System

Abstract

A system is provided.SOLUTION: A system includes an inputting means for a user to input health conditions and symptoms, a diagnosing means for analyzing the inputted information and diagnosing using a generated AI model, and an reserving means for reserving a medical facility based on the diagnostic result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In modern society, many people lead busy lives and often cannot find time to visit a medical institution even when their health condition changes. This leads to problems such as delayed early detection and treatment of illness, increasing the risk of symptoms worsening. Furthermore, the accuracy of self-diagnosis is low, and there are health risks associated with inappropriate treatment. There is a need for a method to improve this situation and make it easy for even busy people to undergo health checkups. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, an input means is provided for the user to input their health condition and symptoms. Next, a diagnostic means is provided for analyzing the input data and making a diagnosis using a generative AI model. This generative AI model compares the user's symptoms using past medical data and a trained knowledge base to identify likely illnesses. Finally, a reservation means is provided for making an appointment with a medical institution based on the diagnosis results. Such a system allows users to easily undergo health checkups even during their busy daily lives, promoting early detection of illnesses and appropriate treatment. Furthermore, by adding a display means for displaying the diagnosis results, users can check their own health condition and quickly take any necessary next steps.

[0006] "User" refers to an individual who uses this system and inputs their health status and symptoms.

[0007] "Health Status" refers to information about the user's current physical condition and medical history.

[0008] "Symptoms" refers to specific abnormalities or discomforts that the user is aware of.

[0009] "Input means" refers to the interface that allows users to input their health status and symptoms into the system.

[0010] "Diagnostic means" refers to means for analyzing input data and identifying likely diseases.

[0011] A "generative AI model" refers to a machine learning model that makes diagnoses based on past medical data and a learned knowledge base.

[0012] "Medical data" refers to data such as past patient information, medical history, and treatment progress.

[0013] A "knowledge base" refers to a collection of specialized medical knowledge and information.

[0014] "Reservation means" refers to the function for reserving a date and time for an examination at a medical institution based on the diagnosis results.

[0015] "Diagnosis Results" refers to the likely diseases and associated information identified by the generative AI model.

[0016] "Display means" refers to an interface for displaying diagnostic results to the user.

[0017] "Medical institution" refers to a facility that provides medical services, such as a hospital or clinic. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[0040] First, the user uses the device to input their health status and symptoms. This input consists of data such as age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[0041] The server analyzes the received data, performs data validation and checks the format, then passes the data to a generative AI model, which compares it with previously learned medical data and knowledge bases to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify the possibility of diseases related to the input symptoms with a high degree of accuracy.

[0042] The generative AI model, used as a diagnostic tool, considers various disease possibilities based on the user's input information and suggests the most likely disease or health condition. When a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of the identified disease and the next action to be taken (e.g., whether a doctor's consultation is necessary).

[0043] The user device displays the received diagnosis results, allowing the user to learn about their health status and take the next step quickly. For example, if a doctor's visit is recommended based on the diagnosis results, the user can enter the desired hospital and appointment date and time through the application's UI.

[0044] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[0045] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[0046] As a specific example, if a user inputs the symptoms of "cough" and "fever," the server receives this and uses a generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[0047] In this way, the system leverages past medical data and knowledge bases, and uses generative AI models to create a self-health checkup service that is easy for even busy people to use.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms into the device's input fields.

[0051] Step 2:

[0052] The terminal structures the input data, converts it to JSON format, adds a timestamp, and sends the data to the server.

[0053] Step 3:

[0054] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[0055] Step 4:

[0056] The server passes the analyzed data to the generative AI model, which then compares it with past medical data and knowledge bases and instructs the AI ​​model to perform a diagnosis.

[0057] Step 5:

[0058] A generative AI model processes the data and identifies likely diseases. The AI ​​model uses vast amounts of medical data to identify diseases that match the user's symptoms.

[0059] Step 6:

[0060] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[0061] Step 7:

[0062] The device displays the received diagnostic results to the user. The device analyzes the diagnostic results and displays them in a format that is easy for the user to understand.

[0063] Step 8:

[0064] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[0065] Step 9:

[0066] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[0067] Step 10:

[0068] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[0069] Step 11:

[0070] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[0071] Step 12:

[0072] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[0073] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[0074] Example 1

[0075] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0076] Conventional health checkup systems have the problem that it is difficult for users to easily check their health status and quickly make an appointment with an appropriate medical institution. In addition, the diagnosis results can sometimes be unreliable, so there is a need for a system that users can use with confidence.

[0077] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0078] In this invention, the server includes a means for analyzing input data, adding a timestamp and performing data validation, a diagnostic means for applying a generative AI model using the analyzed data and comparing it with medical information to make a diagnosis, and a means for transmitting the diagnostic result and diagnostic ID to the user terminal, which allows users to easily check their own health condition, obtain highly accurate diagnostic results, and more quickly make appointments with medical institutions.

[0079] "Input means" refers to a device or interface that allows a user to input health conditions and symptoms.

[0080] "Data validation" is the process of verifying the integrity and correctness of format of received data.

[0081] A "timestamp" is information that indicates the time when data was transmitted by adding the current date and time to the data.

[0082] A "generative AI model" is an artificial intelligence model that uses vast amounts of medical information and a trained knowledge base to identify diseases associated with input symptoms.

[0083] A "diagnostic means" is a device or system that has the ability to use analyzed data to assess a user's health status and apply a generative AI model to make a diagnosis.

[0084] "Reservation means" refers to the functions and interfaces that allow users to make reservations at medical institutions based on diagnostic results.

[0085] A "diagnosis ID" is an identifier associated with a particular diagnosis result and is used to uniquely identify the diagnosis result.

[0086] A "display means" is a device or interface that visually displays diagnostic results or other information to a user.

[0087] "Medical Information" means historical data, knowledge base, and related medical information used in diagnosis and treatment.

[0088] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[0089] First, the user enters their health condition and symptoms using a device such as a smartphone or PC. Specific information to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). Once the user has completed the input, the device converts this information into JSON format and adds the current date and time as a timestamp. The device then sends the converted data to the server.

[0090] The server analyzes the data received from the device and first performs data validation. By checking the data's consistency and format, it ensures that the input information is accurate. The server then passes the data to a generative AI model. This generative AI model is based on a vast amount of medical information and a trained knowledge base, so it can accurately identify the possible diseases associated with the user's input symptoms. The generative AI model identifies the most likely disease and returns the result to the server along with a diagnosis ID.

[0091] The server then sends the diagnosis results to the user's device, including the likelihood of an identified illness and the next course of action (e.g., whether or not a doctor's visit is necessary).

[0092] The user's device receives the diagnosis results and displays them on the application, allowing the user to check their own health status. For example, if a user enters symptoms of "cough" and "fever" and receives a diagnosis of "suspected influenza," the user can make an appointment at the nearest medical institution through the application. The user enters the desired hospital and appointment date and time and presses the "Make an appointment" button.

[0093] The device converts the user's reservation information back into JSON format and sends it to the server. The server receives the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, the server generates a confirmation message and sends it to the user's device. The user can check the received confirmation message on the application and find out that the reservation was successful.

[0094] This system allows users to easily undergo health checkups even in their busy daily lives and quickly make appointments with necessary medical institutions.

[0095] As a specific example, when a user inputs the symptoms of "cough" and "fever," the program's processing proceeds as follows: "Please explain the process by which a user can enter the symptoms of cough and fever, receive a diagnosis that indicates a high possibility of influenza, and then make a hospital appointment within the app." This system thus utilizes past medical information and a knowledge base, and uses a generative AI model to create a self-health checkup service that is easy to use even for busy people.

[0096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0097] Step 1:

[0098] The user launches the application and enters their health status and symptoms.

[0099] The user launches the application using a smartphone or PC, enters their age, gender, medical history, and current symptoms (e.g., cough, fever, etc.) into the input form, and presses the "Submit" button. At this time, the input data is in RAW text format.

[0100] Step 2:

[0101] The terminal converts the input data into JSON format and adds a timestamp.

[0102] When the "Submit" button is pressed, the terminal converts the RAW text data obtained from the form into JSON format. For example, it generates a JSON object containing the entered data, such as "Age: 30, Gender: Male, Symptoms: Cough, Fever." It also obtains the current date and time and adds it to the JSON data as a timestamp. Input: RAW text data Output: JSON data with timestamp.

[0103] Step 3:

[0104] The device sends JSON data to the server.

[0105] The terminal sends the converted time-stamped JSON data to the server via an HTTP POST request. Input: Time-stamped JSON data Output: HTTP POST request.

[0106] Step 4:

[0107] The server receives the data, parses it, and validates it.

[0108] The server receives the HTTP POST request and parses the JSON data. After parsing, it performs data validation to check the consistency and format of the input data. Input: JSON data with a timestamp. Output: Validated data.

[0109] Step 5:

[0110] The server passes the validated data to the generative AI model to perform the diagnosis.

[0111] The server inputs the validated data into the generative AI model. Based on a vast medical information and knowledge base, the generative AI model identifies with high accuracy the possibility of a disease related to the input symptoms. A diagnosis result is obtained. Input: Validated data Output: Diagnosis result and diagnosis ID.

[0112] Step 6:

[0113] The server sends the diagnosis result and diagnosis ID to the user's terminal.

[0114] The server converts the diagnosis results and diagnosis ID obtained from the generative AI model into JSON format and returns them to the user device as an HTTP response. Input: Diagnosis results and diagnosis ID Output: JSON data with timestamp.

[0115] Step 7:

[0116] The user terminal receives and displays the diagnostic results.

[0117] The user device receives the HTTP response from the server and analyzes the JSON data. The diagnosis results are displayed on the application, allowing the user to check their own health status. Input: Diagnosis result and diagnosis ID Output: Displayed diagnosis result.

[0118] Step 8:

[0119] The user makes a medical appointment through the application.

[0120] Based on the diagnosis results, the user is directed to the reservation screen at the nearest medical institution through the application's UI. They enter the necessary reservation information (hospital, desired date and time, etc.) and press the "Make a reservation" button. Input: Reservation information (hospital, date and time, etc.) Output: Reservation information

[0121] Step 9:

[0122] The device sends the reservation information in JSON format to the server.

[0123] When the user presses the "Make a reservation" button, the device converts the reservation information into JSON format and sends it to the server via an HTTP POST request. Input: RAW data of reservation information Output: JSON data of reservation information

[0124] Step 10:

[0125] The server confirms the reservation based on the reservation information and sends the result to the user terminal.

[0126] The server receives the JSON data of the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, it generates a confirmation message and sends it to the user's device as an HTTP response. Input: JSON data of the reservation information Output: Confirmation message

[0127] Step 11:

[0128] The user terminal receives and displays the confirmation message.

[0129] The user terminal receives the HTTP response from the server, parses the confirmation message, and displays it, letting the user know that the reservation was successful. Input: Confirmation message Output: Displayed confirmation message.

[0130] (Application example 1)

[0131] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] Conventional self-health checkup systems allow users to easily check their health status, but they are unable to provide prompt action based on the results of the checkup, suggest necessary over-the-counter medications, or purchase them on the spot. Furthermore, it is difficult to easily make appointments with medical institutions, which can lead to delays in early detection of illness and appropriate treatment. This has resulted in insufficient efficiency in users' health management.

[0133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0134] In this invention, the server includes an input means for the user to input their health condition and symptoms, a diagnosis means for analyzing the input data and making a diagnosis using a generative AI model, a reservation means for making an appointment with a medical institution based on the diagnosis results, and a suggestion means for displaying the diagnosis results of the health condition and symptoms and suggesting or purchasing over-the-counter medications as needed. This enables users to easily check their health condition and quickly purchase over-the-counter medications and make appointments with medical institutions based on the diagnosis results.

[0135] An "input means" is a system component that provides an interface for a user to input health conditions and symptoms.

[0136] A "diagnostic means" is a system component that analyzes input data and performs a diagnosis using a generative AI model.

[0137] A "generative AI model" is an artificial intelligence algorithm that analyzes a user's health condition and symptoms based on past medical data and a learned knowledge base, and derives a diagnosis.

[0138] The "reservation means" is a system component for making a reservation at a medical institution based on the diagnosis results.

[0139] The "suggestion means" is a system component that displays the diagnosis results of health conditions and symptoms, and provides the function of suggesting over-the-counter medicines and assisting in the purchase of medicines as needed.

[0140] The "display means" is a system component that presents the diagnostic results based on the user's symptoms in a visually recognizable form.

[0141] "Medical institution" refers to a medical facility such as a hospital or clinic where users can receive treatment through diagnostic results and appointment procedures.

[0142] "Over-the-counter drugs" are medicines that can be purchased at pharmacies or drug stores without a prescription.

[0143] This invention is a system that allows users to conduct self-health checkups and, if necessary, make appointments with medical institutions or purchase over-the-counter medications on the spot. This system includes the following main components: an input means for users to input their health condition and symptoms, a diagnosis means that analyzes the input data and makes a diagnosis using a generative AI model, a reservation means that makes appointments with medical institutions based on the diagnosis results, and a suggestion means that displays the diagnosis results of the health condition and symptoms and suggests and purchases over-the-counter medications as necessary.

[0144] The operation of the system will be described in detail below. The user uses a terminal to input their health condition and symptoms. The terminal is equipped with a touch panel display and provides an interface that allows for easy input of health information. The information entered by the user is converted into JSON format, time-stamped, and then sent to the server. This communication uses an HTTP request library (for example, Python's requests library).

[0145] The server analyzes the received data and performs basic data validation and format checks using a database management system (DBMS) and data analysis libraries (e.g., pandas and NumPy). Once the data analysis is complete, it is passed to a generative AI model, which runs on a GPU cluster and uses frameworks such as PyTorch to compare the data with past medical data and a trained knowledge base to make a diagnosis.

[0146] The diagnostic results are returned to the server, where the diagnostic result data is formatted in JSON format. This data is then sent back to the device as an HTTP response. The device receives this and displays the diagnostic results to the user. The user interface (UI) is intuitively designed using JavaScript, HTML, and CSS.

[0147] The diagnosis results include the possibility of an identified illness, the next action to be taken (e.g., whether or not a medical visit is necessary), and suggestions for medications for symptoms that can be treated with over-the-counter medications. Based on this, if the user wishes, they can purchase over-the-counter medications on the spot. Furthermore, if a diagnosis indicates that a medical visit is necessary, the user can make an appointment with a medical institution through the application's UI. Once the appointment procedure is completed, the appointment information is also sent to the server and processed.

[0148] Here is a specific example of usage: For example, if a user enters the symptoms "cough" and "fever", the following prompt will be sent to the server:

[0149] Age: 35

[0150] Gender: Male

[0151] Symptoms: Cough, fever

[0152] Timestamp: 2023-10-05T10:05Z

[0153] Based on this input, the generative AI model returns a diagnosis of "cold" or "flu" and presents the user with a diagnosis of "suspected flu." The user can then make an appointment with the nearest medical institution based on this diagnosis. If necessary, the user can also purchase the suggested over-the-counter medication on the spot.

[0154] As described above, the system of the present invention can perform a complete process from self-health checkups to making appointments with medical institutions and purchasing over-the-counter medicines, thereby efficiently and quickly supporting users in managing their health.

[0155] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0156] Step 1:

[0157] The user inputs their health condition and symptoms into the device.

[0158] The data to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.).

[0159] The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[0160] Input: Age, gender, medical history, current specific symptoms

[0161] Output: JSON format data

[0162] Specific operation: The user enters information into the touch panel display and presses the "Send" button.

[0163] Step 2:

[0164] The server parses the received JSON data and performs basic data validation and format checks.

[0165] Specifically, it checks the existence of required fields and validates data types, using data analysis libraries and DBMS.

[0166] Input: JSON format data

[0167] Output: Validated data

[0168] Specific operation: A Python script is executed on the server side to perform data validation.

[0169] Step 3:

[0170] The server passes the verified data to a generative AI model to make a diagnosis.

[0171] The generative AI model compares historical medical data and a trained knowledge base to identify possible illnesses based on input symptoms.

[0172] This uses frameworks such as PyTorch running on GPU clusters.

[0173] Input: Validated data

[0174] Output: Diagnostic results

[0175] Specific operation: The server inputs data into the generative AI model and obtains the diagnosis results.

[0176] Step 4:

[0177] The server formats the diagnostic results from the generated AI model in JSON format and sends them back to the device.

[0178] The returned data includes the diagnosis as well as suggestions for next steps and over-the-counter medications.

[0179] Input: Diagnostic results from a generative AI model

[0180] Output: JSON format diagnostic result data

[0181] Specific operation: The server formats the diagnostic results and sends them to the terminal as an HTTP response.

[0182] Step 5:

[0183] The device displays the diagnostic results it receives to the user.

[0184] The diagnosis results will show the likelihood of the disease being identified and the next action to be taken (e.g., whether or not medical attention is required).

[0185] Input: JSON format diagnostic result data

[0186] Output: Display of diagnostic results

[0187] Specific operation: The diagnostic results are displayed on the device display for the user to check.

