Artificial intelligence-based method and device for providing medical diagnosis service using correlation between symptoms and diseases

Abstract

The present disclosure relates to an artificial intelligence-based method and device for providing a medical diagnosis service using a correlation between symptoms and diseases. The device includes: at least one memory; at least one processor; and an output unit for providing a UI, wherein the processor: provides at least one first UI screen capable of inputting and selecting data related to at least one symptom expressed to a user on the basis of the output unit; transmits the data related to the at least one symptom input from the at least one first UI screen to an artificial intelligence (AI) model to acquire information on a predicted disease corresponding to the at least one symptom; provides a second UI screen including information on the predicted disease and information on one or more hospitals associated with the predicted disease; and provides a third UI screen for making an appointment at a specific hospital on the basis of the selection of the specific hospital among the one or more hospitals through the second UI screen.

Description

Method and device for providing medical diagnosis service using correlation between symptoms and diseases based on artificial intelligence

[0001] The present disclosure relates to a method and device for providing medical diagnostic services. More specifically, the present disclosure relates to a method and device for providing medical diagnostic services using correlations between symptoms and diseases based on artificial intelligence.

[0002] Despite South Korea being a country with high accessibility to medical care, there is a problem in that patients do not have sufficient information about their illnesses and do not have the desire to continuously manage them.

[0003] Hospitals also face a clinical environment where they lack the time and manpower to adequately listen to patients' medical histories, and in some cases, inaccurate diagnoses are made because they are not provided with sufficient information about patients' symptoms.

[0004] To address the aforementioned challenges, there are increasing efforts to integrate artificial intelligence (AI) technologies into medical services. Here, AI refers to machine learning methods based on artificial neural networks (ANNs), which mimic human biological neurons to enable machines to learn.

[0005] The purpose of the embodiments disclosed in the present disclosure is to provide a method and device for providing a medical diagnosis service using correlations between symptoms and diseases based on artificial intelligence.

[0006] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0007] According to one embodiment of the present disclosure, a device for providing a medical diagnosis service using a correlation between symptoms and diseases based on artificial intelligence includes: one or more memories; one or more processors; and an output unit providing a user interface (UI), wherein the one or more processors provide one or more first UI screens for allowing a user to input and select data related to one or more symptoms expressed based on the output unit, input data related to one or more symptoms input from the one or more first UI screens into an artificial intelligence (AI) model to obtain information on a predicted disease corresponding to the one or more symptoms, provide a second UI screen including information on the predicted disease and information on one or more hospitals related to the predicted disease, and provide a third UI screen for making a reservation at the specific hospital based on a specific hospital being selected from among the one or more hospitals through the second UI screen.

[0008] And, the one or more processors can transmit a questionnaire chart containing data related to the one or more symptoms and information on expected diseases to a terminal device used by the specific hospital based on the completion of a reservation at the specific hospital through the third UI screen.

[0009] And, information on the expected disease corresponding to the one or more symptoms may include at least one of the following: a department associated with the expected disease, the severity of the expected disease, the cause and symptoms of the expected disease, an improvement method for improving symptoms according to the expected disease, a list of general medicines suitable for the expected disease, and a description of tests and treatments required for the expected disease.

[0010] And, the one or more processors may provide a fourth UI screen for inquiring about the results of diagnosis from the specific hospital, and update one or more correlation values ​​constituting the AI ​​model based on the correlation between the results of diagnosis from the specific hospital and the predicted disease input through the fourth UI.

[0011] And, the one or more processors may increase a correlation value indicating a correlation between the one or more symptoms and the results diagnosed at the specific hospital based on the difference between the results diagnosed at the specific hospital and the expected disease, according to the AI ​​algorithm learning results.

[0012] And, the one or more processors can identify a plurality of hospitals within a preset range based on the user's location, and identify one or more hospitals among the plurality of hospitals that have a department associated with the expected disease.

[0013] In addition, the AI ​​model can be trained to identify a disease with the highest correlation with the one or more symptoms among the multiple diseases as the predicted disease based on the identification of multiple diseases corresponding to the one or more symptoms.

[0014] And, the AI ​​model can be trained to identify a disease with a high prevalence among the first disease and the second disease as the expected disease based on information about the user, based on the existence of a first disease and a second disease having the highest correlation with one or more symptoms among the plurality of diseases, and the correlation between the one or more symptoms and the first disease and the second disease being the same.

