system

Abstract

We provide the system. [Solution] A means of recording and storing patient medical history information, current treatment information, and past test results, A method for selecting and introducing the most suitable physician based on stored patient information using a generative model, A means of connecting doctors and patients online for diagnosis and consultation, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Cancer patients and their families have many anxieties and questions during treatment, but there are limited means to easily obtain high-quality second opinions. Also, in the current medical system, due to time and location constraints, it is often impossible to obtain opinions from desired doctors. Conventional second opinion services are expensive and difficult for many patients to use. In order to solve the above problems, there is a need to provide an online second opinion service with low cost and high convenience.

Means for Solving the Problems

[0005] This invention provides a system that includes means for recording and storing a patient's medical history, current treatment information, and past test results. By using a means to select and introduce the most suitable physician based on the stored patient information using a generative model, the system proposes the most appropriate physician for the patient. Furthermore, by providing a means for connecting physicians and patients online for diagnosis and consultation, the system eliminates time and location constraints, realizing a low-cost, high-quality second opinion service. In addition, the generative model can provide more accurate physician referrals by comparing the current information with past case data. By providing online diagnosis and consultation reservation functions based on patient input information, the system achieves a highly convenient service.

[0006] "Patient information" refers to medical data such as the patient's personal information, medical history, current treatment information, and past test results.

[0007] A "generative model" refers to an algorithm or software that uses artificial intelligence or machine learning techniques to generate the optimal output based on input data.

[0008] The "optimal doctor" refers to a medical professional with the most suitable expertise and experience for a patient's medical condition and treatment plan.

[0009] "Online diagnosis" refers to a method of providing medical care to patients via the internet.

[0010] "Consultation" refers to a patient asking a doctor questions about treatment plans or symptoms.

[0011] "Recording means" refers to systems and software used to input, store, and manage patient information.

[0012] "Storage means" refers to systems or devices that have the function of storing recorded patient information for a long period of time and retrieving it as needed.

[0013] "Selection method" refers to a system or software that utilizes generative models to select an appropriate physician based on patient information.

[0014] "Referral methods" refer to systems or software that present patients with information on selected doctors and support connections with them.

[0015] "Connection means" refers to communication methods used to connect patients and doctors online for diagnosis and consultation. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the 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.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0030] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. The embodiments for carrying out this invention are described below in detail.

[0038] System Overview

[0039] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of user terminals, a server, and physician terminals.

[0040] User registration and login

[0041] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[0042] Entering patient information

[0043] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor.

[0044] Selecting the optimal doctor

[0045] The server passes the recorded patient information to a generating AI model. The generating AI model selects the most suitable doctor for the patient's condition by comparing it with past case data. The list of selected doctors is saved in association with the patient information and presented to the user.

[0046] Doctor referral and appointment

[0047] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The appointment information is stored on the server and notified to the selected doctor. At this point, the server prepares for the online diagnosis or consultation between the user and the doctor.

[0048] Online diagnosis and consultation

[0049] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[0050] Specific example

[0051] 1. The user registers with the system, entering their name (Taro Yamada), email address (taro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[0052] 2. After logging in, user Yamada Taro enters his medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image).

[0053] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Taro Yamada (e.g., Dr. Sato at Hospital A).

[0054] 4. User Yamada Taro selects Dr. Sato and books an online consultation for next Tuesday at 2:00 PM.

[0055] 5. The server saves the reservation information and notifies Dr. Sato. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user.

[0056] As described above, this system provides a comprehensive and convenient service that allows cancer patients and their families to easily obtain high-quality second opinions.

[0057] The following describes the processing flow.

[0058] Step 1:

[0059] The user opens the service's website or mobile app.

[0060] Step 2:

[0061] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[0062] The terminal sends the entered information to the server.

[0063] Step 3:

[0064] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[0065] The server stores the operation results in the database and processes them for sending the email.

[0066] Step 4:

[0067] The user clicks the confirmation link in the email they received.

[0068] When the device clicks the link, it sends a request to the verification API endpoint.

[0069] Step 5:

[0070] The server receives the confirmation request and updates the user's status to "Confirmed".

[0071] The server saves the update results to the database and returns a success response.

[0072] Step 6:

[0073] The user enters their email address and password in the login form and clicks the "Login" button.

[0074] The terminal sends the entered information to the server.

[0075] Step 7:

[0076] The server verifies the authentication information, and if it is correct, creates a session and authenticates the user.

[0077] The server saves session information to the database and returns a response that includes an authentication token.

[0078] Step 8:

[0079] After logging in, the user enters their medical history, current treatment information, and past test results.

[0080] The terminal displays a medical history input form, and the user enters the information and clicks the submit button.

[0081] Step 9:

[0082] The server saves the received data to the database.

[0083] The server formats the data and inserts it into the database.

[0084] Step 10:

[0085] The server passes the stored patient information to the AI ​​model that generates the data.

[0086] The server extracts the required patient information and sends a request to the AI ​​model's API.

[0087] Step 11:

[0088] The generative AI model analyzes patient information and compares it with relevant past case data.

[0089] The generation AI model generates the optimal list of doctors and returns it to the server.

[0090] Step 12:

[0091] The server saves the generated list of doctors to the database and sends the results to the user.

[0092] The server formats the list of doctors and returns the response to the user.

[0093] Step 13:

[0094] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[0095] The terminal displays available reservation dates and times and sends the user's selection to the server.

[0096] Step 14:

[0097] The server saves the selected doctor and date / time to the booking system.

[0098] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[0099] Step 15:

[0100] The server sends the reservation confirmation result to the user.

[0101] The server sends a reservation confirmation email to the user.

[0102] Step 16:

[0103] The user accesses the app or website at the scheduled time.

[0104] The device verifies the reservation information and connects to the video call gateway.

[0105] Step 17:

[0106] The server creates a video call session and connects the doctor and the user.

[0107] The server calls the real-time communication API to start a session.

[0108] Step 18:

[0109] Users and doctors conduct online diagnoses and consultations.

[0110] The device sends and receives voice and video data, providing real-time communication.

[0111] Step 19:

[0112] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[0113] The server saves the diagnostic information to a database and sends a feedback email to the user.

[0114] (Example 1)

[0115] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0116] In modern medicine, it is difficult for cancer patients and their families to easily obtain high-quality second opinions. Furthermore, the diverse tasks involved, such as managing patient information, selecting the most suitable medical specialist, and arranging online consultations, are time-consuming and labor-intensive when performed manually. Moreover, while it is desirable to perform these processes quickly and accurately, systems for this are still lacking. To address these challenges and provide high-quality medical services to cancer patients and their families, there is a growing need for online second opinion services.

[0117] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0118] This invention includes a server that records and stores a patient's medical history information, current treatment information, and past test results; a server that sends a confirmation email to activate a user account; a server that allows the user to input patient information after logging in; a server that uses a generated AI model to select and introduce the most suitable medical professional based on the stored patient information; a server that connects medical professionals and patients online to conduct diagnoses and consultations; a server that stores and notifies medical professionals of appointment information for diagnoses and consultations; and a server that records and provides diagnoses and feedback. This makes it possible for cancer patients and their families to easily obtain high-quality second opinions.

[0119] "Medical history information" refers to information that shows a patient's past medical records and disease history.

[0120] "Treatment information" refers to information that describes the content and methods of treatment a patient is currently receiving.

[0121] "Test results" refer to information that shows the results and data of medical tests performed in the past.

[0122] A "confirmation email" is an email sent to verify the email address registered by the user and to activate their account.

[0123] A "user account" is an individual account that a user registers and authenticates in order to access and use a system.

[0124] A "generative AI model" is a model that uses artificial intelligence technology to select the most suitable medical professional based on past data.

[0125] A "medical professional" is a doctor or healthcare worker who possesses specialized knowledge and skills to address a patient's medical condition and case.

[0126] "Online diagnosis" refers to the process by which medical professionals provide diagnoses and consultations to patients via the internet.

[0127] "Reservation information" refers to information such as the date and time of online diagnosis or consultation, and the medical professional.

[0128] "Feedback" refers to information that provides evaluations, opinions, and advice after a diagnosis or consultation.

[0129] A "second opinion" refers to a diagnosis or opinion received from a medical professional other than your primary physician.

[0130] This invention relates to an online second opinion service aimed at enabling cancer patients and their families to easily obtain high-quality second opinions. The system primarily consists of a server, user terminals, and medical professional terminals. Detailed embodiments of this invention are described below.

[0131] User registration and login

[0132] When a user accesses the system, they first register. The user enters their name, email address, and password and submits them to the server. The server stores the received information in its database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, their account is activated. Next, the user enters their email address and password on the login screen and is authenticated. The server verifies the authentication information and allows the user to start a session.

[0133] Entering patient information

[0134] After the user logs in, they enter medical history information, current treatment information, and past test results on the patient information input screen. The user terminal sends the entered information to the server. The server stores the entered information in a database and formats the data as needed.

[0135] Selection of the most suitable medical professional

[0136] The server inputs stored patient information into a generative AI model. This generative AI model is built using Python's TensorFlow, among other tools. The generative AI model compares the patient's information with past case data and selects the most suitable medical professional for their condition. The server saves the list of selected medical professionals to a database and displays it to the user.

[0137] Referral and appointment scheduling for medical professionals

[0138] The user selects a preferred medical professional from a list of available professionals and chooses a date and time for an online diagnosis or consultation. The user's terminal sends the selection information to the server. The server stores the reservation information in a database and notifies the selected medical professional.

[0139] Online diagnosis and consultation

[0140] At the scheduled time, the user accesses the system and begins the online diagnosis. The server provides communication methods such as video calls and text chats, connecting the user with a medical professional. Real-time video calls are enabled using technologies such as WebRTC. After the diagnosis and consultation are completed, the server records the diagnosis details and feedback in a database and provides them to the user.

[0141] Specific example

[0142] The following are examples of specific prompt messages:

[0143] "The user registers with the system, entering their name (e.g., Patient A), email address (e.g., patientA@example.com), and password. They receive a confirmation email and click the link to activate their account. After user Patient A logs in, they enter their medical history (e.g., Stage III lung cancer), current treatment information (e.g., chemotherapy), and past test results (most recent CT scan image). The server passes this information to a generating AI model, which selects the most suitable medical professional. The generating AI model lists the most suitable medical professionals for Patient A based on past case data. User Patient A selects a medical professional and books an online consultation for next Tuesday at 2:00 PM. The server saves the reservation information and notifies the medical professional. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user."

[0144] Thus, the present invention provides a comprehensive and convenient service that enables cancer patients and their families to easily obtain high-quality second opinions.

[0145] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0146] Step 1:

[0147] The user accesses the new registration screen and enters their name, email address, and password.

[0148] Input: User's name, email address, and password.

[0149] Output: User information sent to the server.

[0150] Specific action: The user enters "Patient A", "patientA@example.com", and "password123" into the form fields and clicks the "Register" button.

[0151] Step 2:

[0152] The server saves the received information to the database and sends a confirmation email to the user.

[0153] Input: User's submitted name, email address, and password.

[0154] Output: User information stored in the database and a confirmation email sent to the user.

[0155] Specific operation: The server uses an email sending service (e.g., SendGrid) to send a "confirmation email".

[0156] Step 3:

[0157] The user activates their account by clicking the link in the confirmation email.

[0158] Input: The link included in the confirmation email.

[0159] Output: Request to the server and account activation.

[0160] Specific operation: When a user clicks a link in an email, a request is sent to a specific endpoint on the server, and the user's account is activated.

[0161] Step 4:

[0162] The user enters their email address and password on the login screen and undergoes authentication.

[0163] Enter: email address, password.

[0164] Output: Login request to the server and authentication information.

[0165] Specific action: The user enters "patientA@example.com" and "password123" and clicks the "Login" button.

[0166] Step 5:

[0167] The server verifies the authentication information and allows the user to start a session.

[0168] Input: User login request.

[0169] Output: Session started and JWT token generated.

[0170] Specific operation: The server checks the authentication information, creates a session upon success, generates a JWT token, and returns it to the user.

[0171] Step 6:

[0172] The user enters medical history information, current treatment details, and past test results on the patient information input screen.

[0173] Input: Medical history information, current treatment, past test results.

[0174] Output: Patient information sent to the server.

[0175] Specific operation: The user inputs "Lung cancer stage III", treatment "Chemotherapy", and test results "CT scan image".

[0176] Step 7:

[0177] The server saves the entered information to the database and formats the data as needed.

[0178] Input: Patient information submitted by the user.

[0179] Output: Patient information stored in the database.

[0180] Specific operation: The server formats the data and saves it to the appropriate field.

[0181] Step 8:

[0182] The server inputs patient information into an AI model, which then compares it with past case data to select the most suitable medical professional.

[0183] Input: Patient information.

[0184] Output: List of selected medical professionals.

[0185] Specific operation: The server inputs patient information into an AI model (using Python's TensorFlow), and the model selects the most suitable medical professional.

[0186] Step 9:

[0187] The server saves a list of selected medical professionals to a database and displays it to the user.

[0188] Input: A list of selected medical professionals.

[0189] Output: A list of medical professionals displayed to the user.

[0190] Specific operation: The server returns a list of medical professionals to the frontend to display on the user's dashboard.

[0191] Step 10:

[0192] Users can select their preferred medical professional and choose a date and time for an online diagnosis or consultation.

[0193] Input: Selection of medical professional and appointment date / time.

[0194] Output: Reservation information sent to the server.

[0195] Specific action: The user selects Dr. Sato and schedules an online consultation for next Tuesday at 2:00 PM.

[0196] Step 11:

[0197] The server saves the reservation information to a database and notifies the selected medical professional.

[0198] Input: Reservation information submitted by the user.

[0199] Output: Appointment information stored in the database and notifications to medical professionals.

[0200] Specific operation: The server notifies medical professionals of the appointment information via email or in-app notifications.

[0201] Step 12:

[0202] The user accesses the system at the scheduled time and begins the online diagnosis.

[0203] Input: Reservation date and time and access information.

[0204] Output: Online diagnosis initiated.

[0205] Specific action: The user accesses the specified URL and enters the video call screen.

[0206] Step 13:

[0207] The server provides communication methods such as video calls and text chats, connecting medical professionals and users.

[0208] Input: Communication request between user and medical professional.

[0209] Output: Connects to video calls and text chats.

[0210] Specific operation: The server uses technologies such as WebRTC to enable real-time video calls.

[0211] Step 14:

[0212] After the diagnosis and consultation are complete, the server records the diagnosis details and feedback in a database and provides them to the user.

[0213] Input: Diagnostic details, feedback.

[0214] Output: Diagnostic information recorded in the database and feedback to the user.

[0215] Specific action: The server saves the diagnostic report and displays it on the user's dashboard.

[0216] The above describes the processing steps of the system of the present invention.

[0217] (Application Example 1)

[0218] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0219] Traditionally, when cancer patients and their families sought high-quality second opinions, managing information was cumbersome, and the risk of personal information leaks was high. Furthermore, the accuracy of selecting appropriate doctors was low, and the procedures for booking online diagnoses and consultations were complicated, placing a heavy burden on patients and their families. In addition, concerns about the security of digital data acted as a barrier to using online services. To solve these problems, a system is needed that processes medical information safely and efficiently and provides high-quality medical services.

[0220] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0221] In this invention, the server includes means for recording and storing patient medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable physician based on the stored patient information using a generative model; means for connecting physicians and patients online to conduct diagnoses and consultations; means for storing patient information in encryption; and means for encrypting and authenticating user information. This makes it possible to securely manage patient and user information and efficiently provide high-quality second opinions.

[0222] "Patient medical history information" refers to detailed information about a patient's past illnesses and treatments.

[0223] "Current treatment information" refers to information about the treatment a patient is currently receiving.

[0224] "Past test results" refers to information about the results of tests the patient has received in the past.

[0225] "Means of recording and preserving" refers to devices and systems for collecting and electronically storing patient information.

[0226] "Stored patient information" refers to information about patients that is recorded within the system and stored in a database or similar location.

[0227] The term "optimal physician" refers to a medical professional best suited to a patient's condition, as determined by a generative model.

[0228] A "generative model" is an algorithm or machine learning model designed to perform a specific task based on past case data.

[0229] "Means of selection and referral" refers to a mechanism that uses generative models to select appropriate doctors and provide that information to patients.

[0230] "A means of connecting doctors and patients online for diagnosis and consultation" refers to a system that provides an environment where doctors and patients can communicate directly using the internet and digital communication.

[0231] "Methods for encrypting and storing patient information" refers to methods of securely storing patient information in the form of digital data by encrypting it.

[0232] "Methods for encrypting and authenticating user information" refers to a mechanism that encrypts and stores user identification information and uses it during authentication.

[0233] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. To implement this invention, key functions include user registration and login, input of patient information, selection of the most suitable doctor, doctor referral and appointment scheduling, online diagnosis and consultation, and data encryption and storage.

[0234] 1. User registration and login

[0235] Users on their terminals enter basic information such as their name, email address, and password to register. The entered data is received by the server and encrypted using Fernet encryption technology. The encrypted data is securely stored in the database. Users receive a confirmation email and can log in by clicking the link to activate their account.

[0236] 2. Entering patient information

[0237] After logging in, users enter their medical history, current treatment information, and past test results. This information is also encrypted by the server and stored in the database. This step ensures that patient information is securely managed within the system.

[0238] 3. Selection of the most suitable physician

[0239] The server passes the stored patient information to a generating AI model. The generating AI model compares it with past case data and executes prompts to select the most suitable doctor for the patient. The list of selected doctors is presented to the user terminal, associated with the patient information.

[0240] 4. Doctor referral and appointment

[0241] From the presented list of doctors, users select their preferred doctor and book an appointment for an online diagnosis or consultation. The booking information is encrypted by the server and stored in a database. The selected doctor is notified of the booking information and is ready for the online diagnosis or consultation.

[0242] 5. Implementation of online diagnosis and consultation

[0243] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chats, connecting the user's terminal and the doctor's terminal. After the diagnosis and consultation are completed, the diagnosis and feedback are encrypted by the server and provided to the user's terminal.

[0244] Adding specific examples

[0245] 1. The user registers with the system, entering their name (e.g., Ichiro Tanaka), email address (e.g., ichiro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[0246] 2. After logging in, user Ichiro Tanaka enters his medical history information (e.g., stage II gastric cancer), current treatment (e.g., radiation therapy), and past test results (most recent MRI images).

[0247] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Ichiro Tanaka (e.g., Dr. Yamada at Hospital B).

[0248] 4. User Ichiro Tanaka selects Dr. Yamada and books an online consultation for next Wednesday at 2:30 PM.

[0249] 5. The server saves the reservation information and notifies Dr. Yamada. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server encrypts and records the consultation details and sends feedback to the user.

[0250] Example prompts for generative AI models

[0251] Cancer patient information: Stage II gastric cancer, current treatment: radiation therapy, past test results: latest MRI images. Please select the best doctor for this patient.

[0252] The system of the present invention can manage the entire process from user registration to online diagnosis in a highly secure and efficient manner. As a result, cancer patients and their families can obtain high-quality second opinions with peace of mind.

[0253] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0254] Step 1:

[0255] User registration information (name, email address, password) is entered from the user's terminal. The server receives this information and encrypts it using Fernet encryption technology. The encrypted data is stored in the database. The output is that the encrypted user information is stored in the database.

[0256] Step 2:

[0257] After registration is complete, the server sends a confirmation email. The user's device activates the account by clicking the link in the confirmation email. The input is clicking the link in the confirmation email, and the output is account activation.

