METHOD FOR RECOMMENDING MENU BASED ON ELECTROCARDIOGRAM AND COMPUTER PROGRAM RECORDED ON A RECORDING MEDIUM FOR EXECUTING THE METHOD

Abstract

The present invention proposes a method for recommending a menu suited to a user's real-time health condition based on an electrocardiogram (ECG). The method includes the steps of acquiring an electrocardiogram (ECG) signal measured from a user, analyzing the ECG signal using pre-trained artificial intelligence (AI) to identify one or more nutrient deficiencies and excess nutrients corresponding to the user's health condition, and setting a menu including one or more foods and drinks that can replenish the identified nutrient deficiencies and avoid the nutrient excess. Thus, a user can receive a menu recommendation optimized for their current health condition simply by measuring their ECG.

Description

[Technical Field]

[0001] The present invention relates to smart healthcare, and more particularly to a method for recommending a menu suitable for a user's real-time health condition based on an electrocardiogram (ECG), and a computer program recorded on a recording medium for executing the method. [Background technology]

[0002] An electrocardiogram (ECG) is a graphical record of the visual changes in electrical activity generated by the heart muscles. Briefly explaining the cardiac conduction system, the sinoatrial node (SA node) periodically generates electrical signals to induce cardiac contractions. The atrioventricular node (AV node) transmits the electrical signals generated by the SA node through the atria, after slightly delaying them. The electrical signals transmitted from the AV node are then distributed throughout the ventricles via the His bundle and Purkinje fibers.

[0003] The electrocardiogram (ECG) waveforms that can be seen during the cardiac impulse conduction process are as follows: The P wave is seen when the electrical signal generated by the sinoatrial node polarizes the atria, causing the valvular myocardium to contract, then depolarizes and relaxes again. The PQ wave is seen when the atrioventricular node delays the electrical signal to prevent the ventricles from immediately responding when the atria contract. The QRS complex is seen when the delayed electrical signal is transmitted by the AV node (Q), causing the ventricles to immediately polarize (R) and then immediately depolarize (S). The ST wave is seen during the resting period when the ventricles contract and blood moves around the body, preventing the electrical signal from stimulating the heart. The T wave is seen when the ventricles weakly polarize and then depolarize again, causing the ventricles and valvular myocardium to simultaneously relax. In some cases, a U wave due to repolarization of the intraventricular septum can also be seen.

[0004] The order of appearance of waveforms (P waves, PQ waves, QRS waves, ST waves, T waves, and U waves) that can be confirmed by such an electrocardiogram (ECG), as well as their respective shapes, sizes, and intervals, can vary in various forms depending on the health state. In other words, by analyzing the order of appearance, shapes, sizes, and intervals of waveforms included in an electrocardiogram (ECG), it is possible to infer the health state and even the various causes that cause such health state.

[0005] Meanwhile, an artificial neural network (ANN) is a detailed methodology of machine learning, and refers to an algorithm that has the form of a network in which neurons, the basic operational units corresponding to human nerve cells, are linked together. Representative artificial neural networks (ANN) include multilayer perceptrons (MLPs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs).

[0006] Specifically, a multilayer perceptron (MLP) is an artificial neural network (ANN) with multiple hidden layers between the input and output layers. A recurrent neural network (RNN) is an artificial neural network (ANN) with a recurrent connection structure in which the output of neurons is fed back to the input layer. A convolutional neural network (CNN) is an artificial neural network (ANN) that mimics the structure of the human visual nerve, extracts feature maps from multiple convolutional layers, and then extracts only important parts from the feature maps by reducing the dimension of the matrix through subsampling.

[0007] Meanwhile, a menu (diet) is a plan related to the type, amount, and order of food and drink that a person takes in during the meal process. The process of determining such a menu must take into consideration not only a person's preferences but also the nutrients required according to the person's health condition. Therefore, conventional services that recommend or suggest food and drink or menus simply consider only the nutrients required according to the user's general health condition based on static factors such as height, weight, and obesity level.

[0008] However, the nutrients required depending on one's health condition can change from moment to moment depending on the type and intensity of the activity currently being performed or immediately preceding it, and the type and amount of food and drink consumed immediately preceding it. For example, a person who has just completed high-intensity exercise will require macronutrients such as protein and water, while a person who has suddenly experienced diarrhea or vomiting will require micronutrients such as minerals. Furthermore, it is practically difficult for non-medical professionals to periodically draw blood directly to check their own health condition and nutrient needs during the course of daily life.

[0009] Therefore, there is a need for a means for instantly recommending a menu suited to a user's real-time health condition without requiring the user to perform any burdensome actions. Summary of the Invention [Problem to be solved by the invention]

[0010] An object of the present invention is to propose a method that can recommend a menu suitable for a user's real-time health condition based on an electrocardiogram (ECG).

[0011] Another object of the present invention is to propose a computer program recorded on a recording medium for executing a method capable of recommending a menu suited to a user's real-time health condition based on an electrocardiogram (ECG).

[0012] The technical problems of the present invention are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0013] To achieve the above technical objectives, the present invention proposes a method for recommending a menu suited to a user's real-time health condition based on an electrocardiogram (ECG), comprising the steps of acquiring an electrocardiogram (ECG) signal measured from a user, analyzing the ECG signal using pre-trained artificial intelligence (AI) to identify one or more nutrient deficiencies and nutrient excesses corresponding to the user's health condition, and setting a menu including one or more foods and drinks that can replenish the identified nutrient deficiencies and avoid the nutrient excesses.

[0014] The method may further include, after the step of setting the menu, transmitting information about the set menu to a user equipment (UE) pre-configured corresponding to the user.