[0015] And, the one or more processors can identify at least one disease among the plurality of diseases, the correlation between the one or more symptoms and the disease being greater than a predefined value, and sort a predefined number of diseases among the one or more diseases on the second UI screen based on the correlation.

[0016] And, according to one embodiment of the present disclosure, a method for providing an artificial intelligence-based medical diagnosis service performed by a device may include the steps of: providing one or more first UI screens for inputting and selecting data related to one or more symptoms exhibited by a user; inputting data related to one or more symptoms input from the one or more first UI screens into an artificial intelligence (AI) model to obtain information on a predicted disease corresponding to the one or more symptoms; providing a second UI screen including information on the predicted disease and information on one or more hospitals associated with the predicted disease; and providing a third UI screen for making a reservation at a specific hospital based on a specific hospital being selected from among the one or more hospitals through the second UI screen.

[0017] In addition, a computer program stored in a computer-readable recording medium for implementing the present disclosure may be further provided.

[0018] In addition, a computer-readable recording medium recording a computer program for implementing the present disclosure may be further provided.

[0019] According to the aforementioned problem solving means of the present disclosure, a method and device for providing a medical diagnosis service using correlations between symptoms and diseases based on artificial intelligence can be provided.

[0020] In addition, according to the aforementioned problem solving means of the present disclosure, the medical service provision process between patients and medical staff can be carried out more efficiently and accurately.

[0021] In addition, according to the aforementioned problem solving means of the present disclosure, an artificial intelligence model that outputs a predicted disease based on symptoms can be efficiently optimized and trained.

[0022] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0023] FIG. 1 is a schematic diagram of a system for implementing a method for providing an artificial intelligence-based medical diagnosis service according to one embodiment of the present disclosure.

[0024] FIG. 2 is a block diagram illustrating the configuration of a device providing an artificial intelligence-based medical diagnosis service according to one embodiment of the present disclosure.

[0025] FIG. 3 is a flowchart illustrating a method for providing an artificial intelligence-based medical diagnosis service according to one embodiment of the present disclosure.

[0026] FIG. 4, FIG. 5, and FIG. 6 are diagrams illustrating an artificial intelligence-based diagnostic procedure according to one embodiment of the present disclosure.

[0027] FIG. 7A and FIG. 7B are diagrams for explaining an algorithm applied to an artificial intelligence model according to one embodiment of the present disclosure.

[0028] FIG. 8 and FIG. 9 are diagrams for explaining a method for providing artificial intelligence-based diagnostic results according to one embodiment of the present disclosure.

[0029] FIG. 10 and FIG. 11 are drawings for explaining a process for reserving a hospital according to one embodiment of the present disclosure.

[0030] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0031] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0032] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0033] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0034] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0035] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0036] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0037] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0038] As used herein, the term "device according to the present disclosure" encompasses a variety of devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.

[0039] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0040] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0041] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).

[0042] The artificial intelligence-related functions according to the present disclosure are operated via a processor and memory. The processor may be comprised of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a Digital Signal Processor (DSP), a graphics-only processor such as a GPU or a Vision Processing Unit (VPU), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operating rules or artificial intelligence models stored in memory. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0043] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned by a learning algorithm using a plurality of learning data, thereby creating a predefined operation rules or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0044] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0045] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence methodologies can be categorized into supervised learning, in which input data and output data are provided together as training data according to a learning method, so that the solution (output data) to a problem (input data) is determined; unsupervised learning, in which only input data is provided without output data, so that the solution (output data) to a problem (input data) is not determined; and reinforcement learning, in which a reward is provided from an external environment whenever an action is taken in the current state, and learning is performed in a direction to maximize this reward. In addition, artificial intelligence methodologies can be categorized according to the architecture, which is the structure of the learning model. The architecture of widely used deep learning technology can be categorized into convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and generative adversarial networks (GANs).

[0046] The present device and system may include an artificial intelligence model. The artificial intelligence model may be a single artificial intelligence model or may be implemented as multiple artificial intelligence models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to a model in general that has problem-solving capabilities by changing the binding strength of synapses through learning, formed by artificial neurons (nodes) that form a network by combining synapses. The neurons of the neural network may include a combination of weights or biases. The neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a desired result (output) from an arbitrary input (input) by changing the weights of neurons through learning.

