System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving input of symptoms from a user; means for analyzing the symptoms using a generation-related AI model and acquiring an initial diagnostic result; means for determining an appropriate medical department and consultation date and time based on the initial diagnostic result; means for notifying the user of the determined consultation date and time; and means for transmitting consultation contents to a healthcare provider in advance.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Long waiting times at hospitals result in reduced hospital operational efficiency and patients wasting their time. Furthermore, inefficient medical treatment increases the workload of doctors and nurses. There is a need to improve this situation and provide a system that is beneficial to both hospitals and patients. [Means for solving the problem]

[0005] The present invention provides a system that shortens waiting times and realizes efficient medical care by including a means for accepting symptom input from a user, a means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis, a means for determining an appropriate medical department and consultation date and time based on the initial diagnosis, a means for notifying the user of the determined consultation date and time, and a means for transmitting the details of the consultation to a healthcare provider in advance. This system further includes a means for accepting symptom images, analyzing them using an image analysis AI model to improve the accuracy of the initial diagnosis, a means for determining whether an online consultation is applicable, and a means for determining and notifying the date and time of the consultation if an online consultation is selected, thereby providing more flexible and efficient medical care. Furthermore, by notifying healthcare providers of the initial diagnosis results and the basis for the results, the system can reduce the workload of doctors and nurses, thereby improving the efficiency of medical care.

[0006] "User" refers to patients and general consumers who use the system.

[0007] "Symptom entry" refers to the act of a patient entering information about their health condition and symptoms into the system.

[0008] A "generative AI model" refers to an algorithm or program that uses artificial intelligence technology to analyze input data and generate diagnostic results.

[0009] "Initial diagnosis result" refers to the initial diagnostic information based on the patient's symptoms, obtained as a result of analysis by the generative AI model.

[0010] "Appointment Date and Time" refers to the date and time designated for a patient to meet with a healthcare provider.

[0011] "Means of notification" refers to the functionality or method by which the system communicates information to the user or healthcare provider.

[0012] "Healthcare provider" refers to professionals who provide health care services, such as doctors and nurses.

[0013] "Image analysis AI model" refers to artificial intelligence technology used to analyze medical images.

[0014] "Online consultation" refers to remote medical treatment conducted via the internet.

[0015] "Means for determining applicability" refers to an algorithm or procedure for determining whether an online consultation is possible.

[0016] An "optimization algorithm" refers to a mathematical or computer science technique for efficiently allocating resources. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a medical support assistant system for shortening waiting times at hospitals, and is realized in the specific embodiments described below.

[0039] Symptom input and initial diagnosis

[0040] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the diagnosed disease name and recommended medical department. If necessary, the user can take an image related to the symptoms (for example, a photo of an abnormal area on the skin) and send this to the server via the device. The server then inputs this image data into an image analysis AI model, and the analysis results are reflected in the generative AI model's diagnosis.

[0041] As a specific example, if a user inputs the symptom "sore throat" and uploads an image, the server will use a generative AI model to make an initial diagnosis of "cold" and then use an image analysis AI model to confirm specific symptoms (e.g., redness or swelling).

[0042] Reservation optimization and notifications

[0043] Based on the initial diagnosis, the server determines the appropriate department. The user also inputs the desired consultation date and time, which is then sent to the server. The server then determines the optimal consultation date and time based on the desired date and time and existing appointments retrieved from the hospital's reservation system. The server's optimization algorithm efficiently performs this process and notifies the user of the optimal available consultation date and time.

[0044] For example, if a user enters "Tuesday or Wednesday morning next week would be convenient," the server will check the reservation system, find that there is availability at 11:00 a.m. on Tuesday, and notify the user.

[0045] Consultation scheduling and implementation

[0046] Once the reservation is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results obtained by the generative AI model and the basis for the diagnosis to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge about the user's symptoms before the consultation begins, improving the efficiency of the consultation.

[0047] As a concrete example, a user visits the hospital at 11:00 AM on a Tuesday, and the healthcare provider begins the consultation by confirming the initial diagnosis and imaging results for a "sore throat."

[0048] Switching to Online Diagnostics

[0049] The server determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the best time and date for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[0050] For example, if a user inputs "I have a persistent mild cough" and the server diagnoses it as a "mild cold" using a generative AI model, an online consultation will be suggested. If the user selects this option, a date and time for the online consultation will be scheduled and notified to the user and their healthcare provider.

[0051] In this way, the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[0055] Step 2:

[0056] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[0057] Step 3:

[0058] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[0059] Step 4:

[0060] The server determines the appropriate medical department based on the symptom data and the diagnostic results of the generative AI model.

[0061] Step 5:

[0062] The server connects to the hospital's reservation system and obtains the current reservation status.

[0063] Step 6:

[0064] The server's optimization algorithm determines the optimal appointment date and time based on existing appointments and the user's desired date and time.

[0065] Step 7:

[0066] The server registers the determined consultation date and time in the appointment system as confirmed.

[0067] Step 8:

[0068] The server notifies the user's terminal of the confirmed reservation date and time.

[0069] Step 9:

[0070] The user visits the hospital at the scheduled time.

[0071] Step 10:

[0072] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device in advance.

[0073] Step 11:

[0074] The healthcare provider begins the consultation with prior knowledge of the user's symptoms before the consultation begins.

[0075] Step 12:

[0076] When a user uploads an image (eg, a photo of a symptom) to the terminal, the terminal transmits the image data to the server.

[0077] Step 13:

[0078] The server runs an image analysis AI model to improve the accuracy of initial diagnosis results based on information obtained from the images.

[0079] Step 14:

[0080] Based on the initial diagnosis, the server determines whether online consultation is possible.

[0081] Step 15:

[0082] If online consultation is available, the server notifies the user of the online consultation.

[0083] Step 16:

[0084] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[0085] Step 17:

[0086] An optimization algorithm on the server determines the best time and date for the online consultation.

[0087] Step 18:

[0088] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[0089] Step 19:

[0090] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and evidence, and issue any necessary instructions or prescriptions.

[0091] This detailed flow not only allows users to receive efficient medical care while minimizing waiting times, but also allows medical providers to conduct consultations smoothly.

[0092] Example 1

[0093] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0094] In modern hospitals, long waiting times for consultations are a burden for patients. It is also difficult to efficiently guide patients to the appropriate department and arrange consultation dates and times. Furthermore, technology that improves patient convenience is needed to improve the accuracy of initial diagnoses and implement online consultations.

[0095] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0096] In this invention, the server

[0097] a means for accepting symptom input;

[0098] means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis;

[0099] A means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result;

[0100] means for notifying the user of the determined consultation date and time;

[0101] means for proactively transmitting the consultation to a healthcare provider;

[0102] a means for receiving images relating to the symptom;

[0103] The system also includes a means for analyzing the images using an image analysis AI model to improve the accuracy of initial diagnosis results, which will shorten waiting times at hospitals, guide patients to the appropriate department, optimize appointments, improve the accuracy of initial diagnosis, and enable smooth online consultations.