[0258] Step 3:

[0259] The user enters login information (email address, password) from their terminal. The server decrypts the encrypted data in the database and verifies that it matches. The input is the login information, and the output is the result of successful or unsuccessful login authentication.

[0260] Step 4:

[0261] After successful login, patient information (medical history, current treatment information, past test results) is entered from the user's terminal. The server then encrypts this information again using Fernet encryption technology and stores it in the database. The input is patient information, and the output is the storage of encrypted patient information.

[0262] Step 5:

[0263] The server passes patient information from the database to a generating AI model. The generating AI model compares this information with past case data and selects the most suitable doctor for the patient based on the prompt text. The input is encrypted patient information and prompt text, and the output is a list of suitable doctors.

[0264] Step 6:

[0265] A list of suitable doctors is presented to the user's terminal. The user selects a desired doctor from the list and enters the date and time for an online diagnosis or consultation. The input consists of the desired doctor and the date and time of the diagnosis, and the output is the generation of reservation information.

[0266] Step 7:

[0267] The server encrypts the reservation information and stores it in a database. Furthermore, it notifies the selected physicians of the reservation information. The input is the reservation information, and the output is the storage and notification of the encrypted reservation information.

[0268] Step 8:

[0269] At the scheduled time, the user participates in the online diagnosis and consultation. The server manages video calls and text chats and connects the user's terminal with the doctor's terminal. The input is a request to start the online diagnosis, and the output is the start of the diagnosis and consultation session.

[0270] Step 9:

[0271] After the diagnosis and consultation are complete, the server encrypts and records the diagnosis details and feedback, and provides them to the user's terminal. The input is the diagnosis details and feedback, and the output is the storage and provision of encrypted diagnostic data.

[0272] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0273] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and more particularly to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis / consultation.

[0274] System Overview

[0275] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of a user terminal, a server, a physician's terminal, and an emotion engine.

[0276] User registration and login

[0277] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[0278] Entering patient information

[0279] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, the user's input data includes text, audio, and video data, which an emotion engine analyzes to recognize the user's emotions.

[0280] Selecting the optimal doctor

[0281] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[0282] Introduction and Reservation of Doctors

[0283] From the presented list of doctors, the user selects the desired doctor and reserves the time for an online diagnosis or consultation. The reservation information is saved on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis and consultation.

[0284] Conducting Online Diagnosis and Consultation

[0285] At the reserved time, the user participates in the online diagnosis and consultation. The server provides communication means such as video calls and text chats to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis content and feedback and provides them to the user.

[0286] Specific Example

[0287] (1) The user newly registers with the system, enters their name (Ichiro Tanaka), email address (ichiro@example.com), and password. Receives a confirmation email and clicks the link to activate the account.

[0288] (2) After logging in, Ichiro Tanaka enters his medical history information (e.g., lung cancer stage III), current treatment (e.g., chemotherapy), and past test results (latest CT scan images). Additionally, during the input, the emotion engine analyzes the text and voice data and recognizes Ichiro Tanaka's emotion as "uneasy".

[0289] (3) The server passes the patient information and emotion data to the generative AI model, and the generative AI model selects the optimal doctor (e.g., Dr. Nakamura at Hospital B). Based on the emotion data, it is considered that Dr. Nakamura has the expertise to relieve the patient's uneasiness.

[0290] (4) Ichiro Tanaka, the user, selects Dr. Nakamura and reserves an online diagnosis for next Thursday at 16:00.

[0291] 5. The server saves the reservation information and notifies Dr. Nakamura. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. Dr. Nakamura uses Ichiro Tanaka's emotional data as a reference to take an approach that reduces anxiety.

[0292] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to Ichiro Tanaka.

[0293] As described above, this system provides a comprehensive and convenient service that combines an emotional engine to easily enable cancer patients and their families to obtain high-quality second opinions.

[0294] The following describes the processing flow.

[0295] Step 1:

[0296] The user opens the service's website or mobile app.

[0297] Step 2:

[0298] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[0299] The terminal sends the entered information to the server.

[0300] Step 3:

[0301] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[0302] The server stores the operation results in the database and processes them for sending the email.

[0303] Step 4:

[0304] The user clicks the confirmation link in the email they received.

[0305] When the terminal clicks on the link, a request is sent to the verification API endpoint.

[0306] Step 5:

[0307] The server receives the verification request and updates the user's status to "verified".

[0308] The server saves the update result to the database and returns a successful response.

[0309] Step 6:

[0310] The user enters their email address and password in the login form and clicks the "Login" button.

[0311] The terminal sends the entered information to the server.

[0312] Step 7:

[0313] The server verifies the authentication information and, if correct, generates a session to authenticate the user.

[0314] The server saves the session information to the database and returns a response containing an authentication token.

[0315] Step 8:

[0316] After the user logs in, they enter their medical history information, current treatment information, and past test results.

[0317] The terminal displays the medical history input form, and after the user enters the information, they click the send button.

[0318] Step 9:

[0319] The server saves the received patient information and text, audio, and video data to the database.

[0320] The server formats the data and inserts it into the database.

[0321] Step 10:

[0322] The emotion engine analyzes the user's text, voice, and video data to recognize their emotions.

[0323] The emotion engine generates emotion data and returns the results to the server.

[0324] Step 11:

[0325] The server passes stored patient information and emotional data to the generating AI model.

[0326] The server extracts the required patient information and sends a request to the AI ​​model's API.

[0327] Step 12:

[0328] The generative AI model analyzes patient information and emotional data, and compares it with relevant past case data.

[0329] The generation AI model generates the optimal list of doctors and returns it to the server.

[0330] Step 13:

[0331] The server saves the generated list of doctors to the database and sends the results to the user.

[0332] The server formats the list of doctors and returns the response to the user.

[0333] Step 14:

[0334] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[0335] The terminal displays available reservation dates and times and sends the user's selection to the server.

[0336] Step 15:

[0337] The server saves the selected doctor and date / time to the booking system.

[0338] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[0339] Step 16:

[0340] The server sends the reservation confirmation result to the user.

[0341] The server sends a reservation confirmation email to the user.

[0342] Step 17:

[0343] The user accesses the app or website at the scheduled time.

[0344] The device verifies the reservation information and connects to the video call gateway.

[0345] Step 18:

[0346] The server creates a video call session and connects the doctor and the user.

[0347] The server calls the real-time communication API to start a session.

[0348] Step 19:

[0349] Users and doctors conduct online diagnoses and consultations.

[0350] The device sends and receives voice and video data, providing real-time communication.

[0351] Doctors refer to the user's emotional data to adjust diagnoses and advice.

[0352] Step 20:

[0353] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[0354] The server saves the diagnostic information to a database and sends a feedback email to the user.

[0355] (Example 2)

[0356] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0357] There is a need for a system that allows cancer patients and their families to easily and quickly obtain high-quality second opinions. In particular, it is crucial to improve the quality of physician selection, diagnosis, and consultation, taking into account the patient's feelings, but the current system struggles to meet these requirements. Conventional systems have the problem of selecting physicians without considering the patient's feelings, thus failing to alleviate the psychological burden on the patient.

[0358] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0359] In this invention, the server includes means for recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable doctor based on the stored patient information using a generative model; means for analyzing input text, voice, and video data to recognize the patient's emotions; means for selecting the most suitable doctor for the patient based on the recognized emotion data; means for connecting the doctor and patient online to conduct diagnoses and consultations; and means for recording and providing the diagnosis and feedback to the patient. This makes it possible to select a doctor that takes the patient's emotions into consideration, thereby reducing the patient's psychological burden and providing a system that makes it easy to obtain a high-quality second opinion.

[0360] "Patient medical history information" refers to details of illnesses and treatments that a patient has experienced in the past and present, including diagnoses, symptoms, and treatment history.

[0361] "Treatment information" refers to the type and method of treatment a patient is currently receiving, and includes information such as medication, surgery, radiation therapy, and chemotherapy.

[0362] "Test results" refer to the results of medical examinations performed on a patient, and include data from blood tests, imaging diagnostics (CT scans, MRI, etc.), and biopsies.

[0363] A "database" refers to a system for electronically storing and managing information, such as patient information, doctor information, and emotional data.

[0364] An "emotion engine" refers to software and algorithms that analyze input data (text, audio, video, etc.) and automatically identify emotions.

[0365] A "generative model" refers to an AI (artificial intelligence) algorithm that makes new predictions or generates new data based on past data, and it utilizes machine learning and deep learning technologies.

[0366] "Online diagnosis" refers to the process of diagnosing a patient via the internet, and this includes video calls and text chats.

[0367] "Feedback" refers to the opinions and advice that doctors provide to patients after an online diagnosis or consultation, and includes diagnostic results, treatment suggestions, and information about additional tests.

[0368] The "reservation function" refers to a feature within the system that allows patients to reserve a date and time for diagnosis or consultation online in advance.

[0369] "Communication methods" refer to technologies used to connect doctors and patients in online diagnoses and consultations, and include video calls, voice calls, and text chats.

[0370] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and moreover, to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis and consultation.

[0371] This system primarily consists of user terminals, a server, a doctor's terminal, and an emotion engine. User terminals are devices used by users to access the system and input information, including personal computers, smartphones, and tablets. The server is a computer system for managing, analyzing, and storing information, and includes databases, generative AI models, and an emotion engine.

[0372] User registration and login

[0373] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[0374] Entering patient information

[0375] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, user input data includes text, audio, and video data, which the emotion engine analyzes to recognize the user's emotions. For example, the IBM Watson Sentiment Analysis API can be used for text data, and the API can be used to analyze emotions for audio data.

[0376] Selecting the optimal doctor

[0377] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[0378] Doctor referral and appointment

[0379] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The reservation information is stored on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis or consultation.

[0380] Online diagnosis and consultation

[0381] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. For example, it may use the Zoom API or Twilio API to provide video call functionality. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[0382] Specific example

[0383] 1. The user registers with the system, entering their name, email address, and password. They receive a confirmation email and click the link to activate their account.

[0384] 2. After logging in, the user enters their medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image). Furthermore, during the input process, the emotion engine analyzes the text and voice data and recognizes the user's emotion as "anxiety."

[0385] 3. The server passes patient information and emotional data to a generating AI model, which then selects the most suitable doctor. For example, a doctor with expertise in reducing patient anxiety based on emotional data might be selected.

[0386] 4. The user selects a doctor and books an online consultation.

[0387] 5. The server saves the appointment information and notifies the doctor. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. The doctor uses the user's emotional data to implement an approach that reduces anxiety.

[0388] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to the user.

[0389] Example of a prompt

[0390] The following are examples of prompts to input into a generative AI model:

[0391] Patient information:

[0392] Medical history: Stage III lung cancer

[0393] Current treatment: Chemotherapy

[0394] Previous test results: Latest CT scan images

[0395] Emotional data:

[0396] Emotion: Anxiety

[0397] Criteria for selecting the best doctor:

[0398] 1. Expertise in lung cancer

[0399] 2. Communication skills to alleviate patient anxiety

[0400] Please select the most suitable doctor based on the above conditions.

[0401] The above describes specific embodiments for carrying out the present invention.

[0402] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0403] Step 1: User registration and verification

[0404] The user accesses the system's website and enters basic information such as their name, email address, and password.

[0405] (Input): User's basic information (name, email address, password)

[0406] (Output): Request to send confirmation email

[0407] The server will send a confirmation email to the email address you entered. This email will contain a link to activate your account.

[0408] (Input): User's email address

[0409] (Output): Confirmation email (with link)

[0410] The user clicks the link in the confirmation email to activate their account.

[0411] (Input): Clicked the link in the confirmation email

[0412] (Output): Account activation

[0413] Step 2: Log in

[0414] Users log in using their email address and password.

[0415] (Enter): Email address, password

[0416] (Output): Login success or failure message

[0417] Step 3: Entering patient information and sentiment analysis

[0418] After logging in, the user enters their medical history, current treatment information, and past test results.

[0419] (Input): Medical history information, treatment information, test results

[0420] (Output): Request to save input data

[0421] The server saves the input data to the database.

[0422] (Input): Patient information

[0423] (Output): Database save success message

[0424] The device sends text, audio, and video data to the emotion engine for analysis.

[0425] Example: Using the IBM Watson Sentiment Analysis API

[0426] (Input): Text, audio, and video data

[0427] (Output): Emotion analysis results (e.g., "anxiety")

[0428] Step 4: Selecting a physician

[0429] The server generates prompt messages to pass patient information and emotional data to the AI ​​model.

[0430] (Input): Patient information, emotional data

[0431] (Output): Prompt message

[0432] The generative AI model selects the most suitable doctor based on the prompt text.

[0433] (Input): Prompt message

[0434] (Output): Doctor list

[0435] The server presents the user with a list of selected doctors.

[0436] (Input): Doctor list

[0437] (Output): Doctor list displayed on user screen

[0438] Step 5: Doctor referral and appointment

[0439] Users select a doctor from a list of doctors provided and book an online consultation or appointment.

[0440] (Input): Selected doctor, preferred date and time

[0441] (Output): Reservation Request

[0442] The server saves the reservation information to the database and sends a notification to the selected doctor.

[0443] (Input): Reservation information

[0444] (Output): Database saved successfully, notification sent to physician.

[0445] Step 6: Conducting online diagnosis and consultation

[0446] At the scheduled time, the server will provide communication methods such as video calls and text chats.

[0447] Example: Using the Zoom API or Twilio API

[0448] (Input): Reservation date and time

[0449] (Output): Provides communication interface

[0450] Users participate in online diagnostics, and doctors provide diagnoses and consultations.

[0451] (Input): User participation, Doctor participation

[0452] (Output): Diagnosis and consultation implemented.

[0453] Step 7: Processing after diagnosis is complete

[0454] The server records diagnostic information and feedback in a database.

[0455] (Input): Diagnostic details, feedback

[0456] (Output: Database save successful)

[0457] The server sends feedback to the user.

[0458] (Input): Feedback

[0459] (Output): Feedback notification

[0460] The above is a description of this system's program, broken down into processing steps and including specific operations.

[0461] (Application Example 2)

[0462] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0463] There are few systems that allow users facing security issues to easily seek a second opinion from a suitable security expert. Furthermore, there is a lack of systems that provide customized support to reduce the psychological burden on users. In particular, there is a need to provide a higher-quality consultation experience by considering the user's emotional state.

[0464] The identification processing performed by the identification 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 recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable specialist based on the stored patient information using a generation model; means for analyzing the patient's emotions using an emotion engine; means for selecting the most suitable specialist based on the analyzed emotions, connecting the specialist and the patient online, and conducting diagnoses and consultations; and means for providing a reservation function. This makes it possible for users to easily access appropriate security specialists and obtain high-quality second opinions while reducing psychological burden.

[0465] "Patient medical history information" refers to information such as the illnesses, symptoms, and treatment history of the patient that they have suffered from in the past.

[0466] "Current treatment information" refers to information about the treatment a patient is currently receiving and its progress.

[0467] "Past test results" refers to data on diagnoses and test results that the patient has received in the past.

[0468] A "generative model" is an artificial intelligence algorithm used to select the most suitable expert based on collected data.

[0469] An "emotion engine" is a system that analyzes user input data and recognizes their emotional state.

[0470] The "reservation function" is a feature that allows users to specify the date and time for online diagnoses or consultations and make reservations.

[0471] A "specialist" is a professional who is well-versed in a particular field and capable of providing appropriate advice and diagnoses.

[0472] "Online diagnosis" refers to the act of a specialist diagnosing a patient's condition via the internet.

[0473] "Consultation" refers to the act of a specialist providing expert opinions and advice in response to questions and concerns from patients or users.

[0474] An "optimal specialist" is a professional who can provide the most appropriate response based on the patient's symptoms and emotional state.

[0475] This invention relates to an online consultation system for security services. Specifically, it includes a series of processes for analyzing the user's emotions, selecting the most suitable security expert, and connecting them online. Specific embodiments of this system are described below.

[0476] User terminal

[0477] Users access the system using a smartphone or PC. An account is created when a user registers and enters their name, email address, and password. After registration, they receive a confirmation email, click the link to activate their account, and log in. Users enter information about their security issues and past countermeasures. During this process, an emotion engine analyzes this data to recognize the user's emotional state.

[0478] Emotional Engine

[0479] The emotion engine utilizes technologies such as IBM Watson and Microsoft Azure Cognitive Services. It analyzes user-input text and voice data and tags them with emotions. For example, it recognizes emotions like "reassurance," "anxiety," and "doubt." This allows for a quantitative assessment of the user's psychological burden.

[0480] server

[0481] The servers are operated using AWS EC2, Google Cloud Platform, etc. The servers record user information and sentiment data and pass this to a generative AI model. Using generative AI models such as OpenAI GPT-4, the most suitable security expert is selected based on the user's information and sentiment. The selection process includes matching against past case data.

[0482] Generative AI Models

[0483] The generative AI model selects the most suitable expert for the user based on the collected data. This model, known as a "generative AI model," learns from past case data and similar cases. An example of a prompt is shown below:

[0484] USER: Regarding the hacking prevention meeting scheduled for Wednesday afternoon, how can I choose a security expert who will help alleviate my concerns?

[0485] Assistant:

[0486] Expert selection and booking

[0487] A list of experts selected by the server is presented to the user. The user selects their preferred expert and books an online consultation time. Reservation information is managed using the Google Calendar API and Microsoft Outlook API.

[0488] Online diagnosis and consultation

[0489] At the scheduled time, the server initiates a video call using the Zoom API or Google Meet API. The expert and the user connect to conduct a diagnosis and consultation. The diagnosis and feedback are recorded and provided to the user. This allows the user to obtain a high-quality second opinion while reducing psychological burden.

[0490] As a concrete example, a user registers an account and enters a security concern after logging in. At this point, the emotion engine recognizes this as "anxiety." The generative AI model selects the most suitable expert based on the provided information and emotion data, and schedules an online consultation at the user's preferred date and time. A video call begins at the scheduled time, and the expert takes an approach to alleviate the user's anxiety.

[0491] This allows users to easily receive advice from appropriate experts when they face security issues, thereby reducing their psychological burden.

[0492] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0493] Step 1:

[0494] The user terminal provides an interface for users to register with the system. The user enters their name, email address, and password, and presses the registration button. The server receives the input data, creates the account using Firebase Authentication or Auth0, and sends a confirmation email. The user activates their account by clicking the link in the confirmation email and can then log in.

[0495] Input: Name, email address, password

[0496] Output: Account creation confirmation email

[0497] Step 2:

[0498] The user terminal provides a login interface. The user logs in through this interface and begins the process of entering their security issues and past countermeasures. For example, they might enter details such as "the system is frequently being hacked." The entered data is sent to the server in text format.

[0499] Input: Email address, password, security information

[0500] Output: Sending security information to the server

[0501] Step 3:

[0502] The server sends the received security information to the emotion engine, which analyzes the text data to recognize the user's emotions. The emotion engine uses IBM Watson or Microsoft Azure Cognitive Services. The analysis results are output in formats such as "reassured," "anxious," and "doubtful."

[0503] Input: Text data of security information

[0504] Output: Emotional state (e.g., "anxiety")

[0505] Step 4:

[0506] The server passes user information and sentiment data to a generative AI model. The generative AI model uses OpenAI GPT-4 to analyze this data and compare it with past case data to select the most suitable security expert. The selection results are output as a list of multiple experts.

[0507] Input: User information, sentiment data

[0508] Output: List of experts

[0509] Step 5:

[0510] The user's terminal displays a list of experts received from the server. The user selects a desired expert from the list, specifies a date and time for the online consultation, and makes a reservation. The server manages the reservation information using the Google Calendar API or Microsoft Outlook API and notifies the selected expert.