[0047] The processor can create a neural network, train (or learn) a neural network, perform a calculation based on received input data, generate an information signal based on the calculation result, or retrain the neural network. The models of the neural network can include various types of models such as CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Restrcted Boltzman Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Classification Network, etc., but are not limited thereto. The processor can include one or more processors for performing calculations according to the models of the neural network. For example, the neural network can be a deep neural network. It may include a deep neural network.

[0048] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), Generative Adversarial Network (GAN), Liquid State Machine (LSM), Extreme Learning Machine (ELM), It will be understood by those skilled in the art that any neural network may be included, including but not limited to ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Neural Computer), NTM (Neural Turning Machine), CN (Capsule Network), KN (Kohonen Network), and AN (Attention Network).

[0049] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms, including optimization, recommendation, and data creation, can be utilized, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0050] In describing the present disclosure, “user” collectively refers to a patient who receives a medical diagnosis service using correlations between symptoms and diseases based on artificial intelligence.

[0051] FIG. 1 is a schematic diagram of a system for implementing a method for providing an artificial intelligence-based medical diagnosis service according to one embodiment of the present disclosure.

[0052] As illustrated in FIG. 1, a system (1000) for implementing a method for providing an artificial intelligence-based medical diagnosis service may include a device (100) used by a user, a server (200), and terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals (N is a natural number greater than or equal to 2). However, as an example of the present disclosure, terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals on the system (100) may be omitted.

[0053] The devices (100), servers (200), and terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals included in the system (1000) can communicate via a network (W). Here, the network (W) can include a wired network and a wireless network. For example, the network can include various networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN).

[0054] Additionally, the network (W) may include the well-known World Wide Web (WWW). However, the network (W) according to the embodiment of the present disclosure is not limited to the networks listed above, and may include at least a portion of a well-known wireless data network, a well-known telephone network, or a well-known wired / wireless television network.

[0055] The device (100) can receive data related to one or more symptoms input by a user. The device (100) can input data related to one or more symptoms into an artificial intelligence (AI) model to obtain information on expected diseases related to one or more symptoms.

[0056] Meanwhile, the device (100) can identify one or more hospitals / pharmacies associated with the expected disease among a plurality of hospitals (300-1, 300-2, ... 300-N). The device (100) can provide information on the expected disease and information on one or more hospitals / pharmacies associated with the expected disease.

[0057] The configuration of the device (100) and the specific operations performed by the device will be described with reference to FIGS. 2 to 11.

[0058] The server (200) can manage and control an application for performing a method of providing an artificial intelligence-based medical diagnosis service. That is, the device (100) can provide an artificial intelligence-based medical diagnosis service by executing an application provided by the server (200). Various operations performed by the device (100) and UI screens provided can be output through the application.

[0059] In describing the present disclosure, the fact that the device (100) transmits data to terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals may include that the device (100) directly transmits data to terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals and that the device (100) transmits data to terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals via the server (200).

[0060] That is, terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals can also install applications provided by the server (200). In addition, terminal devices (300-1, 300-2, ..., 300-N) used by multiple hospitals can receive various data from the device (100) through applications.

[0061] FIG. 2 is a block diagram illustrating the configuration of a device providing an artificial intelligence-based medical diagnosis service according to one embodiment of the present disclosure.

[0062] As illustrated in FIG. 2, the device (100) may include a memory (110), a communication module (120), a display (130), an input module (140), and a processor (150). However, the present invention is not limited thereto, and the device (100) may have its software and hardware configurations modified / added / omitted within a range apparent to those skilled in the art according to the required operation.

[0063] The memory (110) can store data supporting various functions of the device (100), a program for the operation of the processor (150), input / output data (e.g., music files, still images, moving images, etc.), and a plurality of application programs (or applications) run on the device, data for the operation of the device (100), and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0064] The memory (110) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk.

[0065] Additionally, the memory (110) may include a database that is separate from the device but connected via wire or wirelessly. That is, the database (200) illustrated in FIG. 1 may be implemented as a component of the memory (110).

[0066] The communication module (120) may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0067] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0068] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0069] The display (130) displays (outputs) information processed in the device (100) (e.g., one or more symptoms, expected diseases corresponding to one or more symptoms, etc.).