[0188] Step 6:

[0189] When a user makes an appointment at a medical institution based on the diagnosis results, the user inputs appointment information (date, time, hospital, etc.) and transmits it to the server via the terminal.

[0190] The server receives the reservation information and checks whether the reservation can be made for the specified date and time.

[0191] Input: Reservation information (date, time, hospital, etc.)

[0192] Output: Reservation confirmation message

[0193] Specific operation: The user fills out the reservation form and presses the "Reserve" button.

[0194] Step 7:

[0195] The server verifies that the reservation was successful and generates a confirmation message and sends it to the terminal.

[0196] The terminal will display this confirmation message to the user, letting them know that the reservation was successful.

[0197] Input: Reservation confirmation data

[0198] Output: Reservation confirmation message

[0199] Specific operation: The server generates a reservation success message and sends it to the terminal, which displays the message.

[0200] Step 8:

[0201] The user checks the over-the-counter drug suggestions and purchases them on the spot if necessary.

[0202] Information on suggested over-the-counter medications is displayed, and you can immediately proceed with the purchase.

[0203] Input: Over-the-counter drug proposal data

[0204] Output: Purchase confirmation message

[0205] Specific behavior: The user reviews the over-the-counter drug suggestions and presses the purchase button. The device displays a purchase confirmation.

[0206] Through these steps, users can quickly and efficiently manage their health, making necessary medical appointments and purchasing over-the-counter medications.

[0207] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0208] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[0209] First, the user uses the device to input their health status and symptoms. They enter information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields. The emotion engine then analyzes the user's input data and voice data to recognize the user's emotional state. This emotional state is important data for the subsequent diagnosis process.

[0210] The device converts this information and emotion data into JSON format, adds a timestamp, and sends it to the server.

[0211] The server analyzes the received data and performs data validation and format checks. The server then passes the analyzed health status data and emotion data to the generative AI model, which compares it with the trained medical data and knowledge base to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify possible illnesses with high accuracy by taking into account the user's symptoms and emotional state.

[0212] The generative AI model for diagnostics considers various possible illnesses based on the user's input and emotional state, and suggests the most likely illness or health condition. The emotion engine also adjusts the diagnostic process based on the user's emotional state. For example, if the user is feeling anxious, the system will operate to provide diagnostic results in a more careful and polite manner.

[0213] If a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of a specific illness being identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[0214] The user device displays the received diagnosis results to the user, allowing the user to know their own health condition and take the next action promptly.If the user wishes to see a doctor based on the diagnosis results, they can enter the desired hospital and appointment date and time through the application's UI.

[0215] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[0216] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[0217] As a specific example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the server receives this and uses the generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[0218] In this way, the system leverages historical medical data and knowledge bases, and uses generative AI models and an emotion engine to create a self-health checkup service that is easy for even busy people to use.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields.

[0222] Step 2:

[0223] The emotion engine analyzes the user's input and voice data to recognize their emotional state from their tone of voice and input, identifying emotions such as anxiety, sadness, and anger.

[0224] Step 3:

[0225] The device converts the input data and emotion data into JSON format, adds a timestamp, and sends the data to the server.

[0226] Step 4:

[0227] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[0228] Step 5:

[0229] The server passes the analyzed data to the generative AI model, which then uses the generative AI model to perform a diagnosis based on the health status data and emotion data.

[0230] Step 6:

[0231] A generative AI model processes the data to identify likely illnesses, compares it with vast amounts of medical data, and generates a diagnosis that takes into account the user's symptoms and emotional state.

[0232] Step 7:

[0233] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[0234] Step 8:

[0235] The device receives the diagnosis results and displays them to the user. The device analyzes the results and displays them in a format that is easy for the user to understand. The display method may change depending on the user's emotional state.

[0236] Step 9:

[0237] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[0238] Step 10:

[0239] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[0240] Step 11:

[0241] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[0242] Step 12:

[0243] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[0244] Step 13:

[0245] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[0246] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[0247] Example 2

[0248] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0249] In modern society, busy users need a system that allows them to easily check their health status and, if necessary, make appointments with a medical institution. Furthermore, it is important to provide a diagnosis that takes into account the user's emotional state in order to provide more accurate medical care. However, existing systems face the challenge of being unable to provide a comprehensive diagnosis that includes the user's emotional state.

[0250] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0251] In this invention, the server includes emotion analysis means for analyzing input data and recognizing the emotional state, transmission means for transmitting the analyzed health information and emotional data to the server, and data processing means for receiving the transmitted data and validating and checking the format. This makes it possible to comprehensively diagnose the health information and emotional state input by the user and provide highly accurate diagnostic results.

[0252] The "input amount means" is a means for providing an interface for the user to input health conditions and symptoms.

[0253] The "emotion analysis means" is a means for analyzing the user's input data and voice data and recognizing the user's emotional state.

[0254] The "transmission means" is a means for converting the analyzed health information and emotion data into JSON format and transmitting it to the server.

[0255] The "data processing means" is a means for analyzing data received by the server and performing validation and format checks.

[0256] "Generation means" refers to a means for making a diagnosis using a generative AI model based on received data.

[0257] The "display means" is a means for displaying the diagnosis results based on the user's symptoms and emotional state on the terminal.

[0258] A "generative AI model" is an artificial intelligence model that learns from a vast medical database and makes diagnoses by taking into consideration the user's health information and emotional state in an integrated manner.

[0259] "Data processing means" refers to the server's function of analyzing the health information and emotion data sent by the user and performing any necessary validation and format checks.

[0260] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[0261] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[0262] First, the user accesses the system from their own device (such as a smartphone, tablet, or PC). On the system's user interface, they enter health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into input fields. This input is performed via an input volume means.

[0263] Next, the emotion analysis means analyzes the user's input data and voice data to recognize the user's emotional state. For example, emotions such as "anxiety" or "tension" can be recognized from the tone and speaking style of the voice. This emotional state is important data for the diagnostic process.

[0264] The device converts the input health information and analyzed emotion data into JSON format, adds a timestamp, and sends it to the server. This transmission is performed using a transmission method.

[0265] The server analyzes the received data using a data processing means and validates the input data (checking the format and values). For example, it checks whether the age is within the range or whether symptom data is missing. The verified data is then input into a generation means, and a diagnosis is performed using a generative AI model. The generative AI model uses a vast medical database to comprehensively consider the user's symptoms and emotional state, generating highly accurate diagnostic results.

[0266] When a diagnosis result is obtained, the server sends the diagnosis result data to the user terminal. The result includes the possibility of a specified illness and a recommended next action (e.g., whether or not a doctor's consultation is necessary). The user terminal displays the received diagnosis result to the user on a display means. This allows the user to know about their own health condition and take the next action promptly.

[0267] If the user wishes to see a doctor based on the diagnosis results, they enter the desired hospital and appointment date and time through the application's UI. The device obtains the user's appointment information and sends it back to the server. The server checks whether an appointment can be made for the specified date and time based on the received appointment information. If the appointment is successful, the server generates a confirmation message and sends it to the device. The user's device receives this confirmation message and displays it to the user, informing them that the appointment was successful.

[0268] In this way, users can not only quickly and efficiently manage their health, but also easily make necessary medical appointments.In addition, the emotion engine takes into account the user's emotional state, providing more thorough and accurate diagnosis results.

[0269] Specific examples

[0270] For example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the device sends this data to the server. The server uses the generative AI model to consider the possibility of "cold" or "flu," generates a diagnosis of "suspected influenza," and sends this to the device. After the user confirms the "suspected influenza," they make an appointment with the nearest medical institution, and the server confirms the appointment and notifies them of its success.

[0271] Prompt Sentence Examples

[0272] "A user inputs symptoms of cough and fever. The emotion engine recognizes that the user is anxious. Based on this information, what diagnosis would the generative AI model make and what suggestions would it make in response?"

[0273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0274] Step 1:

[0275] A user accesses the system and enters health information.

[0276] Input: Health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever).

[0277] Specific operation: The user enters health information into the device's user interface.

[0278] Output: The input health information data.

[0279] Step 2:

[0280] An emotion analysis means analyzes the user's emotional state.

[0281] Input: Text and voice data entered by the user.

[0282] Specific operation: The emotion analysis engine performs real-time analysis and recognizes the user's emotional state (e.g., anxiety, tension).

[0283] Output: Parsed emotion data.

[0284] Step 3:

[0285] The device sends health information and emotion data to the server.

[0286] Input: Health information data, emotion data.

[0287] Specific operation: The device converts this data into JSON format, adds a timestamp, and sends it.

[0288] Output: Health and emotion data in JSON format sent to the server.

[0289] Step 4:

[0290] The server receives the data and performs validation.

[0291] Input: Received data in JSON format.

[0292] Specific behavior: The server checks the data format and values, and generates an error message if necessary.

[0293] Output: The validated data.

[0294] Step 5:

[0295] The server uses the generative AI model to perform the diagnosis.

[0296] Input: Validated health and emotion data.

[0297] How it works: The server inputs this data into a generative AI model and makes a diagnosis by referencing a vast medical database.

[0298] Output: Highly accurate diagnostic results.

[0299] Step 6:

[0300] The server transmits the diagnosis results to the user terminal.

[0301] Input: Diagnostic result data.

[0302] Specific operation: The server generates a message to send the diagnostic results to the user terminal.

[0303] Output: Diagnostic results sent to the user's terminal.

[0304] Step 7:

[0305] The user checks the diagnosis results and makes a hospital appointment if necessary.

[0306] Input: Diagnostic results displayed on the user's terminal.

[0307] Specific operation: The user checks the diagnostic results and enters reservation information through the application's UI.

[0308] Output: Appointment information (hospital name, appointment date and time).

[0309] Step 8:

[0310] The terminal transmits the reservation information to the server.

[0311] Input: Reservation information.

[0312] Specific operation: The terminal formats the data to send the reservation information to the server.

[0313] Output: The reservation information sent to the server.

[0314] Step 9:

[0315] The server checks the reservation status and notifies the user.

[0316] Input: Reservation information.

[0317] Specific operation: Based on the received reservation information, the server checks the reservation status at the medical institution, and if the reservation is successful, it generates a confirmation message and sends it to the terminal.

[0318] Output: Booking confirmation message.

[0319] (Application example 2)

[0320] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0321] Conventional self-health checkup systems only require users to input their health condition and symptoms, and do not take into account the user's emotional state. As a result, there is a lack of consideration for how the diagnosis results will be received by the user, and dealing with users who feel anxious is a particular issue. In addition, the procedure for making an appointment with a medical institution based on the diagnosis results is cumbersome, making the system less user-friendly. As such, there is a need for a system that combines highly accurate diagnosis that takes the user's emotions into account with a smooth appointment process with a medical institution.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing input data and emotional state and performing diagnosis using a generative AI model, means for the diagnostic means to adjust the method for providing diagnostic results taking into account the user's emotional state, and means for confirming appointments with medical institutions and notifying the user of the results. This enables highly accurate self-health checkups that take into account the user's emotions, and also simplifies the process of making appointments with medical institutions.

[0323] "Input means" refers to the means by which a user inputs information about their health condition or symptoms into the system.

[0324] The "diagnostic means" is a means for analyzing input health condition and symptom data and emotional state, and making a diagnosis using a generative AI model.

[0325] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[0326] The "means for taking into account the emotional state" is a means for adjusting the method for providing the diagnostic results based on the emotional state of the user.

[0327] "Notification means" refers to the means for confirming an appointment with a medical institution and notifying the user of the results.

[0328] The "display means" is a means for displaying the diagnosis results based on the symptoms and emotional state of the user.

[0329] A "generative AI model" is an artificial intelligence model that uses data on a user's health, symptoms, and emotional state to match it with past medical data and a trained knowledge base to identify likely illnesses.

[0330] "Data" refers to information about a user's health, symptoms, and emotional state.

[0331] "Emotional state" refers to the emotional state of the user, which influences the behavior of the diagnostic tool.

[0332] The present invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system is composed of elements such as an input means, a diagnosis means, a reservation means, a means for considering emotional state, a notification means, and a display means.

[0333] Input Method

[0334] Using a device such as a smartphone, the user inputs information such as age, gender, medical history, and specific symptoms (e.g., cough, fever). An emotion recognition engine then analyzes the voice and text data to recognize the user's emotional state (e.g., anxiety). The input data and emotional state are then stored on the device.

[0335] Diagnostic tools

[0336] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. The server analyzes and validates the received data and performs a diagnosis using a generative AI model. This generative AI model takes into account the user's symptoms and emotional state based on a vast medical data and knowledge base, and identifies possible illnesses with high accuracy.

[0337] Measures that take emotional state into account

[0338] The diagnostic means adjusts the way in which the diagnostic result is provided taking into account the emotional state of the user, for example, if the user is feeling anxious, the diagnostic means operates to provide the diagnostic result in a polite and careful manner.

[0339] Reservation method

[0340] When a diagnosis result is obtained, the server sends it to the user's device. The diagnosis result includes the possibility of a specific illness and the next action to be taken (e.g., whether or not a doctor's examination is necessary). If the user wishes to see a doctor based on the diagnosis result, they input the desired hospital and appointment date and time through the device's UI.

[0341] Notification means

[0342] After the reservation procedure is completed, the terminal sends the reservation information to the server. The server checks whether the reservation is available for the specified date and time, and if the reservation is successful, it generates a confirmation message and sends it again to the terminal. The terminal displays this confirmation message to the user, notifying them that the reservation was successful.

[0343] Display means

[0344] The user device displays the received diagnostic results, allowing the user to know about their own health condition and take immediate action.

[0345] Example

[0346] For example, a 25-year-old male user inputs symptoms of fever and cough, and the emotion engine recognizes "anxiety." The server receives this data and uses the generative AI model to consider the possibility of "cold" or "flu." If the diagnosis is returned as "suspected influenza," the user can make an appointment with a nearby medical institution through the UI and receive a notification that the appointment has been completed.

[0347] Prompt Sentence Examples

[0348] Here are some example prompts for the generative AI model:

[0349] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[0350] In this way, the present invention provides a highly accurate self-health checkup that takes into account the user's emotions, and realizes a system that allows users to easily make appointments at medical institutions.

[0351] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0352] Step 1:

[0353] Users use a device such as a smartphone to input their health status (for example, symptoms such as fever or cough) and basic information (age, gender, medical history). This input data is stored in text format. Furthermore, an emotion recognition engine analyzes the user's emotional state based on voice or text input. The data processing performed here involves converting the user's voice or text data into an emotional state (anxiety, relief, etc.) using an emotion analysis engine (e.g., Azure Emotion API). Comprehensive user data, including the results of this analysis, is output.

[0354] Step 2:

[0355] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. In this step, the input data is properly formatted into JSON, which allows it to be sent to the server in a consistent data format.

[0356] Step 3:

[0357] The server analyzes and validates the received user data. The server checks whether the received data is in the correct format and contains all the required information. In this processing step, the server validates the received data using a data validation library, checking for incorrect data formats and defects, and prepares the clean data for passing to the generative AI model.

[0358] Step 4:

[0359] The server inputs the validated data into a generative AI model. This model compares it with a vast amount of past medical data and knowledge bases, and combines the user's symptoms and emotional state to make a diagnosis. The generative AI model uses prompt sentences to provide a highly accurate diagnosis. Data calculation involves converting user data into prompt sentences, which are then input into the generative AI model, which then outputs a diagnosis result.

[0360] example:

[0361] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[0362] Step 5:

[0363] Once the diagnosis is available, the server sends the results in JSON format to the user's device, where they are formatted into the appropriate fields, including the possible illness identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[0364] Step 6:

[0365] The terminal displays the received diagnosis results to the user. If the user wishes to make an appointment at a medical institution based on the diagnosis results, they can enter the desired hospital and appointment date and time through the terminal's UI. The user enters the desired appointment information and sends it to the server via the reservation method.

[0366] Step 7:

[0367] The server checks whether a reservation can be made for the specified date and time based on the received reservation information. In this process, it checks the availability of the reservation by linking with the medical institution's reservation system. If the reservation is successful, it generates a confirmation message, which is returned to the user's terminal in JSON format.

[0368] Step 8:

[0369] The device receives the reservation confirmation message and displays it to the user. This message lets the user know that the reservation was successful and allows them to take the next action quickly. The action here is to notify and confirm the user, and to display it appropriately in the user interface.

[0370] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0371] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0372] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0376] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0377] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0378] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0379] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0380] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0381] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0382] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0383] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0384] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0385] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0386] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[0387] First, the user uses the device to input their health status and symptoms. This input consists of data such as age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[0388] The server analyzes the received data, performs data validation and checks the format, then passes the data to a generative AI model, which compares it with previously learned medical data and knowledge bases to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify the possibility of diseases related to the input symptoms with a high degree of accuracy.

[0389] The generative AI model, used as a diagnostic tool, considers various disease possibilities based on the user's input information and suggests the most likely disease or health condition. When a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of the identified disease and the next action to be taken (e.g., whether a doctor's consultation is necessary).