[0511] Input: List of experts, preferred consultation date and time

[0512] Output: Saving of reservation information and notification to experts

[0513] Step 6:

[0514] The server initiates the video call at the scheduled time. It uses the Zoom API or Google Meet API to connect the expert and the user. The user then consults with the expert online to receive diagnosis and advice.

[0515] Input: Reservation information, Start video call

[0516] Output: Implementation of online consultations

[0517] Step 7:

[0518] The server records the diagnosis and feedback after the online consultation ends and provides it to the user's device. Users can access this information at a later date. The data is stored in Google Cloud Storage or Amazon S3.

[0519] Input: Content of online consultation

[0520] Output: Diagnostic results, feedback

[0521] Through these steps, users can easily receive advice from appropriate security experts and get personalized, emotion-based responses.

[0522] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0523] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0524] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0525] [Second Embodiment]

[0526] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0527] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0528] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0529] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0530] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0531] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0532] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0533] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0534] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0535] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0536] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0537] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0538] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. The embodiments for carrying out this invention are described below in detail.

[0539] System Overview

[0540] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of user terminals, a server, and physician terminals.

[0541] User registration and login

[0542] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[0543] Entering patient information

[0544] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor.

[0545] Selecting the optimal doctor

[0546] The server passes the recorded patient information to a generating AI model. The generating AI model selects the most suitable doctor for the patient's condition by comparing it with past case data. The list of selected doctors is saved in association with the patient information and presented to the user.

[0547] Doctor referral and appointment

[0548] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The appointment information is stored on the server and notified to the selected doctor. At this point, the server prepares for the online diagnosis or consultation between the user and the doctor.

[0549] Online diagnosis and consultation

[0550] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[0551] Specific example

[0552] 1. The user registers with the system, entering their name (Taro Yamada), email address (taro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[0553] 2. After logging in, user Yamada Taro enters his medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image).

[0554] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Taro Yamada (e.g., Dr. Sato at Hospital A).

[0555] 4. User Yamada Taro selects Dr. Sato and books an online consultation for next Tuesday at 2:00 PM.

[0556] 5. The server saves the reservation information and notifies Dr. Sato. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user.

[0557] As described above, this system provides a comprehensive and convenient service that allows cancer patients and their families to easily obtain high-quality second opinions.

[0558] The following describes the processing flow.

[0559] Step 1:

[0560] The user opens the service's website or mobile app.

[0561] Step 2:

[0562] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[0563] The terminal sends the entered information to the server.

[0564] Step 3:

[0565] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[0566] The server stores the operation results in the database and processes them for sending the email.

[0567] Step 4:

[0568] The user clicks the confirmation link in the email they received.

[0569] When the device clicks the link, it sends a request to the verification API endpoint.

[0570] Step 5:

[0571] The server receives the confirmation request and updates the user's status to "Confirmed".

[0572] The server saves the update results to the database and returns a success response.

[0573] Step 6:

[0574] The user enters their email address and password in the login form and clicks the "Login" button.

[0575] The terminal sends the entered information to the server.

[0576] Step 7:

[0577] The server verifies the authentication information, and if it is correct, creates a session and authenticates the user.

[0578] The server saves session information to the database and returns a response that includes an authentication token.

[0579] Step 8:

[0580] After logging in, the user enters their medical history, current treatment information, and past test results.

[0581] The terminal displays a medical history input form, and the user enters the information and clicks the submit button.

[0582] Step 9:

[0583] The server saves the received data to the database.

[0584] The server formats the data and inserts it into the database.

[0585] Step 10:

[0586] The server passes the stored patient information to the AI ​​model that generates the data.

[0587] The server extracts the required patient information and sends a request to the AI ​​model's API.

[0588] Step 11:

[0589] The generative AI model analyzes patient information and compares it with relevant past case data.

[0590] The generation AI model generates the optimal list of doctors and returns it to the server.

[0591] Step 12:

[0592] The server saves the generated list of doctors to the database and sends the results to the user.

[0593] The server formats the list of doctors and returns the response to the user.

[0594] Step 13:

[0595] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[0596] The terminal displays available reservation dates and times and sends the user's selection to the server.

[0597] Step 14:

[0598] The server saves the selected doctor and date / time to the booking system.

[0599] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[0600] Step 15:

[0601] The server sends the reservation confirmation result to the user.

[0602] The server sends a reservation confirmation email to the user.

[0603] Step 16:

[0604] The user accesses the app or website at the scheduled time.

[0605] The device verifies the reservation information and connects to the video call gateway.

[0606] Step 17:

[0607] The server creates a video call session and connects the doctor and the user.

[0608] The server calls the real-time communication API to start a session.

[0609] Step 18:

[0610] Users and doctors conduct online diagnoses and consultations.

[0611] The device sends and receives voice and video data, providing real-time communication.

[0612] Step 19:

[0613] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[0614] The server saves the diagnostic information to a database and sends a feedback email to the user.

[0615] (Example 1)

[0616] Next, we will describe Example 1. 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."

[0617] In modern medicine, it is difficult for cancer patients and their families to easily obtain high-quality second opinions. Furthermore, the diverse tasks involved, such as managing patient information, selecting the most suitable medical specialist, and arranging online consultations, are time-consuming and labor-intensive when performed manually. Moreover, while it is desirable to perform these processes quickly and accurately, systems for this are still lacking. To address these challenges and provide high-quality medical services to cancer patients and their families, there is a growing need for online second opinion services.

[0618] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0619] This invention includes a server that records and stores a patient's medical history information, current treatment information, and past test results; a server that sends a confirmation email to activate a user account; a server that allows the user to input patient information after logging in; a server that uses a generated AI model to select and introduce the most suitable medical professional based on the stored patient information; a server that connects medical professionals and patients online to conduct diagnoses and consultations; a server that stores and notifies medical professionals of appointment information for diagnoses and consultations; and a server that records and provides diagnoses and feedback. This makes it possible for cancer patients and their families to easily obtain high-quality second opinions.

[0620] "Medical history information" refers to information that shows a patient's past medical records and disease history.

[0621] "Treatment information" refers to information that describes the content and methods of treatment a patient is currently receiving.

[0622] "Test results" refer to information that shows the results and data of medical tests performed in the past.

[0623] A "confirmation email" is an email sent to verify the email address registered by the user and to activate their account.

[0624] A "user account" is an individual account that a user registers and authenticates in order to access and use a system.

[0625] A "generative AI model" is a model that uses artificial intelligence technology to select the most suitable medical professional based on past data.

[0626] A "medical professional" is a doctor or healthcare worker who possesses specialized knowledge and skills to address a patient's medical condition and case.

[0627] "Online diagnosis" refers to the process by which medical professionals provide diagnoses and consultations to patients via the internet.

[0628] "Reservation information" refers to information such as the date and time of online diagnosis or consultation, and the medical professional.

[0629] "Feedback" refers to information that provides evaluations, opinions, and advice after a diagnosis or consultation.

[0630] A "second opinion" refers to a diagnosis or opinion received from a medical professional other than your primary physician.

[0631] This invention relates to an online second opinion service aimed at enabling cancer patients and their families to easily obtain high-quality second opinions. The system primarily consists of a server, user terminals, and medical professional terminals. Detailed embodiments of this invention are described below.

[0632] User registration and login

[0633] When a user accesses the system, they first register. The user enters their name, email address, and password and submits them to the server. The server stores the received information in its database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, their account is activated. Next, the user enters their email address and password on the login screen and is authenticated. The server verifies the authentication information and allows the user to start a session.

[0634] Entering patient information

[0635] After the user logs in, they enter medical history information, current treatment information, and past test results on the patient information input screen. The user terminal sends the entered information to the server. The server stores the entered information in a database and formats the data as needed.

[0636] Selection of the most suitable medical professional

[0637] The server inputs stored patient information into a generative AI model. This generative AI model is built using Python's TensorFlow, among other tools. The generative AI model compares the patient's information with past case data and selects the most suitable medical professional for their condition. The server saves the list of selected medical professionals to a database and displays it to the user.

[0638] Referral and appointment scheduling for medical professionals

[0639] The user selects a preferred medical professional from a list of available professionals and chooses a date and time for an online diagnosis or consultation. The user's terminal sends the selection information to the server. The server stores the reservation information in a database and notifies the selected medical professional.

[0640] Online diagnosis and consultation

[0641] At the scheduled time, the user accesses the system and begins the online diagnosis. The server provides communication methods such as video calls and text chats, connecting the user with a medical professional. Real-time video calls are enabled using technologies such as WebRTC. After the diagnosis and consultation are completed, the server records the diagnosis details and feedback in a database and provides them to the user.

[0642] Specific example

[0643] The following are examples of specific prompt messages:

[0644] "The user registers with the system, entering their name (e.g., Patient A), email address (e.g., patientA@example.com), and password. They receive a confirmation email and click the link to activate their account. After user Patient A logs in, they enter their medical history (e.g., Stage III lung cancer), current treatment information (e.g., chemotherapy), and past test results (most recent CT scan image). The server passes this information to a generating AI model, which selects the most suitable medical professional. The generating AI model lists the most suitable medical professionals for Patient A based on past case data. User Patient A selects a medical professional and books an online consultation for next Tuesday at 2:00 PM. The server saves the reservation information and notifies the medical professional. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user."

[0645] Thus, the present invention provides a comprehensive and convenient service that enables cancer patients and their families to easily obtain high-quality second opinions.

[0646] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0647] Step 1:

[0648] The user accesses the new registration screen and enters their name, email address, and password.

[0649] Input: User's name, email address, and password.

[0650] Output: User information sent to the server.

[0651] Specific action: The user enters "Patient A", "patientA@example.com", and "password123" into the form fields and clicks the "Register" button.

[0652] Step 2:

[0653] The server saves the received information to the database and sends a confirmation email to the user.

[0654] Input: User's submitted name, email address, and password.

[0655] Output: User information stored in the database and a confirmation email sent to the user.

[0656] Specific operation: The server uses an email sending service (e.g., SendGrid) to send a "confirmation email".

[0657] Step 3:

[0658] The user activates their account by clicking the link in the confirmation email.

[0659] Input: The link included in the confirmation email.

[0660] Output: Request to the server and account activation.

[0661] Specific operation: When a user clicks a link in an email, a request is sent to a specific endpoint on the server, and the user's account is activated.

[0662] Step 4:

[0663] The user enters their email address and password on the login screen and undergoes authentication.

[0664] Enter: email address, password.

[0665] Output: Login request to the server and authentication information.

[0666] Specific action: The user enters "patientA@example.com" and "password123" and clicks the "Login" button.

[0667] Step 5:

[0668] The server verifies the authentication information and allows the user to start a session.

[0669] Input: User login request.

[0670] Output: Session started and JWT token generated.

[0671] Specific operation: The server checks the authentication information, creates a session upon success, generates a JWT token, and returns it to the user.

[0672] Step 6:

[0673] The user enters medical history information, current treatment details, and past test results on the patient information input screen.

[0674] Input: Medical history information, current treatment, past test results.

[0675] Output: Patient information sent to the server.

[0676] Specific operation: The user inputs "Lung cancer stage III", treatment "Chemotherapy", and test results "CT scan image".

[0677] Step 7:

[0678] The server saves the entered information to the database and formats the data as needed.

[0679] Input: Patient information submitted by the user.

[0680] Output: Patient information stored in the database.

[0681] Specific operation: The server formats the data and saves it to the appropriate field.

[0682] Step 8:

[0683] The server inputs patient information into an AI model, which then compares it with past case data to select the most suitable medical professional.

[0684] Input: Patient information.

[0685] Output: List of selected medical professionals.

[0686] Specific operation: The server inputs patient information into an AI model (using Python's TensorFlow), and the model selects the most suitable medical professional.

[0687] Step 9:

[0688] The server saves a list of selected medical professionals to a database and displays it to the user.

[0689] Input: A list of selected medical professionals.

[0690] Output: A list of medical professionals displayed to the user.

[0691] Specific operation: The server returns a list of medical professionals to the frontend to display on the user's dashboard.

[0692] Step 10:

[0693] Users can select their preferred medical professional and choose a date and time for an online diagnosis or consultation.

[0694] Input: Selection of medical professional and appointment date / time.

[0695] Output: Reservation information sent to the server.

[0696] Specific action: The user selects Dr. Sato and schedules an online consultation for next Tuesday at 2:00 PM.

[0697] Step 11:

[0698] The server saves the reservation information to a database and notifies the selected medical professional.

[0699] Input: Reservation information submitted by the user.

[0700] Output: Appointment information stored in the database and notifications to medical professionals.

[0701] Specific operation: The server notifies medical professionals of the appointment information via email or in-app notifications.

[0702] Step 12:

[0703] The user accesses the system at the scheduled time and begins the online diagnosis.

[0704] Input: Reservation date and time and access information.

[0705] Output: Online diagnosis initiated.

[0706] Specific action: The user accesses the specified URL and enters the video call screen.

[0707] Step 13:

[0708] The server provides communication methods such as video calls and text chats, connecting medical professionals and users.

[0709] Input: Communication request between user and medical professional.

[0710] Output: Connects to video calls and text chats.

[0711] Specific operation: The server uses technologies such as WebRTC to enable real-time video calls.

[0712] Step 14:

[0713] After the diagnosis and consultation are complete, the server records the diagnosis details and feedback in a database and provides them to the user.

[0714] Input: Diagnostic details, feedback.

[0715] Output: Diagnostic information recorded in the database and feedback to the user.

[0716] Specific action: The server saves the diagnostic report and displays it on the user's dashboard.

[0717] The above describes the processing steps of the system of the present invention.

[0718] (Application Example 1)

[0719] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0720] Traditionally, when cancer patients and their families sought high-quality second opinions, managing information was cumbersome, and the risk of personal information leaks was high. Furthermore, the accuracy of selecting appropriate doctors was low, and the procedures for booking online diagnoses and consultations were complicated, placing a heavy burden on patients and their families. In addition, concerns about the security of digital data acted as a barrier to using online services. To solve these problems, a system is needed that processes medical information safely and efficiently and provides high-quality medical services.

[0721] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0722] In this invention, the server includes means for recording and storing patient medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable physician based on the stored patient information using a generative model; means for connecting physicians and patients online to conduct diagnoses and consultations; means for storing patient information in encryption; and means for encrypting and authenticating user information. This makes it possible to securely manage patient and user information and efficiently provide high-quality second opinions.

[0723] "Patient medical history information" refers to detailed information about a patient's past illnesses and treatments.

[0724] "Current treatment information" refers to information about the treatment a patient is currently receiving.

[0725] "Past test results" refers to information about the results of tests the patient has received in the past.

[0726] "Means of recording and preserving" refers to devices and systems for collecting and electronically storing patient information.

[0727] "Stored patient information" refers to information about patients that is recorded within the system and stored in a database or similar location.

[0728] The term "optimal physician" refers to a medical professional best suited to a patient's condition, as determined by a generative model.

[0729] A "generative model" is an algorithm or machine learning model designed to perform a specific task based on past case data.

[0730] "Means of selection and referral" refers to a mechanism that uses generative models to select appropriate doctors and provide that information to patients.

[0731] "A means of connecting doctors and patients online for diagnosis and consultation" refers to a system that provides an environment where doctors and patients can communicate directly using the internet and digital communication.

[0732] "Methods for encrypting and storing patient information" refers to methods of securely storing patient information in the form of digital data by encrypting it.

[0733] "Methods for encrypting and authenticating user information" refers to a mechanism that encrypts and stores user identification information and uses it during authentication.

[0734] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. To implement this invention, key functions include user registration and login, input of patient information, selection of the most suitable doctor, doctor referral and appointment scheduling, online diagnosis and consultation, and data encryption and storage.

[0735] 1. User registration and login

[0736] Users on their terminals enter basic information such as their name, email address, and password to register. The entered data is received by the server and encrypted using Fernet encryption technology. The encrypted data is securely stored in the database. Users receive a confirmation email and can log in by clicking the link to activate their account.

[0737] 2. Entering patient information

[0738] After logging in, users enter their medical history, current treatment information, and past test results. This information is also encrypted by the server and stored in the database. This step ensures that patient information is securely managed within the system.

[0739] 3. Selection of the most suitable physician

[0740] The server passes the stored patient information to a generating AI model. The generating AI model compares it with past case data and executes prompts to select the most suitable doctor for the patient. The list of selected doctors is presented to the user terminal, associated with the patient information.

[0741] 4. Doctor referral and appointment

[0742] From the presented list of doctors, users select their preferred doctor and book an appointment for an online diagnosis or consultation. The booking information is encrypted by the server and stored in a database. The selected doctor is notified of the booking information and is ready for the online diagnosis or consultation.

[0743] 5. Implementation of online diagnosis and consultation

[0744] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chats, connecting the user's terminal and the doctor's terminal. After the diagnosis and consultation are completed, the diagnosis and feedback are encrypted by the server and provided to the user's terminal.

[0745] Adding specific examples

[0746] 1. The user registers with the system, entering their name (e.g., Ichiro Tanaka), email address (e.g., ichiro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[0747] 2. After logging in, user Ichiro Tanaka enters his medical history information (e.g., stage II gastric cancer), current treatment (e.g., radiation therapy), and past test results (most recent MRI images).

[0748] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Ichiro Tanaka (e.g., Dr. Yamada at Hospital B).

[0749] 4. User Ichiro Tanaka selects Dr. Yamada and books an online consultation for next Wednesday at 2:30 PM.

[0750] 5. The server saves the reservation information and notifies Dr. Yamada. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server encrypts and records the consultation details and sends feedback to the user.

[0751] Example prompts for generative AI models

[0752] Cancer patient information: Stage II gastric cancer, current treatment: radiation therapy, past test results: latest MRI images. Please select the best doctor for this patient.

[0753] The system of the present invention can manage the entire process from user registration to online diagnosis in a highly secure and efficient manner. As a result, cancer patients and their families can obtain high-quality second opinions with peace of mind.

[0754] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0755] Step 1:

[0756] User registration information (name, email address, password) is entered from the user's terminal. The server receives this information and encrypts it using Fernet encryption technology. The encrypted data is stored in the database. The output is that the encrypted user information is stored in the database.

[0757] Step 2:

[0758] After registration is complete, the server sends a confirmation email. The user's device activates the account by clicking the link in the confirmation email. The input is clicking the link in the confirmation email, and the output is account activation.

[0759] Step 3:

[0760] The user enters login information (email address, password) from their terminal. The server decrypts the encrypted data in the database and verifies that it matches. The input is the login information, and the output is the result of successful or unsuccessful login authentication.

[0761] Step 4:

[0762] After successful login, patient information (medical history, current treatment information, past test results) is entered from the user's terminal. The server then encrypts this information again using Fernet encryption technology and stores it in the database. The input is patient information, and the output is the storage of encrypted patient information.

[0763] Step 5:

[0764] The server passes patient information from the database to a generating AI model. The generating AI model compares this information with past case data and selects the most suitable doctor for the patient based on the prompt text. The input is encrypted patient information and prompt text, and the output is a list of suitable doctors.

[0765] Step 6:

[0766] A list of suitable doctors is presented to the user's terminal. The user selects a desired doctor from the list and enters the date and time for an online diagnosis or consultation. The input consists of the desired doctor and the date and time of the diagnosis, and the output is the generation of reservation information.

[0767] Step 7:

[0768] The server encrypts the reservation information and stores it in a database. Furthermore, it notifies the selected physicians of the reservation information. The input is the reservation information, and the output is the storage and notification of the encrypted reservation information.