[0070] For example, the display may display execution screen information of an application (e.g., an application) running on the device (100), or UI (User Interface) or GUI (Graphical User Interface) information according to such execution screen information. The types of UI output from the display (130) will be described later.

[0071] The input module (140) is for receiving information from a user. When information is input through the user input unit, the processor (150) can control the operation of the device (100) to correspond to the input information.

[0072] The input module (140) may include hardware physical keys (e.g., buttons, dome switches, jog wheels, jog switches, etc. located on at least one of the front, rear, and side of the device) and software touch keys. For example, the touch keys may be formed of virtual keys, soft keys, or visual keys displayed on a touchscreen type display (130) through software processing, or may be formed of touch keys placed on a part other than the touchscreen. Meanwhile, the virtual keys or visual keys may be displayed on the touchscreen in various forms, and may be formed of, for example, graphics, text, icons, videos, or a combination thereof.

[0073] The processor (150) may be implemented as a memory storing data for an algorithm for controlling the operation of components within the device (100) or a program reproducing the algorithm, and at least one processor (not shown) that performs the aforementioned operations using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0074] In addition, the processor (150) can control any one or a combination of the components discussed above to implement various embodiments according to the present disclosure described in FIGS. 3 to 11 below on the device (100).

[0075] FIG. 3 is a flowchart illustrating a method for providing an artificial intelligence-based medical diagnosis service according to one embodiment of the present disclosure.

[0076] Figure 3 is a flowchart illustrating a process in which a user exhibiting one or more symptoms receives an artificial intelligence-based medical diagnosis service through a device.

[0077] The device may provide one or more first UI screens for the user to input and select data related to one or more symptoms expressed (S310).

[0078] For example, one or more first UI screens for entering and selecting data related to one or more symptoms may include a UI screen for selecting a symptom type, a UI screen for selecting a symptom site, and a UI screen for entering a time when the symptom started.

[0079] For example, as illustrated in FIG. 4, the device may provide a UI screen that allows the user to select a site of symptom on which the symptom has been manifested.

[0080] For example, based on the selection of "tongue / lips / mucosa" as a symptom site on the UI screen, the device may provide a UI screen for selecting a detailed symptom site within "tongue / lips / mucosa", as illustrated in FIG. 5. As another example, based on the selection of "abdomen" or the like as a symptom site on the UI screen, the device may provide a UI screen for selecting a detailed symptom site within "abdomen", as illustrated in FIG. 6.

[0081] The device may additionally provide a UI screen that allows users to input information about the amount smoked, when symptoms started, and tendencies related to the symptoms.

[0082] The device can input data related to one or more symptoms input from one or more first UI screens into an AI model to obtain information on expected diseases corresponding to one or more symptoms (S320).

[0083] Here, AI models can be developed / trained for diseases of all systems (e.g., dental, circulatory, respiratory, digestive, renal-urinary, endocrine, musculoskeletal, skin, neurological, obstetrics and gynecology, and psychiatric diseases).

[0084] As an example of the present disclosure, as illustrated in FIG. 7a, the AI ​​model may include a Softmax Regression algorithm (e.g., a multi-class version of logistic regression algorithm, etc.).

[0085] The AI ​​model can be trained to output information about a predicted disease corresponding to one or more symptoms based on one or more symptoms input through the first UI screen.

[0086] For example, information on a predicted disease corresponding to one or more symptoms may include at least one of a medical department associated with the predicted disease, the severity of the predicted disease, the cause and symptoms of the predicted disease, a method of improving symptoms according to the predicted disease, a list of general medications suitable for the predicted disease, and a description of tests and treatments required for the predicted disease.

[0087] Additionally, based on the identification of multiple diseases corresponding to one or more symptoms, the AI ​​model can be trained to identify the disease most highly correlated with one or more symptoms among the multiple diseases as the predicted disease.

[0088] Specifically, training data for training an AI model may include data matching multiple symptoms for each disease. Furthermore, correlation scores may be matched to each symptom for each disease.

[0089] The AI ​​model can be trained to identify / output the disease with the highest correlation with one or more symptoms input by the user as the expected disease based on training data containing multiple symptoms with correlation scores applied to each disease.

[0090] Among multiple diseases, it is assumed that there are first and second diseases with the highest correlation with at least one symptom, and that the correlations between at least one symptom and the first and second diseases are identical. In other words, it is assumed that the correlation values ​​between at least one symptom and the first and second diseases are identical.