[0390] The user device displays the received diagnosis results, allowing the user to learn about their health status and take the next step quickly. For example, if a doctor's visit is recommended based on the diagnosis results, the user can enter the desired hospital and appointment date and time through the application's UI.

[0391] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[0392] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[0393] As a specific example, if a user inputs the symptoms of "cough" and "fever," the server receives this and uses a generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[0394] In this way, the system leverages past medical data and knowledge bases, and uses generative AI models to create a self-health checkup service that is easy for even busy people to use.

[0395] The processing flow will be explained below.

[0396] Step 1:

[0397] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms into the device's input fields.

[0398] Step 2:

[0399] The terminal structures the input data, converts it to JSON format, adds a timestamp, and sends the data to the server.

[0400] Step 3:

[0401] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[0402] Step 4:

[0403] The server passes the analyzed data to the generative AI model, which then compares it with past medical data and knowledge bases and instructs the AI ​​model to perform a diagnosis.

[0404] Step 5:

[0405] A generative AI model processes the data and identifies likely diseases. The AI ​​model uses vast amounts of medical data to identify diseases that match the user's symptoms.

[0406] Step 6:

[0407] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[0408] Step 7:

[0409] The device displays the received diagnostic results to the user. The device analyzes the diagnostic results and displays them in a format that is easy for the user to understand.

[0410] Step 8:

[0411] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[0412] Step 9:

[0413] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[0414] Step 10:

[0415] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[0416] Step 11:

[0417] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[0418] Step 12:

[0419] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[0420] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[0421] Example 1

[0422] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0423] Conventional health checkup systems have the problem that it is difficult for users to easily check their health status and quickly make an appointment with an appropriate medical institution. In addition, the diagnosis results can sometimes be unreliable, so there is a need for a system that users can use with confidence.

[0424] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0425] In this invention, the server includes a means for analyzing input data, adding a timestamp and performing data validation, a diagnostic means for applying a generative AI model using the analyzed data and comparing it with medical information to make a diagnosis, and a means for transmitting the diagnostic result and diagnostic ID to the user terminal, which allows users to easily check their own health condition, obtain highly accurate diagnostic results, and more quickly make appointments with medical institutions.

[0426] "Input means" refers to a device or interface that allows a user to input health conditions and symptoms.

[0427] "Data validation" is the process of verifying the integrity and correctness of format of received data.

[0428] A "timestamp" is information that indicates the time when data was transmitted by adding the current date and time to the data.

[0429] A "generative AI model" is an artificial intelligence model that uses vast amounts of medical information and a trained knowledge base to identify diseases associated with input symptoms.

[0430] A "diagnostic means" is a device or system that has the ability to use analyzed data to assess a user's health status and apply a generative AI model to make a diagnosis.

[0431] "Reservation means" refers to the functions and interfaces that allow users to make reservations at medical institutions based on diagnostic results.

[0432] A "diagnosis ID" is an identifier associated with a particular diagnosis result and is used to uniquely identify the diagnosis result.

[0433] A "display means" is a device or interface that visually displays diagnostic results or other information to a user.

[0434] "Medical Information" means historical data, knowledge base, and related medical information used in diagnosis and treatment.

[0435] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[0436] First, the user enters their health condition and symptoms using a device such as a smartphone or PC. Specific information to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). Once the user has completed the input, the device converts this information into JSON format and adds the current date and time as a timestamp. The device then sends the converted data to the server.

[0437] The server analyzes the data received from the device and first performs data validation. By checking the data's consistency and format, it ensures that the input information is accurate. The server then passes the data to a generative AI model. This generative AI model is based on a vast amount of medical information and a trained knowledge base, so it can accurately identify the possible diseases associated with the user's input symptoms. The generative AI model identifies the most likely disease and returns the result to the server along with a diagnosis ID.

[0438] The server then sends the diagnosis results to the user's device, including the likelihood of an identified illness and the next course of action (e.g., whether or not a doctor's visit is necessary).

[0439] The user's device receives the diagnosis results and displays them on the application, allowing the user to check their own health status. For example, if a user enters symptoms of "cough" and "fever" and receives a diagnosis of "suspected influenza," the user can make an appointment at the nearest medical institution through the application. The user enters the desired hospital and appointment date and time and presses the "Make an appointment" button.

[0440] The device converts the user's reservation information back into JSON format and sends it to the server. The server receives the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, the server generates a confirmation message and sends it to the user's device. The user can check the received confirmation message on the application and find out that the reservation was successful.

[0441] This system allows users to easily undergo health checkups even in their busy daily lives and quickly make appointments with necessary medical institutions.

[0442] As a specific example, when a user inputs the symptoms of "cough" and "fever," the program's processing proceeds as follows: "Please explain the process by which a user can enter the symptoms of cough and fever, receive a diagnosis that indicates a high possibility of influenza, and then make a hospital appointment within the app." This system thus utilizes past medical information and a knowledge base, and uses a generative AI model to create a self-health checkup service that is easy to use even for busy people.

[0443] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0444] Step 1:

[0445] The user launches the application and enters their health status and symptoms.

[0446] The user launches the application using a smartphone or PC, enters their age, gender, medical history, and current symptoms (e.g., cough, fever, etc.) into the input form, and presses the "Submit" button. At this time, the input data is in RAW text format.

[0447] Step 2:

[0448] The terminal converts the input data into JSON format and adds a timestamp.

[0449] When the "Submit" button is pressed, the terminal converts the RAW text data obtained from the form into JSON format. For example, it generates a JSON object containing the entered data, such as "Age: 30, Gender: Male, Symptoms: Cough, Fever." It also obtains the current date and time and adds it to the JSON data as a timestamp. Input: RAW text data Output: JSON data with timestamp.

[0450] Step 3:

[0451] The device sends JSON data to the server.

[0452] The terminal sends the converted time-stamped JSON data to the server via an HTTP POST request. Input: Time-stamped JSON data Output: HTTP POST request.

[0453] Step 4:

[0454] The server receives the data, parses it, and validates it.

[0455] The server receives the HTTP POST request and parses the JSON data. After parsing, it performs data validation to check the consistency and format of the input data. Input: JSON data with a timestamp. Output: Validated data.

[0456] Step 5:

[0457] The server passes the validated data to the generative AI model to perform the diagnosis.

[0458] The server inputs the validated data into the generative AI model. Based on a vast medical information and knowledge base, the generative AI model identifies with high accuracy the possibility of a disease related to the input symptoms. A diagnosis result is obtained. Input: Validated data Output: Diagnosis result and diagnosis ID.

[0459] Step 6:

[0460] The server sends the diagnosis result and diagnosis ID to the user's terminal.

[0461] The server converts the diagnosis results and diagnosis ID obtained from the generative AI model into JSON format and returns them to the user device as an HTTP response. Input: Diagnosis results and diagnosis ID Output: JSON data with timestamp.

[0462] Step 7:

[0463] The user terminal receives and displays the diagnostic results.

[0464] The user device receives the HTTP response from the server and analyzes the JSON data. The diagnosis results are displayed on the application, allowing the user to check their own health status. Input: Diagnosis result and diagnosis ID Output: Displayed diagnosis result.

[0465] Step 8:

[0466] The user makes a medical appointment through the application.

[0467] Based on the diagnosis results, the user is directed to the reservation screen at the nearest medical institution through the application's UI. They enter the necessary reservation information (hospital, desired date and time, etc.) and press the "Make a reservation" button. Input: Reservation information (hospital, date and time, etc.) Output: Reservation information

[0468] Step 9:

[0469] The device sends the reservation information in JSON format to the server.

[0470] When the user presses the "Make a reservation" button, the device converts the reservation information into JSON format and sends it to the server via an HTTP POST request. Input: RAW data of reservation information Output: JSON data of reservation information

[0471] Step 10:

[0472] The server confirms the reservation based on the reservation information and sends the result to the user terminal.

[0473] The server receives the JSON data of the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, it generates a confirmation message and sends it to the user's device as an HTTP response. Input: JSON data of the reservation information Output: Confirmation message

[0474] Step 11:

[0475] The user terminal receives and displays the confirmation message.

[0476] The user terminal receives the HTTP response from the server, parses the confirmation message, and displays it, letting the user know that the reservation was successful. Input: Confirmation message Output: Displayed confirmation message.

[0477] (Application example 1)

[0478] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0479] Conventional self-health checkup systems allow users to easily check their health status, but they are unable to provide prompt action based on the results of the checkup, suggest necessary over-the-counter medications, or purchase them on the spot. Furthermore, it is difficult to easily make appointments with medical institutions, which can lead to delays in early detection of illness and appropriate treatment. This has resulted in insufficient efficiency in users' health management.

[0480] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0481] In this invention, the server includes an input means for the user to input their health condition and symptoms, a diagnosis means for analyzing the input data and making a diagnosis using a generative AI model, a reservation means for making an appointment with a medical institution based on the diagnosis results, and a suggestion means for displaying the diagnosis results of the health condition and symptoms and suggesting or purchasing over-the-counter medications as needed. This enables users to easily check their health condition and quickly purchase over-the-counter medications and make appointments with medical institutions based on the diagnosis results.

[0482] An "input means" is a system component that provides an interface for a user to input health conditions and symptoms.

[0483] A "diagnostic means" is a system component that analyzes input data and performs a diagnosis using a generative AI model.

[0484] A "generative AI model" is an artificial intelligence algorithm that analyzes a user's health condition and symptoms based on past medical data and a learned knowledge base, and derives a diagnosis.

[0485] The "reservation means" is a system component for making a reservation at a medical institution based on the diagnosis results.

[0486] The "suggestion means" is a system component that displays the diagnosis results of health conditions and symptoms, and provides the function of suggesting over-the-counter medicines and assisting in the purchase of medicines as needed.

[0487] The "display means" is a system component that presents the diagnostic results based on the user's symptoms in a visually recognizable form.

[0488] "Medical institution" refers to a medical facility such as a hospital or clinic where users can receive treatment through diagnostic results and appointment procedures.

[0489] "Over-the-counter drugs" are medicines that can be purchased at pharmacies or drug stores without a prescription.

[0490] This invention is a system that allows users to conduct self-health checkups and, if necessary, make appointments with medical institutions or purchase over-the-counter medications on the spot. This system includes the following main components: an input means for users to input their health condition and symptoms, a diagnosis means that analyzes the input data and makes a diagnosis using a generative AI model, a reservation means that makes appointments with medical institutions based on the diagnosis results, and a suggestion means that displays the diagnosis results of the health condition and symptoms and suggests and purchases over-the-counter medications as necessary.

[0491] The operation of the system will be described in detail below. The user uses a terminal to input their health condition and symptoms. The terminal is equipped with a touch panel display and provides an interface that allows for easy input of health information. The information entered by the user is converted into JSON format, time-stamped, and then sent to the server. This communication uses an HTTP request library (for example, Python's requests library).

[0492] The server analyzes the received data and performs basic data validation and format checks using a database management system (DBMS) and data analysis libraries (e.g., pandas and NumPy). Once the data analysis is complete, it is passed to a generative AI model, which runs on a GPU cluster and uses frameworks such as PyTorch to compare the data with past medical data and a trained knowledge base to make a diagnosis.

[0493] The diagnostic results are returned to the server, where the diagnostic result data is formatted in JSON format. This data is then sent back to the device as an HTTP response. The device receives this and displays the diagnostic results to the user. The user interface (UI) is intuitively designed using JavaScript, HTML, and CSS.

[0494] The diagnosis results include the possibility of an identified illness, the next action to be taken (e.g., whether or not a medical visit is necessary), and suggestions for medications for symptoms that can be treated with over-the-counter medications. Based on this, if the user wishes, they can purchase over-the-counter medications on the spot. Furthermore, if a diagnosis indicates that a medical visit is necessary, the user can make an appointment with a medical institution through the application's UI. Once the appointment procedure is completed, the appointment information is also sent to the server and processed.

[0495] Here is a specific example of usage: For example, if a user enters the symptoms "cough" and "fever", the following prompt will be sent to the server:

[0496] Age: 35

[0497] Gender: Male

[0498] Symptoms: Cough, fever

[0499] Timestamp: 2023-10-05T10:05Z

[0500] Based on this input, the generative AI model returns a diagnosis of "cold" or "flu" and presents the user with a diagnosis of "suspected flu." The user can then make an appointment with the nearest medical institution based on this diagnosis. If necessary, the user can also purchase the suggested over-the-counter medication on the spot.

[0501] As described above, the system of the present invention can perform a complete process from self-health checkups to making appointments with medical institutions and purchasing over-the-counter medicines, thereby efficiently and quickly supporting users in managing their health.

[0502] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0503] Step 1:

[0504] The user inputs their health condition and symptoms into the device.

[0505] The data to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.).

[0506] The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[0507] Input: Age, gender, medical history, current specific symptoms

[0508] Output: JSON format data

[0509] Specific operation: The user enters information into the touch panel display and presses the "Send" button.

[0510] Step 2:

[0511] The server parses the received JSON data and performs basic data validation and format checks.

[0512] Specifically, it checks the existence of required fields and validates data types, using data analysis libraries and DBMS.

[0513] Input: JSON format data

[0514] Output: Validated data

[0515] Specific operation: A Python script is executed on the server side to perform data validation.

[0516] Step 3:

[0517] The server passes the verified data to a generative AI model to make a diagnosis.

[0518] The generative AI model compares historical medical data and a trained knowledge base to identify possible illnesses based on input symptoms.

[0519] This uses frameworks such as PyTorch running on GPU clusters.

[0520] Input: Validated data

[0521] Output: Diagnostic results

[0522] Specific operation: The server inputs data into the generative AI model and obtains the diagnosis results.

[0523] Step 4:

[0524] The server formats the diagnostic results from the generated AI model in JSON format and sends them back to the device.

[0525] The returned data includes the diagnosis as well as suggestions for next steps and over-the-counter medications.

[0526] Input: Diagnostic results from a generative AI model

[0527] Output: JSON format diagnostic result data

[0528] Specific operation: The server formats the diagnostic results and sends them to the terminal as an HTTP response.

[0529] Step 5:

[0530] The device displays the diagnostic results it receives to the user.

[0531] The diagnosis results will show the likelihood of the disease being identified and the next action to be taken (e.g., whether or not medical attention is required).

[0532] Input: JSON format diagnostic result data

[0533] Output: Display of diagnostic results

[0534] Specific operation: The diagnostic results are displayed on the device display for the user to check.

[0535] Step 6:

[0536] When a user makes an appointment at a medical institution based on the diagnosis results, the user inputs appointment information (date, time, hospital, etc.) and transmits it to the server via the terminal.

[0537] The server receives the reservation information and checks whether the reservation can be made for the specified date and time.

[0538] Input: Reservation information (date, time, hospital, etc.)

[0539] Output: Reservation confirmation message

[0540] Specific operation: The user fills out the reservation form and presses the "Reserve" button.

[0541] Step 7:

[0542] The server verifies that the reservation was successful and generates a confirmation message and sends it to the terminal.

[0543] The terminal will display this confirmation message to the user, letting them know that the reservation was successful.

[0544] Input: Reservation confirmation data

[0545] Output: Reservation confirmation message

[0546] Specific operation: The server generates a reservation success message and sends it to the terminal, which displays the message.

[0547] Step 8:

[0548] The user checks the over-the-counter drug suggestions and purchases them on the spot if necessary.

[0549] Information on suggested over-the-counter medications is displayed, and you can immediately proceed with the purchase.

[0550] Input: Over-the-counter drug proposal data

[0551] Output: Purchase confirmation message

[0552] Specific behavior: The user reviews the over-the-counter drug suggestions and presses the purchase button. The device displays a purchase confirmation.

[0553] Through these steps, users can quickly and efficiently manage their health, making necessary medical appointments and purchasing over-the-counter medications.

[0554] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0555] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[0556] First, the user uses the device to input their health status and symptoms. They enter information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields. The emotion engine then analyzes the user's input data and voice data to recognize the user's emotional state. This emotional state is important data for the subsequent diagnosis process.

[0557] The device converts this information and emotion data into JSON format, adds a timestamp, and sends it to the server.

[0558] The server analyzes the received data and performs data validation and format checks. The server then passes the analyzed health status data and emotion data to the generative AI model, which compares it with the trained medical data and knowledge base to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify possible illnesses with high accuracy by taking into account the user's symptoms and emotional state.

[0559] The generative AI model for diagnostics considers various possible illnesses based on the user's input and emotional state, and suggests the most likely illness or health condition. The emotion engine also adjusts the diagnostic process based on the user's emotional state. For example, if the user is feeling anxious, the system will operate to provide diagnostic results in a more careful and polite manner.

[0560] If a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of a specific illness being identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[0561] The user device displays the received diagnosis results to the user, allowing the user to know their own health condition and take the next action promptly.If the user wishes to see a doctor based on the diagnosis results, they can enter the desired hospital and appointment date and time through the application's UI.