[0015] More specifically, the identifying step may include the steps of: dividing the electrocardiogram (ECG) signal into a plurality of partial signals according to the time series order; inputting the divided partial signals into the artificial intelligence (AI) respectively to obtain a plurality of probability values from the artificial intelligence (AI); and determining whether the nutrients are deficient, normal, or excessive based on the obtained plurality of probability values.

[0016] According to one embodiment, the step of dividing into a plurality of partial signals may involve moving a window of a predetermined size along a time axis and dividing the ECG signal into a plurality of partial signals having sizes corresponding to the window.

[0017] Meanwhile, the AI may include a first artificial neural network (ANN) for electrolytes, a second artificial neural network (ANN) for proteins, and a third artificial neural network (ANN) for water. In this case, the determining step may determine whether the electrolyte is deficient, normal, or excessive based on a plurality of probability values obtained from the first artificial neural network (ANN), determine whether the protein is deficient, normal, or excessive based on a plurality of probability values obtained from the second artificial neural network (ANN), and determine whether the water is deficient, normal, or excessive based on a plurality of probability values obtained from the third artificial neural network (ANN).

[0018] In addition, the hidden layers of the first to third artificial neural networks (ANNs) may include a generalized matrix factorization (GMF) for learning a linear relationship between the features of the ECG signal and the nutrient content, and a multi-layer perceptron (MLP) for learning a non-linear relationship between the features of the ECG signal and the nutrient content.

[0019] The determining step of the method may remove outliers included in the obtained plurality of probability values based on a pre-established valid range, and determine whether the nutrient is deficient, normal, or excessive using one of the results of soft voting based on the average of the probability values from which the outliers have been removed, or the results of hard voting based on a majority vote of the probability values from which the outliers have been removed.

[0020] The step of setting the menu may include the steps of identifying two or more foods from a pre-defined food dictionary that do not contain the excess nutrient or contain a content below a pre-defined threshold and that contain the identified deficient nutrient, identifying a pre-defined human weight corresponding to the user and a time weight corresponding to a time point at which the electrocardiogram (ECG) signal is measured, and selecting one food from the identified two or more foods based on the human weight and the time weight.

[0021] The identifying step may determine that a warning to the user is necessary if the difference between the first time and the second time is within a predetermined minimum biotransformation time, and if the excess nutrient identified based on the electrocardiogram (ECG) signal measured on the user at the first time is identical to the deficient nutrient identified based on the electrocardiogram (ECG) signal measured on the user at the second time.

[0022] To achieve the above technical objectives, the present invention proposes a computer program recorded on a recording medium for executing a method for recommending a menu suitable for a user's real-time health condition based on an electrocardiogram (ECG). The computer program can be coupled to a computing device including a memory, a transceiver, an input / output device, and a processor for processing instructions resident in the memory. The computer program may be recorded on a recording medium to cause the processor to execute the following steps: acquire an electrocardiogram (ECG) signal measured from a user via the transceiver or the input / output device; analyze the ECG signal using pre-trained artificial intelligence (AI) to identify one or more nutrient deficiencies and nutrient excesses corresponding to the user's health condition; and set a menu including one or more foods and drinks that can replenish the identified nutrient deficiencies and avoid the nutrient excesses.

[0023] Further details of the embodiments are included in the detailed description and accompanying drawings. [Effects of the Invention]

[0024] According to an embodiment of the present invention, a menu optimized for the user's current health condition can be recommended simply by the user measuring an electrocardiogram (ECG).

[0025] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be apparent to those skilled in the art to which the present invention pertains from the claims. [Brief explanation of the drawings]

[0026] [Figure 1] 4 is an exemplary diagram illustrating a menu recommendation unit according to an embodiment of the present invention; FIG. [Figure 2]1 is an exemplary diagram illustrating a menu recommendation system according to an embodiment of the present invention; [Figure 3] 2 is a logical block diagram of a menu recommendation server according to an embodiment of the present invention; [Figure 4] 1 is an exemplary diagram illustrating an artificial neural network (ANN) according to an embodiment of the present invention. FIG. [Figure 5] 1 is an exemplary diagram illustrating a process for segmenting an electrocardiogram (ECG) signal according to some embodiments of the present invention. [Figure 6] 1 is an exemplary diagram illustrating a process for segmenting an electrocardiogram (ECG) signal according to some embodiments of the present invention. [Figure 7] 1 is an exemplary diagram illustrating a process for determining whether a nutrient is deficient, normal, or excessive according to some embodiments of the present invention. [Figure 8] 1 is an exemplary diagram illustrating a process for determining whether a nutrient is deficient, normal, or excessive according to some embodiments of the present invention. [Figure 9] FIG. 2 is a hardware configuration diagram of a menu recommendation server according to an embodiment of the present invention. [Figure 10] 2 is a flowchart illustrating a menu recommendation method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0027] It should be noted that the technical terms used herein are merely used to describe specific embodiments and are not intended to limit the present invention. Furthermore, unless otherwise defined herein, technical terms used herein should be interpreted in a way that is commonly understood by a person of ordinary skill in the art to which the present invention pertains, and should not be interpreted in an overly comprehensive or overly narrow sense. Furthermore, if a technical term used herein is incorrect and cannot accurately express the concept of the present invention, it should be understood by substituting a technical term that can be correctly understood by a person skilled in the art. Furthermore, general terms used herein should be interpreted according to their predefined meanings or the context, and should not be interpreted in an overly narrow sense.

[0028] Furthermore, as used herein, singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "comprise" or "have" should not be interpreted as necessarily including all of the components or steps described in the specification, but should be interpreted as not including some of the components or steps, or as possibly including additional components or steps.

[0029] Furthermore, terms including ordinal numbers such as "first" and "second" used in this specification may be used to describe various components, but the components should not be limited to these terms. These terms are used only to distinguish one component from another. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component, without departing from the scope of the present invention.