[0104] A "user" is an individual who uses the system to input their symptoms and desired consultation date and time.

[0105] "Symptom input" refers to the act of a user inputting their own health condition and symptoms they are experiencing into a terminal.

[0106] A "generative AI model" is an artificial intelligence model that analyzes symptoms based on past data and medical knowledge and generates initial diagnosis results.

[0107] The "initial diagnosis result" is the disease name and recommended medical department information obtained as a result of analysis by the generative AI model.

[0108] The "appropriate department" is the medical specialty for which the user should be examined based on the initial diagnosis.

[0109] The "examination date and time" is the date and time designated for the user to receive an examination.

[0110] "Notification" refers to the act of informing the user of the consultation date and time and the results of the initial diagnosis.

[0111] The "image analysis AI model" is an artificial intelligence model that analyzes image data related to symptoms and improves the accuracy of initial diagnosis results.

[0112] An "online consultation" is a consultation conducted between a healthcare provider and a user over the Internet.

[0113] "Healthcare providers" are professionals such as doctors and nurses who provide medical examinations and treatment.

[0114] "Consultation details" refers to the user's symptoms, their analysis results, and detailed information about the consultation.

[0115] The "server" is the central computer in the system that receives input from the user, generates diagnostic results using generative AI models and image analysis AI models, and determines and notifies the patient of the appropriate medical department and consultation date and time.

[0116] A "terminal" is a device through which a user inputs symptoms and desired date and time and communicates with a server.

[0117] The present invention provides a medical support assistant system that shortens waiting times at hospitals and provides efficient medical services. The system accepts symptom input from users, analyzes the input using a generative AI model and an image analysis AI model, and generates an initial diagnosis. It then determines the appropriate department and optimal consultation date and time and notifies the user and healthcare provider.

[0118] First, the user inputs their symptoms using their own device (smartphone, PC, etc.). The device then sends this information to a server. The server then inputs the received symptom information into a generative AI model (such as TensorFlow or PyTorch) and generates an initial diagnosis based on past data and medical knowledge. Specifically, if the symptom input is "sore throat," the server will use the generative AI model to make an initial diagnosis of "cold."

[0119] Additionally, users can take images of their symptoms (e.g., a photo of their throat) and send them to a server via their device. The server inputs this image data into an image analysis AI model (e.g., OpenCV or Keras), and the analysis results are reflected in the generative AI model's diagnostic results. This improves the accuracy of the diagnosis. For example, by uploading a photo of the throat, the image analysis AI model can detect redness and swelling, and these results are added to the diagnostic results.

[0120] Once the diagnosis is complete, the server determines the appropriate medical department (e.g., "Internal Medicine"). Next, the user inputs the desired consultation date and time (e.g., "Tuesday or Wednesday morning next week") and sends it to the server. The server retrieves existing reservations from the hospital's reservation system and determines the optimal consultation date and time by comparing it with the desired date and time. The server notifies the user of the determined date and time (e.g., "Appointment for 11:00 AM on Tuesday").

[0121] Once the appointment is confirmed, the user visits the hospital at the specified date and time for a consultation. The server sends the initial diagnosis and its basis to the medical provider's terminal in advance, allowing the medical provider to obtain prior knowledge of the user's symptoms before the consultation, thereby improving the efficiency of the consultation.

[0122] The server also determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the most appropriate time and date for the online consultation, which will also be notified to the user and the healthcare provider.

[0123] As a concrete example, the following prompt sentence could be input into a generative AI model:

[0124] Prompt: Implement a flow for initial diagnosis and appointment optimization for patients with the symptom "sore throat."

[0125] Prompt: Create a code that optimizes appointments based on the patient's preferred time and the clinic's available time for appointments next week and notifies them.

[0126] Prompt: Develop a system to suggest an online consultation for a patient with mild cold symptoms, determine the best time to schedule the appointment, and notify the user and their healthcare provider.

[0127] In this way, the system of the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The user enters the symptoms.

[0131] Specific actions: The user opens the system's input screen on their smartphone or computer and enters "I have a sore throat."

[0132] Input: Symptoms entered by the user (e.g., "I have a sore throat")

[0133] Output: Data that the device uses to send user symptom input to the server

[0134] Step 2:

[0135] The device sends the symptom information to the server.

[0136] Specific operation: The device sends the entered symptom data to the server via an HTTP request.

[0137] Input: User-entered symptom data

[0138] Output: Symptom data received by the server

[0139] Step 3:

[0140] The symptom information received by the server is input into a generative AI model to generate an initial diagnosis result.

[0141] Specific operation: The server passes the received symptom data to the generative AI model, which then initiates the diagnostic process. The generative AI model performs an initial diagnosis based on past data and medical knowledge, and diagnoses the illness as a "cold."

[0142] Input: Received symptom data

[0143] Output: Initial diagnosis result from the generative AI model (e.g., "cold").

[0144] Step 4:

[0145] The user takes an image of the symptoms and sends it to the server via the terminal.

[0146] Specific operation: The user takes a photo of their throat with their smartphone and clicks the system's upload button to send the image to the server.

[0147] Input: User-taken symptom image

[0148] Output: Image data received by the server

[0149] Step 5:

[0150] The server inputs the image data into an image analysis AI model and reflects the analysis results in the initial diagnosis.

[0151] How it works: The server passes the image data to the image analysis AI model, which then performs image analysis. The image analysis AI model detects redness and swelling and adds the results to the generative AI model's diagnosis.

[0152] Input: Received image data

[0153] Output: Final diagnosis result reflecting the image analysis results

[0154] Step 6:

[0155] The server determines the appropriate medical department based on the initial diagnosis results.

[0156] Specific operation: The server analyzes the initial diagnosis results and determines "internal medicine" as the recommended medical specialty.

[0157] Input: Initial diagnosis result

[0158] Output: The appropriate medical specialty (e.g., "Internal Medicine")

[0159] Step 7:

[0160] The user inputs the desired consultation date and time into the terminal and transmits it to the server.

[0161] Specific operation: The user enters "Tuesday or Wednesday morning next week" as the desired date and time into the system and submits it.

[0162] Input: User's desired appointment date and time

[0163] Output: Desired appointment date and time data received by the server

[0164] Step 8:

[0165] The server compares the desired date and time with the existing reservation status obtained from the hospital's reservation system and determines the optimal date and time for the consultation.

[0166] Specific behavior: The server uses the hospital's reservation system API to check the current availability and finds that 11:00 AM on Tuesday is available.

[0167] Input: User's desired consultation date and time data, and reservation status data from the reservation system

[0168] Output: Best appointment time (e.g. "Tuesday at 11 AM")

[0169] Step 9:

[0170] The server notifies the user of the best time and date for an appointment.