[0091] At this time, the first AI model may be trained to identify a disease with a high prevalence among the first and second diseases as a predicted disease based on information about the user (e.g., the user's age and / or gender, etc.). In other words, the first AI model may be trained to identify / output a disease with a statistically high probability of occurrence within the user's age and / or gender as a predicted disease among the first and second diseases.

[0092] As another example, if the correlation between one or more symptoms and the first and second diseases is identical, the device may identify the first disease or / and the second disease as the likely disease. That is, if the correlation between the first and second diseases is output as the same value through the first AI model, the device may identify the first disease or / and the second disease as the likely disease and provide information about it.

[0093] Additionally or alternatively, as illustrated in FIG. 7b, the AI ​​model can learn and infer.

[0094] As an example of the present disclosure, input data ( ) may mean the user's selection (i.e., data related to one or more symptoms corresponding to the user's selection) for the jth option of the i-th question (i.e., a question output through the first UI to obtain data related to one or more symptoms).

[0095] For example, a question about headaches might be structured as "Where do you feel the pain?", and the options for that question might be "1. Only one side 2. Overall 3. Around the temples." If the user selects "1. Only one side" and "3. Around the temples," the device / AI model would respond to that question with " " can be used to organize data.

[0096] Correlation score ( ) represents the correlation value for the k-th disease according to the response to the j-th choice of the i-th question. A specific correlation value can be defined as a higher value if it is a correlation value that is important for differentiating the k-th disease. The initial correlation value can be one of 10, 2, 1, and 0.

[0097] For example, suppose a condition called migraine is identified / established based on one or more symptoms. In the case of migraine, pain felt on only one side may be important in differentiating the condition.

[0098] Accordingly, a high correlation score may be assigned to symptoms that are only felt on one side. Other symptoms may be assigned the lowest correlation score, as they are not important for disease diagnosis. For example, " "The correlation value can be set as follows.

[0099] And, the correlation ( ) represents the kth disease score according to the user's selection. The correlation can be constructed as in Equation 1. In Equation 1, N represents the number of questions, and M i represents the number of choices for the i-th question.

[0100]

[0101] For example, if a user selected all the questions in the headache algorithm, the score for the first condition, migraine, would be , the score for the second condition, tension headache, is , … , the score for the last twelfth disease, pheochromocytoma, is can be calculated as

[0102] In order to obtain the probability of the kth disease according to the user's selection using the correlation, the softmax function is used. The value can be calculated. can be calculated according to mathematical formula 2.

[0103]

[0104] In mathematical expression 2, K represents the total number of diseases included in the algorithm.

[0105] For example, if a user selects all questions in the headache algorithm, the device / AI model will can be calculated. The probability for the first disease, migraine, is , the probability for the last twelfth disease, pheochromocytoma, is can be calculated. At this time, the AI ​​model can output a predefined number of diseases with a high probability as the diagnosed diseases.

[0106] Actual diagnosed disease data ( ) refers to disease data that users were actually diagnosed with after visiting a hospital in the future.

[0107] For example, if a user is actually diagnosed with migraine during a future hospital visit, migraine will be the first condition output by the AI ​​model (i.e., the condition with the highest probability). This becomes the remaining disease data values ​​are 0 (i.e., ) can be.

[0108] Here, the learning algorithm applied to the AI ​​model defines cross-entropy as a loss function and the probability value for the disease ( ) is the actual diagnosed disease data ( ) to be similar to the correlation value ( ) may be gradient descent, a deep learning algorithm that automatically corrects the error.

[0109] For example, a user may be diagnosed with migraines and ultimately The remainder is close to 1 is a correlation value close to 0 ( ) AI models can be trained.

[0110] The device may provide a second UI screen containing information about the expected disease and information about one or more hospitals associated with the expected disease (S330).

[0111] That is, when a user inputs one or more symptoms, the device may provide a second UI screen containing information about a predicted disease corresponding to one or more symptoms and information about one or more hospitals associated with the predicted disease.

[0112] That is, at least one of the following may be displayed on the second UI screen: a department associated with the expected disease, the severity of the expected disease, the cause and symptoms of the expected disease, an improvement method for improving symptoms according to the expected disease, a list of general medicines suitable for the expected disease, and a description of tests and treatments required for the expected disease.