[0030] When a component is said to be "coupled" or "connected" to another component, it may be directly coupled or connected to the other component, but there may be other components in between. On the other hand, when a component is said to be "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between.

[0031] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings. Identical or similar elements will be given the same reference numerals regardless of the drawing numbers, and redundant description thereof will be omitted. Furthermore, in the description of the present invention, if it is determined that a detailed description of related known technology may obscure the gist of the present invention, such a detailed description will be omitted. It should be noted that the accompanying drawings are merely provided to facilitate understanding of the concept of the present invention, and the concept of the present invention should not be construed as being limited by the accompanying drawings. The concept of the present invention should be construed as extending to all modifications, equivalents, or alternatives other than those shown in the accompanying drawings.

[0032] As described above, conventional services that recommend or suggest food and drink or menus only consider nutrients required according to a user's general health condition based on static factors such as height, weight, obesity level, etc. However, nutrients required according to a health condition may change from moment to moment depending on the type and intensity of an activity currently being performed or performed immediately before, the type and amount of food and drink consumed immediately before, etc.

[0033] To overcome such limitations, the present invention proposes a means for recommending a menu suited to the user's real-time health condition.

[0034] FIG. 1 is an exemplary diagram illustrating a menu recommendation unit according to an embodiment of the present invention.

[0035] As shown in FIG. 1, the menu recommendation means according to one embodiment of the present invention measures a user's electrocardiogram (ECG) 10 using an electrocardiogram reader (ECG reader) 100, analyzes the measured electrocardiogram (ECG) 10 using artificial intelligence (AI), identifies nutrients required according to the user's real-time health condition, and instantly recommends a menu 20 to the user based on the identified nutrients.

[0036] Therefore, according to one embodiment of the present invention, a user can receive recommendations for a menu optimized for the user's current health condition simply by measuring an electrocardiogram (ECG) 10.

[0037] Hereinafter, an apparatus and method for realizing the above-mentioned features will be described in detail.

[0038] FIG. 2 is an exemplary diagram illustrating a menu recommendation system according to an embodiment of the present invention.

[0039] As shown in FIG. 2, a menu recommendation system according to an embodiment of the present invention may include one or more electrocardiographs 100a, 100b, ..., 100n; 100, one or more user devices 200a, 200b, ..., 200n; 200, and a menu recommendation server 300.

[0040] Since the components of the menu recommendation system according to one embodiment of the present invention merely represent functionally divided elements, two or more components may be implemented in an integrated manner in an actual physical environment, or a single component may be implemented in a separated manner in an actual physical environment.

[0041] To explain each component, the electrocardiograph 100 is a device capable of measuring and recording a user's electrocardiogram (ECG) 10 .

[0042] Specifically, the electrocardiograph 100 induces electric potential changes due to electrical activity in the myocardium through electrodes in contact with the user's body, amplifies the induced electric potential changes, and records them as a waveform.

[0043] The electrocardiogram 100 according to an embodiment of the present invention may generate an electrocardiogram (ECG) using any one of standard limb leads, unipolar limb leads, and precordial leads, but the lead type of the electrocardiogram 10 of the electrocardiogram 100 is not limited thereto. The electrocardiogram 100 may include electrodes for 1 lead, 6 leads, or 12 leads, but the number of leads of the electrocardiogram 100 is not limited thereto. The electrocardiogram 100 may be of any one of a watch type 100a, a portable type 100b, and a Holter type 100n, but the type of the electrocardiogram 100 is not limited thereto.

[0044] The electrocardiogram (ECG) signal (i.e., the recorded waveform signal) measured by the electrocardiograph 100 can be directly transmitted to the menu recommendation server 300 by the network function of the electrocardiograph 100 itself, or can be input to the menu recommendation server 300 via a third means. For example, the third means can be any one of removable media, a user device 200, and a data input action by a user, but is not limited thereto.

[0045] Next, the user device 200 can output information about the menu set by the menu recommendation server 300 .

[0046] Specifically, the user device 200 can receive information about a menu from the menu recommendation server 300. Then, the user device 200 can output the received information about the menu.

[0047] The user device 200 according to one embodiment of the present invention is not limited to a user equipment (UE) defined by 3GPP (3rd Generation Partnership Project) or a mobile station (MS) defined by IEEE (Institute of Electrical and Electronics Engineers), but may be any device capable of transmitting and receiving data to and from the menu recommendation server 300 and performing calculations based on the transmitted and received data.

[0048] For example, the user device 200 may be any one of, but is not limited to, a fixed computing device such as a desktop PC 200c, a workstation, or a server, or a mobile computing device such as a smartphone 200a, a laptop PC 200b, a tablet PC, a phablet, a portable multimedia player (PMP), a personal digital assistant (PDA), or an e-book reader.

[0049] As a next configuration, the menu recommendation server 300 can identify nutrients required by the user's real-time health condition based on the electrocardiogram (ECG) 10 measured by the electrocardiograph 100, and transmit information about a menu 20 based on the identified nutrients to the user device 200.

[0050] Specific components and operations of the menu recommendation server 300 will be described later with reference to FIGS.

[0051] The one or more electrocardiographs 100, one or more user devices 200, and menu recommendation server 300 constituting the menu recommendation system as described above may transmit and receive data via a network that directly connects the devices to each other and is a combination of one or more of a secure line, a shared wired communication network, or a mobile communication network.

[0052] For example, the shared wired communication network may include, but is not limited to, Ethernet, x Digital Subscriber Line (xDSL), Hybrid Fiber Coax (HFC), and Fiber To The Home (FTTH). Also, the mobile communication network may include, but is not limited to, Code Division Multiple Access (CDMA), Wideband CDMA (WCDMA), High Speed Packet Access (HSPA), Long Term Evolution (LTE), and 5th generation mobile telecommunications.