[0171] Specific operation: The server sends a reservation confirmation notification to the user's device, displaying "Reservation confirmed for 11:00 AM on Tuesday."

[0172] Input: Best appointment time

[0173] Output: Confirmation of reservation sent to user

[0174] Step 10:

[0175] The user visits the hospital at the designated date and time and receives a medical examination.

[0176] What happens: A user arrives at the hospital at 11:00 AM on a Tuesday and confirms their appointment with the receptionist.

[0177] Input: Reservation date and time

[0178] Output: Start of hospital consultation

[0179] Step 11:

[0180] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device.

[0181] Specific operation: The server sends a report containing the initial diagnosis and image analysis results to the healthcare provider's device.

[0182] Input: Initial diagnosis results, image analysis results

[0183] Output: Sending diagnostic data to healthcare provider

[0184] Step 12:

[0185] Healthcare providers review the submitted data and conduct consultations efficiently.

[0186] Specific operation: The medical provider checks the initial diagnosis results and image analysis results on the device before the consultation and begins the consultation.

[0187] Input: Diagnostic data sent from the server

[0188] Output: Efficient consultation

[0189] Step 13:

[0190] The server determines whether online consultation is applicable based on the initial diagnosis results.

[0191] Specific operation: The server analyzes the diagnosis results of the generative AI model, determines that the patient has a "mild cold," and concludes that an online consultation is possible.

[0192] Input: Initial diagnosis result

[0193] Output: Proposal for online consultation

[0194] Step 14:

[0195] The server sends the online consultation offer to the user.

[0196] Specific operation: The server sends a notification to the user's device asking, "Would you like to have an online consultation?"

[0197] Input: Online consultation suggestion

[0198] Output: Proposal notification to user

[0199] Step 15:

[0200] The user selects an online consultation.

[0201] Specific operation: The user clicks the "Request online consultation" button on the device.

[0202] Input: Select Online Consultation

[0203] Output: Update the server's online appointment schedule flag

[0204] Step 16:

[0205] The server determines the best time and date for the online consultation and notifies the user and the healthcare provider.

[0206] Specific operation: The server checks the reservation system to determine the available date and time for online consultation, and notifies the user and healthcare provider devices of the determined date and time.

[0207] Input: Online consultation selection and appointment status data from the booking system

[0208] Output: Deciding and notifying online consultation date and time

[0209] By going through the above steps, efficient and flexible medical services can be provided.

[0210] (Application example 1)

[0211] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0212] The food delivery industry lacks the means to recommend appropriate menu items that respond to individual customer preferences and circumstances. Furthermore, the system for determining and notifying optimal delivery times is not well developed, which can lead to lower customer satisfaction. Furthermore, the inability to smoothly handle questions or requests about dishes limits the customer experience.

[0213] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0214] In this invention, the server includes a means for receiving information about the user's preferences and situation and presenting recommended menus based on past data and health information, a means for determining and notifying the user of an optimal delivery time based on the user's desired delivery time, and a means for the user to ask questions or make requests about dishes online, thereby enabling food delivery services that meet the individual needs of the user.

[0215] A "user" is an individual who utilizes the system to input information and receive services.

[0216] A "generative AI model" is an artificial intelligence model that analyzes information based on past data and knowledge and generates appropriate results.

[0217] "Symptom input" refers to the act of a user inputting information about their own symptoms or condition into the system.

[0218] The "initial diagnosis result" is information such as the disease name and recommended medical department that is presented as a result of analysis by the generative AI model.

[0219] A "medical department" is a specialized department at a medical institution that provides diagnosis and treatment for specific types of illnesses or symptoms.

[0220] The "examination date and time" is the specific date and time when the user is scheduled to receive an examination.

[0221] "Notification" refers to the act of the system informing the user or information provider of determined information.

[0222] "Healthcare providers" are professionals such as doctors and nurses who provide health care services in hospitals and clinics.

[0223] "Preferences" refer to the types of food or cuisine that a user prefers.

[0224] "Past data" refers to user input information and behavioral history that the system has collected in the past.

[0225] "Health information" is information relating to the user's health condition and medical history.

[0226] A "recommended menu" is a list of dishes suggested by a generative AI model based on the user's preferences and health status.

[0227] "Desired delivery time" refers to the specific time at which a user would like to receive food delivery.

[0228] "Delivery time optimization" is the process of calculating the most appropriate delivery time based on the user's preferences and the restaurant's situation.

[0229] "Online consultation" is a system that allows users to communicate in real time with restaurant chefs or staff via the Internet.

[0230] Overall system configuration

[0231] This invention provides a system that provides customized support to both end users and restaurants in the food delivery industry. The system uses devices such as smartphones and tablets and operates in conjunction with a server. The server uses a generative AI model to analyze user input data and provide optimal menu recommendations and delivery times.

[0232] Hardware and software used

[0233] Hardware: Smartphones, servers

[0234] Software: Flask (Python web framework), TensorFlow (deep learning model), database (e.g., MySQL)

[0235] Specific operation flow of the system

[0236] 1. Enter symptoms and generate a recommendation menu

[0237] Users enter their preferences, allergy information, and current mood through a smartphone app. This information is sent from the device to a server. The server uses a generative AI model to analyze this information and provide the user with the optimal menu recommendations. This menu is generated based on past order data and the user's health information.

[0238] For example, if a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[0239] Example prompt sentence:

[0240] User Information:

[0241] Favourites: Chicken

[0242] Allergies: None

[0243] Mood: Tired

[0244] 2. Reservation optimization and notifications

[0245] After selecting from the recommended menu, the user inputs the desired delivery time. The server determines the optimal delivery time based on the restaurant's congestion status and the delivery staff's schedule, and notifies the user.

[0246] As a specific example, if the user requests "tomorrow at 2:00 p.m.", the server checks the reservation system, calculates the optimal delivery time, and notifies the user.

[0247] 3. Online consultation mode

[0248] If a user has any questions or requests regarding food, they can consult with restaurant staff online through a smartphone app. The server receives these requests and forwards them to the restaurant's chefs in real time.

[0249] Example prompt sentence:

[0250] User Request:

[0251] Dish name:Grilled chicken

[0252] Q: Can I make it less spicy?

[0253] Operational Scenario

[0254] The system begins when users use a smartphone app to enter their information. The information is sent to a server and analyzed by a generative AI model. An optimal menu recommendation is generated and presented to the user. The optimal delivery time is then determined and notified based on the user's desired delivery time. In addition, users can ask questions or make requests about dishes online.

[0255] In this way, the present invention significantly improves the efficiency and customer satisfaction of food delivery, and the customized service allows food delivery to be tailored to the individual needs of users.

[0256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0257] Step 1:

[0258] The user uses their smartphone to input their preferences, allergy information, current mood, etc. into the app. This inputs the user's individual information into the device, and the input data is sent to the server in JSON format.