[0113] As an example of the present disclosure, as illustrated in FIG. 8, the device may sequentially provide predicted diseases (i.e., diseases most closely associated with one or more symptoms) and likely diseases excluding the predicted diseases on a second UI screen.

[0114] For example, the device may identify at least one disease whose symptoms and correlation with one or more of a plurality of diseases exceed a predefined value. The device may then sort a predefined number of diseases among the at least one disease on a second UI screen based on the correlation.

[0115] As another example, the device may omit diseases among a predefined number of diseases whose correlation is below a threshold value, and provide the remaining diseases sorted based on the correlation.

[0116] As another example, as illustrated in FIG. 9, the device may provide information about the department associated with the expected disease and the severity of the expected disease (e.g., whether hospital treatment is required) through a second UI screen.

[0117] As another example, as illustrated in FIG. 10, the device may provide a description of tests and treatments required for a predicted disease through a second UI screen.

[0118] As another example, the device can identify multiple hospitals within a preset range based on the user's current location. The device can identify one or more hospitals among the multiple hospitals that have departments associated with the anticipated condition. The device can provide information about the identified one or more hospitals through a second UI screen.

[0119] Based on a specific hospital being selected from among one or more hospitals through the second UI screen, the device may provide a third UI screen for making a reservation at the specific hospital (S340).

[0120] That is, as illustrated in FIG. 11, the device may include information about a specific hospital (e.g., location, clinic hours, contact information, etc. of a specific hospital) and a UI for making a reservation at a specific hospital on the third UI screen.

[0121] Based on the completion of an appointment at a specific hospital through the 3rd UI screen, the device can generate a questionnaire chart containing data related to one or more symptoms and information about expected diseases.

[0122] Specifically, the device can store a questionnaire template capable of generating a questionnaire. The device can generate a medical terminology-based questionnaire by applying / entering data related to one or more symptoms and information about anticipated diseases into the questionnaire template. The device can transmit the medical terminology-based questionnaire to a terminal device used by a specific hospital.

[0123] Accordingly, medical staff within a specific hospital can receive the user's initial diagnosis results and use them effectively to provide more accurate diagnosis results for the user.

[0124] Meanwhile, the device may provide a fourth UI screen that inquires about the results of a diagnosis made at a specific hospital. That is, the device may provide a fourth UI screen (or a pop-up message, etc.) that inquires about the results of a diagnosis made at a specific hospital after the appointment date with the specific hospital.

[0125] The device can update one or more correlation values ​​that constitute the AI ​​model based on the correlation between i) the diagnosis results from a specific hospital entered through the fourth UI and ii) the predicted disease. That is, the device can confirm through the fourth UI whether the predicted disease predicted by the AI ​​model matches the actual diagnosed result.

[0126] For example, let's assume a case where the diagnosis from a specific hospital differs from the expected condition. Specifically, let's assume a user enters the diagnosis from a specific hospital through the 4th UI, and the entered result differs from the expected condition.

[0127] The device may increase the correlation value, which indicates the correlation between one or more symptoms and the results diagnosed at a specific hospital (i.e., the disease diagnosed at a specific hospital), based on the AI ​​algorithm's learning results. As another example, the device may decrease the correlation value, which indicates the correlation between one or more symptoms and the predicted disease output by the AI ​​model, based on the AI ​​algorithm's learning results.

[0128] Later, when one or more of the above symptoms are input by the user, the AI ​​model can be trained to output a higher correlation between the one or more symptoms and the disease diagnosed by the specific hospital based on the updated correlation value. Accordingly, the AI ​​model can be further refined, increasing the correlation between symptoms and diseases.

[0129] As another example, assume that the diagnosis and predicted disease from a specific hospital are identical. The device can increase / decrease or maintain the correlation value, which indicates the correlation between one or more symptoms and the predicted disease output from the AI ​​model, based on the learning results of the AI ​​algorithm.

[0130] Additionally, the device can share diagnostic results from devices used by specific hospitals. Based on the differences or similarities between the shared diagnostic results and the predicted disease, the device can further train the AI ​​model (i.e., update the correlation score).

