. The second artificial intelligence model may be an artificial neural network learned according to reinforcement learning. The second artificial intelligence model may be a Q-Network, DQN (Depp Q-Network), or relational network (RL) structure suitable for outputting abstract inference through reinforcement learning.

The second artificial intelligence model learned according to reinforcement learning can be updated and optimized by reflecting the evaluation of various rewards.

For example, the 4th compensation can increase the compensation value by analyzing that the more the total calorie intake is greater than the sum of active metabolic rate and basal metabolic rate, the greater the weight gain, and the 5th compensation can increase the compensation value if the total calorie intake is greater than the active metabolic rate and basal metabolic rate. If the value is less than the added value, the compensation value can be higher if analyzed as a greater weight loss, and the sixth compensation is analyzed as a greater increase in muscle mass if the activity ratio calculated by dividing the active metabolic rate by the basal metabolic rate is higher than the reference rate. The compensation value may be higher, and the seventh compensation may be higher if the activity rate calculated by dividing the active metabolic rate by the basal metabolic rate is analyzed as a decrease in muscle mass as the activity rate is lower than the reference rate.

Next, the learning device can obtain an output from the second artificial intelligence model. At this time, the output of the second artificial intelligence model may be information indicating changes in the user's body. In other words, the second artificial intelligence model can identify changes in the user's body by analyzing matching information that matches total calorie intake, active metabolic rate, and basal metabolic rate, and output information about the identified physical changes. At this time, the information about the physical change may include any one of maintaining the status quo, weight loss, weight gain, muscle mass loss, and muscle mass increase. In the case of weight loss, it includes information indicating how much the weight will be reduced, and weight increase. In the case of a decrease in muscle mass, it includes information indicating how much the body weight will increase, in the case of a decrease in muscle mass, it includes information indicating how much the muscle mass will be decreased, and in the case of an increase in muscle mass, it may include information indicating how much the muscle mass will increase. .

Next, the learning device can evaluate the output of the second artificial intelligence model and pay a reward.

For example, if the learning device analyzes that the total calorie intake is greater than the sum of the active metabolic rate and the basal metabolic rate, the greater the fourth reward is awarded, and if the total calorie intake is greater than the sum of the active metabolic rate and the basal metabolic rate, the learning device awards the fourth reward more. If it is analyzed that the lower the weight, the greater the weight loss, the 5th reward is awarded more, and if the activity ratio calculated by dividing the active metabolic rate by the basal metabolic rate is analyzed to be higher than the standard rate, the 6th reward is awarded more. , if the activity rate calculated by dividing the active metabolic rate by the basal metabolic rate is analyzed to be lower than the standard rate, the greater the decrease in muscle mass, the greater the seventh compensation can be awarded.

Next, the learning device may update the second artificial intelligence model based on the evaluation.

Specifically, the learning device determines actions to be taken in specific states so that the expected value of the sum of rewards is maximized in an environment where the second artificial intelligence model analyzes changes in the user's body. The second artificial intelligence model can be updated through the process of optimizing the policy that determines actions.

For example, the learning device has a problem with the results of analyzing the physical changes of the first user based on matching information that matches the first user's total calorie intake, the first user's active metabolic rate, and the first user's basal metabolic rate. If there is none, a second learning signal is generated indicating that there is no problem with the results of analyzing the first user's body changes, and the second learning signal is applied to the second artificial intelligence model to obtain a calorie intake similar to that of the first user; When analyzing the physical changes of a second user who has an active metabolic rate and basal metabolic rate, through the process of learning a second artificial intelligence model to analyze the physical changes of the second user similarly to the physical changes of the first user. , the second artificial intelligence model can be updated.

Meanwhile, the process of optimizing the policy can be accomplished through estimating the maximum 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 can be done through stochastic gradient descent (SGD), etc. The process of optimizing the policy is not limited to this, and various optimization algorithms used in reinforcement learning can be used.

The learning device can gradually update the second artificial intelligence model by repeating the learning process of the second artificial intelligence model described above. Through this, the learning device can learn a second artificial intelligence model that analyzes and outputs changes in the user's body.

That is, when the learning device analyzes changes in the user's body, it can learn the second artificial intelligence model by reflecting reinforcement learning through the fourth to seventh rewards, etc. and adjusting the analysis standard.

In step S608, the device 200 may analyze changes in the first user's body during the first period based on the third output signal.