[0259] input:

[0260] {

[0261] "preferences": "chicken",

[0262] "allergies": "none",

[0263] "mood": "tired"

[0264] }

[0265] output:

[0266] Send JSON data from the terminal to the server.

[0267] Step 2:

[0268] The server parses the received JSON data and passes the input data to the generative AI model, which then generates a recommended menu based on past order data and health information. The generated recommended menu is returned in JSON format and saved on the server.

[0269] input:

[0270] User data in JSON format

[0271] output:

[0272] JSON data of the recommended menu

[0273] Specific behavior:

[0274] Data is input into a generative AI model to generate recommended menus.

[0275] Step 3:

[0276] The server generates a recommended menu, which is sent to the smartphone app and displayed to the user. The user then selects an order and enters the desired delivery time. The entered delivery time is then sent back to the server.

[0277] input:

[0278] JSON data of the recommended menu

[0279] output:

[0280] Displaying a deserialized recommendation menu

[0281] Specific behavior:

[0282] Receive recommended menus from the server and display them to the user in the app.

[0283] Step 4:

[0284] The server calculates the optimal delivery time based on the received delivery time, the restaurant's congestion status, and the delivery person's schedule information. As a result, the optimal delivery time is obtained and notified to the user.

[0285] input:

[0286] User's desired delivery time, restaurant congestion information, delivery staff schedule data

[0287] output:

[0288] Notification of optimal delivery time

[0289] Specific behavior:

[0290] The server retrieves the necessary data from the reservation system and performs calculations using an optimization algorithm.

[0291] Step 5:

[0292] If a user has a question or request about a dish, they can enter it through the online consultation mode on their smartphone app, which then sends the request to the restaurant's chef via the server.

[0293] input:

[0294] Text data of cooking-related questions and requests

[0295] output:

[0296] Sending the request

[0297] Specific behavior:

[0298] The server receives the user's request and forwards it to the restaurant in real time.

[0299] Specific examples

[0300] Example 1:

[0301] If a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[0302] Example prompt sentence:

[0303] User Information:

[0304] Favourites: Chicken

[0305] Allergies: None

[0306] Mood: Tired

[0307] Example 2:

[0308] If the user enters "tomorrow 2:00 PM" as the "desired delivery time," the server will check the reservation system, calculate the optimal delivery time, and notify the user.

[0309] Example prompt sentence:

[0310] Desired delivery time: tomorrow at 2pm

[0311] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0312] The present invention relates to a medical support assistant system that shortens waiting times at hospitals and takes into account the emotions of users, and includes the following specific embodiments.

[0313] Symptom input and initial diagnosis

[0314] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the name of the diagnosed disease and the recommended medical department.

[0315] As a specific example, if a user inputs the symptom "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[0316] Utilizing the Emotion Engine

[0317] The server then analyzes the user's emotions using an emotion engine based on the user's input data. The emotion engine determines anxiety, stress, and urgency from the user's text and reflects this in the initial diagnosis results.

[0318] For example, if a user enters "I have a sore throat and can't sleep at night," the emotion engine will analyze that the user's anxiety is increasing and increase the priority of the consultation.

[0319] Reservation optimization and notifications

[0320] Based on the initial diagnosis and the user's emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user. The server determines the optimal consultation date and time based on the existing reservation status obtained from the hospital's reservation system. The determined consultation date and time is notified to the user.

[0321] As a specific example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and the emotion engine's analysis determines that the user is highly anxious, the server will prioritize reserving the earliest possible date and time (for example, 10:00 a.m. the following day).

[0322] Consultation scheduling and implementation

[0323] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model and their rationale, as well as the analysis results from the emotion engine, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[0324] As a specific example, a user visits a hospital at a specified date and time, and the medical provider confirms in advance the information that the user has a "sore throat" and that the user is "highly anxious," before beginning the examination.

[0325] Switching to Online Diagnostics

[0326] Based on the initial diagnosis and the emotion engine's analysis, the server determines whether an online consultation is appropriate. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[0327] For example, if a user inputs "I have a mild persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[0328] In this way, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[0329] The processing flow will be explained below.

[0330] Step 1:

[0331] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[0332] Step 2:

[0333] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[0334] Step 3:

[0335] The server uses an emotion engine to analyze emotions from the user's input data, which then performs text analysis to determine the user's anxiety and stress levels.

[0336] Step 4:

[0337] The server integrates the initial diagnosis results with the emotional state determined by the emotion engine to determine the priority of medical examinations and necessary measures. For example, if the user's anxiety is increasing, it will recommend an immediate medical examination.

[0338] Step 5:

[0339] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[0340] Step 6:

[0341] The server connects to the hospital's reservation system to obtain the current reservation status. It then analyzes the user's desired date and time and the existing reservation status using an optimization algorithm.

[0342] Step 7:

[0343] The server's optimization algorithm determines the best appointment time based on existing appointments, the user's emotional state, and their preferred date and time. For example, if the emotion engine detects high anxiety, an earlier date and time will be prioritized.

[0344] Step 8:

[0345] The server registers the determined consultation date and time in the appointment system as confirmed.

[0346] Step 9:

[0347] The server notifies the user's terminal of the confirmed consultation date and time.

[0348] Step 10:

[0349] The user visits the hospital at the scheduled time.

[0350] Step 11:

[0351] The server sends the initial diagnosis results of the generative AI model and their rationale, as well as the emotion analysis results of the emotion engine, to the healthcare provider's device in advance.

[0352] Step 12:

[0353] Before the consultation begins, the healthcare provider reviews information about the user's symptoms and emotional state and prepares for the consultation.

[0354] Step 13:

[0355] The healthcare provider initiates the consultation and uses the information provided in advance to provide efficient and appropriate care.

[0356] Step 14:

[0357] When a user uploads an image of a symptom (eg, an abnormal area of ​​skin) to the terminal, the terminal transmits the image data to the server.

[0358] Step 15:

[0359] The server runs an image analysis AI model and uses the information obtained from the images to improve the accuracy of initial diagnosis results.

[0360] Step 16:

[0361] The server determines whether online consultation is applicable based on the initial diagnosis results and the analysis results of the emotion engine.

[0362] Step 17:

[0363] If online consultation is available, the server notifies the user of the online consultation.

[0364] Step 18:

[0365] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[0366] Step 19:

[0367] An optimization algorithm on the server determines the best time and date for the online consultation.

[0368] Step 20:

[0369] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[0370] Step 21:

[0371] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and rationale, as well as the analysis results of the emotion engine, and issue any necessary instructions or prescriptions.

[0372] This detailed process flow allows users to receive efficient, flexible medical care that takes into consideration their emotions while minimizing waiting times, and also allows medical providers to receive information in advance, allowing for a smoother consultation.