[0562] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[0563] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[0564] As a specific example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the server receives this and uses the generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[0565] In this way, the system leverages historical medical data and knowledge bases, and uses generative AI models and an emotion engine to create a self-health checkup service that is easy for even busy people to use.

[0566] The processing flow will be explained below.

[0567] Step 1:

[0568] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields.

[0569] Step 2:

[0570] The emotion engine analyzes the user's input and voice data to recognize their emotional state from their tone of voice and input, identifying emotions such as anxiety, sadness, and anger.

[0571] Step 3:

[0572] The device converts the input data and emotion data into JSON format, adds a timestamp, and sends the data to the server.

[0573] Step 4:

[0574] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[0575] Step 5:

[0576] The server passes the analyzed data to the generative AI model, which then uses the generative AI model to perform a diagnosis based on the health status data and emotion data.

[0577] Step 6:

[0578] A generative AI model processes the data to identify likely illnesses, compares it with vast amounts of medical data, and generates a diagnosis that takes into account the user's symptoms and emotional state.

[0579] Step 7:

[0580] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[0581] Step 8:

[0582] The device receives the diagnosis results and displays them to the user. The device analyzes the results and displays them in a format that is easy for the user to understand. The display method may change depending on the user's emotional state.

[0583] Step 9:

[0584] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[0585] Step 10:

[0586] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[0587] Step 11:

[0588] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[0589] Step 12:

[0590] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[0591] Step 13:

[0592] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[0593] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[0594] Example 2

[0595] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0596] In modern society, busy users need a system that allows them to easily check their health status and, if necessary, make appointments with a medical institution. Furthermore, it is important to provide a diagnosis that takes into account the user's emotional state in order to provide more accurate medical care. However, existing systems face the challenge of being unable to provide a comprehensive diagnosis that includes the user's emotional state.

[0597] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0598] In this invention, the server includes emotion analysis means for analyzing input data and recognizing the emotional state, transmission means for transmitting the analyzed health information and emotional data to the server, and data processing means for receiving the transmitted data and validating and checking the format. This makes it possible to comprehensively diagnose the health information and emotional state input by the user and provide highly accurate diagnostic results.

[0599] The "input amount means" is a means for providing an interface for the user to input health conditions and symptoms.

[0600] The "emotion analysis means" is a means for analyzing the user's input data and voice data and recognizing the user's emotional state.

[0601] The "transmission means" is a means for converting the analyzed health information and emotion data into JSON format and transmitting it to the server.

[0602] The "data processing means" is a means for analyzing data received by the server and performing validation and format checks.

[0603] "Generation means" refers to a means for making a diagnosis using a generative AI model based on received data.

[0604] The "display means" is a means for displaying the diagnosis results based on the user's symptoms and emotional state on the terminal.

[0605] A "generative AI model" is an artificial intelligence model that learns from a vast medical database and makes diagnoses by taking into consideration the user's health information and emotional state in an integrated manner.

[0606] "Data processing means" refers to the server's function of analyzing the health information and emotion data sent by the user and performing any necessary validation and format checks.

[0607] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[0608] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[0609] First, the user accesses the system from their own device (such as a smartphone, tablet, or PC). On the system's user interface, they enter health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into input fields. This input is performed via an input volume means.

[0610] Next, the emotion analysis means analyzes the user's input data and voice data to recognize the user's emotional state. For example, emotions such as "anxiety" or "tension" can be recognized from the tone and speaking style of the voice. This emotional state is important data for the diagnostic process.

[0611] The device converts the input health information and analyzed emotion data into JSON format, adds a timestamp, and sends it to the server. This transmission is performed using a transmission method.

[0612] The server analyzes the received data using a data processing means and validates the input data (checking the format and values). For example, it checks whether the age is within the range or whether symptom data is missing. The verified data is then input into a generation means, and a diagnosis is performed using a generative AI model. The generative AI model uses a vast medical database to comprehensively consider the user's symptoms and emotional state, generating highly accurate diagnostic results.

[0613] When a diagnosis result is obtained, the server sends the diagnosis result data to the user terminal. The result includes the possibility of a specified illness and a recommended next action (e.g., whether or not a doctor's consultation is necessary). The user terminal displays the received diagnosis result to the user on a display means. This allows the user to know about their own health condition and take the next action promptly.

[0614] If the user wishes to see a doctor based on the diagnosis results, they enter the desired hospital and appointment date and time through the application's UI. The device obtains the user's appointment information and sends it back to the server. The server checks whether an appointment can be made for the specified date and time based on the received appointment information. If the appointment is successful, the server generates a confirmation message and sends it to the device. The user's device receives this confirmation message and displays it to the user, informing them that the appointment was successful.

[0615] In this way, users can not only quickly and efficiently manage their health, but also easily make necessary medical appointments.In addition, the emotion engine takes into account the user's emotional state, providing more thorough and accurate diagnosis results.

[0616] Specific examples

[0617] For example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the device sends this data to the server. The server uses the generative AI model to consider the possibility of "cold" or "flu," generates a diagnosis of "suspected influenza," and sends this to the device. After the user confirms the "suspected influenza," they make an appointment with the nearest medical institution, and the server confirms the appointment and notifies them of its success.

[0618] Prompt Sentence Examples

[0619] "A user inputs symptoms of cough and fever. The emotion engine recognizes that the user is anxious. Based on this information, what diagnosis would the generative AI model make and what suggestions would it make in response?"

[0620] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0621] Step 1:

[0622] A user accesses the system and enters health information.

[0623] Input: Health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever).

[0624] Specific operation: The user enters health information into the device's user interface.

[0625] Output: The input health information data.

[0626] Step 2:

[0627] An emotion analysis means analyzes the user's emotional state.

[0628] Input: Text and voice data entered by the user.

[0629] Specific operation: The emotion analysis engine performs real-time analysis and recognizes the user's emotional state (e.g., anxiety, tension).

[0630] Output: Parsed emotion data.

[0631] Step 3:

[0632] The device sends health information and emotion data to the server.

[0633] Input: Health information data, emotion data.

[0634] Specific operation: The device converts this data into JSON format, adds a timestamp, and sends it.

[0635] Output: Health and emotion data in JSON format sent to the server.

[0636] Step 4:

[0637] The server receives the data and performs validation.

[0638] Input: Received data in JSON format.

[0639] Specific behavior: The server checks the data format and values, and generates an error message if necessary.

[0640] Output: The validated data.

[0641] Step 5:

[0642] The server uses the generative AI model to perform the diagnosis.

[0643] Input: Validated health and emotion data.

[0644] How it works: The server inputs this data into a generative AI model and makes a diagnosis by referencing a vast medical database.

[0645] Output: Highly accurate diagnostic results.

[0646] Step 6:

[0647] The server transmits the diagnosis results to the user terminal.

[0648] Input: Diagnostic result data.

[0649] Specific operation: The server generates a message to send the diagnostic results to the user terminal.

[0650] Output: Diagnostic results sent to the user's terminal.

[0651] Step 7:

[0652] The user checks the diagnosis results and makes a hospital appointment if necessary.

[0653] Input: Diagnostic results displayed on the user's terminal.

[0654] Specific operation: The user checks the diagnostic results and enters reservation information through the application's UI.

[0655] Output: Appointment information (hospital name, appointment date and time).

[0656] Step 8:

[0657] The terminal transmits the reservation information to the server.

[0658] Input: Reservation information.

[0659] Specific operation: The terminal formats the data to send the reservation information to the server.

[0660] Output: The reservation information sent to the server.

[0661] Step 9:

[0662] The server checks the reservation status and notifies the user.

[0663] Input: Reservation information.

[0664] Specific operation: Based on the received reservation information, the server checks the reservation status at the medical institution, and if the reservation is successful, it generates a confirmation message and sends it to the terminal.

[0665] Output: Booking confirmation message.

[0666] (Application example 2)

[0667] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0668] Conventional self-health checkup systems only require users to input their health condition and symptoms, and do not take into account the user's emotional state. As a result, there is a lack of consideration for how the diagnosis results will be received by the user, and dealing with users who feel anxious is a particular issue. In addition, the procedure for making an appointment with a medical institution based on the diagnosis results is cumbersome, making the system less user-friendly. As such, there is a need for a system that combines highly accurate diagnosis that takes the user's emotions into account with a smooth appointment process with a medical institution.

[0669] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing input data and emotional state and performing diagnosis using a generative AI model, means for the diagnostic means to adjust the method for providing diagnostic results taking into account the user's emotional state, and means for confirming appointments with medical institutions and notifying the user of the results. This enables highly accurate self-health checkups that take into account the user's emotions, and also simplifies the process of making appointments with medical institutions.

[0670] "Input means" refers to the means by which a user inputs information about their health condition or symptoms into the system.

[0671] The "diagnostic means" is a means for analyzing input health condition and symptom data and emotional state, and making a diagnosis using a generative AI model.

[0672] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[0673] The "means for taking into account the emotional state" is a means for adjusting the method for providing the diagnostic results based on the emotional state of the user.

[0674] "Notification means" refers to the means for confirming an appointment with a medical institution and notifying the user of the results.

[0675] The "display means" is a means for displaying the diagnosis results based on the symptoms and emotional state of the user.

[0676] A "generative AI model" is an artificial intelligence model that uses data on a user's health, symptoms, and emotional state to match it with past medical data and a trained knowledge base to identify likely illnesses.

[0677] "Data" refers to information about a user's health, symptoms, and emotional state.

[0678] "Emotional state" refers to the emotional state of the user, which influences the behavior of the diagnostic tool.

[0679] The present invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system is composed of elements such as an input means, a diagnosis means, a reservation means, a means for considering emotional state, a notification means, and a display means.

[0680] Input Method

[0681] Using a device such as a smartphone, the user inputs information such as age, gender, medical history, and specific symptoms (e.g., cough, fever). An emotion recognition engine then analyzes the voice and text data to recognize the user's emotional state (e.g., anxiety). The input data and emotional state are then stored on the device.

[0682] Diagnostic tools

[0683] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. The server analyzes and validates the received data and performs a diagnosis using a generative AI model. This generative AI model takes into account the user's symptoms and emotional state based on a vast medical data and knowledge base, and identifies possible illnesses with high accuracy.

[0684] Measures that take emotional state into account

[0685] The diagnostic means adjusts the way in which the diagnostic result is provided taking into account the emotional state of the user, for example, if the user is feeling anxious, the diagnostic means operates to provide the diagnostic result in a polite and careful manner.

[0686] Reservation method

[0687] When a diagnosis result is obtained, the server sends it to the user's device. The diagnosis result includes the possibility of a specific illness and the next action to be taken (e.g., whether or not a doctor's examination is necessary). If the user wishes to see a doctor based on the diagnosis result, they input the desired hospital and appointment date and time through the device's UI.

[0688] Notification means

[0689] After the reservation procedure is completed, the terminal sends the reservation information to the server. The server checks whether the reservation is available for the specified date and time, and if the reservation is successful, it generates a confirmation message and sends it again to the terminal. The terminal displays this confirmation message to the user, notifying them that the reservation was successful.

[0690] Display means

[0691] The user device displays the received diagnostic results, allowing the user to know about their own health condition and take immediate action.

[0692] Example

[0693] For example, a 25-year-old male user inputs symptoms of fever and cough, and the emotion engine recognizes "anxiety." The server receives this data and uses the generative AI model to consider the possibility of "cold" or "flu." If the diagnosis is returned as "suspected influenza," the user can make an appointment with a nearby medical institution through the UI and receive a notification that the appointment has been completed.

[0694] Prompt Sentence Examples

[0695] Here are some example prompts for the generative AI model:

[0696] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[0697] In this way, the present invention provides a highly accurate self-health checkup that takes into account the user's emotions, and realizes a system that allows users to easily make appointments at medical institutions.

[0698] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0699] Step 1:

[0700] Users use a device such as a smartphone to input their health status (for example, symptoms such as fever or cough) and basic information (age, gender, medical history). This input data is stored in text format. Furthermore, an emotion recognition engine analyzes the user's emotional state based on voice or text input. The data processing performed here involves converting the user's voice or text data into an emotional state (anxiety, relief, etc.) using an emotion analysis engine (e.g., Azure Emotion API). Comprehensive user data, including the results of this analysis, is output.

[0701] Step 2:

[0702] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. In this step, the input data is properly formatted into JSON, which allows it to be sent to the server in a consistent data format.

[0703] Step 3:

[0704] The server analyzes and validates the received user data. The server checks whether the received data is in the correct format and contains all the required information. In this processing step, the server validates the received data using a data validation library, checking for incorrect data formats and defects, and prepares the clean data for passing to the generative AI model.

[0705] Step 4:

[0706] The server inputs the validated data into a generative AI model. This model compares it with a vast amount of past medical data and knowledge bases, and combines the user's symptoms and emotional state to make a diagnosis. The generative AI model uses prompt sentences to provide a highly accurate diagnosis. Data calculation involves converting user data into prompt sentences, which are then input into the generative AI model, which then outputs a diagnosis result.

[0707] example:

[0708] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[0709] Step 5:

[0710] Once the diagnosis is available, the server sends the results in JSON format to the user's device, where they are formatted into the appropriate fields, including the possible illness identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[0711] Step 6:

[0712] The terminal displays the received diagnosis results to the user. If the user wishes to make an appointment at a medical institution based on the diagnosis results, they can enter the desired hospital and appointment date and time through the terminal's UI. The user enters the desired appointment information and sends it to the server via the reservation method.

[0713] Step 7:

[0714] The server checks whether a reservation can be made for the specified date and time based on the received reservation information. In this process, it checks the availability of the reservation by linking with the medical institution's reservation system. If the reservation is successful, it generates a confirmation message, which is returned to the user's terminal in JSON format.

[0715] Step 8:

[0716] The device receives the reservation confirmation message and displays it to the user. This message lets the user know that the reservation was successful and allows them to take the next action quickly. The action here is to notify and confirm the user, and to display it appropriately in the user interface.

[0717] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0718] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0719] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0720] [Third embodiment]

[0721] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0722] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0723] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0724] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0725] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0726] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0727] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0728] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0729] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0730] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0731] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0732] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0733] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[0734] First, the user uses the device to input their health status and symptoms. This input consists of data such as age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[0735] The server analyzes the received data, performs data validation and checks the format, then passes the data to a generative AI model, which compares it with previously learned medical data and knowledge bases to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify the possibility of diseases related to the input symptoms with a high degree of accuracy.

[0736] The generative AI model, used as a diagnostic tool, considers various disease possibilities based on the user's input information and suggests the most likely disease or health condition. When a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of the identified disease and the next action to be taken (e.g., whether a doctor's consultation is necessary).

[0737] The user device displays the received diagnosis results, allowing the user to learn about their health status and take the next step quickly. For example, if a doctor's visit is recommended based on the diagnosis results, the user can enter the desired hospital and appointment date and time through the application's UI.

[0738] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[0739] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[0740] As a specific example, if a user inputs the symptoms of "cough" and "fever," the server receives this and uses a generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[0741] In this way, the system leverages past medical data and knowledge bases, and uses generative AI models to create a self-health checkup service that is easy for even busy people to use.

[0742] The processing flow will be explained below.

[0743] Step 1:

[0744] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms into the device's input fields.

[0745] Step 2:

[0746] The terminal structures the input data, converts it to JSON format, adds a timestamp, and sends the data to the server.

[0747] Step 3:

[0748] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[0749] Step 4:

[0750] The server passes the analyzed data to the generative AI model, which then compares it with past medical data and knowledge bases and instructs the AI ​​model to perform a diagnosis.

[0751] Step 5:

[0752] A generative AI model processes the data and identifies likely diseases. The AI ​​model uses vast amounts of medical data to identify diseases that match the user's symptoms.

[0753] Step 6:

[0754] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[0755] Step 7:

[0756] The device displays the received diagnostic results to the user. The device analyzes the diagnostic results and displays them in a format that is easy for the user to understand.

[0757] Step 8:

[0758] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[0759] Step 9:

[0760] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[0761] Step 10:

[0762] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[0763] Step 11:

[0764] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[0765] Step 12:

[0766] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[0767] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[0768] Example 1

[0769] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0770] Conventional health checkup systems have the problem that it is difficult for users to easily check their health status and quickly make an appointment with an appropriate medical institution. In addition, the diagnosis results can sometimes be unreliable, so there is a need for a system that users can use with confidence.

[0771] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0772] In this invention, the server includes a means for analyzing input data, adding a timestamp and performing data validation, a diagnostic means for applying a generative AI model using the analyzed data and comparing it with medical information to make a diagnosis, and a means for transmitting the diagnostic result and diagnostic ID to the user terminal, which allows users to easily check their own health condition, obtain highly accurate diagnostic results, and more quickly make appointments with medical institutions.

[0773] "Input means" refers to a device or interface that allows a user to input health conditions and symptoms.

[0774] "Data validation" is the process of verifying the integrity and correctness of format of received data.