That is, when the third output signal representing the change in the body of the first user is obtained, the device 200 determines how and how much the change in the body of the first user has changed based on the third output signal, and through this, Changes in the first user's body can be analyzed during one period.

For example, based on the third output signal, the device 200 may determine the physical change of the first user during the first period as one of maintaining status quo, weight loss, weight gain, muscle mass decrease, and muscle mass increase, and weight If it is a decrease, check how much body weight was lost during the baseline period. If it is a weight gain, check how much body weight was gained during the baseline period. If it is a loss of muscle mass, check how much muscle mass was lost during the baseline period. In this case, you can check how much muscle mass has increased during the reference period.

Figure 7 is a flowchart for explaining the process of estimating calorie intake and adding it to total calorie intake according to one embodiment.

Referring to FIG. 7 , first, in step S701, the device 200 may receive a first image generated by photographing the first food from the first user terminal 110.

Specifically, the first user terminal 110 may generate a first image by photographing the first food that the first user wants to eat using a camera provided in the first user terminal 110, and the device (200) When the first food that the first user wants to eat is photographed using the camera of the first user terminal 110, the first food generated by photographing the first food from the first user terminal 110 Images can be received.

In step S702, the device 200 may generate a fourth input signal by encoding the first image.

Specifically, the device 200 may generate a fourth input signal by encoding pixels of the first image into color information. Color information may include, but is not limited to, RGB color information, brightness information, and saturation information. The device 200 can convert color information into a numerical value and encode an image in the form of a data sheet including this value.

In step S703, the device 200 may input the fourth input signal to the third artificial intelligence model learned in advance. Here, the third artificial intelligence model may be trained to recognize the type and amount of food through image analysis.

The third artificial intelligence model is an algorithm that receives an input signal generated by encoding an image, recognizes the type and amount of food in the image through the input signal, and outputs an output signal indicating the type and amount of the recognized food. It can be.

The third artificial intelligence model according to one embodiment is implemented as a convolutional neural network, and the convolutional neural network consists of a feature extraction neural network and a classification neural network, and the feature extraction neural network sequentially stacks the input signal into a convolutional layer and a pooling layer. do. The convolution layer contains convolution operations, convolution filters, and activation functions. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. The activation function generally uses, but is not limited to, the ReLU function, sigmoid function, and tanh function. The pooling layer is a layer that reduces the size of the input matrix and uses a method of extracting representative values by grouping pixels in a specific area. The calculation of the pooling layer generally uses average or maximum values, but is not limited to these. The operation is performed using a square matrix, and a 9X9 matrix is generally used. The convolution layer and the pooling layer are alternately repeated until the input becomes sufficiently small while maintaining the difference.

According to one embodiment, a classification neural network has a hidden layer and an output layer. In a convolutional neural network implemented as a third artificial intelligence model, there are generally three or more hidden layers, and the number of nodes in each hidden layer is set to 100, but in some cases, it can be set to more. The activation function of the hidden layer uses the ReLU function, sigmoid function, and tanh function, but is not limited to these. There are a total of two output layer nodes in the convolutional neural network, and the output values for the type of food and the output value for the amount of food can be output through the two output layer nodes, respectively.

In step S704, when the type of food is recognized as the first food and the amount of food is recognized as the first weight through the fourth input signal, the device 200 selects the first food and the first weight from the third artificial intelligence model. A fourth output signal representing the signal can be obtained.

For example, the device 200 inputs a fourth input signal to the third artificial intelligence model, and when the type of food is recognized as a hamburger and the amount of food is recognized as 500g through the fourth input signal, the third artificial intelligence model A fourth output signal representing hamburger and 500g can be obtained from the model.

In other words, the third artificial intelligence model can use an input signal generated by encoding an image as input, and information indicating the type and amount of food as output.

Encoding according to one embodiment may be accomplished by storing color information for each pixel of an image in the form of a numerical data sheet. The color information may include RGB color, brightness information, and saturation information contained in one pixel. , but is not limited to this.

According to one embodiment, the third artificial intelligence model may be composed of a feature extraction neural network and a classification neural network. The feature extraction neural network may perform the task of separating food and background in an image of food, and the classification neural network may perform the task of separating food and background from an image of food. You can perform the task of determining what type of food is in an image and how much food is in the image.