[0053] The components of the menu recommendation server 300 having the above-mentioned features will now be described in detail.

[0054] Figure 3 is a logical block diagram of a menu recommendation server according to an embodiment of the present invention. Figure 4 is an example diagram illustrating an artificial neural network (ANN) according to an embodiment of the present invention. Figures 5 and 6 are example diagrams illustrating a process of segmenting an electrocardiogram (ECG) signal according to some embodiments of the present invention. Figures 7 and 8 are example diagrams illustrating a process of determining whether a nutrient is deficient, normal, or excessive according to some embodiments of the present invention.

[0055] As shown in FIG. 3, the menu recommendation server 300 according to an embodiment of the present invention may include a communication unit 305, an input / output unit 310, an artificial intelligence learning unit 315, an electrocardiogram dissection unit 320, a nutrient analysis unit 325, and a menu setting unit 330.

[0056] The components of the menu recommendation server 300 according to one embodiment of the present invention merely represent functionally separated components, and therefore, two or more components may be implemented in an integrated manner in an actual physical environment, or one component may be implemented in a separated manner in an actual physical environment.

[0057] To explain each component, the communication unit 305 can send and receive data to and from the electrocardiograph 100 and the user device 200.

[0058] Specifically, the communication unit 305 can receive an electrocardiogram (ECG) 10 signal from the electrocardiograph 100. The communication unit 305 can also transmit information about a menu 20 to the user device 200.

[0059] The next component, the input / output unit 310, can receive commands from an administrator through a user interface (UI) or output calculation results.

[0060] Specifically, the input / output unit 310 may receive an input of a window size, which is a criterion for disaggregating an electrocardiogram (ECG) 10 signal. The input / output unit 310 may receive an input of a validated range, which is a criterion for removing outliers from probability values acquired from an artificial intelligence (AI). The input / output unit 310 may receive an input of a food dictionary in which food and nutrients are matched and organized. The input / output unit 310 may receive an input of a threshold content, which is a boundary value at which additional intake is permitted for excess nutrients. The input / output unit 310 may receive an input of a minimum biotransformation time, which is a criterion for determining whether a special situation has occurred in the user. The input / output unit 310 may also receive an input of a threshold distance, which is a reference range for providing restaurant information.

[0061] Meanwhile, the input / output unit 310 can receive an activation function to be applied to the GMF layer of the artificial neural network (ANN), an activation function to be applied to the MLP layer, a weight, and a bias.

[0062] The input / output unit 310 can also output a signal of the user's electrocardiogram (ECG) 10. The input / output unit 310 can also output information about a menu 20 to be recommended to the user.

[0063] As the next configuration, the artificial intelligence learning unit 315 can train artificial intelligence (AI) to identify deficiency and excess nutrients corresponding to the user's health condition based on the signal of the electrocardiogram (ECG) 10.

[0064] Specifically, the artificial intelligence (AI) to be learned by the artificial intelligence learning unit 315 may include a first artificial neural network (ANN) related to electrolytes, a second artificial neural network (ANN) related to proteins, and a third artificial neural network (ANN) related to water.

[0065] The artificial intelligence learning unit 315 can train a first artificial neural network (ANN) based on data on electrocardiogram (ECG) signal characteristics and electrolyte content input by the administrator. The artificial intelligence learning unit 315 can train a second artificial neural network (ANN) based on data on electrocardiogram (ECG) signal characteristics and protein content input by the administrator. The artificial intelligence learning unit 315 can train a third artificial neural network (ANN) based on data on electrocardiogram (ECG) signal characteristics and water content input by the administrator.

[0066] Here, an electrolyte is a substance that dissolves in a solvent and ionizes to generate positive and negative ions. According to an embodiment of the present invention, the electrolyte may include, but is not limited to, sodium (Na), potassium (Ka), and calcium (Ca). A protein is an organic substance formed by the binding of amino acids. According to an embodiment of the present invention, the protein may include, but is not limited to, albumin.

[0067] Each of the first artificial neural network (ANN), second artificial neural network (ANN), and third artificial neural network (ANN) to be learned by the artificial intelligence learning unit 315 may include an input layer, a hidden layer, and an output layer.

[0068] In particular, as shown in FIG. 4, the hidden layers of the first to third artificial neural networks (ANN) according to one embodiment of the present invention can be configured in a mixed form of GMF (Generalized Matrix Factorization) and MLP (Multi-Layer Perceptron).

[0069] Hereinafter, for convenience of explanation, all or part of the first artificial neural network (ANN) to the third artificial neural network (ANN) may be simply referred to as an artificial neural network (ANN).

[0070] In each artificial neural network (ANN) according to an embodiment of the present invention, the GMF layer is a layer for learning the linearity relation between the features of the electrocardiogram (ECG) signal and the nutrient content, and can be realized by the following equation (1).

[0071]

number

[0072] In this case, p u is a dense vector of electrocardiogram (ECG) signal features, q i is the dense vector of nutrient content, pu○qi is the Hadamard product between the dense vector of electrocardiogram (ECG) signal features and the dense vector of nutrient content, a is the activation function of the artificial neural network (ANN), h is the edge weight of the hidden layer, and h T can be a vector product of edge weights.

[0073] A dense vector is a vector whose dimension is reduced by embedding a vector represented by one-hot encoding. In other words, a dense vector is a vector whose dimension is reduced by removing zero values from a sparse vector represented by one-hot encoding.

[0074] In addition, in each artificial neural network (ANN), the MLP layer is a layer for learning the non-linear relationship between the features of the electrocardiogram (ECG) signal and the content of nutrients, and can be embodied as the following Equations 2 and 3.