[0775] A "timestamp" is information that indicates the time when data was transmitted by adding the current date and time to the data.

[0776] A "generative AI model" is an artificial intelligence model that uses vast amounts of medical information and a trained knowledge base to identify diseases associated with input symptoms.

[0777] A "diagnostic means" is a device or system that has the ability to use analyzed data to assess a user's health status and apply a generative AI model to make a diagnosis.

[0778] "Reservation means" refers to the functions and interfaces that allow users to make reservations at medical institutions based on diagnostic results.

[0779] A "diagnosis ID" is an identifier associated with a particular diagnosis result and is used to uniquely identify the diagnosis result.

[0780] A "display means" is a device or interface that visually displays diagnostic results or other information to a user.

[0781] "Medical Information" means historical data, knowledge base, and related medical information used in diagnosis and treatment.

[0782] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[0783] First, the user enters their health condition and symptoms using a device such as a smartphone or PC. Specific information to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). Once the user has completed the input, the device converts this information into JSON format and adds the current date and time as a timestamp. The device then sends the converted data to the server.

[0784] The server analyzes the data received from the device and first performs data validation. By checking the data's consistency and format, it ensures that the input information is accurate. The server then passes the data to a generative AI model. This generative AI model is based on a vast amount of medical information and a trained knowledge base, so it can accurately identify the possible diseases associated with the user's input symptoms. The generative AI model identifies the most likely disease and returns the result to the server along with a diagnosis ID.

[0785] The server then sends the diagnosis results to the user's device, including the likelihood of an identified illness and the next course of action (e.g., whether or not a doctor's visit is necessary).

[0786] The user's device receives the diagnosis results and displays them on the application, allowing the user to check their own health status. For example, if a user enters symptoms of "cough" and "fever" and receives a diagnosis of "suspected influenza," the user can make an appointment at the nearest medical institution through the application. The user enters the desired hospital and appointment date and time and presses the "Make an appointment" button.

[0787] The device converts the user's reservation information back into JSON format and sends it to the server. The server receives the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, the server generates a confirmation message and sends it to the user's device. The user can check the received confirmation message on the application and find out that the reservation was successful.

[0788] This system allows users to easily undergo health checkups even in their busy daily lives and quickly make appointments with necessary medical institutions.

[0789] As a specific example, when a user inputs the symptoms of "cough" and "fever," the program's processing proceeds as follows: "Please explain the process by which a user can enter the symptoms of cough and fever, receive a diagnosis that indicates a high possibility of influenza, and then make a hospital appointment within the app." This system thus utilizes past medical information and a knowledge base, and uses a generative AI model to create a self-health checkup service that is easy to use even for busy people.

[0790] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0791] Step 1:

[0792] The user launches the application and enters their health status and symptoms.

[0793] The user launches the application using a smartphone or PC, enters their age, gender, medical history, and current symptoms (e.g., cough, fever, etc.) into the input form, and presses the "Submit" button. At this time, the input data is in RAW text format.

[0794] Step 2:

[0795] The terminal converts the input data into JSON format and adds a timestamp.

[0796] When the "Submit" button is pressed, the terminal converts the RAW text data obtained from the form into JSON format. For example, it generates a JSON object containing the entered data, such as "Age: 30, Gender: Male, Symptoms: Cough, Fever." It also obtains the current date and time and adds it to the JSON data as a timestamp. Input: RAW text data Output: JSON data with timestamp.

[0797] Step 3:

[0798] The device sends JSON data to the server.

[0799] The terminal sends the converted time-stamped JSON data to the server via an HTTP POST request. Input: Time-stamped JSON data Output: HTTP POST request.

[0800] Step 4:

[0801] The server receives the data, parses it, and validates it.

[0802] The server receives the HTTP POST request and parses the JSON data. After parsing, it performs data validation to check the consistency and format of the input data. Input: JSON data with a timestamp. Output: Validated data.

[0803] Step 5:

[0804] The server passes the validated data to the generative AI model to perform the diagnosis.

[0805] The server inputs the validated data into the generative AI model. Based on a vast medical information and knowledge base, the generative AI model identifies with high accuracy the possibility of a disease related to the input symptoms. A diagnosis result is obtained. Input: Validated data Output: Diagnosis result and diagnosis ID.

[0806] Step 6:

[0807] The server sends the diagnosis result and diagnosis ID to the user's terminal.

[0808] The server converts the diagnosis results and diagnosis ID obtained from the generative AI model into JSON format and returns them to the user device as an HTTP response. Input: Diagnosis results and diagnosis ID Output: JSON data with timestamp.

[0809] Step 7:

[0810] The user terminal receives and displays the diagnostic results.

[0811] The user device receives the HTTP response from the server and analyzes the JSON data. The diagnosis results are displayed on the application, allowing the user to check their own health status. Input: Diagnosis result and diagnosis ID Output: Displayed diagnosis result.

[0812] Step 8:

[0813] The user makes a medical appointment through the application.

[0814] Based on the diagnosis results, the user is directed to the reservation screen at the nearest medical institution through the application's UI. They enter the necessary reservation information (hospital, desired date and time, etc.) and press the "Make a reservation" button. Input: Reservation information (hospital, date and time, etc.) Output: Reservation information

[0815] Step 9:

[0816] The device sends the reservation information in JSON format to the server.

[0817] When the user presses the "Make a reservation" button, the device converts the reservation information into JSON format and sends it to the server via an HTTP POST request. Input: RAW data of reservation information Output: JSON data of reservation information

[0818] Step 10:

[0819] The server confirms the reservation based on the reservation information and sends the result to the user terminal.

[0820] The server receives the JSON data of the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, it generates a confirmation message and sends it to the user's device as an HTTP response. Input: JSON data of the reservation information Output: Confirmation message

[0821] Step 11:

[0822] The user terminal receives and displays the confirmation message.

[0823] The user terminal receives the HTTP response from the server, parses the confirmation message, and displays it, letting the user know that the reservation was successful. Input: Confirmation message Output: Displayed confirmation message.

[0824] (Application example 1)

[0825] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0826] Conventional self-health checkup systems allow users to easily check their health status, but they are unable to provide prompt action based on the results of the checkup, suggest necessary over-the-counter medications, or purchase them on the spot. Furthermore, it is difficult to easily make appointments with medical institutions, which can lead to delays in early detection of illness and appropriate treatment. This has resulted in insufficient efficiency in users' health management.

[0827] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0828] In this invention, the server includes an input means for the user to input their health condition and symptoms, a diagnosis means for analyzing the input data and making a diagnosis using a generative AI model, a reservation means for making an appointment with a medical institution based on the diagnosis results, and a suggestion means for displaying the diagnosis results of the health condition and symptoms and suggesting or purchasing over-the-counter medications as needed. This enables users to easily check their health condition and quickly purchase over-the-counter medications and make appointments with medical institutions based on the diagnosis results.

[0829] An "input means" is a system component that provides an interface for a user to input health conditions and symptoms.

[0830] A "diagnostic means" is a system component that analyzes input data and performs a diagnosis using a generative AI model.

[0831] A "generative AI model" is an artificial intelligence algorithm that analyzes a user's health condition and symptoms based on past medical data and a learned knowledge base, and derives a diagnosis.

[0832] The "reservation means" is a system component for making a reservation at a medical institution based on the diagnosis results.

[0833] The "suggestion means" is a system component that displays the diagnosis results of health conditions and symptoms, and provides the function of suggesting over-the-counter medicines and assisting in the purchase of medicines as needed.

[0834] The "display means" is a system component that presents the diagnostic results based on the user's symptoms in a visually recognizable form.

[0835] "Medical institution" refers to a medical facility such as a hospital or clinic where users can receive treatment through diagnostic results and appointment procedures.

[0836] "Over-the-counter drugs" are medicines that can be purchased at pharmacies or drug stores without a prescription.

[0837] This invention is a system that allows users to conduct self-health checkups and, if necessary, make appointments with medical institutions or purchase over-the-counter medications on the spot. This system includes the following main components: an input means for users to input their health condition and symptoms, a diagnosis means that analyzes the input data and makes a diagnosis using a generative AI model, a reservation means that makes appointments with medical institutions based on the diagnosis results, and a suggestion means that displays the diagnosis results of the health condition and symptoms and suggests and purchases over-the-counter medications as necessary.

[0838] The operation of the system will be described in detail below. The user uses a terminal to input their health condition and symptoms. The terminal is equipped with a touch panel display and provides an interface that allows for easy input of health information. The information entered by the user is converted into JSON format, time-stamped, and then sent to the server. This communication uses an HTTP request library (for example, Python's requests library).

[0839] The server analyzes the received data and performs basic data validation and format checks using a database management system (DBMS) and data analysis libraries (e.g., pandas and NumPy). Once the data analysis is complete, it is passed to a generative AI model, which runs on a GPU cluster and uses frameworks such as PyTorch to compare the data with past medical data and a trained knowledge base to make a diagnosis.

[0840] The diagnostic results are returned to the server, where the diagnostic result data is formatted in JSON format. This data is then sent back to the device as an HTTP response. The device receives this and displays the diagnostic results to the user. The user interface (UI) is intuitively designed using JavaScript, HTML, and CSS.

[0841] The diagnosis results include the possibility of an identified illness, the next action to be taken (e.g., whether or not a medical visit is necessary), and suggestions for medications for symptoms that can be treated with over-the-counter medications. Based on this, if the user wishes, they can purchase over-the-counter medications on the spot. Furthermore, if a diagnosis indicates that a medical visit is necessary, the user can make an appointment with a medical institution through the application's UI. Once the appointment procedure is completed, the appointment information is also sent to the server and processed.

[0842] Here is a specific example of usage: For example, if a user enters the symptoms "cough" and "fever", the following prompt will be sent to the server:

[0843] Age: 35

[0844] Gender: Male

[0845] Symptoms: Cough, fever

[0846] Timestamp: 2023-10-05T10:05Z

[0847] Based on this input, the generative AI model returns a diagnosis of "cold" or "flu" and presents the user with a diagnosis of "suspected flu." The user can then make an appointment with the nearest medical institution based on this diagnosis. If necessary, the user can also purchase the suggested over-the-counter medication on the spot.

[0848] As described above, the system of the present invention can perform a complete process from self-health checkups to making appointments with medical institutions and purchasing over-the-counter medicines, thereby efficiently and quickly supporting users in managing their health.

[0849] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0850] Step 1:

[0851] The user inputs their health condition and symptoms into the device.

[0852] The data to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.).

[0853] The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[0854] Input: Age, gender, medical history, current specific symptoms

[0855] Output: JSON format data

[0856] Specific operation: The user enters information into the touch panel display and presses the "Send" button.

[0857] Step 2:

[0858] The server parses the received JSON data and performs basic data validation and format checks.

[0859] Specifically, it checks the existence of required fields and validates data types, using data analysis libraries and DBMS.

[0860] Input: JSON format data

[0861] Output: Validated data

[0862] Specific operation: A Python script is executed on the server side to perform data validation.

[0863] Step 3:

[0864] The server passes the verified data to a generative AI model to make a diagnosis.

[0865] The generative AI model compares historical medical data and a trained knowledge base to identify possible illnesses based on input symptoms.

[0866] This uses frameworks such as PyTorch running on GPU clusters.

[0867] Input: Validated data

[0868] Output: Diagnostic results

[0869] Specific operation: The server inputs data into the generative AI model and obtains the diagnosis results.

[0870] Step 4:

[0871] The server formats the diagnostic results from the generated AI model in JSON format and sends them back to the device.

[0872] The returned data includes the diagnosis as well as suggestions for next steps and over-the-counter medications.

[0873] Input: Diagnostic results from a generative AI model

[0874] Output: JSON format diagnostic result data

[0875] Specific operation: The server formats the diagnostic results and sends them to the terminal as an HTTP response.

[0876] Step 5:

[0877] The device displays the diagnostic results it receives to the user.

[0878] The diagnosis results will show the likelihood of the disease being identified and the next action to be taken (e.g., whether or not medical attention is required).

[0879] Input: JSON format diagnostic result data

[0880] Output: Display of diagnostic results

[0881] Specific operation: The diagnostic results are displayed on the device display for the user to check.

[0882] Step 6:

[0883] When a user makes an appointment at a medical institution based on the diagnosis results, the user inputs appointment information (date, time, hospital, etc.) and transmits it to the server via the terminal.

[0884] The server receives the reservation information and checks whether the reservation can be made for the specified date and time.

[0885] Input: Reservation information (date, time, hospital, etc.)

[0886] Output: Reservation confirmation message

[0887] Specific operation: The user fills out the reservation form and presses the "Reserve" button.

[0888] Step 7:

[0889] The server verifies that the reservation was successful and generates a confirmation message and sends it to the terminal.

[0890] The terminal will display this confirmation message to the user, letting them know that the reservation was successful.

[0891] Input: Reservation confirmation data

[0892] Output: Reservation confirmation message

[0893] Specific operation: The server generates a reservation success message and sends it to the terminal, which displays the message.

[0894] Step 8:

[0895] The user checks the over-the-counter drug suggestions and purchases them on the spot if necessary.

[0896] Information on suggested over-the-counter medications is displayed, and you can immediately proceed with the purchase.

[0897] Input: Over-the-counter drug proposal data

[0898] Output: Purchase confirmation message

[0899] Specific behavior: The user reviews the over-the-counter drug suggestions and presses the purchase button. The device displays a purchase confirmation.

[0900] Through these steps, users can quickly and efficiently manage their health, making necessary medical appointments and purchasing over-the-counter medications.

[0901] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0902] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[0903] First, the user uses the device to input their health status and symptoms. They enter information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields. The emotion engine then analyzes the user's input data and voice data to recognize the user's emotional state. This emotional state is important data for the subsequent diagnosis process.

[0904] The device converts this information and emotion data into JSON format, adds a timestamp, and sends it to the server.

[0905] The server analyzes the received data and performs data validation and format checks. The server then passes the analyzed health status data and emotion data to the generative AI model, which compares it with the trained medical data and knowledge base to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify possible illnesses with high accuracy by taking into account the user's symptoms and emotional state.

[0906] The generative AI model for diagnostics considers various possible illnesses based on the user's input and emotional state, and suggests the most likely illness or health condition. The emotion engine also adjusts the diagnostic process based on the user's emotional state. For example, if the user is feeling anxious, the system will operate to provide diagnostic results in a more careful and polite manner.

[0907] If a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of a specific illness being identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[0908] The user device displays the received diagnosis results to the user, allowing the user to know their own health condition and take the next action promptly.If the user wishes to see a doctor based on the diagnosis results, they can enter the desired hospital and appointment date and time through the application's UI.

[0909] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[0910] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[0911] As a specific example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the server receives this and uses the generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[0912] In this way, the system leverages historical medical data and knowledge bases, and uses generative AI models and an emotion engine to create a self-health checkup service that is easy for even busy people to use.

[0913] The processing flow will be explained below.

[0914] Step 1:

[0915] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields.

[0916] Step 2:

[0917] The emotion engine analyzes the user's input and voice data to recognize their emotional state from their tone of voice and input, identifying emotions such as anxiety, sadness, and anger.

[0918] Step 3:

[0919] The device converts the input data and emotion data into JSON format, adds a timestamp, and sends the data to the server.

[0920] Step 4:

[0921] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[0922] Step 5:

[0923] The server passes the analyzed data to the generative AI model, which then uses the generative AI model to perform a diagnosis based on the health status data and emotion data.

[0924] Step 6:

[0925] A generative AI model processes the data to identify likely illnesses, compares it with vast amounts of medical data, and generates a diagnosis that takes into account the user's symptoms and emotional state.

[0926] Step 7:

[0927] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[0928] Step 8:

[0929] The device receives the diagnosis results and displays them to the user. The device analyzes the results and displays them in a format that is easy for the user to understand. The display method may change depending on the user's emotional state.

[0930] Step 9:

[0931] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[0932] Step 10:

[0933] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[0934] Step 11:

[0935] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[0936] Step 12:

[0937] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[0938] Step 13:

[0939] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[0940] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[0941] Example 2

[0942] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0943] In modern society, busy users need a system that allows them to easily check their health status and, if necessary, make appointments with a medical institution. Furthermore, it is important to provide a diagnosis that takes into account the user's emotional state in order to provide more accurate medical care. However, existing systems face the challenge of being unable to provide a comprehensive diagnosis that includes the user's emotional state.

[0944] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0945] In this invention, the server includes emotion analysis means for analyzing input data and recognizing the emotional state, transmission means for transmitting the analyzed health information and emotional data to the server, and data processing means for receiving the transmitted data and validating and checking the format. This makes it possible to comprehensively diagnose the health information and emotional state input by the user and provide highly accurate diagnostic results.

[0946] The "input amount means" is a means for providing an interface for the user to input health conditions and symptoms.

[0947] The "emotion analysis means" is a means for analyzing the user's input data and voice data and recognizing the user's emotional state.

[0948] The "transmission means" is a means for converting the analyzed health information and emotion data into JSON format and transmitting it to the server.