[0769] Step 8:

[0770] At the scheduled time, the user participates in the online diagnosis and consultation. The server manages video calls and text chats and connects the user's terminal with the doctor's terminal. The input is a request to start the online diagnosis, and the output is the start of the diagnosis and consultation session.

[0771] Step 9:

[0772] After the diagnosis and consultation are complete, the server encrypts and records the diagnosis details and feedback, and provides them to the user's terminal. The input is the diagnosis details and feedback, and the output is the storage and provision of encrypted diagnostic data.

[0773] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0774] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and more particularly to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis / consultation.

[0775] System Overview

[0776] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of a user terminal, a server, a physician's terminal, and an emotion engine.

[0777] User registration and login

[0778] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[0779] Entering patient information

[0780] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, the user's input data includes text, audio, and video data, which an emotion engine analyzes to recognize the user's emotions.

[0781] Selecting the optimal doctor

[0782] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[0783] Doctor referral and appointment

[0784] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The reservation information is stored on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis or consultation.

[0785] Online diagnosis and consultation

[0786] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[0787] Specific example

[0788] 1. The user registers with the system, entering their name (Ichiro Tanaka), email address (ichiro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[0789] 2. After logging in, user Ichiro Tanaka enters his medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image). Furthermore, while he is entering the information, the emotion engine analyzes the text and voice data and recognizes Ichiro Tanaka's emotion as "anxiety."

[0790] 3. The server passes patient information and emotional data to a generating AI model, which then selects the most suitable doctor (e.g., Dr. Nakamura from Hospital B). Based on the emotional data, it is considered that Dr. Nakamura possesses the expertise to alleviate the patient's anxiety.

[0791] 4. User Ichiro Tanaka selects Dr. Nakamura and books an online consultation for next Thursday at 4:00 PM.

[0792] 5. The server saves the reservation information and notifies Dr. Nakamura. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. Dr. Nakamura uses Ichiro Tanaka's emotional data as a reference to take an approach that reduces anxiety.

[0793] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to Ichiro Tanaka.

[0794] As described above, this system provides a comprehensive and convenient service that combines an emotional engine to easily enable cancer patients and their families to obtain high-quality second opinions.

[0795] The following describes the processing flow.

[0796] Step 1:

[0797] The user opens the service's website or mobile app.

[0798] Step 2:

[0799] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[0800] The terminal sends the entered information to the server.

[0801] Step 3:

[0802] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[0803] The server stores the operation results in the database and processes them for sending the email.

[0804] Step 4:

[0805] The user clicks the confirmation link in the email they received.

[0806] When the device clicks the link, it sends a request to the verification API endpoint.

[0807] Step 5:

[0808] The server receives the confirmation request and updates the user's status to "Confirmed".

[0809] The server saves the update results to the database and returns a success response.

[0810] Step 6:

[0811] The user enters their email address and password in the login form and clicks the "Login" button.

[0812] The terminal sends the entered information to the server.

[0813] Step 7:

[0814] The server verifies the authentication information, and if it is correct, creates a session and authenticates the user.

[0815] The server saves session information to the database and returns a response that includes an authentication token.

[0816] Step 8:

[0817] After logging in, the user enters their medical history, current treatment information, and past test results.

[0818] The terminal displays a medical history input form, and the user enters the information and clicks the submit button.

[0819] Step 9:

[0820] The server stores patient information and text, audio, and video data received by the server in a database.

[0821] The server formats the data and inserts it into the database.

[0822] Step 10:

[0823] The emotion engine analyzes the user's text, voice, and video data to recognize their emotions.

[0824] The emotion engine generates emotion data and returns the results to the server.

[0825] Step 11:

[0826] The server passes stored patient information and emotional data to the generating AI model.

[0827] The server extracts the required patient information and sends a request to the AI ​​model's API.

[0828] Step 12:

[0829] The generative AI model analyzes patient information and emotional data, and compares it with relevant past case data.

[0830] The generation AI model generates the optimal list of doctors and returns it to the server.

[0831] Step 13:

[0832] The server saves the generated list of doctors to the database and sends the results to the user.

[0833] The server formats the list of doctors and returns the response to the user.

[0834] Step 14:

[0835] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[0836] The terminal displays available reservation dates and times and sends the user's selection to the server.

[0837] Step 15:

[0838] The server saves the selected doctor and date / time to the booking system.

[0839] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[0840] Step 16:

[0841] The server sends the reservation confirmation result to the user.

[0842] The server sends a reservation confirmation email to the user.

[0843] Step 17:

[0844] The user accesses the app or website at the scheduled time.

[0845] The device verifies the reservation information and connects to the video call gateway.

[0846] Step 18:

[0847] The server creates a video call session and connects the doctor and the user.

[0848] The server calls the real-time communication API to start a session.

[0849] Step 19:

[0850] Users and doctors conduct online diagnoses and consultations.

[0851] The device sends and receives voice and video data, providing real-time communication.

[0852] Doctors refer to the user's emotional data to adjust diagnoses and advice.

[0853] Step 20:

[0854] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[0855] The server saves the diagnostic information to a database and sends a feedback email to the user.

[0856] (Example 2)

[0857] Next, we will describe Example 2. 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".

[0858] There is a need for a system that allows cancer patients and their families to easily and quickly obtain high-quality second opinions. In particular, it is crucial to improve the quality of physician selection, diagnosis, and consultation, taking into account the patient's feelings, but the current system struggles to meet these requirements. Conventional systems have the problem of selecting physicians without considering the patient's feelings, thus failing to alleviate the psychological burden on the patient.

[0859] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0860] In this invention, the server includes means for recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable doctor based on the stored patient information using a generative model; means for analyzing input text, voice, and video data to recognize the patient's emotions; means for selecting the most suitable doctor for the patient based on the recognized emotion data; means for connecting the doctor and patient online to conduct diagnoses and consultations; and means for recording and providing the diagnosis and feedback to the patient. This makes it possible to select a doctor that takes the patient's emotions into consideration, thereby reducing the patient's psychological burden and providing a system that makes it easy to obtain a high-quality second opinion.

[0861] "Patient medical history information" refers to details of illnesses and treatments that a patient has experienced in the past and present, including diagnoses, symptoms, and treatment history.

[0862] "Treatment information" refers to the type and method of treatment a patient is currently receiving, and includes information such as medication, surgery, radiation therapy, and chemotherapy.

[0863] "Test results" refer to the results of medical examinations performed on a patient, and include data from blood tests, imaging diagnostics (CT scans, MRI, etc.), and biopsies.

[0864] A "database" refers to a system for electronically storing and managing information, such as patient information, doctor information, and emotional data.

[0865] An "emotion engine" refers to software and algorithms that analyze input data (text, audio, video, etc.) and automatically identify emotions.

[0866] A "generative model" refers to an AI (artificial intelligence) algorithm that makes new predictions or generates new data based on past data, and it utilizes machine learning and deep learning technologies.

[0867] "Online diagnosis" refers to the process of diagnosing a patient via the internet, and this includes video calls and text chats.

[0868] "Feedback" refers to the opinions and advice that doctors provide to patients after an online diagnosis or consultation, and includes diagnostic results, treatment suggestions, and information about additional tests.

[0869] The "reservation function" refers to a feature within the system that allows patients to reserve a date and time for diagnosis or consultation online in advance.

[0870] "Communication methods" refer to technologies used to connect doctors and patients in online diagnoses and consultations, and include video calls, voice calls, and text chats.

[0871] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and moreover, to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis and consultation.

[0872] This system primarily consists of user terminals, a server, a doctor's terminal, and an emotion engine. User terminals are devices used by users to access the system and input information, including personal computers, smartphones, and tablets. The server is a computer system for managing, analyzing, and storing information, and includes databases, generative AI models, and an emotion engine.

[0873] User registration and login

[0874] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[0875] Entering patient information

[0876] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, user input data includes text, audio, and video data, which the emotion engine analyzes to recognize the user's emotions. For example, the IBM Watson Sentiment Analysis API can be used for text data, and the API can be used to analyze emotions for audio data.

[0877] Selecting the optimal doctor

[0878] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[0879] Doctor referral and appointment

[0880] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The reservation information is stored on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis or consultation.

[0881] Online diagnosis and consultation

[0882] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. For example, it may use the Zoom API or Twilio API to provide video call functionality. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[0883] Specific example

[0884] 1. The user registers with the system, entering their name, email address, and password. They receive a confirmation email and click the link to activate their account.

[0885] 2. After logging in, the user enters their medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image). Furthermore, during the input process, the emotion engine analyzes the text and voice data and recognizes the user's emotion as "anxiety."

[0886] 3. The server passes patient information and emotional data to a generating AI model, which then selects the most suitable doctor. For example, a doctor with expertise in reducing patient anxiety based on emotional data might be selected.

[0887] 4. The user selects a doctor and books an online consultation.

[0888] 5. The server saves the appointment information and notifies the doctor. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. The doctor uses the user's emotional data to implement an approach that reduces anxiety.

[0889] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to the user.

[0890] Example of a prompt

[0891] The following are examples of prompts to input into a generative AI model:

[0892] Patient information:

[0893] Medical history: Stage III lung cancer

[0894] Current treatment: Chemotherapy

[0895] Previous test results: Latest CT scan images

[0896] Emotional data:

[0897] Emotion: Anxiety

[0898] Criteria for selecting the best doctor:

[0899] 1. Expertise in lung cancer

[0900] 2. Communication skills to alleviate patient anxiety

[0901] Please select the most suitable doctor based on the above conditions.

[0902] The above describes specific embodiments for carrying out the present invention.

[0903] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0904] Step 1: User registration and verification

[0905] The user accesses the system's website and enters basic information such as their name, email address, and password.

[0906] (Input): User's basic information (name, email address, password)

[0907] (Output): Request to send confirmation email

[0908] The server will send a confirmation email to the email address you entered. This email will contain a link to activate your account.

[0909] (Input): User's email address

[0910] (Output): Confirmation email (with link)

[0911] The user clicks the link in the confirmation email to activate their account.

[0912] (Input): Clicked the link in the confirmation email

[0913] (Output): Account activation

[0914] Step 2: Log in

[0915] Users log in using their email address and password.

[0916] (Enter): Email address, password

[0917] (Output): Login success or failure message

[0918] Step 3: Entering patient information and sentiment analysis

[0919] After logging in, the user enters their medical history, current treatment information, and past test results.

[0920] (Input): Medical history information, treatment information, test results

[0921] (Output): Request to save input data

[0922] The server saves the input data to the database.

[0923] (Input): Patient information

[0924] (Output): Database save success message

[0925] The device sends text, audio, and video data to the emotion engine for analysis.

[0926] Example: Using the IBM Watson Sentiment Analysis API

[0927] (Input): Text, audio, and video data

[0928] (Output): Emotion analysis results (e.g., "anxiety")

[0929] Step 4: Selecting a physician

[0930] The server generates prompt messages to pass patient information and emotional data to the AI ​​model.

[0931] (Input): Patient information, emotional data

[0932] (Output): Prompt message

[0933] The generative AI model selects the most suitable doctor based on the prompt text.

[0934] (Input): Prompt message

[0935] (Output): Doctor list

[0936] The server presents the user with a list of selected doctors.

[0937] (Input): Doctor list

[0938] (Output): Doctor list displayed on user screen

[0939] Step 5: Doctor referral and appointment

[0940] Users select a doctor from a list of doctors provided and book an online consultation or appointment.

[0941] (Input): Selected doctor, preferred date and time

[0942] (Output): Reservation Request

[0943] The server saves the reservation information to the database and sends a notification to the selected doctor.

[0944] (Input): Reservation information

[0945] (Output): Database saved successfully, notification sent to physician.

[0946] Step 6: Conducting online diagnosis and consultation

[0947] At the scheduled time, the server will provide communication methods such as video calls and text chats.

[0948] Example: Using the Zoom API or Twilio API

[0949] (Input): Reservation date and time

[0950] (Output): Provides communication interface

[0951] Users participate in online diagnostics, and doctors provide diagnoses and consultations.

[0952] (Input): User participation, Doctor participation

[0953] (Output): Diagnosis and consultation implemented.

[0954] Step 7: Processing after diagnosis is complete

[0955] The server records diagnostic information and feedback in a database.

[0956] (Input): Diagnostic details, feedback

[0957] (Output: Database save successful)

[0958] The server sends feedback to the user.

[0959] (Input): Feedback

[0960] (Output): Feedback notification

[0961] The above is a description of this system's program, broken down into processing steps and including specific operations.

[0962] (Application Example 2)

[0963] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0964] There are few systems that allow users facing security issues to easily seek a second opinion from a suitable security expert. Furthermore, there is a lack of systems that provide customized support to reduce the psychological burden on users. In particular, there is a need to provide a higher-quality consultation experience by considering the user's emotional state.

[0965] The identification processing performed by the identification 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 recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable specialist based on the stored patient information using a generation model; means for analyzing the patient's emotions using an emotion engine; means for selecting the most suitable specialist based on the analyzed emotions, connecting the specialist and the patient online, and conducting diagnoses and consultations; and means for providing a reservation function. This makes it possible for users to easily access appropriate security specialists and obtain high-quality second opinions while reducing psychological burden.

[0966] "Patient medical history information" refers to information such as the illnesses, symptoms, and treatment history of the patient that they have suffered from in the past.

[0967] "Current treatment information" refers to information about the treatment a patient is currently receiving and its progress.

[0968] "Past test results" refers to data on diagnoses and test results that the patient has received in the past.

[0969] A "generative model" is an artificial intelligence algorithm used to select the most suitable expert based on collected data.

[0970] An "emotion engine" is a system that analyzes user input data and recognizes their emotional state.

[0971] The "reservation function" is a feature that allows users to specify the date and time for online diagnoses or consultations and make reservations.

[0972] A "specialist" is a professional who is well-versed in a particular field and capable of providing appropriate advice and diagnoses.

[0973] "Online diagnosis" refers to the act of a specialist diagnosing a patient's condition via the internet.

[0974] "Consultation" refers to the act of a specialist providing expert opinions and advice in response to questions and concerns from patients or users.

[0975] An "optimal specialist" is a professional who can provide the most appropriate response based on the patient's symptoms and emotional state.

[0976] This invention relates to an online consultation system for security services. Specifically, it includes a series of processes for analyzing the user's emotions, selecting the most suitable security expert, and connecting them online. Specific embodiments of this system are described below.

[0977] User terminal

[0978] Users access the system using a smartphone or PC. An account is created when a user registers and enters their name, email address, and password. After registration, they receive a confirmation email, click the link to activate their account, and log in. Users enter information about their security issues and past countermeasures. During this process, an emotion engine analyzes this data to recognize the user's emotional state.

[0979] Emotional Engine

[0980] The emotion engine utilizes technologies such as IBM Watson and Microsoft Azure Cognitive Services. It analyzes user-input text and voice data and tags them with emotions. For example, it recognizes emotions like "reassurance," "anxiety," and "doubt." This allows for a quantitative assessment of the user's psychological burden.

[0981] server

[0982] The servers are operated using AWS EC2, Google Cloud Platform, etc. The servers record user information and sentiment data and pass this to a generative AI model. Using generative AI models such as OpenAI GPT-4, the most suitable security expert is selected based on the user's information and sentiment. The selection process includes matching against past case data.

[0983] Generative AI Models

[0984] The generative AI model selects the most suitable expert for the user based on the collected data. This model, known as a "generative AI model," learns from past case data and similar cases. An example of a prompt is shown below:

[0985] USER: Regarding the hacking prevention meeting scheduled for Wednesday afternoon, how can I choose a security expert who will help alleviate my concerns?

[0986] Assistant:

[0987] Expert selection and booking

[0988] A list of experts selected by the server is presented to the user. The user selects their preferred expert and books an online consultation time. Reservation information is managed using the Google Calendar API and Microsoft Outlook API.

[0989] Online diagnosis and consultation

[0990] At the scheduled time, the server initiates a video call using the Zoom API or Google Meet API. The expert and the user connect to conduct a diagnosis and consultation. The diagnosis and feedback are recorded and provided to the user. This allows the user to obtain a high-quality second opinion while reducing psychological burden.

[0991] As a concrete example, a user registers an account and enters a security concern after logging in. At this point, the emotion engine recognizes this as "anxiety." The generative AI model selects the most suitable expert based on the provided information and emotion data, and schedules an online consultation at the user's preferred date and time. A video call begins at the scheduled time, and the expert takes an approach to alleviate the user's anxiety.

[0992] This allows users to easily receive advice from appropriate experts when they face security issues, thereby reducing their psychological burden.

[0993] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0994] Step 1:

[0995] The user terminal provides an interface for users to register with the system. The user enters their name, email address, and password, and presses the registration button. The server receives the input data, creates the account using Firebase Authentication or Auth0, and sends a confirmation email. The user activates their account by clicking the link in the confirmation email and can then log in.

[0996] Input: Name, email address, password

[0997] Output: Account creation confirmation email

[0998] Step 2:

[0999] The user terminal provides a login interface. The user logs in through this interface and begins the process of entering their security issues and past countermeasures. For example, they might enter details such as "the system is frequently being hacked." The entered data is sent to the server in text format.

[1000] Input: Email address, password, security information

[1001] Output: Sending security information to the server

[1002] Step 3:

[1003] The server sends the received security information to the emotion engine, which analyzes the text data to recognize the user's emotions. The emotion engine uses IBM Watson or Microsoft Azure Cognitive Services. The analysis results are output in formats such as "reassured," "anxious," and "doubtful."

[1004] Input: Text data of security information

[1005] Output: Emotional state (e.g., "anxiety")

[1006] Step 4:

[1007] The server passes user information and sentiment data to a generative AI model. The generative AI model uses OpenAI GPT-4 to analyze this data and compare it with past case data to select the most suitable security expert. The selection results are output as a list of multiple experts.

[1008] Input: User information, sentiment data

[1009] Output: List of experts

[1010] Step 5:

[1011] The user's terminal displays a list of experts received from the server. The user selects a desired expert from the list, specifies a date and time for the online consultation, and makes a reservation. The server manages the reservation information using the Google Calendar API or Microsoft Outlook API and notifies the selected expert.

[1012] Input: List of experts, preferred consultation date and time

[1013] Output: Saving of reservation information and notification to experts

[1014] Step 6:

[1015] The server initiates the video call at the scheduled time. It uses the Zoom API or Google Meet API to connect the expert and the user. The user then consults with the expert online to receive diagnosis and advice.

[1016] Input: Reservation information, Start video call

[1017] Output: Implementation of online consultations

[1018] Step 7:

[1019] The server records the diagnosis and feedback after the online consultation ends and provides it to the user's device. Users can access this information at a later date. The data is stored in Google Cloud Storage or Amazon S3.

[1020] Input: Content of online consultation

[1021] Output: Diagnostic results, feedback

[1022] Through these steps, users can easily receive advice from appropriate security experts and get personalized, emotion-based responses.

[1023] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1024] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1025] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1026] [Third Embodiment]

[1027] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1028] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1030] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1031] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1032] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1034] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1035] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1037] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1039] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. The embodiments for carrying out this invention are described below in detail.

[1040] System Overview

[1041] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of user terminals, a server, and physician terminals.

[1042] User registration and login

[1043] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[1044] Entering patient information

[1045] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor.

[1046] Selecting the optimal doctor

[1047] The server passes the recorded patient information to a generating AI model. The generating AI model selects the most suitable doctor for the patient's condition by comparing it with past case data. The list of selected doctors is saved in association with the patient information and presented to the user.