[0075]

number

[0076]

number

[0077] In this case, p u is a dense vector of electrocardiogram (ECG) signal features, q i is the dense vector of nutrient content, z is the concatenation of the dense vector of ECG signal features and the dense vector of nutrient content, a is the activation function of the artificial neural network (ANN), W is the weight of each layer that makes up the MLP, and W T is the vector product of the weights, b is the bias of each layer that makes up the MLP, L is the number of layers that make up the hidden layer, and δ can be the sum of a sequence.

[0078] Each artificial neural network (ANN) can also be configured in the form of a recurrent neural network with a recurrent connection structure, in which the probability values output to the output layer are added to a vector for the nutrient content and then input back to the input layer.

[0079] In this way, each artificial neural network (ANN) of the artificial intelligence learning unit 315 has a form that combines GMF and MLP, and can simultaneously learn not only the linear relationship between the characteristics of the electrocardiogram (ECG) signal and the nutrient content, but also the nonlinear relationship.

[0080] Referring to FIG. 3, the next configuration will be described. The electrocardiogram disassembly unit 320 can disassemble the signal of the electrocardiogram (ECG) 10 measured by the electrocardiograph 100.

[0081] Specifically, the electrocardiogram disassembly unit 320 can acquire an electrocardiogram (ECG) 10 signal measured on a user. That is, the electrocardiogram disassembly unit 320 can directly receive the electrocardiogram (ECG) 10 signal from the electrocardiograph 100 via the communication unit 305 or can directly receive the electrocardiogram (ECG) 10 signal via the input / output unit 310.

[0082] The electrocardiogram decomposition unit 320 can divide the signal of the electrocardiogram (ECG) 10 into a plurality of segmentation signals according to the time series measured from the user.

[0083] 5, the electrocardiogram disassembly unit 320 can divide the electrocardiogram (ECG) 10 signal into a plurality of partial signals S1, S2, S3, ... by discretely dividing the electrocardiogram (ECG) 10 signal into parts of a certain magnitude without overlapping regions. In this case, the magnitude for discretely dividing the electrocardiogram (ECG) 10 signal may be a certain value preset by the input / output unit 310, but is not limited thereto and may also be a randomized value.

[0084] 6, the electrocardiogram disassembly unit 320 can divide the electrocardiogram (ECG) 10 signal into a plurality of partial signals S1, S2, S3, ... each having a size corresponding to the window by cutting the electrocardiogram (ECG) 10 signal while sliding the window along the time axis. In this case, the size of the window for cutting the electrocardiogram (ECG) 10 signal may be a constant value preset by the input / output unit 310.

[0085] Meanwhile, the signal of the electrocardiogram (ECG) 10 may contain noise generated due to the user's behavior during the measurement process, etc. Therefore, the ECG disassembly unit 320 can remove noise contained in the divided partial signals S1, S2, S3, ...

[0086] Specifically, the ECG disassembly unit 320 can identify displacements of P waves, PQ waves, QRS waves, ST waves, and T waves included in each of the divided partial signals S1, S2, S3, .... The ECG disassembly unit 320 can generate a normal distribution of the displacements of the identified P waves, PQ waves, QRS waves, ST waves, and T waves. Then, the ECG disassembly unit 320 can selectively remove only partial signals having displacements of P waves, PQ waves, QRS waves, ST waves, or T waves included in a predetermined noise range from the generated normal distribution.

[0087] Referring to FIG. 3, the next configuration will be described. The nutrient analysis unit 325 can analyze the electrocardiogram (ECG) 10 signal using artificial intelligence (AI) to identify one or more lacked nutrients and surplus nutrients corresponding to the user's health condition.

[0088] Here, a deficient nutrient is a nutrient that requires immediate intake in a high amount depending on the user's health condition, an excess nutrient is a nutrient that does not cause health problems even if not taken immediately depending on the user's health condition, and a normal nutrient is a nutrient that requires intake in an amount sufficient for daily life depending on the user's health condition.

[0089] Preferably, the nutrient analysis unit 325 can input the plurality of partial signals S1, S2, S3, ... divided by the electrocardiogram disassembly unit 320 into an artificial intelligence (AI) respectively, and obtain a plurality of probability values P1, P2, P3, ..., Pn from the artificial intelligence (AI).

[0090] According to one embodiment of the present invention, the artificial intelligence (AI) includes a first artificial neural network (ANN) to a third artificial neural network (ANN), and the nutrient analysis unit 325 can input a plurality of partial signals S1, S2, S3, ... to the first artificial neural network (ANN) to the third artificial neural network (ANN), respectively.

[0091] Specifically, the ECG disassembly unit 320 may extract one or more features from displacements of P waves, PQ waves, QRS waves, ST waves, and T waves included in each of the divided partial signals S1, S2, S3, etc., according to a predetermined feature extraction standard. The ECG disassembly unit 320 may one-hot encode the extracted one or more features to generate a vector of ECG signal features. The ECG disassembly unit 320 may embed the generated ECG signal feature vector to generate a dense vector with reduced dimensions. The ECG disassembly unit 320 may input the generated dense vector to the GMF layer and MLP layer of each of the first to third artificial neural networks (ANN). The electrocardiogram disassembly unit 320 can obtain a plurality of probability values P1, P2, P3, ..., Pn corresponding to a plurality of partial signals S1, S2, S3, ... from each of the first artificial neural network (ANN) to the third artificial neural network (ANN).

[0092] Then, the nutrient analysis unit 325 can determine whether each nutrient is deficient, normal, or excessive based on the obtained plurality of probability values P1, P2, P3, . . . , Pn.