[0949] The "data processing means" is a means for analyzing data received by the server and performing validation and format checks.

[0950] "Generation means" refers to a means for making a diagnosis using a generative AI model based on received data.

[0951] The "display means" is a means for displaying the diagnosis results based on the user's symptoms and emotional state on the terminal.

[0952] A "generative AI model" is an artificial intelligence model that learns from a vast medical database and makes diagnoses by taking into consideration the user's health information and emotional state in an integrated manner.

[0953] "Data processing means" refers to the server's function of analyzing the health information and emotion data sent by the user and performing any necessary validation and format checks.

[0954] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[0955] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[0956] First, the user accesses the system from their own device (such as a smartphone, tablet, or PC). On the system's user interface, they enter health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into input fields. This input is performed via an input volume means.

[0957] Next, the emotion analysis means analyzes the user's input data and voice data to recognize the user's emotional state. For example, emotions such as "anxiety" or "tension" can be recognized from the tone and speaking style of the voice. This emotional state is important data for the diagnostic process.

[0958] The device converts the input health information and analyzed emotion data into JSON format, adds a timestamp, and sends it to the server. This transmission is performed using a transmission method.

[0959] The server analyzes the received data using a data processing means and validates the input data (checking the format and values). For example, it checks whether the age is within the range or whether symptom data is missing. The verified data is then input into a generation means, and a diagnosis is performed using a generative AI model. The generative AI model uses a vast medical database to comprehensively consider the user's symptoms and emotional state, generating highly accurate diagnostic results.

[0960] When a diagnosis result is obtained, the server sends the diagnosis result data to the user terminal. The result includes the possibility of a specified illness and a recommended next action (e.g., whether or not a doctor's consultation is necessary). The user terminal displays the received diagnosis result to the user on a display means. This allows the user to know about their own health condition and take the next action promptly.

[0961] If the user wishes to see a doctor based on the diagnosis results, they enter the desired hospital and appointment date and time through the application's UI. The device obtains the user's appointment information and sends it back to the server. The server checks whether an appointment can be made for the specified date and time based on the received appointment information. If the appointment is successful, the server generates a confirmation message and sends it to the device. The user's device receives this confirmation message and displays it to the user, informing them that the appointment was successful.

[0962] In this way, users can not only quickly and efficiently manage their health, but also easily make necessary medical appointments.In addition, the emotion engine takes into account the user's emotional state, providing more thorough and accurate diagnosis results.

[0963] Specific examples

[0964] For example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the device sends this data to the server. The server uses the generative AI model to consider the possibility of "cold" or "flu," generates a diagnosis of "suspected influenza," and sends this to the device. After the user confirms the "suspected influenza," they make an appointment with the nearest medical institution, and the server confirms the appointment and notifies them of its success.

[0965] Prompt Sentence Examples

[0966] "A user inputs symptoms of cough and fever. The emotion engine recognizes that the user is anxious. Based on this information, what diagnosis would the generative AI model make and what suggestions would it make in response?"

[0967] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0968] Step 1:

[0969] A user accesses the system and enters health information.

[0970] Input: Health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever).

[0971] Specific operation: The user enters health information into the device's user interface.

[0972] Output: The input health information data.

[0973] Step 2:

[0974] An emotion analysis means analyzes the user's emotional state.

[0975] Input: Text and voice data entered by the user.

[0976] Specific operation: The emotion analysis engine performs real-time analysis and recognizes the user's emotional state (e.g., anxiety, tension).

[0977] Output: Parsed emotion data.

[0978] Step 3:

[0979] The device sends health information and emotion data to the server.

[0980] Input: Health information data, emotion data.

[0981] Specific operation: The device converts this data into JSON format, adds a timestamp, and sends it.

[0982] Output: Health and emotion data in JSON format sent to the server.

[0983] Step 4:

[0984] The server receives the data and performs validation.

[0985] Input: Received data in JSON format.

[0986] Specific behavior: The server checks the data format and values, and generates an error message if necessary.

[0987] Output: The validated data.

[0988] Step 5:

[0989] The server uses the generative AI model to perform the diagnosis.

[0990] Input: Validated health and emotion data.

[0991] How it works: The server inputs this data into a generative AI model and makes a diagnosis by referencing a vast medical database.

[0992] Output: Highly accurate diagnostic results.

[0993] Step 6:

[0994] The server transmits the diagnosis results to the user terminal.

[0995] Input: Diagnostic result data.

[0996] Specific operation: The server generates a message to send the diagnostic results to the user terminal.

[0997] Output: Diagnostic results sent to the user's terminal.

[0998] Step 7:

[0999] The user checks the diagnosis results and makes a hospital appointment if necessary.

[1000] Input: Diagnostic results displayed on the user's terminal.

[1001] Specific operation: The user checks the diagnostic results and enters reservation information through the application's UI.

[1002] Output: Appointment information (hospital name, appointment date and time).

[1003] Step 8:

[1004] The terminal transmits the reservation information to the server.

[1005] Input: Reservation information.

[1006] Specific operation: The terminal formats the data to send the reservation information to the server.

[1007] Output: The reservation information sent to the server.

[1008] Step 9:

[1009] The server checks the reservation status and notifies the user.

[1010] Input: Reservation information.

[1011] Specific operation: Based on the received reservation information, the server checks the reservation status at the medical institution, and if the reservation is successful, it generates a confirmation message and sends it to the terminal.

[1012] Output: Booking confirmation message.

[1013] (Application example 2)

[1014] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1015] Conventional self-health checkup systems only require users to input their health condition and symptoms, and do not take into account the user's emotional state. As a result, there is a lack of consideration for how the diagnosis results will be received by the user, and dealing with users who feel anxious is a particular issue. In addition, the procedure for making an appointment with a medical institution based on the diagnosis results is cumbersome, making the system less user-friendly. As such, there is a need for a system that combines highly accurate diagnosis that takes the user's emotions into account with a smooth appointment process with a medical institution.

[1016] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing input data and emotional state and performing diagnosis using a generative AI model, means for the diagnostic means to adjust the method for providing diagnostic results taking into account the user's emotional state, and means for confirming appointments with medical institutions and notifying the user of the results. This enables highly accurate self-health checkups that take into account the user's emotions, and also simplifies the process of making appointments with medical institutions.

[1017] "Input means" refers to the means by which a user inputs information about their health condition or symptoms into the system.

[1018] The "diagnostic means" is a means for analyzing input health condition and symptom data and emotional state, and making a diagnosis using a generative AI model.

[1019] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[1020] The "means for taking into account the emotional state" is a means for adjusting the method for providing the diagnostic results based on the emotional state of the user.

[1021] "Notification means" refers to the means for confirming an appointment with a medical institution and notifying the user of the results.

[1022] The "display means" is a means for displaying the diagnosis results based on the symptoms and emotional state of the user.

[1023] A "generative AI model" is an artificial intelligence model that uses data on a user's health, symptoms, and emotional state to match it with past medical data and a trained knowledge base to identify likely illnesses.

[1024] "Data" refers to information about a user's health, symptoms, and emotional state.

[1025] "Emotional state" refers to the emotional state of the user, which influences the behavior of the diagnostic tool.

[1026] The present invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system is composed of elements such as an input means, a diagnosis means, a reservation means, a means for considering emotional state, a notification means, and a display means.

[1027] Input Method

[1028] Using a device such as a smartphone, the user inputs information such as age, gender, medical history, and specific symptoms (e.g., cough, fever). An emotion recognition engine then analyzes the voice and text data to recognize the user's emotional state (e.g., anxiety). The input data and emotional state are then stored on the device.

[1029] Diagnostic tools

[1030] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. The server analyzes and validates the received data and performs a diagnosis using a generative AI model. This generative AI model takes into account the user's symptoms and emotional state based on a vast medical data and knowledge base, and identifies possible illnesses with high accuracy.

[1031] Measures that take emotional state into account

[1032] The diagnostic means adjusts the way in which the diagnostic result is provided taking into account the emotional state of the user, for example, if the user is feeling anxious, the diagnostic means operates to provide the diagnostic result in a polite and careful manner.

[1033] Reservation method

[1034] When a diagnosis result is obtained, the server sends it to the user's device. The diagnosis result includes the possibility of a specific illness and the next action to be taken (e.g., whether or not a doctor's examination is necessary). If the user wishes to see a doctor based on the diagnosis result, they input the desired hospital and appointment date and time through the device's UI.

[1035] Notification means

[1036] After the reservation procedure is completed, the terminal sends the reservation information to the server. The server checks whether the reservation is available for the specified date and time, and if the reservation is successful, it generates a confirmation message and sends it again to the terminal. The terminal displays this confirmation message to the user, notifying them that the reservation was successful.

[1037] Display means

[1038] The user device displays the received diagnostic results, allowing the user to know about their own health condition and take immediate action.

[1039] Example

[1040] For example, a 25-year-old male user inputs symptoms of fever and cough, and the emotion engine recognizes "anxiety." The server receives this data and uses the generative AI model to consider the possibility of "cold" or "flu." If the diagnosis is returned as "suspected influenza," the user can make an appointment with a nearby medical institution through the UI and receive a notification that the appointment has been completed.

[1041] Prompt Sentence Examples

[1042] Here are some example prompts for the generative AI model:

[1043] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[1044] In this way, the present invention provides a highly accurate self-health checkup that takes into account the user's emotions, and realizes a system that allows users to easily make appointments at medical institutions.

[1045] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1046] Step 1:

[1047] Users use a device such as a smartphone to input their health status (for example, symptoms such as fever or cough) and basic information (age, gender, medical history). This input data is stored in text format. Furthermore, an emotion recognition engine analyzes the user's emotional state based on voice or text input. The data processing performed here involves converting the user's voice or text data into an emotional state (anxiety, relief, etc.) using an emotion analysis engine (e.g., Azure Emotion API). Comprehensive user data, including the results of this analysis, is output.

[1048] Step 2:

[1049] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. In this step, the input data is properly formatted into JSON, which allows it to be sent to the server in a consistent data format.

[1050] Step 3:

[1051] The server analyzes and validates the received user data. The server checks whether the received data is in the correct format and contains all the required information. In this processing step, the server validates the received data using a data validation library, checking for incorrect data formats and defects, and prepares the clean data for passing to the generative AI model.

[1052] Step 4:

[1053] The server inputs the validated data into a generative AI model. This model compares it with a vast amount of past medical data and knowledge bases, and combines the user's symptoms and emotional state to make a diagnosis. The generative AI model uses prompt sentences to provide a highly accurate diagnosis. Data calculation involves converting user data into prompt sentences, which are then input into the generative AI model, which then outputs a diagnosis result.

[1054] example:

[1055] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[1056] Step 5:

[1057] Once the diagnosis is available, the server sends the results in JSON format to the user's device, where they are formatted into the appropriate fields, including the possible illness identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[1058] Step 6:

[1059] The terminal displays the received diagnosis results to the user. If the user wishes to make an appointment at a medical institution based on the diagnosis results, they can enter the desired hospital and appointment date and time through the terminal's UI. The user enters the desired appointment information and sends it to the server via the reservation method.

[1060] Step 7:

[1061] The server checks whether a reservation can be made for the specified date and time based on the received reservation information. In this process, it checks the availability of the reservation by linking with the medical institution's reservation system. If the reservation is successful, it generates a confirmation message, which is returned to the user's terminal in JSON format.

[1062] Step 8:

[1063] The device receives the reservation confirmation message and displays it to the user. This message lets the user know that the reservation was successful and allows them to take the next action quickly. The action here is to notify and confirm the user, and to display it appropriately in the user interface.

[1064] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1065] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1066] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1067] [Fourth embodiment]

[1068] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1069] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1070] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1071] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1072] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1073] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1074] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1075] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1076] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1077] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1078] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1079] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1080] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1081] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[1082] First, the user uses the device to input their health status and symptoms. This input consists of data such as age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[1083] The server analyzes the received data, performs data validation and checks the format, then passes the data to a generative AI model, which compares it with previously learned medical data and knowledge bases to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify the possibility of diseases related to the input symptoms with a high degree of accuracy.

[1084] The generative AI model, used as a diagnostic tool, considers various disease possibilities based on the user's input information and suggests the most likely disease or health condition. When a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of the identified disease and the next action to be taken (e.g., whether a doctor's consultation is necessary).

[1085] The user device displays the received diagnosis results, allowing the user to learn about their health status and take the next step quickly. For example, if a doctor's visit is recommended based on the diagnosis results, the user can enter the desired hospital and appointment date and time through the application's UI.

[1086] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[1087] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[1088] As a specific example, if a user inputs the symptoms of "cough" and "fever," the server receives this and uses a generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[1089] In this way, the system leverages past medical data and knowledge bases, and uses generative AI models to create a self-health checkup service that is easy for even busy people to use.

[1090] The processing flow will be explained below.

[1091] Step 1:

[1092] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms into the device's input fields.

[1093] Step 2:

[1094] The terminal structures the input data, converts it to JSON format, adds a timestamp, and sends the data to the server.

[1095] Step 3:

[1096] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[1097] Step 4:

[1098] The server passes the analyzed data to the generative AI model, which then compares it with past medical data and knowledge bases and instructs the AI ​​model to perform a diagnosis.

[1099] Step 5:

[1100] A generative AI model processes the data and identifies likely diseases. The AI ​​model uses vast amounts of medical data to identify diseases that match the user's symptoms.

[1101] Step 6:

[1102] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[1103] Step 7:

[1104] The device displays the received diagnostic results to the user. The device analyzes the diagnostic results and displays them in a format that is easy for the user to understand.

[1105] Step 8:

[1106] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[1107] Step 9:

[1108] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[1109] Step 10:

[1110] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[1111] Step 11:

[1112] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[1113] Step 12:

[1114] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[1115] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[1116] Example 1

[1117] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1118] Conventional health checkup systems have the problem that it is difficult for users to easily check their health status and quickly make an appointment with an appropriate medical institution. In addition, the diagnosis results can sometimes be unreliable, so there is a need for a system that users can use with confidence.

[1119] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1120] In this invention, the server includes a means for analyzing input data, adding a timestamp and performing data validation, a diagnostic means for applying a generative AI model using the analyzed data and comparing it with medical information to make a diagnosis, and a means for transmitting the diagnostic result and diagnostic ID to the user terminal, which allows users to easily check their own health condition, obtain highly accurate diagnostic results, and more quickly make appointments with medical institutions.

[1121] "Input means" refers to a device or interface that allows a user to input health conditions and symptoms.

[1122] "Data validation" is the process of verifying the integrity and correctness of format of received data.

[1123] A "timestamp" is information that indicates the time when data was transmitted by adding the current date and time to the data.

[1124] A "generative AI model" is an artificial intelligence model that uses vast amounts of medical information and a trained knowledge base to identify diseases associated with input symptoms.

[1125] A "diagnostic means" is a device or system that has the ability to use analyzed data to assess a user's health status and apply a generative AI model to make a diagnosis.

[1126] "Reservation means" refers to the functions and interfaces that allow users to make reservations at medical institutions based on diagnostic results.

[1127] A "diagnosis ID" is an identifier associated with a particular diagnosis result and is used to uniquely identify the diagnosis result.

[1128] A "display means" is a device or interface that visually displays diagnostic results or other information to a user.

[1129] "Medical Information" means historical data, knowledge base, and related medical information used in diagnosis and treatment.

[1130] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system functions in conjunction with three parties: the user, the terminal, and the server.

[1131] First, the user enters their health condition and symptoms using a device such as a smartphone or PC. Specific information to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.). Once the user has completed the input, the device converts this information into JSON format and adds the current date and time as a timestamp. The device then sends the converted data to the server.

[1132] The server analyzes the data received from the device and first performs data validation. By checking the data's consistency and format, it ensures that the input information is accurate. The server then passes the data to a generative AI model. This generative AI model is based on a vast amount of medical information and a trained knowledge base, so it can accurately identify the possible diseases associated with the user's input symptoms. The generative AI model identifies the most likely disease and returns the result to the server along with a diagnosis ID.

[1133] The server then sends the diagnosis results to the user's device, including the likelihood of an identified illness and the next course of action (e.g., whether or not a doctor's visit is necessary).

[1134] The user's device receives the diagnosis results and displays them on the application, allowing the user to check their own health status. For example, if a user enters symptoms of "cough" and "fever" and receives a diagnosis of "suspected influenza," the user can make an appointment at the nearest medical institution through the application. The user enters the desired hospital and appointment date and time and presses the "Make an appointment" button.

[1135] The device converts the user's reservation information back into JSON format and sends it to the server. The server receives the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, the server generates a confirmation message and sends it to the user's device. The user can check the received confirmation message on the application and find out that the reservation was successful.

[1136] This system allows users to easily undergo health checkups even in their busy daily lives and quickly make appointments with necessary medical institutions.