[0131] For example, a terminal device used by a specific hospital may input a user's diagnostic results into a provided questionnaire. The device may then receive the questionnaire from the server, in which the hospital entered the diagnostic results. The device may further train an AI model (i.e., update its correlation score) based on the differences or similarities between the shared diagnostic results and the predicted disease.

[0132] Additionally, while the above example focuses on hospitals, the method of providing information related to pharmacies can also be applied. That is, "hospital" in the above example could be replaced with "pharmacy."

[0133] As an example of the present disclosure, the device may provide a service that rewards a user when the user performs and certifies an activity to promote health over a certain period of time.

[0134] For example, if a user uploads authentication data for an activity that improves one or more symptoms and / or anticipated conditions, the device may provide a reward for that activity after verifying the authentication data.

[0135] The device may input authentication data for the activity into a separate AI model (e.g., a second AI model) to obtain information on whether the authentication data is associated with an activity that can improve one or more symptoms or / and expected conditions. If the authentication data is identified as being associated with an activity that can improve one or more symptoms or / and expected conditions, the device may provide a reward to the user.

[0136] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0137] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0138] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. One or more memories; one or more processors; and Includes an output section that provides a user interface (UI), One or more of the above processors, Based on the above output section, one or more first UI screens are provided for the user to input and select data related to one or more symptoms expressed, By inputting data related to one or more symptoms input from one or more first UI screens into an artificial intelligence (AI) model, information on expected diseases corresponding to the one or more symptoms is obtained, Providing a second UI screen containing information about the above predicted disease and information about one or more hospitals associated with the above predicted disease, A device that provides a third UI screen for making a reservation at a specific hospital based on selection of a specific hospital from among one or more hospitals through the second UI screen.

2. In paragraph 1, One or more of the above processors, A device that transmits a questionnaire chart containing data related to one or more symptoms and information on expected diseases to a terminal device used by the specific hospital based on completion of a reservation at the specific hospital through the third UI screen.

3. In paragraph 2, Information about the expected disease corresponding to one or more of the above symptoms, A device comprising at least one of the following: a medical department associated with the expected disease, the severity of the expected disease, the cause and symptoms of the expected disease, an improvement method for improving symptoms according to the expected disease, a list of general medicines suitable for the expected disease, and a description of tests and treatments required for the expected disease.

4. In paragraph 3, One or more of the above processors, Provides a 4th UI screen for inquiring about the results of diagnosis from the specific hospital mentioned above, A device that updates one or more correlation values ​​constituting the AI ​​model based on the correlation between the diagnosis result from the specific hospital input through the fourth UI and the predicted disease.

5. In paragraph 4, One or more of the above processors, A device that increases a correlation value indicating a correlation between one or more symptoms and the results diagnosed at the specific hospital based on the difference between the results diagnosed at the specific hospital and the expected disease, according to the results of AI algorithm learning.

6. In paragraph 5, One or more of the above processors, Identify multiple hospitals within a preset range based on the user's location, A device for identifying one or more hospitals among the plurality of hospitals that have a department associated with the expected disease.

7. In paragraph 6, The above AI model is, A device that learns to identify a disease with the highest correlation with the one or more symptoms among the multiple diseases as the predicted disease based on the identification of multiple diseases corresponding to the one or more symptoms.

8. In paragraph 7, The above AI model is, A device that learns to identify a disease with a high prevalence among the first disease and the second disease as the expected disease based on information about the user, based on the existence of a first disease and a second disease having the highest correlation with one or more of the symptoms among the plurality of diseases, and the correlation between the one or more symptoms and the first disease and the second disease being the same.

9. In paragraph 8, One or more of the above processors, Identifying at least one disease among the above multiple diseases whose correlation with one or more symptoms is greater than a predefined value, A device that arranges a predefined number of diseases among the at least one disease on the second UI screen based on the degree of correlation.

10. A method for providing an artificial intelligence-based medical diagnosis service performed by a device, the method comprising: A step of providing one or more first UI screens for allowing a user to input and select data related to one or more symptoms expressed; A step of inputting data related to one or more symptoms input from one or more first UI screens into an artificial intelligence (AI) model to obtain information on a predicted disease corresponding to the one or more symptoms; providing a second UI screen including information about the expected disease and information about one or more hospitals associated with the expected disease; and A method comprising the step of providing a third UI screen for making a reservation at a specific hospital based on selection of a specific hospital from among one or more hospitals through the second UI screen.

Images