[0093] Specifically, the nutrient analysis unit 325 can determine whether electrolytes are deficient, normal, or excessive based on a plurality of probability values obtained from a first artificial neural network (ANN). The nutrient analysis unit 325 can determine whether protein is deficient, normal, or excessive based on a plurality of probability values obtained from a second artificial neural network (ANN). And, the nutrient analysis unit 325 can determine whether water is deficient, normal, or excessive based on a plurality of probability values obtained from a third artificial neural network (ANN).

[0094] 7 and 8, the nutrient analysis unit 325 can remove outliers from the plurality of probability values P1, P2, P3, ..., Pn obtained from each artificial neural network (ANN) based on a predetermined validated range. The nutrient analysis unit 325 can determine whether a nutrient is deficient, normal, or excessive using a result of soft voting based on an average value Pa of the plurality of probability values P1, P2, ..., Pm from which the outliers have been removed, or a result of hard voting based on a majority vote of the plurality of probability values P1, P2, ..., Pm from which the outliers have been removed.

[0095] In this case, for soft boarding, the nutrient analysis unit 325 can calculate an average value Pa of the plurality of probability values P1, P2, ..., Pm from which outliers have been removed. The nutrient analysis unit 325 can determine a deficiency if the calculated average value Pa is smaller than or equal to a preset deficiency criterion Cl, determine an excess if the calculated average value Pa is larger than or equal to a surplus criterion Cs, and determine a normality if the calculated average value Pa is larger than the deficiency criterion Cl but smaller than the surplus criterion Cs.

[0096] In contrast, for hardboarding, the nutrient analysis unit 325 can determine whether each of the multiple probability values P1, P2, ..., Pm from which outliers have been removed is deficient, normal, or excessive. That is, the nutrient analysis unit 325 can determine a deficiency if each probability value Px is smaller than or equal to the deficiency criterion Cl, determine an excess if each probability value Px is larger than or equal to the excess criterion Cs, and determine a normal if each probability value Px is larger than the deficiency criterion Cl but smaller than the excess criterion Cs. The nutrient analysis unit 325 can determine the most common determination result among the multiple determination results as the final result.

[0097] Meanwhile, the nutrient analysis unit 325 may receive electrocardiogram (ECG) 10 signals measured at a first time and a second time, the difference between which is within a predetermined minimum biotransformation time, for the user. The nutrient analysis unit 325 may determine that a warning is necessary for the user if an excess nutrient identified based on the electrocardiogram (ECG) 10 signal measured for the user at the first time and a deficient nutrient identified based on the electrocardiogram (ECG) 10 signal measured for the user at the second time are identical. If it is determined that a warning is necessary for the user, the nutrient analysis unit 325 may transmit a message to the user device (UE) 200 configured corresponding to the user, notifying that an abnormality has occurred in the body.

[0098] Referring to FIG. 3, the menu setting unit 330 can set a menu including one or more foods and drinks that can replenish the nutrient deficiency identified by the nutrient analysis unit 325 and prevent excess nutrients.

[0099] Specifically, the menu setting unit 330 can identify two or more types of food that do not contain excess nutrients or contain nutrients at or below a predetermined threshold content and contain deficient nutrients from a pre-set food dictionary based on the information about deficient nutrients, excess nutrients, and normal nutrients identified by the nutrient analysis unit 325.

[0100] The menu setting unit 330 can identify a preset human weight corresponding to the user and a time weight corresponding to the time point at which the electrocardiogram (ECG) 10 signal is measured.

[0101] In this case, the personal weighting value may be a value set corresponding to the type of nutrient deficiency and excess identified based on the ECG 10 signal measured for the user and those set as cohabitants, and the time weighting value may be a value set corresponding to the type of season or meal time corresponding to the time when the ECG 10 signal was measured for the user.

[0102] The menu setting unit 330 may select one of the two or more identified meals based on the personal weight and the time weight. Then, the menu setting unit 330 may identify one or more menu templates including the selected meal and set a menu using the identified one or more menu templates. In this case, the menu template may be a list including two or more meals that are pre-set based on the compatibility between the meals.

[0103] In this way, when setting a menu using a meal template, the menu setting unit 330 may set the menu by further including information on the order of intake and recommended intake amounts of ingredients included in one or more meals included in the meal template. Also, the menu setting unit 330 may set the menu by further including information on restaurants that are located within a preset threshold distance from the user device 200 and can provide one or more meals included in the menu, based on location information of the user device 200.

[0104] The menu setting unit 330 can transmit information about the set menu to a user equipment (UE) 200 that is pre-set corresponding to the user.

[0105] Hereinafter, hardware for implementing the logical components of the menu recommendation server 300 having the above-mentioned features will be described in more detail.

[0106] FIG. 9 is a hardware configuration diagram of a menu recommendation server according to an embodiment of the present invention.

[0107] As shown in FIG. 9, a menu recommendation server 300 according to one embodiment of the present invention may include a processor 350, a memory 355, a transceiver 360, an input / output device 365, a data bus 370, and a storage 375.

[0108] Specifically, the processor 350 can implement the operations and functions of the menu recommendation server 300 based on commands from software 380 a that implements a menu recommendation method and resides in the memory 355 .

[0109] The memory 355 may have software 380b stored in the storage 375 and implementing a menu recommendation method loaded therein.

[0110] The transceiver 360 may transmit data to and receive data from one or more of the electrocardiograph 100 and the user equipment (UE) 200 .

[0111] The input / output device 365 can receive input of signals required for the operation of the menu recommendation server 300 or output the calculation results to the outside according to instructions from the processor 350 .

[0112] The data bus 370 is connected to the processor 350, the memory 355, the transceiver 360, the input / output device 365, and the storage 375, respectively, and can serve as a communication path for transmitting signals between the respective components.

[0113] The storage 375 may store an application programming interface (API), library files, resource files, etc., required for executing software 380a implementing a menu recommendation method according to various embodiments of the present invention. The storage 375 may store software 380b implementing a menu recommendation method according to various embodiments of the present invention. The storage 375 may also include a database 385 for storing artificial intelligence (AI) learning data, a food dictionary, menu templates, various setting values, etc.