[1137] As a specific example, when a user inputs the symptoms of "cough" and "fever," the program's processing proceeds as follows: "Please explain the process by which a user can enter the symptoms of cough and fever, receive a diagnosis that indicates a high possibility of influenza, and then make a hospital appointment within the app." This system thus utilizes past medical information and a knowledge base, and uses a generative AI model to create a self-health checkup service that is easy to use even for busy people.

[1138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1139] Step 1:

[1140] The user launches the application and enters their health status and symptoms.

[1141] The user launches the application using a smartphone or PC, enters their age, gender, medical history, and current symptoms (e.g., cough, fever, etc.) into the input form, and presses the "Submit" button. At this time, the input data is in RAW text format.

[1142] Step 2:

[1143] The terminal converts the input data into JSON format and adds a timestamp.

[1144] When the "Submit" button is pressed, the terminal converts the RAW text data obtained from the form into JSON format. For example, it generates a JSON object containing the entered data, such as "Age: 30, Gender: Male, Symptoms: Cough, Fever." It also obtains the current date and time and adds it to the JSON data as a timestamp. Input: RAW text data Output: JSON data with timestamp.

[1145] Step 3:

[1146] The device sends JSON data to the server.

[1147] The terminal sends the converted time-stamped JSON data to the server via an HTTP POST request. Input: Time-stamped JSON data Output: HTTP POST request.

[1148] Step 4:

[1149] The server receives the data, parses it, and validates it.

[1150] The server receives the HTTP POST request and parses the JSON data. After parsing, it performs data validation to check the consistency and format of the input data. Input: JSON data with a timestamp. Output: Validated data.

[1151] Step 5:

[1152] The server passes the validated data to the generative AI model to perform the diagnosis.

[1153] The server inputs the validated data into the generative AI model. Based on a vast medical information and knowledge base, the generative AI model identifies with high accuracy the possibility of a disease related to the input symptoms. A diagnosis result is obtained. Input: Validated data Output: Diagnosis result and diagnosis ID.

[1154] Step 6:

[1155] The server sends the diagnosis result and diagnosis ID to the user's terminal.

[1156] The server converts the diagnosis results and diagnosis ID obtained from the generative AI model into JSON format and returns them to the user device as an HTTP response. Input: Diagnosis results and diagnosis ID Output: JSON data with timestamp.

[1157] Step 7:

[1158] The user terminal receives and displays the diagnostic results.

[1159] The user device receives the HTTP response from the server and analyzes the JSON data. The diagnosis results are displayed on the application, allowing the user to check their own health status. Input: Diagnosis result and diagnosis ID Output: Displayed diagnosis result.

[1160] Step 8:

[1161] The user makes a medical appointment through the application.

[1162] Based on the diagnosis results, the user is directed to the reservation screen at the nearest medical institution through the application's UI. They enter the necessary reservation information (hospital, desired date and time, etc.) and press the "Make a reservation" button. Input: Reservation information (hospital, date and time, etc.) Output: Reservation information

[1163] Step 9:

[1164] The device sends the reservation information in JSON format to the server.

[1165] When the user presses the "Make a reservation" button, the device converts the reservation information into JSON format and sends it to the server via an HTTP POST request. Input: RAW data of reservation information Output: JSON data of reservation information

[1166] Step 10:

[1167] The server confirms the reservation based on the reservation information and sends the result to the user terminal.

[1168] The server receives the JSON data of the reservation information and checks whether a reservation can be made for the specified date and time. If the reservation is successful, it generates a confirmation message and sends it to the user's device as an HTTP response. Input: JSON data of the reservation information Output: Confirmation message

[1169] Step 11:

[1170] The user terminal receives and displays the confirmation message.

[1171] The user terminal receives the HTTP response from the server, parses the confirmation message, and displays it, letting the user know that the reservation was successful. Input: Confirmation message Output: Displayed confirmation message.

[1172] (Application example 1)

[1173] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1174] Conventional self-health checkup systems allow users to easily check their health status, but they are unable to provide prompt action based on the results of the checkup, suggest necessary over-the-counter medications, or purchase them on the spot. Furthermore, it is difficult to easily make appointments with medical institutions, which can lead to delays in early detection of illness and appropriate treatment. This has resulted in insufficient efficiency in users' health management.

[1175] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1176] In this invention, the server includes an input means for the user to input their health condition and symptoms, a diagnosis means for analyzing the input data and making a diagnosis using a generative AI model, a reservation means for making an appointment with a medical institution based on the diagnosis results, and a suggestion means for displaying the diagnosis results of the health condition and symptoms and suggesting or purchasing over-the-counter medications as needed. This enables users to easily check their health condition and quickly purchase over-the-counter medications and make appointments with medical institutions based on the diagnosis results.

[1177] An "input means" is a system component that provides an interface for a user to input health conditions and symptoms.

[1178] A "diagnostic means" is a system component that analyzes input data and performs a diagnosis using a generative AI model.

[1179] A "generative AI model" is an artificial intelligence algorithm that analyzes a user's health condition and symptoms based on past medical data and a learned knowledge base, and derives a diagnosis.

[1180] The "reservation means" is a system component for making a reservation at a medical institution based on the diagnosis results.

[1181] The "suggestion means" is a system component that displays the diagnosis results of health conditions and symptoms, and provides the function of suggesting over-the-counter medicines and assisting in the purchase of medicines as needed.

[1182] The "display means" is a system component that presents the diagnostic results based on the user's symptoms in a visually recognizable form.

[1183] "Medical institution" refers to a medical facility such as a hospital or clinic where users can receive treatment through diagnostic results and appointment procedures.

[1184] "Over-the-counter drugs" are medicines that can be purchased at pharmacies or drug stores without a prescription.

[1185] This invention is a system that allows users to conduct self-health checkups and, if necessary, make appointments with medical institutions or purchase over-the-counter medications on the spot. This system includes the following main components: an input means for users to input their health condition and symptoms, a diagnosis means that analyzes the input data and makes a diagnosis using a generative AI model, a reservation means that makes appointments with medical institutions based on the diagnosis results, and a suggestion means that displays the diagnosis results of the health condition and symptoms and suggests and purchases over-the-counter medications as necessary.

[1186] The operation of the system will be described in detail below. The user uses a terminal to input their health condition and symptoms. The terminal is equipped with a touch panel display and provides an interface that allows for easy input of health information. The information entered by the user is converted into JSON format, time-stamped, and then sent to the server. This communication uses an HTTP request library (for example, Python's requests library).

[1187] The server analyzes the received data and performs basic data validation and format checks using a database management system (DBMS) and data analysis libraries (e.g., pandas and NumPy). Once the data analysis is complete, it is passed to a generative AI model, which runs on a GPU cluster and uses frameworks such as PyTorch to compare the data with past medical data and a trained knowledge base to make a diagnosis.

[1188] The diagnostic results are returned to the server, where the diagnostic result data is formatted in JSON format. This data is then sent back to the device as an HTTP response. The device receives this and displays the diagnostic results to the user. The user interface (UI) is intuitively designed using JavaScript, HTML, and CSS.

[1189] The diagnosis results include the possibility of an identified illness, the next action to be taken (e.g., whether or not a medical visit is necessary), and suggestions for medications for symptoms that can be treated with over-the-counter medications. Based on this, if the user wishes, they can purchase over-the-counter medications on the spot. Furthermore, if a diagnosis indicates that a medical visit is necessary, the user can make an appointment with a medical institution through the application's UI. Once the appointment procedure is completed, the appointment information is also sent to the server and processed.

[1190] Here is a specific example of usage: For example, if a user enters the symptoms "cough" and "fever", the following prompt will be sent to the server:

[1191] Age: 35

[1192] Gender: Male

[1193] Symptoms: Cough, fever

[1194] Timestamp: 2023-10-05T10:05Z

[1195] Based on this input, the generative AI model returns a diagnosis of "cold" or "flu" and presents the user with a diagnosis of "suspected flu." The user can then make an appointment with the nearest medical institution based on this diagnosis. If necessary, the user can also purchase the suggested over-the-counter medication on the spot.

[1196] As described above, the system of the present invention can perform a complete process from self-health checkups to making appointments with medical institutions and purchasing over-the-counter medicines, thereby efficiently and quickly supporting users in managing their health.

[1197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1198] Step 1:

[1199] The user inputs their health condition and symptoms into the device.

[1200] The data to be entered includes age, gender, medical history, and current specific symptoms (e.g., cough, fever, etc.).

[1201] The device converts this information into JSON format, adds a timestamp, and sends it to the server.

[1202] Input: Age, gender, medical history, current specific symptoms

[1203] Output: JSON format data

[1204] Specific operation: The user enters information into the touch panel display and presses the "Send" button.

[1205] Step 2:

[1206] The server parses the received JSON data and performs basic data validation and format checks.

[1207] Specifically, it checks the existence of required fields and validates data types, using data analysis libraries and DBMS.

[1208] Input: JSON format data

[1209] Output: Validated data

[1210] Specific operation: A Python script is executed on the server side to perform data validation.

[1211] Step 3:

[1212] The server passes the verified data to a generative AI model to make a diagnosis.

[1213] The generative AI model compares historical medical data and a trained knowledge base to identify possible illnesses based on input symptoms.

[1214] This uses frameworks such as PyTorch running on GPU clusters.

[1215] Input: Validated data

[1216] Output: Diagnostic results

[1217] Specific operation: The server inputs data into the generative AI model and obtains the diagnosis results.

[1218] Step 4:

[1219] The server formats the diagnostic results from the generated AI model in JSON format and sends them back to the device.

[1220] The returned data includes the diagnosis as well as suggestions for next steps and over-the-counter medications.

[1221] Input: Diagnostic results from a generative AI model

[1222] Output: JSON format diagnostic result data

[1223] Specific operation: The server formats the diagnostic results and sends them to the terminal as an HTTP response.

[1224] Step 5:

[1225] The device displays the diagnostic results it receives to the user.

[1226] The diagnosis results will show the likelihood of the disease being identified and the next action to be taken (e.g., whether or not medical attention is required).

[1227] Input: JSON format diagnostic result data

[1228] Output: Display of diagnostic results

[1229] Specific operation: The diagnostic results are displayed on the device display for the user to check.

[1230] Step 6:

[1231] When a user makes an appointment at a medical institution based on the diagnosis results, the user inputs appointment information (date, time, hospital, etc.) and transmits it to the server via the terminal.

[1232] The server receives the reservation information and checks whether the reservation can be made for the specified date and time.

[1233] Input: Reservation information (date, time, hospital, etc.)

[1234] Output: Reservation confirmation message

[1235] Specific operation: The user fills out the reservation form and presses the "Reserve" button.

[1236] Step 7:

[1237] The server verifies that the reservation was successful and generates a confirmation message and sends it to the terminal.

[1238] The terminal will display this confirmation message to the user, letting them know that the reservation was successful.

[1239] Input: Reservation confirmation data

[1240] Output: Reservation confirmation message

[1241] Specific operation: The server generates a reservation success message and sends it to the terminal, which displays the message.

[1242] Step 8:

[1243] The user checks the over-the-counter drug suggestions and purchases them on the spot if necessary.

[1244] Information on suggested over-the-counter medications is displayed, and you can immediately proceed with the purchase.

[1245] Input: Over-the-counter drug proposal data

[1246] Output: Purchase confirmation message

[1247] Specific behavior: The user reviews the over-the-counter drug suggestions and presses the purchase button. The device displays a purchase confirmation.

[1248] Through these steps, users can quickly and efficiently manage their health, making necessary medical appointments and purchasing over-the-counter medications.

[1249] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1250] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[1251] First, the user uses the device to input their health status and symptoms. They enter information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields. The emotion engine then analyzes the user's input data and voice data to recognize the user's emotional state. This emotional state is important data for the subsequent diagnosis process.

[1252] The device converts this information and emotion data into JSON format, adds a timestamp, and sends it to the server.

[1253] The server analyzes the received data and performs data validation and format checks. The server then passes the analyzed health status data and emotion data to the generative AI model, which compares it with the trained medical data and knowledge base to perform a diagnosis. This generative AI model is based on a vast amount of medical data and is able to identify possible illnesses with high accuracy by taking into account the user's symptoms and emotional state.

[1254] The generative AI model for diagnostics considers various possible illnesses based on the user's input and emotional state, and suggests the most likely illness or health condition. The emotion engine also adjusts the diagnostic process based on the user's emotional state. For example, if the user is feeling anxious, the system will operate to provide diagnostic results in a more careful and polite manner.

[1255] If a diagnosis result is obtained, the server sends the result to the user's device. The server analyzes the diagnosis result data and returns it to the user's device along with a diagnosis ID. The diagnosis result includes the possibility of a specific illness being identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[1256] The user device displays the received diagnosis results to the user, allowing the user to know their own health condition and take the next action promptly.If the user wishes to see a doctor based on the diagnosis results, they can enter the desired hospital and appointment date and time through the application's UI.

[1257] Once the device has received the user's reservation information, it sends it back to the server. The server then checks whether a reservation can be made for the specified date and time based on the received reservation information. If the reservation is successful, the server generates a confirmation message and sends it to the device.

[1258] The user device will receive this confirmation message and display it to the user to let them know that the appointment was successful, allowing them to easily take a health checkup and make the necessary medical appointment even in their busy daily lives.

[1259] As a specific example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the server receives this and uses the generative AI model to identify the possibility of "cold" or "flu." The diagnosis result is then returned to the device, and the user confirms the diagnosis of "suspected influenza." If the user wants to make an appointment at the nearest medical institution, they select the appointment date and time through the application's UI and confirm the appointment. After the server receives the reservation information, it confirms that the appointment was successful and notifies the user. This series of steps allows users to quickly and efficiently manage their health and make appointments with medical institutions.

[1260] In this way, the system leverages historical medical data and knowledge bases, and uses generative AI models and an emotion engine to create a self-health checkup service that is easy for even busy people to use.

[1261] The processing flow will be explained below.

[1262] Step 1:

[1263] The user uses the device to input their health status and symptoms. The user enters information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into the device's input fields.

[1264] Step 2:

[1265] The emotion engine analyzes the user's input and voice data to recognize their emotional state from their tone of voice and input, identifying emotions such as anxiety, sadness, and anger.

[1266] Step 3:

[1267] The device converts the input data and emotion data into JSON format, adds a timestamp, and sends the data to the server.

[1268] Step 4:

[1269] The server parses the received data and performs data validation and format checks to ensure the data is in the correct format.

[1270] Step 5:

[1271] The server passes the analyzed data to the generative AI model, which then uses the generative AI model to perform a diagnosis based on the health status data and emotion data.

[1272] Step 6:

[1273] A generative AI model processes the data to identify likely illnesses, compares it with vast amounts of medical data, and generates a diagnosis that takes into account the user's symptoms and emotional state.

[1274] Step 7:

[1275] The server receives the diagnosis results from the AI ​​model and prepares a response to return to the user device along with the diagnosis ID. The server sends the diagnosis results in JSON format.

[1276] Step 8:

[1277] The device receives the diagnosis results and displays them to the user. The device analyzes the results and displays them in a format that is easy for the user to understand. The display method may change depending on the user's emotional state.

[1278] Step 9:

[1279] If the user checks the diagnosis results and wishes to make an appointment with a medical institution if necessary, they can use the application's UI to select the appointment date and time and hospital.

[1280] Step 10:

[1281] The device sends the user's reservation information in JSON format to the server, which includes data such as the hospital ID, date and time, and user ID.

[1282] Step 11:

[1283] The server receives the reservation information and checks whether the reservation can be made for the specified date and time. The server then connects with the medical institution's system to check whether the reservation can be made.

[1284] Step 12:

[1285] The server generates the reservation result and prepares a response to return to the user device. If the reservation is successful, it generates a response containing a confirmation message and the reservation ID.

[1286] Step 13:

[1287] The device displays the received reservation confirmation message to the user. The device notifies the user that the reservation was successful and displays the reservation ID.

[1288] This series of processing steps allows users to easily make health checkups and medical appointments even in their busy daily lives.

[1289] Example 2

[1290] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1291] In modern society, busy users need a system that allows them to easily check their health status and, if necessary, make appointments with a medical institution. Furthermore, it is important to provide a diagnosis that takes into account the user's emotional state in order to provide more accurate medical care. However, existing systems face the challenge of being unable to provide a comprehensive diagnosis that includes the user's emotional state.

[1292] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1293] In this invention, the server includes emotion analysis means for analyzing input data and recognizing the emotional state, transmission means for transmitting the analyzed health information and emotional data to the server, and data processing means for receiving the transmitted data and validating and checking the format. This makes it possible to comprehensively diagnose the health information and emotional state input by the user and provide highly accurate diagnostic results.

[1294] The "input amount means" is a means for providing an interface for the user to input health conditions and symptoms.

[1295] The "emotion analysis means" is a means for analyzing the user's input data and voice data and recognizing the user's emotional state.

[1296] The "transmission means" is a means for converting the analyzed health information and emotion data into JSON format and transmitting it to the server.

[1297] The "data processing means" is a means for analyzing data received by the server and performing validation and format checks.