[1048] Doctor referral and appointment

[1049] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The appointment information is stored on the server and notified to the selected doctor. At this point, the server prepares for the online diagnosis or consultation between the user and the doctor.

[1050] Online diagnosis and consultation

[1051] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[1052] Specific example

[1053] 1. The user registers with the system, entering their name (Taro Yamada), email address (taro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[1054] 2. After logging in, user Yamada Taro enters his medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image).

[1055] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Taro Yamada (e.g., Dr. Sato at Hospital A).

[1056] 4. User Yamada Taro selects Dr. Sato and books an online consultation for next Tuesday at 2:00 PM.

[1057] 5. The server saves the reservation information and notifies Dr. Sato. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user.

[1058] As described above, this system provides a comprehensive and convenient service that allows cancer patients and their families to easily obtain high-quality second opinions.

[1059] The following describes the processing flow.

[1060] Step 1:

[1061] The user opens the service's website or mobile app.

[1062] Step 2:

[1063] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[1064] The terminal sends the entered information to the server.

[1065] Step 3:

[1066] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[1067] The server stores the operation results in the database and processes them for sending the email.

[1068] Step 4:

[1069] The user clicks the confirmation link in the email they received.

[1070] When the device clicks the link, it sends a request to the verification API endpoint.

[1071] Step 5:

[1072] The server receives the confirmation request and updates the user's status to "Confirmed".

[1073] The server saves the update results to the database and returns a success response.

[1074] Step 6:

[1075] The user enters their email address and password in the login form and clicks the "Login" button.

[1076] The terminal sends the entered information to the server.

[1077] Step 7:

[1078] The server verifies the authentication information, and if it is correct, creates a session and authenticates the user.

[1079] The server saves session information to the database and returns a response that includes an authentication token.

[1080] Step 8:

[1081] After logging in, the user enters their medical history, current treatment information, and past test results.

[1082] The terminal displays a medical history input form, and the user enters the information and clicks the submit button.

[1083] Step 9:

[1084] The server saves the received data to the database.

[1085] The server formats the data and inserts it into the database.

[1086] Step 10:

[1087] The server passes the stored patient information to the AI ​​model that generates the data.

[1088] The server extracts the required patient information and sends a request to the AI ​​model's API.

[1089] Step 11:

[1090] The generative AI model analyzes patient information and compares it with relevant past case data.

[1091] The generation AI model generates the optimal list of doctors and returns it to the server.

[1092] Step 12:

[1093] The server saves the generated list of doctors to the database and sends the results to the user.

[1094] The server formats the list of doctors and returns the response to the user.

[1095] Step 13:

[1096] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[1097] The terminal displays available reservation dates and times and sends the user's selection to the server.

[1098] Step 14:

[1099] The server saves the selected doctor and date / time to the booking system.

[1100] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[1101] Step 15:

[1102] The server sends the reservation confirmation result to the user.

[1103] The server sends a reservation confirmation email to the user.

[1104] Step 16:

[1105] The user accesses the app or website at the scheduled time.

[1106] The device verifies the reservation information and connects to the video call gateway.

[1107] Step 17:

[1108] The server creates a video call session and connects the doctor and the user.

[1109] The server calls the real-time communication API to start a session.

[1110] Step 18:

[1111] Users and doctors conduct online diagnoses and consultations.

[1112] The device sends and receives voice and video data, providing real-time communication.

[1113] Step 19:

[1114] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[1115] The server saves the diagnostic information to a database and sends a feedback email to the user.

[1116] (Example 1)

[1117] Next, we will describe Example 1. 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."

[1118] In modern medicine, it is difficult for cancer patients and their families to easily obtain high-quality second opinions. Furthermore, the diverse tasks involved, such as managing patient information, selecting the most suitable medical specialist, and arranging online consultations, are time-consuming and labor-intensive when performed manually. Moreover, while it is desirable to perform these processes quickly and accurately, systems for this are still lacking. To address these challenges and provide high-quality medical services to cancer patients and their families, there is a growing need for online second opinion services.

[1119] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1120] This invention includes a server that records and stores a patient's medical history information, current treatment information, and past test results; a server that sends a confirmation email to activate a user account; a server that allows the user to input patient information after logging in; a server that uses a generated AI model to select and introduce the most suitable medical professional based on the stored patient information; a server that connects medical professionals and patients online to conduct diagnoses and consultations; a server that stores and notifies medical professionals of appointment information for diagnoses and consultations; and a server that records and provides diagnoses and feedback. This makes it possible for cancer patients and their families to easily obtain high-quality second opinions.

[1121] "Medical history information" refers to information that shows a patient's past medical records and disease history.

[1122] "Treatment information" refers to information that describes the content and methods of treatment a patient is currently receiving.

[1123] "Test results" refer to information that shows the results and data of medical tests performed in the past.

[1124] A "confirmation email" is an email sent to verify the email address registered by the user and to activate their account.

[1125] A "user account" is an individual account that a user registers and authenticates in order to access and use a system.

[1126] A "generative AI model" is a model that uses artificial intelligence technology to select the most suitable medical professional based on past data.

[1127] A "medical professional" is a doctor or healthcare worker who possesses specialized knowledge and skills to address a patient's medical condition and case.

[1128] "Online diagnosis" refers to the process by which medical professionals provide diagnoses and consultations to patients via the internet.

[1129] "Reservation information" refers to information such as the date and time of online diagnosis or consultation, and the medical professional.

[1130] "Feedback" refers to information that provides evaluations, opinions, and advice after a diagnosis or consultation.

[1131] A "second opinion" refers to a diagnosis or opinion received from a medical professional other than your primary physician.

[1132] This invention relates to an online second opinion service aimed at enabling cancer patients and their families to easily obtain high-quality second opinions. The system primarily consists of a server, user terminals, and medical professional terminals. Detailed embodiments of this invention are described below.

[1133] User registration and login

[1134] When a user accesses the system, they first register. The user enters their name, email address, and password and submits them to the server. The server stores the received information in its database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, their account is activated. Next, the user enters their email address and password on the login screen and is authenticated. The server verifies the authentication information and allows the user to start a session.

[1135] Entering patient information

[1136] After the user logs in, they enter medical history information, current treatment information, and past test results on the patient information input screen. The user terminal sends the entered information to the server. The server stores the entered information in a database and formats the data as needed.

[1137] Selection of the most suitable medical professional

[1138] The server inputs stored patient information into a generative AI model. This generative AI model is built using Python's TensorFlow, among other tools. The generative AI model compares the patient's information with past case data and selects the most suitable medical professional for their condition. The server saves the list of selected medical professionals to a database and displays it to the user.

[1139] Referral and appointment scheduling for medical professionals

[1140] The user selects a preferred medical professional from a list of available professionals and chooses a date and time for an online diagnosis or consultation. The user's terminal sends the selection information to the server. The server stores the reservation information in a database and notifies the selected medical professional.

[1141] Online diagnosis and consultation

[1142] At the scheduled time, the user accesses the system and begins the online diagnosis. The server provides communication methods such as video calls and text chats, connecting the user with a medical professional. Real-time video calls are enabled using technologies such as WebRTC. After the diagnosis and consultation are completed, the server records the diagnosis details and feedback in a database and provides them to the user.

[1143] Specific example

[1144] The following are examples of specific prompt messages:

[1145] "The user registers with the system, entering their name (e.g., Patient A), email address (e.g., patientA@example.com), and password. They receive a confirmation email and click the link to activate their account. After user Patient A logs in, they enter their medical history (e.g., Stage III lung cancer), current treatment information (e.g., chemotherapy), and past test results (most recent CT scan image). The server passes this information to a generating AI model, which selects the most suitable medical professional. The generating AI model lists the most suitable medical professionals for Patient A based on past case data. User Patient A selects a medical professional and books an online consultation for next Tuesday at 2:00 PM. The server saves the reservation information and notifies the medical professional. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user."

[1146] Thus, the present invention provides a comprehensive and convenient service that enables cancer patients and their families to easily obtain high-quality second opinions.

[1147] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1148] Step 1:

[1149] The user accesses the new registration screen and enters their name, email address, and password.

[1150] Input: User's name, email address, and password.

[1151] Output: User information sent to the server.

[1152] Specific action: The user enters "Patient A", "patientA@example.com", and "password123" into the form fields and clicks the "Register" button.

[1153] Step 2:

[1154] The server saves the received information to the database and sends a confirmation email to the user.

[1155] Input: User's submitted name, email address, and password.

[1156] Output: User information stored in the database and a confirmation email sent to the user.

[1157] Specific operation: The server uses an email sending service (e.g., SendGrid) to send a "confirmation email".

[1158] Step 3:

[1159] The user activates their account by clicking the link in the confirmation email.

[1160] Input: The link included in the confirmation email.

[1161] Output: Request to the server and account activation.

[1162] Specific operation: When a user clicks a link in an email, a request is sent to a specific endpoint on the server, and the user's account is activated.

[1163] Step 4:

[1164] The user enters their email address and password on the login screen and undergoes authentication.

[1165] Enter: email address, password.

[1166] Output: Login request to the server and authentication information.

[1167] Specific action: The user enters "patientA@example.com" and "password123" and clicks the "Login" button.

[1168] Step 5:

[1169] The server verifies the authentication information and allows the user to start a session.

[1170] Input: User login request.

[1171] Output: Session started and JWT token generated.

[1172] Specific operation: The server checks the authentication information, creates a session upon success, generates a JWT token, and returns it to the user.

[1173] Step 6:

[1174] The user enters medical history information, current treatment details, and past test results on the patient information input screen.

[1175] Input: Medical history information, current treatment, past test results.

[1176] Output: Patient information sent to the server.

[1177] Specific operation: The user inputs "Lung cancer stage III", treatment "Chemotherapy", and test results "CT scan image".

[1178] Step 7:

[1179] The server saves the entered information to the database and formats the data as needed.

[1180] Input: Patient information submitted by the user.

[1181] Output: Patient information stored in the database.

[1182] Specific operation: The server formats the data and saves it to the appropriate field.

[1183] Step 8:

[1184] The server inputs patient information into an AI model, which then compares it with past case data to select the most suitable medical professional.

[1185] Input: Patient information.

[1186] Output: List of selected medical professionals.

[1187] Specific operation: The server inputs patient information into an AI model (using Python's TensorFlow), and the model selects the most suitable medical professional.

[1188] Step 9:

[1189] The server saves a list of selected medical professionals to a database and displays it to the user.

[1190] Input: A list of selected medical professionals.

[1191] Output: A list of medical professionals displayed to the user.

[1192] Specific operation: The server returns a list of medical professionals to the frontend to display on the user's dashboard.

[1193] Step 10:

[1194] Users can select their preferred medical professional and choose a date and time for an online diagnosis or consultation.

[1195] Input: Selection of medical professional and appointment date / time.

[1196] Output: Reservation information sent to the server.

[1197] Specific action: The user selects Dr. Sato and schedules an online consultation for next Tuesday at 2:00 PM.

[1198] Step 11:

[1199] The server saves the reservation information to a database and notifies the selected medical professional.

[1200] Input: Reservation information submitted by the user.

[1201] Output: Appointment information stored in the database and notifications to medical professionals.

[1202] Specific operation: The server notifies medical professionals of the appointment information via email or in-app notifications.

[1203] Step 12:

[1204] The user accesses the system at the scheduled time and begins the online diagnosis.

[1205] Input: Reservation date and time and access information.

[1206] Output: Online diagnosis initiated.

[1207] Specific action: The user accesses the specified URL and enters the video call screen.

[1208] Step 13:

[1209] The server provides communication methods such as video calls and text chats, connecting medical professionals and users.

[1210] Input: Communication request between user and medical professional.

[1211] Output: Connects to video calls and text chats.

[1212] Specific operation: The server uses technologies such as WebRTC to enable real-time video calls.

[1213] Step 14:

[1214] After the diagnosis and consultation are complete, the server records the diagnosis details and feedback in a database and provides them to the user.

[1215] Input: Diagnostic details, feedback.

[1216] Output: Diagnostic information recorded in the database and feedback to the user.

[1217] Specific action: The server saves the diagnostic report and displays it on the user's dashboard.

[1218] The above describes the processing steps of the system of the present invention.

[1219] (Application Example 1)

[1220] Next, we will explain Application Example 1. In the following explanation, 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."

[1221] Traditionally, when cancer patients and their families sought high-quality second opinions, managing information was cumbersome, and the risk of personal information leaks was high. Furthermore, the accuracy of selecting appropriate doctors was low, and the procedures for booking online diagnoses and consultations were complicated, placing a heavy burden on patients and their families. In addition, concerns about the security of digital data acted as a barrier to using online services. To solve these problems, a system is needed that processes medical information safely and efficiently and provides high-quality medical services.

[1222] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1223] In this invention, the server includes means for recording and storing patient medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable physician based on the stored patient information using a generative model; means for connecting physicians and patients online to conduct diagnoses and consultations; means for storing patient information in encryption; and means for encrypting and authenticating user information. This makes it possible to securely manage patient and user information and efficiently provide high-quality second opinions.

[1224] "Patient medical history information" refers to detailed information about a patient's past illnesses and treatments.

[1225] "Current treatment information" refers to information about the treatment a patient is currently receiving.

[1226] "Past test results" refers to information about the results of tests the patient has received in the past.

[1227] "Means of recording and preserving" refers to devices and systems for collecting and electronically storing patient information.

[1228] "Stored patient information" refers to information about patients that is recorded within the system and stored in a database or similar location.

[1229] The term "optimal physician" refers to a medical professional best suited to a patient's condition, as determined by a generative model.

[1230] A "generative model" is an algorithm or machine learning model designed to perform a specific task based on past case data.

[1231] "Means of selection and referral" refers to a mechanism that uses generative models to select appropriate doctors and provide that information to patients.

[1232] "A means of connecting doctors and patients online for diagnosis and consultation" refers to a system that provides an environment where doctors and patients can communicate directly using the internet and digital communication.

[1233] "Methods for encrypting and storing patient information" refers to methods of securely storing patient information in the form of digital data by encrypting it.

[1234] "Methods for encrypting and authenticating user information" refers to a mechanism that encrypts and stores user identification information and uses it during authentication.

[1235] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. To implement this invention, key functions include user registration and login, input of patient information, selection of the most suitable doctor, doctor referral and appointment scheduling, online diagnosis and consultation, and data encryption and storage.

[1236] 1. User registration and login

[1237] Users on their terminals enter basic information such as their name, email address, and password to register. The entered data is received by the server and encrypted using Fernet encryption technology. The encrypted data is securely stored in the database. Users receive a confirmation email and can log in by clicking the link to activate their account.

[1238] 2. Entering patient information

[1239] After logging in, users enter their medical history, current treatment information, and past test results. This information is also encrypted by the server and stored in the database. This step ensures that patient information is securely managed within the system.

[1240] 3. Selection of the most suitable physician

[1241] The server passes the stored patient information to a generating AI model. The generating AI model compares it with past case data and executes prompts to select the most suitable doctor for the patient. The list of selected doctors is presented to the user terminal, associated with the patient information.

[1242] 4. Doctor referral and appointment

[1243] From the presented list of doctors, users select their preferred doctor and book an appointment for an online diagnosis or consultation. The booking information is encrypted by the server and stored in a database. The selected doctor is notified of the booking information and is ready for the online diagnosis or consultation.

[1244] 5. Implementation of online diagnosis and consultation

[1245] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chats, connecting the user's terminal and the doctor's terminal. After the diagnosis and consultation are completed, the diagnosis and feedback are encrypted by the server and provided to the user's terminal.

[1246] Adding specific examples

[1247] 1. The user registers with the system, entering their name (e.g., Ichiro Tanaka), email address (e.g., ichiro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[1248] 2. After logging in, user Ichiro Tanaka enters his medical history information (e.g., stage II gastric cancer), current treatment (e.g., radiation therapy), and past test results (most recent MRI images).

[1249] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Ichiro Tanaka (e.g., Dr. Yamada at Hospital B).

[1250] 4. User Ichiro Tanaka selects Dr. Yamada and books an online consultation for next Wednesday at 2:30 PM.

[1251] 5. The server saves the reservation information and notifies Dr. Yamada. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server encrypts and records the consultation details and sends feedback to the user.

[1252] Example prompts for generative AI models

[1253] Cancer patient information: Stage II gastric cancer, current treatment: radiation therapy, past test results: latest MRI images. Please select the best doctor for this patient.

[1254] The system of the present invention can manage the entire process from user registration to online diagnosis in a highly secure and efficient manner. As a result, cancer patients and their families can obtain high-quality second opinions with peace of mind.

[1255] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1256] Step 1:

[1257] User registration information (name, email address, password) is entered from the user's terminal. The server receives this information and encrypts it using Fernet encryption technology. The encrypted data is stored in the database. The output is that the encrypted user information is stored in the database.

[1258] Step 2:

[1259] After registration is complete, the server sends a confirmation email. The user's device activates the account by clicking the link in the confirmation email. The input is clicking the link in the confirmation email, and the output is account activation.

[1260] Step 3:

[1261] The user enters login information (email address, password) from their terminal. The server decrypts the encrypted data in the database and verifies that it matches. The input is the login information, and the output is the result of successful or unsuccessful login authentication.

[1262] Step 4:

[1263] After successful login, patient information (medical history, current treatment information, past test results) is entered from the user's terminal. The server then encrypts this information again using Fernet encryption technology and stores it in the database. The input is patient information, and the output is the storage of encrypted patient information.

[1264] Step 5:

[1265] The server passes patient information from the database to a generating AI model. The generating AI model compares this information with past case data and selects the most suitable doctor for the patient based on the prompt text. The input is encrypted patient information and prompt text, and the output is a list of suitable doctors.

[1266] Step 6:

[1267] A list of suitable doctors is presented to the user's terminal. The user selects a desired doctor from the list and enters the date and time for an online diagnosis or consultation. The input consists of the desired doctor and the date and time of the diagnosis, and the output is the generation of reservation information.

[1268] Step 7:

[1269] The server encrypts the reservation information and stores it in a database. Furthermore, it notifies the selected physicians of the reservation information. The input is the reservation information, and the output is the storage and notification of the encrypted reservation information.

[1270] Step 8:

[1271] At the scheduled time, the user participates in the online diagnosis and consultation. The server manages video calls and text chats and connects the user's terminal with the doctor's terminal. The input is a request to start the online diagnosis, and the output is the start of the diagnosis and consultation session.

[1272] Step 9:

[1273] After the diagnosis and consultation are complete, the server encrypts and records the diagnosis details and feedback, and provides them to the user's terminal. The input is the diagnosis details and feedback, and the output is the storage and provision of encrypted diagnostic data.

[1274] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1275] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and more particularly to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis / consultation.

[1276] System Overview

[1277] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of a user terminal, a server, a physician's terminal, and an emotion engine.

[1278] User registration and login

[1279] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[1280] Entering patient information

[1281] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, the user's input data includes text, audio, and video data, which an emotion engine analyzes to recognize the user's emotions.

[1282] Selecting the optimal doctor

[1283] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[1284] Doctor referral and appointment

[1285] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The reservation information is stored on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis or consultation.

[1286] Online diagnosis and consultation

[1287] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[1288] Specific example

[1289] 1. The user registers with the system, entering their name (Ichiro Tanaka), email address (ichiro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[1290] 2. After logging in, user Ichiro Tanaka enters his medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image). Furthermore, while he is entering the information, the emotion engine analyzes the text and voice data and recognizes Ichiro Tanaka's emotion as "anxiety."