[0373] Example 2

[0374] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0375] In conventional medical treatment systems, it often takes time for the system to determine the appropriate medical department and consultation date and time after the user inputs their symptoms, and the user's emotional state is rarely taken into consideration. As a result, users end up feeling anxious while waiting for their appointment, which reduces the efficiency of medical treatment. In addition, determining the appropriate consultation date and time and selecting online consultations are often done manually, which can disrupt the smooth flow of medical treatment.

[0376] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0377] In this invention, the server includes means for accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis, means for notifying the user of the determined consultation date and time, means for analyzing the emotional state using an emotion engine based on the user's symptom input, means for reflecting the analyzed emotional state in the initial diagnosis and setting the priority of the consultation, and means for transmitting the details of the consultation and the emotional state to a healthcare provider in advance. This makes it possible to efficiently perform the process from the user's symptom input to determining the consultation date and time, and improve the quality and efficiency of medical care by taking the user's emotional state into consideration.

[0378] "User" refers to an individual who uses the system to input their symptoms and receive medical treatment.

[0379] "Symptom input" refers to the act of a user inputting their own physical condition or state into a terminal.

[0380] "Terminal" refers to a computing device used by a user, such as a computer, smartphone, or tablet.

[0381] The term "server" refers to a computer system that receives information from users and uses generative AI models and emotion engines to analyze the data and determine appointment dates and times.

[0382] A "generative AI model" refers to an artificial intelligence system that generates initial diagnostic results from symptom information based on past data and medical knowledge.

[0383] "Initial diagnosis result" refers to the diagnosis obtained as a result of the generative AI model analyzing symptom information.

[0384] An "emotion engine" refers to a system that analyzes the user's emotional state from the text they input and determines their level of anxiety or stress.

[0385] "Appointment Date and Time" refers to the date and time designated for a user to meet with a healthcare provider.

[0386] A "department" refers to a hospital division that specializes in a particular area of ​​medicine.

[0387] "Notification" refers to the act of informing the user of the determined consultation date and time and details of the consultation.

[0388] "Examination details" refers to the specific details of medical treatment and examinations based on the user's symptoms.

[0389] "Healthcare provider" refers to a medical professional such as a doctor or nurse who provides medical services to a user.

[0390] "Online medical consultation" refers to a system in which a medical provider examines or consults with a user via the Internet.

[0391] "Emotional state" refers to psychological states such as anxiety, stress, and urgency that are determined from the text entered by the user.

[0392] "Consultation priority" refers to the criteria for determining the degree of priority for a user's consultation based on the analysis results of the emotion engine.

[0393] This invention relates to a medical support assistant system that shortens waiting times in hospitals and takes into account the user's emotions. The main components are a user terminal, a server, a generative AI model, and an emotion engine.

[0394] User terminal

[0395] Users input their symptoms using devices such as PCs, smartphones, and tablets. This symptom information is then sent from the device to a server. The device then sends the data to the server via the Internet using a secure communication protocol (e.g., HTTPS).

[0396] Specific examples

[0397] The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom entry field.

[0398] server

[0399] The server receives symptom information sent by the user and inputs it into the generative AI model. The generative AI model analyzes the symptom information based on past data and medical knowledge and generates an initial diagnosis. The server also analyzes the user's emotional state using an emotion engine. The analysis results are reflected in the initial diagnosis and are used to set examination priorities.

[0400] Software used

[0401] Generative AI model: A model that generates initial diagnosis results based on past data and medical knowledge

[0402] Emotion Engine: An engine that analyzes the emotional state of a user from their input text.

[0403] Specific examples

[0404] The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends a doctor visit. It also uses an emotion engine to analyze the user's anxieties and prioritizes the consultation.

[0405] Deciding and notifying the appointment date and time

[0406] The server determines the date and time of the consultation based on the initial diagnosis and emotion analysis results. It also works with the hospital's reservation system to determine the optimal consultation date and time, taking into account the user's preferred date and time. The server then notifies the user of the determined consultation date and time.

[0407] Specific examples

[0408] The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[0409] Providing information to healthcare providers

[0410] The server sends the initial diagnosis results from the generative AI model and the analysis results from the emotion engine to the healthcare provider's device in advance, allowing the healthcare provider to have prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[0411] Specific examples

[0412] The user visits the hospital at the specified date and time, and the medical provider confirms the information that the user has a sore throat and that the user is highly anxious beforehand and begins the examination.

[0413] Choosing an online consultation

[0414] The server determines whether an online consultation is appropriate based on the initial diagnosis and the analysis results of the emotion engine. If the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user.

[0415] Specific examples

[0416] If a user inputs "I have a mild, persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[0417] Prompt Sentence Examples

[0418] "Perform an initial diagnosis based on the symptoms entered by the user and recommend possible illnesses and medical specialties. Example: sore throat."

[0419] "Analyze user input text to determine anxiety or stress levels. Example: My throat hurts and I can't sleep at night."

[0420] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0421] Step 1:

[0422] The user enters the symptom information.

[0423] Input: The user inputs the symptoms on the device they use (PC, smartphone, tablet).

[0424] Data processing: Collect user input data in text format.

[0425] Output: Symptom information sent from the device to the server.

[0426] Specific operation: The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom input field.

[0427] Step 2:

[0428] The device sends the symptom information to the server.

[0429] Input: Symptom information entered by the user into the device.

[0430] Data Processing: Symptom information is encrypted using a secure communication protocol (e.g., HTTPS).

[0431] Output: Encrypted symptom information sent to the server.

[0432] Specific operation: The device sends input data such as "I've had a sore throat since last night and I also have a slight fever" to the server via HTTPS.

[0433] Step 3:

[0434] The server performs an initial diagnosis using the generated AI model.

[0435] Input: The symptom information sent to the server.

[0436] Data calculation: Symptom information is input into the generative AI model and analyzed based on past data and medical knowledge.

[0437] Output: Initial diagnosis (diagnosed disease name and recommended medical department).

[0438] Specific operation: The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends seeing an internal medicine doctor.

[0439] Step 4:

[0440] The server performs emotion analysis using an emotion engine.

[0441] Input: User symptom information and initial diagnosis results.

[0442] Data calculation: Symptom information is input into the emotion engine and the emotional state (anxiety, stress, urgency) is analyzed.

[0443] Output: Sentiment analysis results (user's emotional state).

[0444] Specific operation: The server uses an emotion engine to analyze the user's anxiety from symptom text such as "I've had a sore throat since last night and I also have a slight fever," and sets a high priority for medical treatment.

[0445] Step 5:

[0446] The server determines the appropriate appointment date and time and notifies the patient.

[0447] Input: Initial diagnosis results and sentiment analysis results, existing hospital reservations, and the user's desired date and time.

[0448] Data processing: In cooperation with the reservation system, the optimal appointment date and time is determined taking into account the user's wishes and emotional state.

[0449] Output: The determined appointment date and time, and notification of the same.