[1298] "Generation means" refers to a means for making a diagnosis using a generative AI model based on received data.

[1299] The "display means" is a means for displaying the diagnosis results based on the user's symptoms and emotional state on the terminal.

[1300] A "generative AI model" is an artificial intelligence model that learns from a vast medical database and makes diagnoses by taking into consideration the user's health information and emotional state in an integrated manner.

[1301] "Data processing means" refers to the server's function of analyzing the health information and emotion data sent by the user and performing any necessary validation and format checks.

[1302] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[1303] This invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system works in conjunction with the user, terminal, server, and emotion engine that recognizes the user's emotions.

[1304] First, the user accesses the system from their own device (such as a smartphone, tablet, or PC). On the system's user interface, they enter health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever) into input fields. This input is performed via an input volume means.

[1305] Next, the emotion analysis means analyzes the user's input data and voice data to recognize the user's emotional state. For example, emotions such as "anxiety" or "tension" can be recognized from the tone and speaking style of the voice. This emotional state is important data for the diagnostic process.

[1306] The device converts the input health information and analyzed emotion data into JSON format, adds a timestamp, and sends it to the server. This transmission is performed using a transmission method.

[1307] The server analyzes the received data using a data processing means and validates the input data (checking the format and values). For example, it checks whether the age is within the range or whether symptom data is missing. The verified data is then input into a generation means, and a diagnosis is performed using a generative AI model. The generative AI model uses a vast medical database to comprehensively consider the user's symptoms and emotional state, generating highly accurate diagnostic results.

[1308] When a diagnosis result is obtained, the server sends the diagnosis result data to the user terminal. The result includes the possibility of a specified illness and a recommended next action (e.g., whether or not a doctor's consultation is necessary). The user terminal displays the received diagnosis result to the user on a display means. This allows the user to know about their own health condition and take the next action promptly.

[1309] If the user wishes to see a doctor based on the diagnosis results, they enter the desired hospital and appointment date and time through the application's UI. The device obtains the user's appointment information and sends it back to the server. The server checks whether an appointment can be made for the specified date and time based on the received appointment information. If the appointment is successful, the server generates a confirmation message and sends it to the device. The user's device receives this confirmation message and displays it to the user, informing them that the appointment was successful.

[1310] In this way, users can not only quickly and efficiently manage their health, but also easily make necessary medical appointments.In addition, the emotion engine takes into account the user's emotional state, providing more thorough and accurate diagnosis results.

[1311] Specific examples

[1312] For example, if a user inputs the symptoms of "cough" and "fever" and the emotion engine recognizes "anxiety," the device sends this data to the server. The server uses the generative AI model to consider the possibility of "cold" or "flu," generates a diagnosis of "suspected influenza," and sends this to the device. After the user confirms the "suspected influenza," they make an appointment with the nearest medical institution, and the server confirms the appointment and notifies them of its success.

[1313] Prompt Sentence Examples

[1314] "A user inputs symptoms of cough and fever. The emotion engine recognizes that the user is anxious. Based on this information, what diagnosis would the generative AI model make and what suggestions would it make in response?"

[1315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1316] Step 1:

[1317] A user accesses the system and enters health information.

[1318] Input: Health information such as age, gender, medical history, and specific symptoms (e.g., cough, fever).

[1319] Specific operation: The user enters health information into the device's user interface.

[1320] Output: The input health information data.

[1321] Step 2:

[1322] An emotion analysis means analyzes the user's emotional state.

[1323] Input: Text and voice data entered by the user.

[1324] Specific operation: The emotion analysis engine performs real-time analysis and recognizes the user's emotional state (e.g., anxiety, tension).

[1325] Output: Parsed emotion data.

[1326] Step 3:

[1327] The device sends health information and emotion data to the server.

[1328] Input: Health information data, emotion data.

[1329] Specific operation: The device converts this data into JSON format, adds a timestamp, and sends it.

[1330] Output: Health and emotion data in JSON format sent to the server.

[1331] Step 4:

[1332] The server receives the data and performs validation.

[1333] Input: Received data in JSON format.

[1334] Specific behavior: The server checks the data format and values, and generates an error message if necessary.

[1335] Output: The validated data.

[1336] Step 5:

[1337] The server uses the generative AI model to perform the diagnosis.

[1338] Input: Validated health and emotion data.

[1339] How it works: The server inputs this data into a generative AI model and makes a diagnosis by referencing a vast medical database.

[1340] Output: Highly accurate diagnostic results.

[1341] Step 6:

[1342] The server transmits the diagnosis results to the user terminal.

[1343] Input: Diagnostic result data.

[1344] Specific operation: The server generates a message to send the diagnostic results to the user terminal.

[1345] Output: Diagnostic results sent to the user's terminal.

[1346] Step 7:

[1347] The user checks the diagnosis results and makes a hospital appointment if necessary.

[1348] Input: Diagnostic results displayed on the user's terminal.

[1349] Specific operation: The user checks the diagnostic results and enters reservation information through the application's UI.

[1350] Output: Appointment information (hospital name, appointment date and time).

[1351] Step 8:

[1352] The terminal transmits the reservation information to the server.

[1353] Input: Reservation information.

[1354] Specific operation: The terminal formats the data to send the reservation information to the server.

[1355] Output: The reservation information sent to the server.

[1356] Step 9:

[1357] The server checks the reservation status and notifies the user.

[1358] Input: Reservation information.

[1359] Specific operation: Based on the received reservation information, the server checks the reservation status at the medical institution, and if the reservation is successful, it generates a confirmation message and sends it to the terminal.

[1360] Output: Booking confirmation message.

[1361] (Application example 2)

[1362] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1363] Conventional self-health checkup systems only require users to input their health condition and symptoms, and do not take into account the user's emotional state. As a result, there is a lack of consideration for how the diagnosis results will be received by the user, and dealing with users who feel anxious is a particular issue. In addition, the procedure for making an appointment with a medical institution based on the diagnosis results is cumbersome, making the system less user-friendly. As such, there is a need for a system that combines highly accurate diagnosis that takes the user's emotions into account with a smooth appointment process with a medical institution.

[1364] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing input data and emotional state and performing diagnosis using a generative AI model, means for the diagnostic means to adjust the method for providing diagnostic results taking into account the user's emotional state, and means for confirming appointments with medical institutions and notifying the user of the results. This enables highly accurate self-health checkups that take into account the user's emotions, and also simplifies the process of making appointments with medical institutions.

[1365] "Input means" refers to the means by which a user inputs information about their health condition or symptoms into the system.

[1366] The "diagnostic means" is a means for analyzing input health condition and symptom data and emotional state, and making a diagnosis using a generative AI model.

[1367] The "reservation means" is a means for making a reservation at a medical institution based on the diagnosis results.

[1368] The "means for taking into account the emotional state" is a means for adjusting the method for providing the diagnostic results based on the emotional state of the user.

[1369] "Notification means" refers to the means for confirming an appointment with a medical institution and notifying the user of the results.

[1370] The "display means" is a means for displaying the diagnosis results based on the symptoms and emotional state of the user.

[1371] A "generative AI model" is an artificial intelligence model that uses data on a user's health, symptoms, and emotional state to match it with past medical data and a trained knowledge base to identify likely illnesses.

[1372] "Data" refers to information about a user's health, symptoms, and emotional state.

[1373] "Emotional state" refers to the emotional state of the user, which influences the behavior of the diagnostic tool.

[1374] The present invention is a self-health checkup system that allows users to easily check their health condition and, if necessary, make an appointment with a medical institution. This system is composed of elements such as an input means, a diagnosis means, a reservation means, a means for considering emotional state, a notification means, and a display means.

[1375] Input Method

[1376] Using a device such as a smartphone, the user inputs information such as age, gender, medical history, and specific symptoms (e.g., cough, fever). An emotion recognition engine then analyzes the voice and text data to recognize the user's emotional state (e.g., anxiety). The input data and emotional state are then stored on the device.

[1377] Diagnostic tools

[1378] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. The server analyzes and validates the received data and performs a diagnosis using a generative AI model. This generative AI model takes into account the user's symptoms and emotional state based on a vast medical data and knowledge base, and identifies possible illnesses with high accuracy.

[1379] Measures that take emotional state into account

[1380] The diagnostic means adjusts the way in which the diagnostic result is provided taking into account the emotional state of the user, for example, if the user is feeling anxious, the diagnostic means operates to provide the diagnostic result in a polite and careful manner.

[1381] Reservation method

[1382] When a diagnosis result is obtained, the server sends it to the user's device. The diagnosis result includes the possibility of a specific illness and the next action to be taken (e.g., whether or not a doctor's examination is necessary). If the user wishes to see a doctor based on the diagnosis result, they input the desired hospital and appointment date and time through the device's UI.

[1383] Notification means

[1384] After the reservation procedure is completed, the terminal sends the reservation information to the server. The server checks whether the reservation is available for the specified date and time, and if the reservation is successful, it generates a confirmation message and sends it again to the terminal. The terminal displays this confirmation message to the user, notifying them that the reservation was successful.

[1385] Display means

[1386] The user device displays the received diagnostic results, allowing the user to know about their own health condition and take immediate action.

[1387] Example

[1388] For example, a 25-year-old male user inputs symptoms of fever and cough, and the emotion engine recognizes "anxiety." The server receives this data and uses the generative AI model to consider the possibility of "cold" or "flu." If the diagnosis is returned as "suspected influenza," the user can make an appointment with a nearby medical institution through the UI and receive a notification that the appointment has been completed.

[1389] Prompt Sentence Examples

[1390] Here are some example prompts for the generative AI model:

[1391] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[1392] In this way, the present invention provides a highly accurate self-health checkup that takes into account the user's emotions, and realizes a system that allows users to easily make appointments at medical institutions.

[1393] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1394] Step 1:

[1395] Users use a device such as a smartphone to input their health status (for example, symptoms such as fever or cough) and basic information (age, gender, medical history). This input data is stored in text format. Furthermore, an emotion recognition engine analyzes the user's emotional state based on voice or text input. The data processing performed here involves converting the user's voice or text data into an emotional state (anxiety, relief, etc.) using an emotion analysis engine (e.g., Azure Emotion API). Comprehensive user data, including the results of this analysis, is output.

[1396] Step 2:

[1397] The device converts the input health and emotional state data into JSON format, adds a timestamp, and sends it to the server. In this step, the input data is properly formatted into JSON, which allows it to be sent to the server in a consistent data format.

[1398] Step 3:

[1399] The server analyzes and validates the received user data. The server checks whether the received data is in the correct format and contains all the required information. In this processing step, the server validates the received data using a data validation library, checking for incorrect data formats and defects, and prepares the clean data for passing to the generative AI model.

[1400] Step 4:

[1401] The server inputs the validated data into a generative AI model. This model compares it with a vast amount of past medical data and knowledge bases, and combines the user's symptoms and emotional state to make a diagnosis. The generative AI model uses prompt sentences to provide a highly accurate diagnosis. Data calculation involves converting user data into prompt sentences, which are then input into the generative AI model, which then outputs a diagnosis result.

[1402] example:

[1403] "A 25-year-old male presents with a fever and cough. He appears anxious. Please suggest possible symptoms and next steps."

[1404] Step 5:

[1405] Once the diagnosis is available, the server sends the results in JSON format to the user's device, where they are formatted into the appropriate fields, including the possible illness identified and the next action to be taken (e.g., whether or not a doctor's consultation is necessary).

[1406] Step 6:

[1407] The terminal displays the received diagnosis results to the user. If the user wishes to make an appointment at a medical institution based on the diagnosis results, they can enter the desired hospital and appointment date and time through the terminal's UI. The user enters the desired appointment information and sends it to the server via the reservation method.

[1408] Step 7:

[1409] The server checks whether a reservation can be made for the specified date and time based on the received reservation information. In this process, it checks the availability of the reservation by linking with the medical institution's reservation system. If the reservation is successful, it generates a confirmation message, which is returned to the user's terminal in JSON format.

[1410] Step 8:

[1411] The device receives the reservation confirmation message and displays it to the user. This message lets the user know that the reservation was successful and allows them to take the next action quickly. The action here is to notify and confirm the user, and to display it appropriately in the user interface.

[1412] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1413] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1414] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1415] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1416] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1417] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1418] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1419] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1420] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1421] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1422] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1423] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1424] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1425] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1426] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1427] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1428] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1429] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1430] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1431] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1432] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1433] The following is further disclosed regarding the above embodiment.

[1434] (Claim 1)

[1435] an input means for the user to input health conditions and symptoms;

[1436] A diagnostic means for analyzing input data and making a diagnosis using a generative AI model;

[1437] A reservation method for making an appointment with a medical institution based on the diagnosis results;

[1438] A system including:

[1439] (Claim 2)

[1440] 10. The system of claim 1, further comprising a display means for displaying a diagnosis based on the user's symptoms.

[1441] (Claim 3)

[1442] 10. The system of claim 1, wherein the diagnostic means includes a generative AI model that uses the user's health status and symptom data to identify likely illnesses by matching it with historical medical data and a trained knowledge base.

[1443] "Example 1"

[1444] (Claim 1)

[1445] an input means for the user to input health conditions and symptoms;

[1446] A means for analyzing the input data, adding a timestamp and performing data validation;

[1447] A diagnostic means for applying a generative AI model using the analyzed data and comparing it with medical information to make a diagnosis;

[1448] A reservation method for making an appointment with a medical institution based on the diagnosis results;

[1449] a means for transmitting the diagnosis result and the diagnosis ID to a user terminal;

[1450] A system including:

[1451] (Claim 2)

[1452] 10. The system of claim 1, further comprising a display means for displaying a diagnosis based on the user's symptoms.

[1453] (Claim 3)

[1454] 10. The system of claim 1, wherein the diagnostic means includes a generative AI model that uses the user's health status and symptom data to identify likely health risks by matching it with past medical information and a trained knowledge base.

[1455] "Application Example 1"

[1456] (Claim 1)

[1457] an input means for the user to input health conditions and symptoms;

[1458] A diagnostic means for analyzing input data and making a diagnosis using a generative AI model;

[1459] A reservation method for making an appointment with a medical institution based on the diagnosis results;

[1460] It displays the diagnosis results of health conditions and symptoms, and provides a suggestion tool that allows users to suggest and purchase over-the-counter medications as needed.

[1461] A system including:

[1462] (Claim 2)

[1463] 10. The system of claim 1, further comprising a display means for displaying a diagnosis based on the user's symptoms.

[1464] (Claim 3)

[1465] 10. The system of claim 1, wherein the diagnostic means includes a generative AI model that uses the user's health status and symptom data to identify likely illnesses by matching it with historical medical data and a trained knowledge base.

[1466] "Example 2: Combining Emotion Engines"

[1467] (Claim 1)

[1468] An input quantity means for a user to input health conditions and symptoms;

[1469] emotion analysis means for analyzing input data and recognizing an emotional state;

[1470] a transmitting means for transmitting the analyzed health information and emotion data to a server;

[1471] data processing means for receiving the transmitted data and performing validation and format checks;

[1472] A generating means for performing a diagnosis using a generating AI model based on the received data;

[1473] A reservation method for making an appointment with a medical institution based on the diagnosis results;

[1474] A system including:

[1475] (Claim 2)

[1476] 10. The system of claim 1, further comprising a display means for displaying a diagnosis based on the user's symptoms and emotional state.

[1477] (Claim 3)

[1478] 10. The system of claim 1, wherein the diagnostic means includes a generative AI model that uses the user's health status, symptom data, and emotional data to identify likely illnesses by matching them with historical medical data and a trained knowledge base.

[1479] "Application example 2 when combining emotion engines"

[1480] (Claim 1)

[1481] an input means for the user to input health conditions and symptoms;

[1482] A diagnostic means for analyzing input data and emotional state and making a diagnosis using a generative AI model;

[1483] A reservation method for making an appointment with a medical institution based on the diagnosis results;

[1484] A diagnostic means for adjusting the method of providing the diagnostic result by taking into account the emotional state of the user;

[1485] A means to confirm medical appointments and notify the user of the results;

[1486] A system including:

[1487] (Claim 2)

[1488] 10. The system of claim 1, further comprising a display means for displaying a diagnosis based on the user's symptoms and emotional state.

[1489] (Claim 3)

[1490] 10. The system of claim 1, wherein the diagnostic means includes a generative AI model that uses data on the user's health, symptoms, and emotional state to identify likely illnesses by matching it with historical medical data and a trained knowledge base. [Explanation of symbols]

[1491] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an input means for the user to input health conditions and symptoms; A diagnostic means for analyzing input data and making a diagnosis using a generative AI model; A reservation method for making an appointment with a medical institution based on the diagnosis results; A system including:

2. The system of claim 1 further comprising a display means for displaying a diagnosis based on the user's symptoms.

3. 10. The system of claim 1, wherein the diagnostic means includes a generative AI model that uses the user's health status and symptom data to identify likely illnesses by matching it with historical medical data and a trained knowledge base.

Images