The method by which a feature extraction neural network distinguishes between food and background is based on the data sheet of the input signal encoding the image, where the change in each value of color information is more than 30% in 6 or more of the 8 pixels including one pixel. A group of pixels that are detected as objects can be used as the boundary between food and background, but are not limited to this.

The feature extraction neural network sequentially stacks the input signal into a convolutional layer and a pooling layer. The convolution layer contains convolution operations, convolution filters, and activation functions. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. The activation function generally uses, but is not limited to, the ReLU function, sigmoid function, and tanh function. The pooling layer is a layer that reduces the size of the input matrix and uses a method of extracting representative values by grouping pixels in a specific area. The calculation of the pooling layer generally uses average or maximum values, but is not limited to these. The operation is performed using a square matrix, and a 9X9 matrix is generally used. The convolution layer and the pooling layer are alternately repeated until the input becomes sufficiently small while maintaining the difference.

The classification neural network can identify the type of food in the image by checking the shape of the food distinguished from the background through a feature extraction neural network and checking whether it is similar to a predefined representative food for each food. At this time, information stored in the database can be used to compare foods.

The classification neural network prioritizes the task of identifying the type of food, and can even determine the amount of food depending on the shape and size of the identified food.

A classification neural network has a hidden layer and an output layer. Generally, there are more than 5 hidden layers, and each hidden layer has 80 nodes, but in some cases, it can be set to more. The activation function of the hidden layer uses the ReLU function, sigmoid function, and tanh function, but is not limited to these. There can be a total of two output layer nodes in the classification neural network.

The output of the classification neural network is an output value for the type of food and an output value for the amount of food, which can indicate the type of food and the amount of food. For example, if the output value is (1, 300), the type of food is hamburger and the amount of food is 300g, and if the output value is (2, 500), the type of food is pizza and the amount of food is 300g. You can indicate that the amount is 500g.

According to one embodiment, the third artificial intelligence model can learn by receiving a third learning signal generated by the corrected answer input by the user when the user discovers a problem in the output through the third artificial intelligence model. Problems with output through the third artificial intelligence model may mean that an output value indicating a different type of food is output, or an output value indicating a different amount of food is output.

The third learning signal according to one embodiment is created based on the error between the correct answer and the output value, and in some cases, SGD using delta, a batch method, or a method following a backpropagation algorithm may be used. The third artificial intelligence model performs learning by modifying the existing weights using the third learning signal, and in some cases, momentum can be used. A cost function can be used to calculate the error, and the Cross entropy function can be used as the cost function.

The learning device in which learning of the third artificial intelligence model is performed may be the same device as the device 200 that recognizes the type and amount of food through image analysis using the learned third artificial intelligence model, or may be a separate device. . Below, the process by which the third artificial intelligence model is learned is explained.

The third artificial intelligence model includes an input layer through which training samples are input and an output layer through which training outputs are output, and may be learned based on the difference between the training outputs and the first labels. Here, the first labels may be defined based on representative images for each type of food and representative images for each weight of each food. The third artificial intelligence model is connected to a group of multiple nodes, and is defined by weights between connected nodes and an activation function that activates the nodes.

The learning device can learn a third artificial intelligence model using the GD (Gradient Descent) technique or the SGD (Stochastic Gradient Descent) technique. The learning device may use a loss function designed by the outputs and labels of the third artificial intelligence model.

The learning device can calculate the training error using a predefined loss function. The loss function may be predefined with labels, outputs, and parameters as input variables, where the parameters may be set by weights in the third artificial intelligence model. 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 find weights that affect the training error using a backpropagation technique. Here, the weights are relationships between nodes in the third artificial intelligence model. 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 may acquire labeled training food images from a database. The learning device can acquire pre-labeled information on food images set by type of food and food images set by weight of each food, and the food images can be labeled according to the type and amount of pre-classified food. .

According to one embodiment, the learning device can acquire 1000 labeled training food images and generate first training food vectors based on the labeled training food images. Various methods can be employed to extract the first training food vectors.

According to one embodiment, the learning device may obtain first training outputs by applying the first training food vectors to the third artificial intelligence model. The learning device may learn a third artificial intelligence model based on the first training outputs and first labels. The learning device may learn the third artificial intelligence model by calculating training errors corresponding to the first training outputs and optimizing the connection relationship of nodes in the third artificial intelligence model to minimize the training errors. Through this, the third artificial intelligence model can recognize the type and amount of food in the image.

In step S705, the device 200 may analyze that the first user eats the first food of the first weight based on the fourth output signal.