[0450] Specific operation: The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[0451] Step 6:

[0452] The server transmits the consultation details and emotional state to the healthcare provider.

[0453] Input: Initial diagnostic results of the generative AI model and analysis results of the emotion engine.

[0454] Data processing: Organize the medical examination details and emotional state and send them to the medical provider's terminal.

[0455] Output: Consultation details and emotional state sent to the healthcare provider.

[0456] Specific operation: The server sends the information "sore throat" and "user's anxiety is high" to the healthcare provider's terminal.

[0457] Step 7:

[0458] The user chooses to visit the clinic or have an online consultation.

[0459] Input: Confirmation of appointment or suggestion of online consultation.

[0460] Data calculation: Determines the optimal diagnostic method based on the user's selection.

[0461] Output: Notification of time and date for online consultation or to arrange a face-to-face consultation with a healthcare provider.

[0462] Specific operation: The user checks the notification on their smartphone and visits the hospital at the specified date and time. Alternatively, the user selects online consultation, and the server proposes 3:00 PM on the same day as the date and time for the online consultation and sends a notification to the user's smartphone.

[0463] (Application example 2)

[0464] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0465] Long waiting times and inefficient diagnoses are major problems in modern medical settings and pharmacies. Rapid and appropriate responses are required, especially when users complain of symptoms, but traditional approaches have difficulty meeting these requirements. Furthermore, because treatment and medication recommendations are made without taking the user's emotional state into consideration, user satisfaction and trust tend to decline. Furthermore, the difficulty of scheduling appointments with the appropriate department or pharmacist reduces medical efficiency and increases the workload of healthcare providers.

[0466] The identification processing 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 accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis result, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result, means for notifying the user of the determined consultation date and time, means for transmitting the details of the consultation to a healthcare provider in advance, means for analyzing the user's input data using emotion analysis means and determining the user's emotional state, and means for adjusting appointment priorities and determining the optimal consultation date and time taking the user's emotional state into consideration. This makes it possible to shorten waiting times and realize medical support that takes the user's emotional state into consideration, thereby improving medical efficiency and user satisfaction.

[0467] The "means for accepting symptom input from the user" is an interface that allows the user to input their own symptoms into the system.

[0468] "Means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis" refers to the algorithms and processes for using AI technology to analyze the symptoms entered by the user and obtain a provisional diagnosis.

[0469] The "means for determining an appropriate medical department and consultation date and time" is a system for optimally selecting the medical department and consultation date and time that the user should visit based on the results of the initial diagnosis.

[0470] The "means for notifying the user of the determined appointment date and time" refers to a mechanical or electronic means for communicating the determined appointment date and time and related information to the user.

[0471] The "means for proactively transmitting medical examination details to a healthcare provider" refers to the technology and process for proactively transmitting the user's symptom information and initial diagnosis results to a healthcare provider.

[0472] "Means for analyzing user input data using emotion analysis means and determining the user's emotional state" refers to emotion analysis technology and processes for evaluating the user's emotional state based on the user's input information.

[0473] The "means for adjusting appointment priorities and determining optimal consultation dates and times, taking into account the user's emotional state" is a system for adjusting the priority of appointment dates and times, taking into account the user's emotional state, based on the results of emotion analysis, and making optimal appointments.

[0474] The "means for accepting symptom images" is an interface for receiving image data relating to symptoms provided by the user.

[0475] "Means for improving the accuracy of initial diagnosis results by analyzing using an image analysis AI model" refers to the technology and process for improving the accuracy of initial diagnosis by using AI technology to analyze image data.

[0476] The "means for determining whether an online consultation is applicable" refers to the algorithms and processes for determining whether an online consultation is applicable based on the provided symptom information and diagnosis results.

[0477] The "means for determining and notifying the date and time of an appointment when an online consultation is selected" is a system for determining an appropriate date and time for the appointment when an online consultation is selected and notifying the user and the healthcare provider.

[0478] The present invention is a system that consistently supports users from inputting their symptoms to making appointments and online consultations, and specific embodiments required to implement the present invention will be described below.

[0479] Hardware and Software Configuration

[0480] The system includes the following hardware and software:

[0481] Hardware: smartphones, robots, servers

[0482] Software: Python, generative AI model, sentiment analysis engine, reservation management system

[0483] Processing flow

[0484] Symptom input and initial diagnosis

[0485] Users input their symptoms via smartphone or robot. Once the symptoms are entered, the device sends this information to a server. The server then inputs the symptom information into a generative AI model, analyzes it, and generates an initial diagnosis. This diagnosis includes the diagnosed disease name and recommended medical department.

[0486] As a specific example, if a user inputs "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[0487] Sentiment analysis and prioritization

[0488] The server then uses a sentiment analysis engine to analyze the user's emotional state based on the user's input data. The analysis results, along with the diagnosis, are used to adjust the priority of appointments. For example, if a user inputs "I have a sore throat and can't sleep at night," the sentiment analysis engine will determine that the user's anxiety is increasing and raise the priority of the appointment.

[0489] Reservation optimization and notifications

[0490] Based on the initial diagnosis and emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user, and calculates the optimal consultation date and time. The determined consultation date and time is notified to the user.

[0491] For example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and emotion analysis indicates high anxiety, the server will prioritize reserving the earliest possible date and time, such as 10:00 a.m. the following day.

[0492] Consultation scheduling and implementation

[0493] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model, along with the rationale behind the diagnosis, as well as the emotional analysis results, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[0494] ●Example of prompt sentence:

[0495] Symptoms: Sore throat, sleepless nights

[0496] Desired appointment date and time: 2023-10-15 10:00:00, 2023-10-16 11:00:00

[0497] Initial diagnosis result: Common cold (cold)

[0498] Sentiment analysis results: High anxiety

[0499] Best time to see a doctor: 2023-10-15 14:00:00

[0500] Proposing and implementing online consultations

[0501] The server determines whether an online consultation is appropriate based on the initial diagnosis and sentiment analysis. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. The user can then consult with a healthcare provider via the Internet at the specified time.

[0502] As described above, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[0503] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0504] Step 1:

[0505] The user inputs symptoms into the terminal. The terminal receives the symptom data (in text format) entered by the user and sends the data to the server. At this point, the input is the user's symptom information, and the output is the symptom data sent to the server.

[0506] Step 2:

[0507] The server inputs the received symptom data into a generative AI model. The generative AI model analyzes the symptom data based on past case data and medical knowledge, and generates an initial diagnosis. The input at this point is the symptom data sent to the server, and the output is the initial diagnosis (diagnosed disease name and recommended medical department).

[0508] Step 3:

[0509] The server uses a sentiment analysis engine to analyze the user's emotional state from the symptom data. The sentiment analysis engine performs text analysis to determine the user's anxiety and stress levels. At this point, the input is the symptom data, and the output is the user's emotional state (e.g., high anxiety, normal, relaxed).