[1291] 3. The server passes patient information and emotional data to a generating AI model, which then selects the most suitable doctor (e.g., Dr. Nakamura from Hospital B). Based on the emotional data, it is considered that Dr. Nakamura possesses the expertise to alleviate the patient's anxiety.

[1292] 4. User Ichiro Tanaka selects Dr. Nakamura and books an online consultation for next Thursday at 4:00 PM.

[1293] 5. The server saves the reservation information and notifies Dr. Nakamura. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. Dr. Nakamura uses Ichiro Tanaka's emotional data as a reference to take an approach that reduces anxiety.

[1294] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to Ichiro Tanaka.

[1295] As described above, this system provides a comprehensive and convenient service that combines an emotional engine to easily enable cancer patients and their families to obtain high-quality second opinions.

[1296] The following describes the processing flow.

[1297] Step 1:

[1298] The user opens the service's website or mobile app.

[1299] Step 2:

[1300] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[1301] The terminal sends the entered information to the server.

[1302] Step 3:

[1303] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[1304] The server stores the operation results in the database and processes them for sending the email.

[1305] Step 4:

[1306] The user clicks the confirmation link in the email they received.

[1307] When the device clicks the link, it sends a request to the verification API endpoint.

[1308] Step 5:

[1309] The server receives the confirmation request and updates the user's status to "Confirmed".

[1310] The server saves the update results to the database and returns a success response.

[1311] Step 6:

[1312] The user enters their email address and password in the login form and clicks the "Login" button.

[1313] The terminal sends the entered information to the server.

[1314] Step 7:

[1315] The server verifies the authentication information, and if it is correct, creates a session and authenticates the user.

[1316] The server saves session information to the database and returns a response that includes an authentication token.

[1317] Step 8:

[1318] After logging in, the user enters their medical history, current treatment information, and past test results.

[1319] The terminal displays a medical history input form, and the user enters the information and clicks the submit button.

[1320] Step 9:

[1321] The server stores patient information and text, audio, and video data received by the server in a database.

[1322] The server formats the data and inserts it into the database.

[1323] Step 10:

[1324] The emotion engine analyzes the user's text, voice, and video data to recognize their emotions.

[1325] The emotion engine generates emotion data and returns the results to the server.

[1326] Step 11:

[1327] The server passes stored patient information and emotional data to the generating AI model.

[1328] The server extracts the required patient information and sends a request to the AI ​​model's API.

[1329] Step 12:

[1330] The generative AI model analyzes patient information and emotional data, and compares it with relevant past case data.

[1331] The generation AI model generates the optimal list of doctors and returns it to the server.

[1332] Step 13:

[1333] The server saves the generated list of doctors to the database and sends the results to the user.

[1334] The server formats the list of doctors and returns the response to the user.

[1335] Step 14:

[1336] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[1337] The terminal displays available reservation dates and times and sends the user's selection to the server.

[1338] Step 15:

[1339] The server saves the selected doctor and date / time to the booking system.

[1340] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[1341] Step 16:

[1342] The server sends the reservation confirmation result to the user.

[1343] The server sends a reservation confirmation email to the user.

[1344] Step 17:

[1345] The user accesses the app or website at the scheduled time.

[1346] The device verifies the reservation information and connects to the video call gateway.

[1347] Step 18:

[1348] The server creates a video call session and connects the doctor and the user.

[1349] The server calls the real-time communication API to start a session.

[1350] Step 19:

[1351] Users and doctors conduct online diagnoses and consultations.

[1352] The device sends and receives voice and video data, providing real-time communication.

[1353] Doctors refer to the user's emotional data to adjust diagnoses and advice.

[1354] Step 20:

[1355] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[1356] The server saves the diagnostic information to a database and sends a feedback email to the user.

[1357] (Example 2)

[1358] Next, we will describe Example 2. 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."

[1359] There is a need for a system that allows cancer patients and their families to easily and quickly obtain high-quality second opinions. In particular, it is crucial to improve the quality of physician selection, diagnosis, and consultation, taking into account the patient's feelings, but the current system struggles to meet these requirements. Conventional systems have the problem of selecting physicians without considering the patient's feelings, thus failing to alleviate the psychological burden on the patient.

[1360] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1361] In this invention, the server includes means for recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable doctor based on the stored patient information using a generative model; means for analyzing input text, voice, and video data to recognize the patient's emotions; means for selecting the most suitable doctor for the patient based on the recognized emotion data; means for connecting the doctor and patient online to conduct diagnoses and consultations; and means for recording and providing the diagnosis and feedback to the patient. This makes it possible to select a doctor that takes the patient's emotions into consideration, thereby reducing the patient's psychological burden and providing a system that makes it easy to obtain a high-quality second opinion.

[1362] "Patient medical history information" refers to details of illnesses and treatments that a patient has experienced in the past and present, including diagnoses, symptoms, and treatment history.

[1363] "Treatment information" refers to the type and method of treatment a patient is currently receiving, and includes information such as medication, surgery, radiation therapy, and chemotherapy.

[1364] "Test results" refer to the results of medical examinations performed on a patient, and include data from blood tests, imaging diagnostics (CT scans, MRI, etc.), and biopsies.

[1365] A "database" refers to a system for electronically storing and managing information, such as patient information, doctor information, and emotional data.

[1366] An "emotion engine" refers to software and algorithms that analyze input data (text, audio, video, etc.) and automatically identify emotions.

[1367] A "generative model" refers to an AI (artificial intelligence) algorithm that makes new predictions or generates new data based on past data, and it utilizes machine learning and deep learning technologies.

[1368] "Online diagnosis" refers to the process of diagnosing a patient via the internet, and this includes video calls and text chats.

[1369] "Feedback" refers to the opinions and advice that doctors provide to patients after an online diagnosis or consultation, and includes diagnostic results, treatment suggestions, and information about additional tests.

[1370] The "reservation function" refers to a feature within the system that allows patients to reserve a date and time for diagnosis or consultation online in advance.

[1371] "Communication methods" refer to technologies used to connect doctors and patients in online diagnoses and consultations, and include video calls, voice calls, and text chats.

[1372] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and moreover, to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis and consultation.

[1373] This system primarily consists of user terminals, a server, a doctor's terminal, and an emotion engine. User terminals are devices used by users to access the system and input information, including personal computers, smartphones, and tablets. The server is a computer system for managing, analyzing, and storing information, and includes databases, generative AI models, and an emotion engine.

[1374] User registration and login

[1375] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[1376] Entering patient information

[1377] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, user input data includes text, audio, and video data, which the emotion engine analyzes to recognize the user's emotions. For example, the IBM Watson Sentiment Analysis API can be used for text data, and the API can be used to analyze emotions for audio data.

[1378] Selecting the optimal doctor

[1379] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[1380] Doctor referral and appointment

[1381] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The reservation information is stored on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis or consultation.

[1382] Online diagnosis and consultation

[1383] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. For example, it may use the Zoom API or Twilio API to provide video call functionality. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[1384] Specific example

[1385] 1. The user registers with the system, entering their name, email address, and password. They receive a confirmation email and click the link to activate their account.

[1386] 2. After logging in, the user enters their medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image). Furthermore, during the input process, the emotion engine analyzes the text and voice data and recognizes the user's emotion as "anxiety."

[1387] 3. The server passes patient information and emotional data to a generating AI model, which then selects the most suitable doctor. For example, a doctor with expertise in reducing patient anxiety based on emotional data might be selected.

[1388] 4. The user selects a doctor and books an online consultation.

[1389] 5. The server saves the appointment information and notifies the doctor. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. The doctor uses the user's emotional data to implement an approach that reduces anxiety.

[1390] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to the user.

[1391] Example of a prompt

[1392] The following are examples of prompts to input into a generative AI model:

[1393] Patient information:

[1394] Medical history: Stage III lung cancer

[1395] Current treatment: Chemotherapy

[1396] Previous test results: Latest CT scan images

[1397] Emotional data:

[1398] Emotion: Anxiety

[1399] Criteria for selecting the best doctor:

[1400] 1. Expertise in lung cancer

[1401] 2. Communication skills to alleviate patient anxiety

[1402] Please select the most suitable doctor based on the above conditions.

[1403] The above describes specific embodiments for carrying out the present invention.

[1404] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1405] Step 1: User registration and verification

[1406] The user accesses the system's website and enters basic information such as their name, email address, and password.

[1407] (Input): User's basic information (name, email address, password)

[1408] (Output): Request to send confirmation email

[1409] The server will send a confirmation email to the email address you entered. This email will contain a link to activate your account.

[1410] (Input): User's email address

[1411] (Output): Confirmation email (with link)

[1412] The user clicks the link in the confirmation email to activate their account.

[1413] (Input): Clicked the link in the confirmation email

[1414] (Output): Account activation

[1415] Step 2: Log in

[1416] Users log in using their email address and password.

[1417] (Enter): Email address, password

[1418] (Output): Login success or failure message

[1419] Step 3: Entering patient information and sentiment analysis

[1420] After logging in, the user enters their medical history, current treatment information, and past test results.

[1421] (Input): Medical history information, treatment information, test results

[1422] (Output): Request to save input data

[1423] The server saves the input data to the database.

[1424] (Input): Patient information

[1425] (Output): Database save success message

[1426] The device sends text, audio, and video data to the emotion engine for analysis.

[1427] Example: Using the IBM Watson Sentiment Analysis API

[1428] (Input): Text, audio, and video data

[1429] (Output): Emotion analysis results (e.g., "anxiety")

[1430] Step 4: Selecting a physician

[1431] The server generates prompt messages to pass patient information and emotional data to the AI ​​model.

[1432] (Input): Patient information, emotional data

[1433] (Output): Prompt message

[1434] The generative AI model selects the most suitable doctor based on the prompt text.

[1435] (Input): Prompt message

[1436] (Output): Doctor list

[1437] The server presents the user with a list of selected doctors.

[1438] (Input): Doctor list

[1439] (Output): Doctor list displayed on user screen

[1440] Step 5: Doctor referral and appointment

[1441] Users select a doctor from a list of doctors provided and book an online consultation or appointment.

[1442] (Input): Selected doctor, preferred date and time

[1443] (Output): Reservation Request

[1444] The server saves the reservation information to the database and sends a notification to the selected doctor.

[1445] (Input): Reservation information

[1446] (Output): Database saved successfully, notification sent to physician.

[1447] Step 6: Conducting online diagnosis and consultation

[1448] At the scheduled time, the server will provide communication methods such as video calls and text chats.

[1449] Example: Using the Zoom API or Twilio API

[1450] (Input): Reservation date and time

[1451] (Output): Provides communication interface

[1452] Users participate in online diagnostics, and doctors provide diagnoses and consultations.

[1453] (Input): User participation, Doctor participation

[1454] (Output): Diagnosis and consultation implemented.

[1455] Step 7: Processing after diagnosis is complete

[1456] The server records diagnostic information and feedback in a database.

[1457] (Input): Diagnostic details, feedback

[1458] (Output: Database save successful)

[1459] The server sends feedback to the user.

[1460] (Input): Feedback

[1461] (Output): Feedback notification

[1462] The above is a description of this system's program, broken down into processing steps and including specific operations.

[1463] (Application Example 2)

[1464] Next, we will explain application example 2. In the following explanation, 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."

[1465] There are few systems that allow users facing security issues to easily seek a second opinion from a suitable security expert. Furthermore, there is a lack of systems that provide customized support to reduce the psychological burden on users. In particular, there is a need to provide a higher-quality consultation experience by considering the user's emotional state.

[1466] The identification processing performed by the identification 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 recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable specialist based on the stored patient information using a generation model; means for analyzing the patient's emotions using an emotion engine; means for selecting the most suitable specialist based on the analyzed emotions, connecting the specialist and the patient online, and conducting diagnoses and consultations; and means for providing a reservation function. This makes it possible for users to easily access appropriate security specialists and obtain high-quality second opinions while reducing psychological burden.

[1467] "Patient medical history information" refers to information such as the illnesses, symptoms, and treatment history of the patient that they have suffered from in the past.

[1468] "Current treatment information" refers to information about the treatment a patient is currently receiving and its progress.

[1469] "Past test results" refers to data on diagnoses and test results that the patient has received in the past.

[1470] A "generative model" is an artificial intelligence algorithm used to select the most suitable expert based on collected data.

[1471] An "emotion engine" is a system that analyzes user input data and recognizes their emotional state.

[1472] The "reservation function" is a feature that allows users to specify the date and time for online diagnoses or consultations and make reservations.

[1473] A "specialist" is a professional who is well-versed in a particular field and capable of providing appropriate advice and diagnoses.

[1474] "Online diagnosis" refers to the act of a specialist diagnosing a patient's condition via the internet.

[1475] "Consultation" refers to the act of a specialist providing expert opinions and advice in response to questions and concerns from patients or users.

[1476] An "optimal specialist" is a professional who can provide the most appropriate response based on the patient's symptoms and emotional state.

[1477] This invention relates to an online consultation system for security services. Specifically, it includes a series of processes for analyzing the user's emotions, selecting the most suitable security expert, and connecting them online. Specific embodiments of this system are described below.

[1478] User terminal

[1479] Users access the system using a smartphone or PC. An account is created when a user registers and enters their name, email address, and password. After registration, they receive a confirmation email, click the link to activate their account, and log in. Users enter information about their security issues and past countermeasures. During this process, an emotion engine analyzes this data to recognize the user's emotional state.

[1480] Emotional Engine

[1481] The emotion engine utilizes technologies such as IBM Watson and Microsoft Azure Cognitive Services. It analyzes user-input text and voice data and tags them with emotions. For example, it recognizes emotions like "reassurance," "anxiety," and "doubt." This allows for a quantitative assessment of the user's psychological burden.

[1482] server

[1483] The servers are operated using AWS EC2, Google Cloud Platform, etc. The servers record user information and sentiment data and pass this to a generative AI model. Using generative AI models such as OpenAI GPT-4, the most suitable security expert is selected based on the user's information and sentiment. The selection process includes matching against past case data.

[1484] Generative AI Models

[1485] The generative AI model selects the most suitable expert for the user based on the collected data. This model, known as a "generative AI model," learns from past case data and similar cases. An example of a prompt is shown below:

[1486] USER: Regarding the hacking prevention meeting scheduled for Wednesday afternoon, how can I choose a security expert who will help alleviate my concerns?

[1487] Assistant:

[1488] Expert selection and booking

[1489] A list of experts selected by the server is presented to the user. The user selects their preferred expert and books an online consultation time. Reservation information is managed using the Google Calendar API and Microsoft Outlook API.

[1490] Online diagnosis and consultation

[1491] At the scheduled time, the server initiates a video call using the Zoom API or Google Meet API. The expert and the user connect to conduct a diagnosis and consultation. The diagnosis and feedback are recorded and provided to the user. This allows the user to obtain a high-quality second opinion while reducing psychological burden.

[1492] As a concrete example, a user registers an account and enters a security concern after logging in. At this point, the emotion engine recognizes this as "anxiety." The generative AI model selects the most suitable expert based on the provided information and emotion data, and schedules an online consultation at the user's preferred date and time. A video call begins at the scheduled time, and the expert takes an approach to alleviate the user's anxiety.

[1493] This allows users to easily receive advice from appropriate experts when they face security issues, thereby reducing their psychological burden.

[1494] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1495] Step 1:

[1496] The user terminal provides an interface for users to register with the system. The user enters their name, email address, and password, and presses the registration button. The server receives the input data, creates the account using Firebase Authentication or Auth0, and sends a confirmation email. The user activates their account by clicking the link in the confirmation email and can then log in.

[1497] Input: Name, email address, password

[1498] Output: Account creation confirmation email

[1499] Step 2:

[1500] The user terminal provides a login interface. The user logs in through this interface and begins the process of entering their security issues and past countermeasures. For example, they might enter details such as "the system is frequently being hacked." The entered data is sent to the server in text format.

[1501] Input: Email address, password, security information

[1502] Output: Sending security information to the server

[1503] Step 3:

[1504] The server sends the received security information to the emotion engine, which analyzes the text data to recognize the user's emotions. The emotion engine uses IBM Watson or Microsoft Azure Cognitive Services. The analysis results are output in formats such as "reassured," "anxious," and "doubtful."

[1505] Input: Text data of security information

[1506] Output: Emotional state (e.g., "anxiety")

[1507] Step 4:

[1508] The server passes user information and sentiment data to a generative AI model. The generative AI model uses OpenAI GPT-4 to analyze this data and compare it with past case data to select the most suitable security expert. The selection results are output as a list of multiple experts.

[1509] Input: User information, sentiment data

[1510] Output: List of experts

[1511] Step 5:

[1512] The user's terminal displays a list of experts received from the server. The user selects a desired expert from the list, specifies a date and time for the online consultation, and makes a reservation. The server manages the reservation information using the Google Calendar API or Microsoft Outlook API and notifies the selected expert.

[1513] Input: List of experts, preferred consultation date and time

[1514] Output: Saving of reservation information and notification to experts

[1515] Step 6:

[1516] The server initiates the video call at the scheduled time. It uses the Zoom API or Google Meet API to connect the expert and the user. The user then consults with the expert online to receive diagnosis and advice.

[1517] Input: Reservation information, Start video call

[1518] Output: Implementation of online consultations

[1519] Step 7:

[1520] The server records the diagnosis and feedback after the online consultation ends and provides it to the user's device. Users can access this information at a later date. The data is stored in Google Cloud Storage or Amazon S3.

[1521] Input: Content of online consultation

[1522] Output: Diagnostic results, feedback

[1523] Through these steps, users can easily receive advice from appropriate security experts and get personalized, emotion-based responses.

[1524] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1525] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1526] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1527] [Fourth Embodiment]

[1528] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1529] As shown in Figure 7, the 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.

[1530] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1531] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1532] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1533] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1534] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1535] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1536] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1537] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1538] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1539] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1540] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1541] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. The embodiments for carrying out this invention are described below in detail.

[1542] System Overview

[1543] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of user terminals, a server, and physician terminals.

[1544] User registration and login

[1545] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[1546] Entering patient information

[1547] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor.

[1548] Selecting the optimal doctor

[1549] The server passes the recorded patient information to a generating AI model. The generating AI model selects the most suitable doctor for the patient's condition by comparing it with past case data. The list of selected doctors is saved in association with the patient information and presented to the user.

[1550] Doctor referral and appointment

[1551] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The appointment information is stored on the server and notified to the selected doctor. At this point, the server prepares for the online diagnosis or consultation between the user and the doctor.

[1552] Online diagnosis and consultation

[1553] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[1554] Specific example

[1555] 1. The user registers with the system, entering their name (Taro Yamada), email address (taro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[1556] 2. After logging in, user Yamada Taro enters his medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image).

[1557] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Taro Yamada (e.g., Dr. Sato at Hospital A).

[1558] 4. User Yamada Taro selects Dr. Sato and books an online consultation for next Tuesday at 2:00 PM.

[1559] 5. The server saves the reservation information and notifies Dr. Sato. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user.

[1560] As described above, this system provides a comprehensive and convenient service that allows cancer patients and their families to easily obtain high-quality second opinions.

[1561] The following describes the processing flow.

[1562] Step 1:

[1563] The user opens the service's website or mobile app.

[1564] Step 2:

[1565] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[1566] The terminal sends the entered information to the server.

[1567] Step 3:

[1568] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[1569] The server stores the operation results in the database and processes them for sending the email.

[1570] Step 4:

[1571] The user clicks the confirmation link in the email they received.

[1572] When the device clicks the link, it sends a request to the verification API endpoint.