That is, when the fourth output signal representing the first food and the first weight is obtained, the device 200 confirms the first food and the first weight based on the fourth output signal, and through this, the first user It can be analyzed as eating the first food of the first weight.

The device 200 may transmit a notification message to the first user terminal 110 notifying that the first user has photographed the first food in order to eat the first food of the first weight. At this time, when a request for modification of at least one of the first food and the first weight is received through confirmation of the notification message, the device 200 generates a third learning signal through the contents of the modification request and sends it to the third artificial intelligence model. By inputting a third learning signal, the third artificial intelligence model can be learned and updated through the third learning signal.

In step S706, the device 200 may check the calories per unit weight of the first food as a first value. At this time, the device 200 may check how many calories are consumed per unit weight of the first food based on the first food information and set the confirmed calories as the first value. Here, the first food information may be obtained through a database or an external server.

In step S707, when the calories per unit weight of the first food are confirmed to be a first value, the device 200 may calculate a second value by multiplying the first value and the first weight.

For example, if the calories per unit weight of the first food are set to 2 calories per 1g and the first weight is confirmed to be 300g, the device 200 provides 600 calories calculated through (2 2 It can be calculated as a number.

In step S708, if it is confirmed that the first user ate the first food within the first period, the device 200 may add a second value to the total calorie intake of the first period.

Specifically, if the first user captures the first food through the first user terminal 110 and then eats the captured first food within the first period, the image displayed on the screen of the first user terminal 110 If the meal completion button of the first food is selected within the first period, the device 200 may receive a request for processing the meal completion of the first food from the first user terminal 110, and the meal completion processing request of the first food may be completed within the first period. When a meal completion processing request is received, it can be confirmed that the first user ate the first food within the first period, and if it is confirmed that the first user ate the first food within the first period, the total calorie intake in the first period A second value can be added to .

Figure 8 is a flow chart for explaining the process of estimating the user's calorie intake by confirming the actual amount eaten according to one embodiment.

Referring to FIG. 8 , first, in step S801, the device 200 may receive a second image generated by photographing the remaining first food from the first user terminal 110.

Specifically, the first user terminal 110 uses a camera provided in the first user terminal 110 to photograph the first food remaining after the first user eats the first food to create a second image. Can be generated, and when the device 200 uses the camera of the first user terminal 110 to photograph the first food remaining after the first user eats the first food, the first user terminal 110 A second image generated by photographing the remaining first food may be received from 110 .

In step S802, the device 200 may generate a fifth input signal by encoding the second image.

In step S803, the device 200 may input the fifth input signal to the third artificial intelligence model learned in advance.

In step S804, when the type of food is recognized as the first food and the amount of food is recognized as the second weight through the fifth input signal, the device 200 calculates the first food and the second weight from the third artificial intelligence model. A fifth output signal representing the signal can be obtained.

In step S805, the device 200 may analyze that the first user left the first food of the second weight based on the fifth output signal.

In step S806, the device 200 may calculate the third weight by subtracting the second weight from the first weight.

That is, the device 200 subtracts the second weight, which is the weight of the first food left after eating, from the first weight, which is the weight of the first food before eating, and calculates the third weight, which is the weight of the food actually eaten by the first user. It can be calculated.

In step S807, the device 200 may calculate the third value by multiplying the first value and the third weight.

At step S808, device 200 may add a third number to the total calorie intake for the first period.

That is, the device 200 may check the weight of food actually eaten by the first user and add a third value, rather than a second value, to the total calorie intake in the first period.

Figure 9 is an exemplary diagram of the configuration of a device according to an embodiment.

Device 200 according to one embodiment includes a processor 210 and memory 220. The processor 210 may include at least one device described above with reference to FIGS. 1 to 8 or may perform at least one method described above with reference to FIGS. 1 to 8 . 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 8 .

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

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

The device 200 may be used to learn an artificial intelligence model or use a learned artificial intelligence model. Memory 220 may include a learning or learned artificial intelligence model. The processor 210 may learn or execute the artificial intelligence model algorithm stored in the memory 220. The learning device that trains the artificial intelligence model and the device 200 that uses the learned artificial intelligence model may be the same or may be separate.

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.