[0510] Step 4:

[0511] Based on the initial diagnosis and emotion analysis results, the server uses the appointment management system to determine the appropriate department and optimal consultation date and time. During this process, the desired consultation date and time entered by the user is also taken into consideration. The input at this point is the initial diagnosis result, emotion analysis result, and the user's desired consultation date and time, and the output is the determined optimal consultation date and time.

[0512] Step 5:

[0513] The server notifies the user of the determined appointment date and time. Notification can be done via smartphone, email, etc. The input at this point is the determined appointment date and time, and the output is a notification message sent to the user.

[0514] Step 6:

[0515] The server sends the initial diagnosis results and their rationale, as well as the emotion analysis results, generated by the generative AI model, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins. The input at this point is the initial diagnosis results, rationale, and emotion analysis results, and the output is this data sent to the healthcare provider.

[0516] Step 7:

[0517] The server determines whether an online consultation is applicable based on the initial diagnosis result and emotion analysis. If it is determined that an online consultation is applicable, it proposes an online consultation to the user. At this point, the input is the initial diagnosis result and emotion analysis result, and the output is a message proposing an online consultation.

[0518] Step 8:

[0519] If the user selects an online consultation, the server determines the optimal time and date for the online consultation and notifies the user and the healthcare provider. At this point, the input is the user's preference for an online consultation, and the output is a notification of the optimal time and date for the online consultation.

[0520] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0521] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0522] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0523] [Second embodiment]

[0524] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0525] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0526] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0527] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0528] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0529] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0530] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0531] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0532] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0533] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0534] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0535] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0536] The present invention relates to a medical support assistant system for shortening waiting times at hospitals, and is realized in the specific embodiments described below.

[0537] Symptom input and initial diagnosis

[0538] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the diagnosed disease name and recommended medical department. If necessary, the user can take an image related to the symptoms (for example, a photo of an abnormal area on the skin) and send this to the server via the device. The server then inputs this image data into an image analysis AI model, and the analysis results are reflected in the generative AI model's diagnosis.

[0539] As a specific example, if a user inputs the symptom "sore throat" and uploads an image, the server will use a generative AI model to make an initial diagnosis of "cold" and then use an image analysis AI model to confirm specific symptoms (e.g., redness or swelling).

[0540] Reservation optimization and notifications

[0541] Based on the initial diagnosis, the server determines the appropriate department. The user also inputs the desired consultation date and time, which is then sent to the server. The server then determines the optimal consultation date and time based on the desired date and time and existing appointments retrieved from the hospital's reservation system. The server's optimization algorithm efficiently performs this process and notifies the user of the optimal available consultation date and time.

[0542] For example, if a user enters "Tuesday or Wednesday morning next week would be convenient," the server will check the reservation system, find that there is availability at 11:00 a.m. on Tuesday, and notify the user.

[0543] Consultation scheduling and implementation

[0544] Once the reservation is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results obtained by the generative AI model and the basis for the diagnosis to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge about the user's symptoms before the consultation begins, improving the efficiency of the consultation.

[0545] As a concrete example, a user visits the hospital at 11:00 AM on a Tuesday, and the healthcare provider begins the consultation by confirming the initial diagnosis and imaging results for a "sore throat."

[0546] Switching to Online Diagnostics

[0547] The server determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the best time and date for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[0548] For example, if a user inputs "I have a persistent mild cough" and the server diagnoses it as a "mild cold" using a generative AI model, an online consultation will be suggested. If the user selects this option, a date and time for the online consultation will be scheduled and notified to the user and their healthcare provider.

[0549] In this way, the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[0550] The processing flow will be explained below.

[0551] Step 1:

[0552] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[0553] Step 2:

[0554] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[0555] Step 3:

[0556] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[0557] Step 4:

[0558] The server determines the appropriate medical department based on the symptom data and the diagnostic results of the generative AI model.

[0559] Step 5:

[0560] The server connects to the hospital's reservation system and obtains the current reservation status.

[0561] Step 6:

[0562] The server's optimization algorithm determines the optimal appointment date and time based on existing appointments and the user's desired date and time.

[0563] Step 7:

[0564] The server registers the determined consultation date and time in the appointment system as confirmed.

[0565] Step 8:

[0566] The server notifies the user's terminal of the confirmed reservation date and time.

[0567] Step 9:

[0568] The user visits the hospital at the scheduled time.

[0569] Step 10:

[0570] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device in advance.

[0571] Step 11:

[0572] The healthcare provider begins the consultation with prior knowledge of the user's symptoms before the consultation begins.

[0573] Step 12:

[0574] When a user uploads an image (eg, a photo of a symptom) to the terminal, the terminal transmits the image data to the server.

[0575] Step 13:

[0576] The server runs an image analysis AI model to improve the accuracy of initial diagnosis results based on information obtained from the images.

[0577] Step 14:

[0578] Based on the initial diagnosis, the server determines whether online consultation is possible.

[0579] Step 15:

[0580] If online consultation is available, the server notifies the user of the online consultation.

[0581] Step 16:

[0582] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[0583] Step 17:

[0584] An optimization algorithm on the server determines the best time and date for the online consultation.

[0585] Step 18:

[0586] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[0587] Step 19:

[0588] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and evidence, and issue any necessary instructions or prescriptions.

[0589] This detailed flow not only allows users to receive efficient medical care while minimizing waiting times, but also allows medical providers to conduct consultations smoothly.

[0590] Example 1

[0591] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] In modern hospitals, long waiting times for consultations are a burden for patients. It is also difficult to efficiently guide patients to the appropriate department and arrange consultation dates and times. Furthermore, technology that improves patient convenience is needed to improve the accuracy of initial diagnoses and implement online consultations.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0594] In this invention, the server

[0595] a means for accepting symptom input;

[0596] means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis;

[0597] A means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result;

[0598] means for notifying the user of the determined consultation date and time;

[0599] means for proactively transmitting the consultation to a healthcare provider;

[0600] a means for receiving images relating to the symptom;

[0601] The system also includes a means for analyzing the images using an image analysis AI model to improve the accuracy of initial diagnosis results, which will shorten waiting times at hospitals, guide patients to the appropriate department, optimize appointments, improve the accuracy of initial diagnosis, and enable smooth online consultations.

[0602] A "user" is an individual who uses the system to input their symptoms and desired consultation date and time.

[0603] "Symptom input" refers to the act of a user inputting their own health condition and symptoms they are experiencing into a terminal.

[0604] A "generative AI model" is an artificial intelligence model that analyzes symptoms based on past data and medical knowledge and generates initial diagnosis results.

[0605] The "initial diagnosis result" is the disease name and recommended medical department information obtained as a result of analysis by the generative AI model.

[0606] The "appropriate department" is the medical specialty for which the user should be examined based on the initial diagnosis.

[0607] The "examination date and time" is the date and time designated for the user to receive an examination.