[0114] According to one embodiment of the present invention, the software 380a, 380b for implementing the menu recommendation method, which is resident in the memory 355 or stored in the storage 375, may be a computer program recorded on a recording medium to cause the processor 350 to execute the steps of acquiring an electrocardiogram (ECG) 10 signal measured on a user via the transceiver 360 or the input / output device 365, analyzing the electrocardiogram (ECG) 10 signal using pre-trained artificial intelligence (AI) by the processor 350 to identify one or more deficiency and excess nutrients corresponding to the user's health condition, and setting a menu including one or more foods and drinks that can replenish the identified deficiency nutrients and avoid excess nutrients.

[0115] More specifically, the processor 350 may include, but is not limited to, one or more of a central processing unit (CPU), an application-specific integrated circuit (ASIC), a chipset, and a logic circuit.

[0116] The memory 355 may include, but is not limited to, one or more of a read-only memory (ROM), a random access memory (RAM), a flash memory, and a memory card.

[0117] The input / output device 365 may include, but is not limited to, one or more of input devices such as a button, a switch, a keyboard, a mouse, a joystick, and a touch screen, and output devices such as a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), an active matrix organic light emitting diode (AMOLED), a printer, and a plotter.

[0118] When the embodiments described herein are implemented using software, the methods described above may be implemented as modules (processes, functions, etc.) that perform the respective functions described above. Each module may reside in memory 355 and be executed by processor 350. Memory 355 may be internal or external to processor 350 and may be coupled to processor 350 via various known means.

[0119] 9 may be implemented by various means (e.g., hardware, firmware, software, or a combination thereof). When implemented by hardware, an embodiment of the present invention may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc.

[0120] Furthermore, when embodied in firmware or software, an embodiment of the present invention may be embodied in the form of modules, procedures, functions, etc. that perform the above-described functions or operations and recorded on a recording medium that can be read by various computer means. Here, the recording medium may include program instructions, data files, data structures, etc., alone or in combination.

[0121] The program instructions recorded on the recording medium may be specially designed and constructed for the present invention, or may be of the type well known and available to those of ordinary skill in the computer software art. For example, recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as compact disk read-only memories (CD-ROMs) and digital video disks (DVDs), magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as read-only memories (ROMs), random access memories (RAMs), flash memories, etc.

[0122] Examples of program instructions include not only machine code, such as produced by a compiler, but also high-level language code that is executable by a computer via an interpreter, etc. Such hardware devices may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

[0123] The operation of the menu recommendation server 300 as described above will now be described in detail.

[0124] FIG. 10 is a flowchart illustrating a menu recommendation method according to an embodiment of the present invention.

[0125] As shown in FIG. 10, a menu recommendation server 300 according to an embodiment of the present invention can acquire an electrocardiogram (ECG) 10 signal measured from a user (S100).

[0126] Specifically, the menu recommendation server 300 can receive an electrocardiogram (ECG) 10 signal directly from the electrocardiograph 100, or can receive a signal directly from a user or other person.

[0127] Next, the menu recommendation server 300 can divide the signal of the electrocardiogram (ECG) 10 into a plurality of partial signals S1, S2, S3, . . . according to the time series priorities measured from the user (S200).

[0128] According to one embodiment, the menu recommendation server 300 can divide the signal of the electrocardiogram (ECG) 10 into a plurality of partial signals S1, S2, S3, ... by cutting the signal of the electrocardiogram (ECG) 10 discretely at regular sizes without overlapping regions. According to another embodiment, the menu recommendation server 300 can divide the signal of the electrocardiogram (ECG) 10 into a plurality of partial signals S1, S2, S3, ... having sizes corresponding to the window by cutting the signal of the electrocardiogram (ECG) 10 while sliding a window along the time axis.

[0129] Meanwhile, the menu recommendation server 300 can also remove noise contained in the divided partial signals S1, S2, S3, . . .

[0130] Then, the menu recommendation server 300 can analyze the plurality of partial signals S1, S2, S3, ... using artificial intelligence (AI) to obtain a plurality of probability values P1, P2, P3, ..., Pn (S300).

[0131] Specifically, the menu recommendation server 300 may extract one or more features from the displacements of P waves, PQ waves, QRS waves, ST waves, and T waves included in each of the divided partial signals S1, S2, S3, etc., according to a predetermined feature extraction standard. The menu recommendation server 300 may generate a vector of electrocardiogram (ECG) signal features by one-hot encoding the extracted one or more features. The menu recommendation server 300 may embed the generated ECG signal feature vector to generate a dense vector with reduced dimensions. The menu recommendation server 300 may input the generated dense vector to the GMF layer and MLP layer of each of the first to third artificial neural networks (ANN). The menu recommendation server 300 may then obtain a plurality of probability values P1, P2, P3, etc., Pn corresponding to the plurality of partial signals S1, S2, S3, etc., from each of the first to third artificial neural networks (ANN).

[0132] Then, the menu recommendation server 300 can determine whether the nutritional content is deficient, normal, or excessive based on the obtained plurality of probability values P1, P2, P3, . . . , Pn (S400).

[0133] Specifically, the menu recommendation server 300 can determine whether electrolytes are deficient, normal, or excessive based on a plurality of probability values obtained from a first artificial neural network (ANN). The menu recommendation server 300 can determine whether protein is deficient, normal, or excessive based on a plurality of probability values obtained from a second artificial neural network (ANN). And the menu recommendation server 300 can determine whether water is deficient, normal, or excessive based on a plurality of probability values obtained from a third artificial neural network (ANN).