Claims (3)

In the method of automatically processing the creation of customized diet management consulting information using an artificial intelligence model performed by a device and providing diet management services and mental health care services using the same,
Analyzing a change in the body of the first user for a first predetermined period of time based on monitoring information about the change in the body of the first user;
estimating the amount of physical change in the first period based on a result of analyzing the physical change of the first user during the first period;
calculating a goal achievement rate in the first period based on the amount of physical change in the first period and a preset target value of the first user;
setting the diet difficulty level of the first user to a first level based on the goal achievement rate of the first period;
Confirming that the second period after the first period belongs to the first season, and confirming that the food category preferred by the first user is the first category;
Generating first matching information by matching the first grade, the first season, and the first category;
Generating a first input signal by encoding the first matching information;
Inputting the first input signal to a first artificial intelligence model trained to select a recommended diet through analysis of diet difficulty, season, and preferred food category;
When the recommended diet for the first user is selected through the first input signal, obtaining a first output signal representing the recommended diet for the first user from the first artificial intelligence model;
Setting the recommended diet of the first user as a first diet based on the first output signal;
generating first consulting information recommending the first diet as a customized diet for the first user during the second period;
Transmitting the first consulting information to a first user terminal;
Analyzing a change in the body of the first user during the second period based on monitoring information about the change in the body of the first user;
estimating the amount of physical change in the second period based on a result of analyzing the physical change of the first user during the second period;
calculating a goal achievement rate in the second period based on the amount of physical change in the second period and the target value of the first user;
If it is confirmed that the goal achievement rate of the second period is higher than the goal achievement rate of the first period, checking the remaining value remaining up to the target value of the first user;
If the remaining value is confirmed to be greater than a preset standard value, maintaining the diet difficulty level of the first user at the first level;
If the remaining value is confirmed to be less than the reference value, changing the difficulty level of the first user's diet to a second level that is easier than the first level;
If it is confirmed that the goal achievement rate of the second period is lower than the goal achievement rate of the first period, changing the diet difficulty level of the first user to a third level that is more difficult than the first level;
confirming that a third period after the second period belongs to a second season;
When the first user's diet difficulty level is maintained at the first level, second matching information is generated by matching the first grade, the second season, and the first category, and the first user's diet difficulty level is When changed to the second grade, second matching information is generated by matching the second grade, the second season, and the first category, and when the diet difficulty of the first user is changed to the third grade, the first user's diet difficulty level is changed to the third grade. Generating second matching information by matching 3 grades, the second season, and the first category;
Generating a second input signal by encoding the second matching information;
Inputting the second input signal to the first artificial intelligence model;
When the recommended diet for the first user is selected through the second input signal, obtaining a second output signal representing the recommended diet for the first user from the first artificial intelligence model;
setting the recommended diet of the first user as a second diet based on the second output signal;
generating second consulting information recommending the second diet as a customized diet for the first user during the third period;
Transmitting the second consulting information to the first user terminal;
When it is confirmed that the goal achievement rate of the second period is lower than the goal achievement rate of the first period, determining that a mental health check of the first user is necessary;
Containing at least one of the first user's posting upload history, the first user's location movement history, the first user's music listening history, the first user's video viewing history, and the first user's post viewing history collecting activity data of the first user;
extracting activity details performed during the second period from the activity data of the first user as first activity data;
Analyzing activity keywords indicating an activity state during the second period based on the first activity data;
Based on the activity keyword, diagnosing whether there is a problem with the first user's mental health according to a preset classification standard; and
When it is diagnosed that the first user has a first type of mental health problem, transmitting a notification message recommending consultation for the first type of problem to the first user terminal,
Analyzing changes in the body of the first user during the first period,
collecting the calories consumed by the first user during the first period and calculating the total calorie intake of the first period;
calculating an active metabolic rate for the first period by collecting calories consumed by the first user during the first period;
calculating the basal metabolic rate of the first user based on the gender, age, weight, and height of the first user;
Generating third matching information by matching the total calorie intake of the first period, the active metabolic rate of the first period, and the basal metabolic rate of the first user;
Generating a third input signal by encoding the third matching information;
Inputting the third input signal to a second artificial intelligence model learned to identify body changes through analysis of total calorie intake, active metabolic rate, and basal metabolic rate;
When the physical change of the first user is identified through the third input signal, obtaining a third output signal representing the physical change of the first user from the second artificial intelligence model; and
Based on the third output signal, analyzing a change in the body of the first user during the first period of time,
Automated processing of user-tailored diet management consulting information generation using an artificial intelligence model and a method of providing diet management services and mental health care services using this. delete delete