[1573] Step 5:

[1574] The server receives the confirmation request and updates the user's status to "Confirmed".

[1575] The server saves the update results to the database and returns a success response.

[1576] Step 6:

[1577] The user enters their email address and password in the login form and clicks the "Login" button.

[1578] The terminal sends the entered information to the server.

[1579] Step 7:

[1580] The server verifies the authentication information, and if it is correct, creates a session and authenticates the user.

[1581] The server saves session information to the database and returns a response that includes an authentication token.

[1582] Step 8:

[1583] After logging in, the user enters their medical history, current treatment information, and past test results.

[1584] The terminal displays a medical history input form, and the user enters the information and clicks the submit button.

[1585] Step 9:

[1586] The server saves the received data to the database.

[1587] The server formats the data and inserts it into the database.

[1588] Step 10:

[1589] The server passes the stored patient information to the AI ​​model that generates the data.

[1590] The server extracts the required patient information and sends a request to the AI ​​model's API.

[1591] Step 11:

[1592] The generative AI model analyzes patient information and compares it with relevant past case data.

[1593] The generation AI model generates the optimal list of doctors and returns it to the server.

[1594] Step 12:

[1595] The server saves the generated list of doctors to the database and sends the results to the user.

[1596] The server formats the list of doctors and returns the response to the user.

[1597] Step 13:

[1598] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[1599] The terminal displays available reservation dates and times and sends the user's selection to the server.

[1600] Step 14:

[1601] The server saves the selected doctor and date / time to the booking system.

[1602] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[1603] Step 15:

[1604] The server sends the reservation confirmation result to the user.

[1605] The server sends a reservation confirmation email to the user.

[1606] Step 16:

[1607] The user accesses the app or website at the scheduled time.

[1608] The device verifies the reservation information and connects to the video call gateway.

[1609] Step 17:

[1610] The server creates a video call session and connects the doctor and the user.

[1611] The server calls the real-time communication API to start a session.

[1612] Step 18:

[1613] Users and doctors conduct online diagnoses and consultations.

[1614] The device sends and receives voice and video data, providing real-time communication.

[1615] Step 19:

[1616] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[1617] The server saves the diagnostic information to a database and sends a feedback email to the user.

[1618] (Example 1)

[1619] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1620] In modern medicine, it is difficult for cancer patients and their families to easily obtain high-quality second opinions. Furthermore, the diverse tasks involved, such as managing patient information, selecting the most suitable medical specialist, and arranging online consultations, are time-consuming and labor-intensive when performed manually. Moreover, while it is desirable to perform these processes quickly and accurately, systems for this are still lacking. To address these challenges and provide high-quality medical services to cancer patients and their families, there is a growing need for online second opinion services.

[1621] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1622] This invention includes a server that records and stores a patient's medical history information, current treatment information, and past test results; a server that sends a confirmation email to activate a user account; a server that allows the user to input patient information after logging in; a server that uses a generated AI model to select and introduce the most suitable medical professional based on the stored patient information; a server that connects medical professionals and patients online to conduct diagnoses and consultations; a server that stores and notifies medical professionals of appointment information for diagnoses and consultations; and a server that records and provides diagnoses and feedback. This makes it possible for cancer patients and their families to easily obtain high-quality second opinions.

[1623] "Medical history information" refers to information that shows a patient's past medical records and disease history.

[1624] "Treatment information" refers to information that describes the content and methods of treatment a patient is currently receiving.

[1625] "Test results" refer to information that shows the results and data of medical tests performed in the past.

[1626] A "confirmation email" is an email sent to verify the email address registered by the user and to activate their account.

[1627] A "user account" is an individual account that a user registers and authenticates in order to access and use a system.

[1628] A "generative AI model" is a model that uses artificial intelligence technology to select the most suitable medical professional based on past data.

[1629] A "medical professional" is a doctor or healthcare worker who possesses specialized knowledge and skills to address a patient's medical condition and case.

[1630] "Online diagnosis" refers to the process by which medical professionals provide diagnoses and consultations to patients via the internet.

[1631] "Reservation information" refers to information such as the date and time of online diagnosis or consultation, and the medical professional.

[1632] "Feedback" refers to information that provides evaluations, opinions, and advice after a diagnosis or consultation.

[1633] A "second opinion" refers to a diagnosis or opinion received from a medical professional other than your primary physician.

[1634] This invention relates to an online second opinion service aimed at enabling cancer patients and their families to easily obtain high-quality second opinions. The system primarily consists of a server, user terminals, and medical professional terminals. Detailed embodiments of this invention are described below.

[1635] User registration and login

[1636] When a user accesses the system, they first register. The user enters their name, email address, and password and submits them to the server. The server stores the received information in its database and sends a confirmation email to the user. When the user clicks the link in the confirmation email, their account is activated. Next, the user enters their email address and password on the login screen and is authenticated. The server verifies the authentication information and allows the user to start a session.

[1637] Entering patient information

[1638] After the user logs in, they enter medical history information, current treatment information, and past test results on the patient information input screen. The user terminal sends the entered information to the server. The server stores the entered information in a database and formats the data as needed.

[1639] Selection of the most suitable medical professional

[1640] The server inputs stored patient information into a generative AI model. This generative AI model is built using Python's TensorFlow, among other tools. The generative AI model compares the patient's information with past case data and selects the most suitable medical professional for their condition. The server saves the list of selected medical professionals to a database and displays it to the user.

[1641] Referral and appointment scheduling for medical professionals

[1642] The user selects a preferred medical professional from a list of available professionals and chooses a date and time for an online diagnosis or consultation. The user's terminal sends the selection information to the server. The server stores the reservation information in a database and notifies the selected medical professional.

[1643] Online diagnosis and consultation

[1644] At the scheduled time, the user accesses the system and begins the online diagnosis. The server provides communication methods such as video calls and text chats, connecting the user with a medical professional. Real-time video calls are enabled using technologies such as WebRTC. After the diagnosis and consultation are completed, the server records the diagnosis details and feedback in a database and provides them to the user.

[1645] Specific example

[1646] The following are examples of specific prompt messages:

[1647] "The user registers with the system, entering their name (e.g., Patient A), email address (e.g., patientA@example.com), and password. They receive a confirmation email and click the link to activate their account. After user Patient A logs in, they enter their medical history (e.g., Stage III lung cancer), current treatment information (e.g., chemotherapy), and past test results (most recent CT scan image). The server passes this information to a generating AI model, which selects the most suitable medical professional. The generating AI model lists the most suitable medical professionals for Patient A based on past case data. User Patient A selects a medical professional and books an online consultation for next Tuesday at 2:00 PM. The server saves the reservation information and notifies the medical professional. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server records the consultation details and sends feedback to the user."

[1648] Thus, the present invention provides a comprehensive and convenient service that enables cancer patients and their families to easily obtain high-quality second opinions.

[1649] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1650] Step 1:

[1651] The user accesses the new registration screen and enters their name, email address, and password.

[1652] Input: User's name, email address, and password.

[1653] Output: User information sent to the server.

[1654] Specific action: The user enters "Patient A", "patientA@example.com", and "password123" into the form fields and clicks the "Register" button.

[1655] Step 2:

[1656] The server saves the received information to the database and sends a confirmation email to the user.

[1657] Input: User's submitted name, email address, and password.

[1658] Output: User information stored in the database and a confirmation email sent to the user.

[1659] Specific operation: The server uses an email sending service (e.g., SendGrid) to send a "confirmation email".

[1660] Step 3:

[1661] The user activates their account by clicking the link in the confirmation email.

[1662] Input: The link included in the confirmation email.

[1663] Output: Request to the server and account activation.

[1664] Specific operation: When a user clicks a link in an email, a request is sent to a specific endpoint on the server, and the user's account is activated.

[1665] Step 4:

[1666] The user enters their email address and password on the login screen and undergoes authentication.

[1667] Enter: email address, password.

[1668] Output: Login request to the server and authentication information.

[1669] Specific action: The user enters "patientA@example.com" and "password123" and clicks the "Login" button.

[1670] Step 5:

[1671] The server verifies the authentication information and allows the user to start a session.

[1672] Input: User login request.

[1673] Output: Session started and JWT token generated.

[1674] Specific operation: The server checks the authentication information, creates a session upon success, generates a JWT token, and returns it to the user.

[1675] Step 6:

[1676] The user enters medical history information, current treatment details, and past test results on the patient information input screen.

[1677] Input: Medical history information, current treatment, past test results.

[1678] Output: Patient information sent to the server.

[1679] Specific operation: The user inputs "Lung cancer stage III", treatment "Chemotherapy", and test results "CT scan image".

[1680] Step 7:

[1681] The server saves the entered information to the database and formats the data as needed.

[1682] Input: Patient information submitted by the user.

[1683] Output: Patient information stored in the database.

[1684] Specific operation: The server formats the data and saves it to the appropriate field.

[1685] Step 8:

[1686] The server inputs patient information into an AI model, which then compares it with past case data to select the most suitable medical professional.

[1687] Input: Patient information.

[1688] Output: List of selected medical professionals.

[1689] Specific operation: The server inputs patient information into an AI model (using Python's TensorFlow), and the model selects the most suitable medical professional.

[1690] Step 9:

[1691] The server saves a list of selected medical professionals to a database and displays it to the user.

[1692] Input: A list of selected medical professionals.

[1693] Output: A list of medical professionals displayed to the user.

[1694] Specific operation: The server returns a list of medical professionals to the frontend to display on the user's dashboard.

[1695] Step 10:

[1696] Users can select their preferred medical professional and choose a date and time for an online diagnosis or consultation.

[1697] Input: Selection of medical professional and appointment date / time.

[1698] Output: Reservation information sent to the server.

[1699] Specific action: The user selects Dr. Sato and schedules an online consultation for next Tuesday at 2:00 PM.

[1700] Step 11:

[1701] The server saves the reservation information to a database and notifies the selected medical professional.

[1702] Input: Reservation information submitted by the user.

[1703] Output: Appointment information stored in the database and notifications to medical professionals.

[1704] Specific operation: The server notifies medical professionals of the appointment information via email or in-app notifications.

[1705] Step 12:

[1706] The user accesses the system at the scheduled time and begins the online diagnosis.

[1707] Input: Reservation date and time and access information.

[1708] Output: Online diagnosis initiated.

[1709] Specific action: The user accesses the specified URL and enters the video call screen.

[1710] Step 13:

[1711] The server provides communication methods such as video calls and text chats, connecting medical professionals and users.

[1712] Input: Communication request between user and medical professional.

[1713] Output: Connects to video calls and text chats.

[1714] Specific operation: The server uses technologies such as WebRTC to enable real-time video calls.

[1715] Step 14:

[1716] After the diagnosis and consultation are complete, the server records the diagnosis details and feedback in a database and provides them to the user.

[1717] Input: Diagnostic details, feedback.

[1718] Output: Diagnostic information recorded in the database and feedback to the user.

[1719] Specific action: The server saves the diagnostic report and displays it on the user's dashboard.

[1720] The above describes the processing steps of the system of the present invention.

[1721] (Application Example 1)

[1722] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1723] Traditionally, when cancer patients and their families sought high-quality second opinions, managing information was cumbersome, and the risk of personal information leaks was high. Furthermore, the accuracy of selecting appropriate doctors was low, and the procedures for booking online diagnoses and consultations were complicated, placing a heavy burden on patients and their families. In addition, concerns about the security of digital data acted as a barrier to using online services. To solve these problems, a system is needed that processes medical information safely and efficiently and provides high-quality medical services.

[1724] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1725] In this invention, the server includes means for recording and storing patient medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable physician based on the stored patient information using a generative model; means for connecting physicians and patients online to conduct diagnoses and consultations; means for storing patient information in encryption; and means for encrypting and authenticating user information. This makes it possible to securely manage patient and user information and efficiently provide high-quality second opinions.

[1726] "Patient medical history information" refers to detailed information about a patient's past illnesses and treatments.

[1727] "Current treatment information" refers to information about the treatment a patient is currently receiving.

[1728] "Past test results" refers to information about the results of tests the patient has received in the past.

[1729] "Means of recording and preserving" refers to devices and systems for collecting and electronically storing patient information.

[1730] "Stored patient information" refers to information about patients that is recorded within the system and stored in a database or similar location.

[1731] The term "optimal physician" refers to a medical professional best suited to a patient's condition, as determined by a generative model.

[1732] A "generative model" is an algorithm or machine learning model designed to perform a specific task based on past case data.

[1733] "Means of selection and referral" refers to a mechanism that uses generative models to select appropriate doctors and provide that information to patients.

[1734] "A means of connecting doctors and patients online for diagnosis and consultation" refers to a system that provides an environment where doctors and patients can communicate directly using the internet and digital communication.

[1735] "Methods for encrypting and storing patient information" refers to methods of securely storing patient information in the form of digital data by encrypting it.

[1736] "Methods for encrypting and authenticating user information" refers to a mechanism that encrypts and stores user identification information and uses it during authentication.

[1737] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions. To implement this invention, key functions include user registration and login, input of patient information, selection of the most suitable doctor, doctor referral and appointment scheduling, online diagnosis and consultation, and data encryption and storage.

[1738] 1. User registration and login

[1739] Users on their terminals enter basic information such as their name, email address, and password to register. The entered data is received by the server and encrypted using Fernet encryption technology. The encrypted data is securely stored in the database. Users receive a confirmation email and can log in by clicking the link to activate their account.

[1740] 2. Entering patient information

[1741] After logging in, users enter their medical history, current treatment information, and past test results. This information is also encrypted by the server and stored in the database. This step ensures that patient information is securely managed within the system.

[1742] 3. Selection of the most suitable physician

[1743] The server passes the stored patient information to a generating AI model. The generating AI model compares it with past case data and executes prompts to select the most suitable doctor for the patient. The list of selected doctors is presented to the user terminal, associated with the patient information.

[1744] 4. Doctor referral and appointment

[1745] From the presented list of doctors, users select their preferred doctor and book an appointment for an online diagnosis or consultation. The booking information is encrypted by the server and stored in a database. The selected doctor is notified of the booking information and is ready for the online diagnosis or consultation.

[1746] 5. Implementation of online diagnosis and consultation

[1747] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chats, connecting the user's terminal and the doctor's terminal. After the diagnosis and consultation are completed, the diagnosis and feedback are encrypted by the server and provided to the user's terminal.

[1748] Adding specific examples

[1749] 1. The user registers with the system, entering their name (e.g., Ichiro Tanaka), email address (e.g., ichiro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[1750] 2. After logging in, user Ichiro Tanaka enters his medical history information (e.g., stage II gastric cancer), current treatment (e.g., radiation therapy), and past test results (most recent MRI images).

[1751] 3. The server passes this information to the generating AI model, which then selects the most suitable doctor. Based on past case data, the generating AI model lists the most suitable doctors for Ichiro Tanaka (e.g., Dr. Yamada at Hospital B).

[1752] 4. User Ichiro Tanaka selects Dr. Yamada and books an online consultation for next Wednesday at 2:30 PM.

[1753] 5. The server saves the reservation information and notifies Dr. Yamada. At the scheduled time, the user participates in the online consultation, the server initiates a video call, and the consultation is conducted. After the consultation is complete, the server encrypts and records the consultation details and sends feedback to the user.

[1754] Example prompts for generative AI models

[1755] Cancer patient information: Stage II gastric cancer, current treatment: radiation therapy, past test results: latest MRI images. Please select the best doctor for this patient.

[1756] The system of the present invention can manage the entire process from user registration to online diagnosis in a highly secure and efficient manner. As a result, cancer patients and their families can obtain high-quality second opinions with peace of mind.

[1757] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1758] Step 1:

[1759] User registration information (name, email address, password) is entered from the user's terminal. The server receives this information and encrypts it using Fernet encryption technology. The encrypted data is stored in the database. The output is that the encrypted user information is stored in the database.

[1760] Step 2:

[1761] After registration is complete, the server sends a confirmation email. The user's device activates the account by clicking the link in the confirmation email. The input is clicking the link in the confirmation email, and the output is account activation.

[1762] Step 3:

[1763] The user enters login information (email address, password) from their terminal. The server decrypts the encrypted data in the database and verifies that it matches. The input is the login information, and the output is the result of successful or unsuccessful login authentication.

[1764] Step 4:

[1765] After successful login, patient information (medical history, current treatment information, past test results) is entered from the user's terminal. The server then encrypts this information again using Fernet encryption technology and stores it in the database. The input is patient information, and the output is the storage of encrypted patient information.

[1766] Step 5:

[1767] The server passes patient information from the database to a generating AI model. The generating AI model compares this information with past case data and selects the most suitable doctor for the patient based on the prompt text. The input is encrypted patient information and prompt text, and the output is a list of suitable doctors.

[1768] Step 6:

[1769] A list of suitable doctors is presented to the user's terminal. The user selects a desired doctor from the list and enters the date and time for an online diagnosis or consultation. The input consists of the desired doctor and the date and time of the diagnosis, and the output is the generation of reservation information.

[1770] Step 7:

[1771] The server encrypts the reservation information and stores it in a database. Furthermore, it notifies the selected physicians of the reservation information. The input is the reservation information, and the output is the storage and notification of the encrypted reservation information.

[1772] Step 8:

[1773] At the scheduled time, the user participates in the online diagnosis and consultation. The server manages video calls and text chats and connects the user's terminal with the doctor's terminal. The input is a request to start the online diagnosis, and the output is the start of the diagnosis and consultation session.

[1774] Step 9:

[1775] After the diagnosis and consultation are complete, the server encrypts and records the diagnosis details and feedback, and provides them to the user's terminal. The input is the diagnosis details and feedback, and the output is the storage and provision of encrypted diagnostic data.

[1776] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1777] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and more particularly to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis / consultation.

[1778] System Overview

[1779] This system collects patient information, selects the most suitable physician using a generated AI model, and provides a series of functions for online diagnosis and consultation. The system mainly consists of a user terminal, a server, a physician's terminal, and an emotion engine.

[1780] User registration and login

[1781] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[1782] Entering patient information

[1783] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, the user's input data includes text, audio, and video data, which an emotion engine analyzes to recognize the user's emotions.

[1784] Selecting the optimal doctor

[1785] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[1786] Doctor referral and appointment

[1787] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The reservation information is stored on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis or consultation.

[1788] Online diagnosis and consultation

[1789] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[1790] Specific example

[1791] 1. The user registers with the system, entering their name (Ichiro Tanaka), email address (ichiro@example.com), and password. They receive a confirmation email and click the link to activate their account.

[1792] 2. After logging in, user Ichiro Tanaka enters his medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image). Furthermore, while he is entering the information, the emotion engine analyzes the text and voice data and recognizes Ichiro Tanaka's emotion as "anxiety."

[1793] 3. The server passes patient information and emotional data to a generating AI model, which then selects the most suitable doctor (e.g., Dr. Nakamura from Hospital B). Based on the emotional data, it is considered that Dr. Nakamura possesses the expertise to alleviate the patient's anxiety.

[1794] 4. User Ichiro Tanaka selects Dr. Nakamura and books an online consultation for next Thursday at 4:00 PM.

[1795] 5. The server saves the reservation information and notifies Dr. Nakamura. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. Dr. Nakamura uses Ichiro Tanaka's emotional data as a reference to take an approach that reduces anxiety.

[1796] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to Ichiro Tanaka.

[1797] As described above, this system provides a comprehensive and convenient service that combines an emotional engine to easily enable cancer patients and their families to obtain high-quality second opinions.

[1798] The following describes the processing flow.

[1799] Step 1:

[1800] The user opens the service's website or mobile app.