[0134] To this end, the menu recommendation server 300 can remove outliers included in the plurality of probability values P1, P2, P3, ..., Pn obtained from each artificial neural network (ANN) based on a preset valid range. The menu recommendation server 300 can determine whether a nutrient is deficient, normal, or excessive using a result of soft boarding based on an average value Pa of the plurality of probability values P1, P2, ..., Pm from which the outliers have been removed, or a result of hard boarding based on a majority vote of the plurality of probability values P1, P2, ..., Pm from which the outliers have been removed.

[0135] Next, the menu recommendation server 300 can set a menu including one or more foods and drinks that can replenish nutrient deficiencies and avoid excess nutrients (S500).

[0136] Specifically, the menu recommendation server 300 can identify two or more meals that do not contain excess nutrients or contain nutrients at or below a predetermined threshold level and contain deficiencies of nutrients from a preset meal dictionary based on the identified information on deficiency, excess, and normal nutrients. The menu recommendation server 300 can identify a preset personal weighting value corresponding to a user and a time weighting value corresponding to the time point at which the electrocardiogram (ECG) 10 signal was measured. The menu recommendation server 300 can select one meal from the identified two or more meals based on the personal weighting value and the time weighting value. The menu recommendation server 300 can identify one or more menu templates including the selected meal and set a menu using the identified one or more menu templates.

[0137] Finally, the menu recommendation server 300 may transmit information about the set menu to a user equipment (UE) 200 that is pre-set corresponding to the user (S600).

[0138] As described above, the present specification and drawings have disclosed preferred embodiments of the present invention. However, it will be obvious to those skilled in the art to which the present invention pertains that other modifications based on the technical concept of the present invention are possible in addition to the disclosed embodiments. Furthermore, although specific terms are used in the present specification and drawings, these are used in general terms merely to facilitate the description of the present invention and to facilitate understanding of the invention, and are not intended to limit the scope of the present invention. Therefore, the above detailed description should not be construed as limiting in all respects, but should be considered as illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included within the scope of the present invention.

Claims

1. acquiring an electrocardiogram (ECG) signal measured from a user; analyzing the electrocardiogram (ECG) signal using pre-trained artificial intelligence (AI) to identify one or more nutrient deficiencies and nutrient excesses corresponding to the user's health condition; and setting a menu including one or more foods and drinks that can replenish the identified nutrient deficiencies and avoid the nutrient excesses.

2. The identifying step comprises: dividing the electrocardiogram (ECG) signal into a plurality of sub-signals according to their chronological order; inputting the divided partial signals into the artificial intelligence (AI), respectively, and obtaining a plurality of probability values from the artificial intelligence (AI); 2. The method of claim 1, further comprising: determining whether the nutritional content is deficient, normal, or excessive based on the plurality of probability values obtained.

3. 3. The menu recommendation method of claim 2, wherein the step of dividing into a plurality of partial signals comprises moving a window of a predetermined size along a time axis and dividing the electrocardiogram (ECG) signal into a plurality of partial signals having sizes corresponding to the window.

4. The artificial intelligence (AI) comprises a first artificial neural network (ANN) for electrolytes, a second artificial neural network (ANN) for proteins, and a third artificial neural network (ANN) for water; 3. The menu recommendation method of claim 2, wherein the determining step determines whether electrolytes are deficient, normal, or excess based on a plurality of probability values obtained from the first artificial neural network (ANN), determines whether protein is deficient, normal, or excess based on a plurality of probability values obtained from the second artificial neural network (ANN), and determines whether water is deficient, normal, or excess based on a plurality of probability values obtained from the third artificial neural network (ANN).

5. 5. The menu recommendation method of claim 4, wherein hidden layers of the first to third artificial neural networks (ANNs) include a generalized matrix factorization (GMF) for learning a linear relationship between the features of the ECG signal and nutrient contents, and a multi-layer perceptron (MLP) for learning a non-linear relationship between the features of the ECG signal and nutrient contents.

6. 3. The menu recommendation method of claim 2, wherein the determining step removes outliers included in the plurality of obtained probability values based on a predetermined validated range, and determines whether the nutrient is deficient, normal, or excessive using one of a result of soft voting based on an average value of the probability values from which the outliers have been removed, or a result of hard voting based on a majority vote of the probability values from which the outliers have been removed.

7. 2. The menu recommendation method of claim 1, further comprising, after the step of setting the menu, transmitting information about the set menu to a user equipment (UE) that is pre-set corresponding to the user.

8. The step of setting the menu includes: Identifying two or more foods from a predetermined food dictionary that do not contain the excess nutrient or contain the excess nutrient at a content below a predetermined threshold and that contain the identified deficient nutrient; identifying a pre-set human weight corresponding to the user and a time weight corresponding to a time point at which the electrocardiogram (ECG) signal is measured; and selecting one of the identified two or more meals based on the personal weight and the time weight.

9. 2. The menu recommendation method of claim 1, wherein the identifying step determines that a warning is necessary for the user when a difference between the first time and the second time is within a predetermined minimum biotransformation time, and an excess nutrient identified based on an electrocardiogram (ECG) signal measured on the user at the first time is identical to a deficiency nutrient identified based on an electrocardiogram (ECG) signal measured on the user at the second time.

10. A memory; a transceiver; an input / output device; a processor for processing instructions resident in the memory; acquiring, by the processor, an electrocardiogram (ECG) signal measured from a user via the transceiver or input / output device; analyzing the electrocardiogram (ECG) signal using pre-trained artificial intelligence (AI) by the processor to identify one or more nutrient deficiencies and nutrient surpluses corresponding to the user's health condition; A computer program recorded on a recording medium, causing the processor to execute a step of setting a menu including one or more foods and drinks that can replenish the identified deficient nutrients and avoid the excess nutrients.

Images