[1801] Step 2:

[1802] The user enters the required information (name, email address, password) into the new registration form and clicks the "Register" button.

[1803] The terminal sends the entered information to the server.

[1804] Step 3:

[1805] The server saves the received information to the database and sends a confirmation email to the user for authentication.

[1806] The server stores the operation results in the database and processes them for sending the email.

[1807] Step 4:

[1808] The user clicks the confirmation link in the email they received.

[1809] When the device clicks the link, it sends a request to the verification API endpoint.

[1810] Step 5:

[1811] The server receives the confirmation request and updates the user's status to "Confirmed".

[1812] The server saves the update results to the database and returns a success response.

[1813] Step 6:

[1814] The user enters their email address and password in the login form and clicks the "Login" button.

[1815] The terminal sends the entered information to the server.

[1816] Step 7:

[1817] The server verifies the authentication information, and if it is correct, creates a session and authenticates the user.

[1818] The server saves session information to the database and returns a response that includes an authentication token.

[1819] Step 8:

[1820] After logging in, the user enters their medical history, current treatment information, and past test results.

[1821] The terminal displays a medical history input form, and the user enters the information and clicks the submit button.

[1822] Step 9:

[1823] The server stores patient information and text, audio, and video data received by the server in a database.

[1824] The server formats the data and inserts it into the database.

[1825] Step 10:

[1826] The emotion engine analyzes the user's text, voice, and video data to recognize their emotions.

[1827] The emotion engine generates emotion data and returns the results to the server.

[1828] Step 11:

[1829] The server passes stored patient information and emotional data to the generating AI model.

[1830] The server extracts the required patient information and sends a request to the AI ​​model's API.

[1831] Step 12:

[1832] The generative AI model analyzes patient information and emotional data, and compares it with relevant past case data.

[1833] The generation AI model generates the optimal list of doctors and returns it to the server.

[1834] Step 13:

[1835] The server saves the generated list of doctors to the database and sends the results to the user.

[1836] The server formats the list of doctors and returns the response to the user.

[1837] Step 14:

[1838] The user selects a preferred doctor from the suggested list and chooses a date and time for the online consultation.

[1839] The terminal displays available reservation dates and times and sends the user's selection to the server.

[1840] Step 15:

[1841] The server saves the selected doctor and date / time to the booking system.

[1842] The server saves the doctor's name and date / time details to a database and sends a notification to the doctor.

[1843] Step 16:

[1844] The server sends the reservation confirmation result to the user.

[1845] The server sends a reservation confirmation email to the user.

[1846] Step 17:

[1847] The user accesses the app or website at the scheduled time.

[1848] The device verifies the reservation information and connects to the video call gateway.

[1849] Step 18:

[1850] The server creates a video call session and connects the doctor and the user.

[1851] The server calls the real-time communication API to start a session.

[1852] Step 19:

[1853] Users and doctors conduct online diagnoses and consultations.

[1854] The device sends and receives voice and video data, providing real-time communication.

[1855] Doctors refer to the user's emotional data to adjust diagnoses and advice.

[1856] Step 20:

[1857] After the diagnosis is complete, the server records the diagnosis details and provides feedback to the user.

[1858] The server saves the diagnostic information to a database and sends a feedback email to the user.

[1859] (Example 2)

[1860] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1861] There is a need for a system that allows cancer patients and their families to easily and quickly obtain high-quality second opinions. In particular, it is crucial to improve the quality of physician selection, diagnosis, and consultation, taking into account the patient's feelings, but the current system struggles to meet these requirements. Conventional systems have the problem of selecting physicians without considering the patient's feelings, thus failing to alleviate the psychological burden on the patient.

[1862] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1863] In this invention, the server includes means for recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable doctor based on the stored patient information using a generative model; means for analyzing input text, voice, and video data to recognize the patient's emotions; means for selecting the most suitable doctor for the patient based on the recognized emotion data; means for connecting the doctor and patient online to conduct diagnoses and consultations; and means for recording and providing the diagnosis and feedback to the patient. This makes it possible to select a doctor that takes the patient's emotions into consideration, thereby reducing the patient's psychological burden and providing a system that makes it easy to obtain a high-quality second opinion.

[1864] "Patient medical history information" refers to details of illnesses and treatments that a patient has experienced in the past and present, including diagnoses, symptoms, and treatment history.

[1865] "Treatment information" refers to the type and method of treatment a patient is currently receiving, and includes information such as medication, surgery, radiation therapy, and chemotherapy.

[1866] "Test results" refer to the results of medical examinations performed on a patient, and include data from blood tests, imaging diagnostics (CT scans, MRI, etc.), and biopsies.

[1867] A "database" refers to a system for electronically storing and managing information, such as patient information, doctor information, and emotional data.

[1868] An "emotion engine" refers to software and algorithms that analyze input data (text, audio, video, etc.) and automatically identify emotions.

[1869] A "generative model" refers to an AI (artificial intelligence) algorithm that makes new predictions or generates new data based on past data, and it utilizes machine learning and deep learning technologies.

[1870] "Online diagnosis" refers to the process of diagnosing a patient via the internet, and this includes video calls and text chats.

[1871] "Feedback" refers to the opinions and advice that doctors provide to patients after an online diagnosis or consultation, and includes diagnostic results, treatment suggestions, and information about additional tests.

[1872] The "reservation function" refers to a feature within the system that allows patients to reserve a date and time for diagnosis or consultation online in advance.

[1873] "Communication methods" refer to technologies used to connect doctors and patients in online diagnoses and consultations, and include video calls, voice calls, and text chats.

[1874] This invention relates to an online second opinion service that enables cancer patients and their families to easily obtain high-quality second opinions, and moreover, to a system that incorporates an emotion engine that recognizes the user's emotions and reflects them in the selection of doctors and online diagnosis and consultation.

[1875] This system primarily consists of user terminals, a server, a doctor's terminal, and an emotion engine. User terminals are devices used by users to access the system and input information, including personal computers, smartphones, and tablets. The server is a computer system for managing, analyzing, and storing information, and includes databases, generative AI models, and an emotion engine.

[1876] User registration and login

[1877] When a user accesses the system, they must first register. The user enters basic information such as their name, email address, and password, and receives a confirmation email to complete the registration. After confirmation, they can log in.

[1878] Entering patient information

[1879] After logging in, users enter their medical history, current treatment information, and past test results. This information is recorded in the system's database and used later as foundational data to select the most suitable doctor. In addition, user input data includes text, audio, and video data, which the emotion engine analyzes to recognize the user's emotions. For example, the IBM Watson Sentiment Analysis API can be used for text data, and the API can be used to analyze emotions for audio data.

[1880] Selecting the optimal doctor

[1881] The server passes recorded patient information and emotional data recognized by the emotion engine to a generative AI model. The generative AI model selects the most suitable doctor for the patient's condition and emotions by comparing it with past case data. The list of selected doctors is stored in association with the patient information and presented to the user.

[1882] Doctor referral and appointment

[1883] From the presented list of doctors, the user selects their preferred doctor and books an appointment for an online diagnosis or consultation. The reservation information is stored on the server and notified to the selected doctor. At this stage, the server prepares for the online diagnosis or consultation.

[1884] Online diagnosis and consultation

[1885] At the scheduled time, the user participates in an online diagnosis and consultation. The server provides communication methods such as video calls and text chat to connect the doctor and the user. For example, it may use the Zoom API or Twilio API to provide video call functionality. After the diagnosis and consultation are completed, the server records the diagnosis and feedback and provides it to the user.

[1886] Specific example

[1887] 1. The user registers with the system, entering their name, email address, and password. They receive a confirmation email and click the link to activate their account.

[1888] 2. After logging in, the user enters their medical history information (e.g., stage III lung cancer), current treatment (e.g., chemotherapy), and past test results (most recent CT scan image). Furthermore, during the input process, the emotion engine analyzes the text and voice data and recognizes the user's emotion as "anxiety."

[1889] 3. The server passes patient information and emotional data to a generating AI model, which then selects the most suitable doctor. For example, a doctor with expertise in reducing patient anxiety based on emotional data might be selected.

[1890] 4. The user selects a doctor and books an online consultation.

[1891] 5. The server saves the appointment information and notifies the doctor. At the scheduled time, the user participates in the online consultation, and the server initiates the video call. The doctor uses the user's emotional data to implement an approach that reduces anxiety.

[1892] 6. After the diagnosis is complete, the server records the diagnosis details and sends feedback to the user.

[1893] Example of a prompt

[1894] The following are examples of prompts to input into a generative AI model:

[1895] Patient information:

[1896] Medical history: Stage III lung cancer

[1897] Current treatment: Chemotherapy

[1898] Previous test results: Latest CT scan images

[1899] Emotional data:

[1900] Emotion: Anxiety

[1901] Criteria for selecting the best doctor:

[1902] 1. Expertise in lung cancer

[1903] 2. Communication skills to alleviate patient anxiety

[1904] Please select the most suitable doctor based on the above conditions.

[1905] The above describes specific embodiments for carrying out the present invention.

[1906] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1907] Step 1: User registration and verification

[1908] The user accesses the system's website and enters basic information such as their name, email address, and password.

[1909] (Input): User's basic information (name, email address, password)

[1910] (Output): Request to send confirmation email

[1911] The server will send a confirmation email to the email address you entered. This email will contain a link to activate your account.

[1912] (Input): User's email address

[1913] (Output): Confirmation email (with link)

[1914] The user clicks the link in the confirmation email to activate their account.

[1915] (Input): Clicked the link in the confirmation email

[1916] (Output): Account activation

[1917] Step 2: Log in

[1918] Users log in using their email address and password.

[1919] (Enter): Email address, password

[1920] (Output): Login success or failure message

[1921] Step 3: Entering patient information and sentiment analysis

[1922] After logging in, the user enters their medical history, current treatment information, and past test results.

[1923] (Input): Medical history information, treatment information, test results

[1924] (Output): Request to save input data

[1925] The server saves the input data to the database.

[1926] (Input): Patient information

[1927] (Output): Database save success message

[1928] The device sends text, audio, and video data to the emotion engine for analysis.

[1929] Example: Using the IBM Watson Sentiment Analysis API

[1930] (Input): Text, audio, and video data

[1931] (Output): Emotion analysis results (e.g., "anxiety")

[1932] Step 4: Selecting a physician

[1933] The server generates prompt messages to pass patient information and emotional data to the AI ​​model.

[1934] (Input): Patient information, emotional data

[1935] (Output): Prompt message

[1936] The generative AI model selects the most suitable doctor based on the prompt text.

[1937] (Input): Prompt message

[1938] (Output): Doctor list

[1939] The server presents the user with a list of selected doctors.

[1940] (Input): Doctor list

[1941] (Output): Doctor list displayed on user screen

[1942] Step 5: Doctor referral and appointment

[1943] Users select a doctor from a list of doctors provided and book an online consultation or appointment.

[1944] (Input): Selected doctor, preferred date and time

[1945] (Output): Reservation Request

[1946] The server saves the reservation information to the database and sends a notification to the selected doctor.

[1947] (Input): Reservation information

[1948] (Output): Database saved successfully, notification sent to physician.

[1949] Step 6: Conducting online diagnosis and consultation

[1950] At the scheduled time, the server will provide communication methods such as video calls and text chats.

[1951] Example: Using the Zoom API or Twilio API

[1952] (Input): Reservation date and time

[1953] (Output): Provides communication interface

[1954] Users participate in online diagnostics, and doctors provide diagnoses and consultations.

[1955] (Input): User participation, Doctor participation

[1956] (Output): Diagnosis and consultation implemented.

[1957] Step 7: Processing after diagnosis is complete

[1958] The server records diagnostic information and feedback in a database.

[1959] (Input): Diagnostic details, feedback

[1960] (Output: Database save successful)

[1961] The server sends feedback to the user.

[1962] (Input): Feedback

[1963] (Output): Feedback notification

[1964] The above is a description of this system's program, broken down into processing steps and including specific operations.

[1965] (Application Example 2)

[1966] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1967] There are few systems that allow users facing security issues to easily seek a second opinion from a suitable security expert. Furthermore, there is a lack of systems that provide customized support to reduce the psychological burden on users. In particular, there is a need to provide a higher-quality consultation experience by considering the user's emotional state.

[1968] The identification processing performed by the identification 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 recording and storing the patient's medical history information, current treatment information, and past test results; means for selecting and introducing the most suitable specialist based on the stored patient information using a generation model; means for analyzing the patient's emotions using an emotion engine; means for selecting the most suitable specialist based on the analyzed emotions, connecting the specialist and the patient online, and conducting diagnoses and consultations; and means for providing a reservation function. This makes it possible for users to easily access appropriate security specialists and obtain high-quality second opinions while reducing psychological burden.

[1969] "Patient medical history information" refers to information such as the illnesses, symptoms, and treatment history of the patient that they have suffered from in the past.

[1970] "Current treatment information" refers to information about the treatment a patient is currently receiving and its progress.

[1971] "Past test results" refers to data on diagnoses and test results that the patient has received in the past.

[1972] A "generative model" is an artificial intelligence algorithm used to select the most suitable expert based on collected data.

[1973] An "emotion engine" is a system that analyzes user input data and recognizes their emotional state.

[1974] The "reservation function" is a feature that allows users to specify the date and time for online diagnoses or consultations and make reservations.

[1975] A "specialist" is a professional who is well-versed in a particular field and capable of providing appropriate advice and diagnoses.

[1976] "Online diagnosis" refers to the act of a specialist diagnosing a patient's condition via the internet.

[1977] "Consultation" refers to the act of a specialist providing expert opinions and advice in response to questions and concerns from patients or users.

[1978] An "optimal specialist" is a professional who can provide the most appropriate response based on the patient's symptoms and emotional state.

[1979] This invention relates to an online consultation system for security services. Specifically, it includes a series of processes for analyzing the user's emotions, selecting the most suitable security expert, and connecting them online. Specific embodiments of this system are described below.

[1980] User terminal

[1981] Users access the system using a smartphone or PC. An account is created when a user registers and enters their name, email address, and password. After registration, they receive a confirmation email, click the link to activate their account, and log in. Users enter information about their security issues and past countermeasures. During this process, an emotion engine analyzes this data to recognize the user's emotional state.

[1982] Emotional Engine

[1983] The emotion engine utilizes technologies such as IBM Watson and Microsoft Azure Cognitive Services. It analyzes user-input text and voice data and tags them with emotions. For example, it recognizes emotions like "reassurance," "anxiety," and "doubt." This allows for a quantitative assessment of the user's psychological burden.

[1984] server

[1985] The servers are operated using AWS EC2, Google Cloud Platform, etc. The servers record user information and sentiment data and pass this to a generative AI model. Using generative AI models such as OpenAI GPT-4, the most suitable security expert is selected based on the user's information and sentiment. The selection process includes matching against past case data.

[1986] Generative AI Models

[1987] The generative AI model selects the most suitable expert for the user based on the collected data. This model, known as a "generative AI model," learns from past case data and similar cases. An example of a prompt is shown below:

[1988] USER: Regarding the hacking prevention meeting scheduled for Wednesday afternoon, how can I choose a security expert who will help alleviate my concerns?

[1989] Assistant:

[1990] Expert selection and booking

[1991] A list of experts selected by the server is presented to the user. The user selects their preferred expert and books an online consultation time. Reservation information is managed using the Google Calendar API and Microsoft Outlook API.

[1992] Online diagnosis and consultation

[1993] At the scheduled time, the server initiates a video call using the Zoom API or Google Meet API. The expert and the user connect to conduct a diagnosis and consultation. The diagnosis and feedback are recorded and provided to the user. This allows the user to obtain a high-quality second opinion while reducing psychological burden.

[1994] As a concrete example, a user registers an account and enters a security concern after logging in. At this point, the emotion engine recognizes this as "anxiety." The generative AI model selects the most suitable expert based on the provided information and emotion data, and schedules an online consultation at the user's preferred date and time. A video call begins at the scheduled time, and the expert takes an approach to alleviate the user's anxiety.

[1995] This allows users to easily receive advice from appropriate experts when they face security issues, thereby reducing their psychological burden.

[1996] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1997] Step 1:

[1998] The user terminal provides an interface for users to register with the system. The user enters their name, email address, and password, and presses the registration button. The server receives the input data, creates the account using Firebase Authentication or Auth0, and sends a confirmation email. The user activates their account by clicking the link in the confirmation email and can then log in.

[1999] Input: Name, email address, password

[2000] Output: Account creation confirmation email

[2001] Step 2:

[2002] The user terminal provides a login interface. The user logs in through this interface and begins the process of entering their security issues and past countermeasures. For example, they might enter details such as "the system is frequently being hacked." The entered data is sent to the server in text format.

[2003] Input: Email address, password, security information

[2004] Output: Sending security information to the server

[2005] Step 3:

[2006] The server sends the received security information to the emotion engine, which analyzes the text data to recognize the user's emotions. The emotion engine uses IBM Watson or Microsoft Azure Cognitive Services. The analysis results are output in formats such as "reassured," "anxious," and "doubtful."

[2007] Input: Text data of security information

[2008] Output: Emotional state (e.g., "anxiety")

[2009] Step 4:

[2010] The server passes user information and sentiment data to a generative AI model. The generative AI model uses OpenAI GPT-4 to analyze this data and compare it with past case data to select the most suitable security expert. The selection results are output as a list of multiple experts.

[2011] Input: User information, sentiment data

[2012] Output: List of experts

[2013] Step 5:

[2014] The user's terminal displays a list of experts received from the server. The user selects a desired expert from the list, specifies a date and time for the online consultation, and makes a reservation. The server manages the reservation information using the Google Calendar API or Microsoft Outlook API and notifies the selected expert.

[2015] Input: List of experts, preferred consultation date and time

[2016] Output: Saving of reservation information and notification to experts

[2017] Step 6:

[2018] The server initiates the video call at the scheduled time. It uses the Zoom API or Google Meet API to connect the expert and the user. The user then consults with the expert online to receive diagnosis and advice.

[2019] Input: Reservation information, Start video call

[2020] Output: Implementation of online consultations

[2021] Step 7:

[2022] The server records the diagnosis and feedback after the online consultation ends and provides it to the user's device. Users can access this information at a later date. The data is stored in Google Cloud Storage or Amazon S3.

[2023] Input: Content of online consultation

[2024] Output: Diagnostic results, feedback

[2025] Through these steps, users can easily receive advice from appropriate security experts and get personalized, emotion-based responses.

[2026] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2027] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2028] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2029] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2030] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2031] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2032] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2033] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[2034] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[2035] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[2036] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[2037] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[2038] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[2039] 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.

[2040] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[2041] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[2042] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[2043] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[2044] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[2045] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2046] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[2047] The following is further disclosed regarding the embodiments described above.

[2048] (Claim 1)

[2049] A means of recording and storing patient medical history information, current treatment information, and past test results,

[2050] A method for selecting and introducing the most suitable physician based on stored patient information using a generative model,

[2051] A means of connecting doctors and patients online for diagnosis and consultation,

[2052] A system that includes this.

[2053] (Claim 2)

[2054] The system according to claim 1, wherein the generative model selects the most suitable p...

Claims

1. A means of recording and storing patient medical history information, current treatment information, and past test results, A method for selecting and introducing the most suitable physician based on stored patient information using a generative model, A means of connecting doctors and patients online for diagnosis and consultation, A system that includes this.

2. The system according to claim 1, wherein the generative model selects the most suitable physician by comparing it with past case data.

3. The system according to claim 1, which provides an online diagnostic and consultation booking function based on patient input information.

Images