[0608] "Notification" refers to the act of informing the user of the consultation date and time and the results of the initial diagnosis.

[0609] The "image analysis AI model" is an artificial intelligence model that analyzes image data related to symptoms and improves the accuracy of initial diagnosis results.

[0610] An "online consultation" is a consultation conducted between a healthcare provider and a user over the Internet.

[0611] "Healthcare providers" are professionals such as doctors and nurses who provide medical examinations and treatment.

[0612] "Consultation details" refers to the user's symptoms, their analysis results, and detailed information about the consultation.

[0613] The "server" is the central computer in the system that receives input from the user, generates diagnostic results using generative AI models and image analysis AI models, and determines and notifies the patient of the appropriate medical department and consultation date and time.

[0614] A "terminal" is a device through which a user inputs symptoms and desired date and time and communicates with a server.

[0615] The present invention provides a medical support assistant system that shortens waiting times at hospitals and provides efficient medical services. The system accepts symptom input from users, analyzes the input using a generative AI model and an image analysis AI model, and generates an initial diagnosis. It then determines the appropriate department and optimal consultation date and time and notifies the user and healthcare provider.

[0616] First, the user inputs their symptoms using their own device (smartphone, PC, etc.). The device then sends this information to a server. The server then inputs the received symptom information into a generative AI model (such as TensorFlow or PyTorch) and generates an initial diagnosis based on past data and medical knowledge. Specifically, if the symptom input is "sore throat," the server will use the generative AI model to make an initial diagnosis of "cold."

[0617] Additionally, users can take images of their symptoms (e.g., a photo of their throat) and send them to a server via their device. The server inputs this image data into an image analysis AI model (e.g., OpenCV or Keras), and the analysis results are reflected in the generative AI model's diagnostic results. This improves the accuracy of the diagnosis. For example, by uploading a photo of the throat, the image analysis AI model can detect redness and swelling, and these results are added to the diagnostic results.

[0618] Once the diagnosis is complete, the server determines the appropriate medical department (e.g., "Internal Medicine"). Next, the user inputs the desired consultation date and time (e.g., "Tuesday or Wednesday morning next week") and sends it to the server. The server retrieves existing reservations from the hospital's reservation system and determines the optimal consultation date and time by comparing it with the desired date and time. The server notifies the user of the determined date and time (e.g., "Appointment for 11:00 AM on Tuesday").

[0619] Once the appointment is confirmed, the user visits the hospital at the specified date and time for a consultation. The server sends the initial diagnosis and its basis to the medical provider's terminal in advance, allowing the medical provider to obtain prior knowledge of the user's symptoms before the consultation, thereby improving the efficiency of the consultation.

[0620] The server also determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the most appropriate time and date for the online consultation, which will also be notified to the user and the healthcare provider.

[0621] As a concrete example, the following prompt sentence could be input into a generative AI model:

[0622] Prompt: Implement a flow for initial diagnosis and appointment optimization for patients with the symptom "sore throat."

[0623] Prompt: Create a code that optimizes appointments based on the patient's preferred time and the clinic's available time for appointments next week and notifies them.

[0624] Prompt: Develop a system to suggest an online consultation for a patient with mild cold symptoms, determine the best time to schedule the appointment, and notify the user and their healthcare provider.

[0625] In this way, the system of the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[0626] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0627] Step 1:

[0628] The user enters the symptoms.

[0629] Specific actions: The user opens the system's input screen on their smartphone or computer and enters "I have a sore throat."

[0630] Input: Symptoms entered by the user (e.g., "I have a sore throat")

[0631] Output: Data that the device uses to send user symptom input to the server

[0632] Step 2:

[0633] The device sends the symptom information to the server.

[0634] Specific operation: The device sends the entered symptom data to the server via an HTTP request.

[0635] Input: User-entered symptom data

[0636] Output: Symptom data received by the server

[0637] Step 3:

[0638] The symptom information received by the server is input into a generative AI model to generate an initial diagnosis result.

[0639] Specific operation: The server passes the received symptom data to the generative AI model, which then initiates the diagnostic process. The generative AI model performs an initial diagnosis based on past data and medical knowledge, and diagnoses the illness as a "cold."

[0640] Input: Received symptom data

[0641] Output: Initial diagnosis result from the generative AI model (e.g., "cold").

[0642] Step 4:

[0643] The user takes an image of the symptoms and sends it to the server via the terminal.

[0644] Specific operation: The user takes a photo of their throat with their smartphone and clicks the system's upload button to send the image to the server.

[0645] Input: User-taken symptom image

[0646] Output: Image data received by the server

[0647] Step 5:

[0648] The server inputs the image data into an image analysis AI model and reflects the analysis results in the initial diagnosis.

[0649] How it works: The server passes the image data to the image analysis AI model, which then performs image analysis. The image analysis AI model detects redness and swelling and adds the results to the generative AI model's diagnosis.

[0650] Input: Received image data

[0651] Output: Final diagnosis result reflecting the image analysis results

[0652] Step 6:

[0653] The server determines the appropriate medical department based on the initial diagnosis results.

[0654] Specific operation: The server analyzes the initial diagnosis results and determines "internal medicine" as the recommended medical specialty.

[0655] Input: Initial diagnosis result

[0656] Output: The appropriate medical specialty (e.g., "Internal Medicine")

[0657] Step 7:

[0658] The user inputs the desired consultation date and time into the terminal and transmits it to the server.

[0659] Specific operation: The user enters "Tuesday or Wednesday morning next week" as the desired date and time into the system and submits it.

[0660] Input: User's desired appointment date and time

[0661] Output: Desired appointment date and time data received by the server

[0662] Step 8:

[0663] The server compares the desired date and time with the existing reservation status obtained from the hospital's reservation system and determines the optimal date and time for the consultation.

[0664] Specific behavior: The server uses the hospital's reservation system API to check the current availability and finds that 11:00 AM on Tuesday is available.

[0665] Input: User's desired consultation date and time data, and reservation status data from the reservation system

[0666] Output: Best appointment time (e.g. "Tuesday at 11 AM")

[0667] Step 9:

[0668] The server notifies the user of the best time and date for an appointment.

[0669] Specific operation: The server sends a reservation confirmation notification to the user's device, displaying "Reservation confirmed for 11:00 AM on Tuesday."

[0670] Input: Best appointment time

[0671] Output: Confirmation of reservation sent to user

[0672] Step 10:

[0673] The user visits the hospital at the designated date and time and receives a medical examination.

[0674] What happens: A user arrives at the hospital at 11:00 AM on a Tuesday and confirms their appointment with the receptionist.

[0675] Input: Reservation date and time

[0676] Output: Start of hospital consultation

[0677] Step 11:

[0678] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device.

[0679] Specific operation: The server sends a report containing the initial diagnosis and image analysis results to the healthcare provider's device.

[0680] Input: Initial diagnosis results, image analysis results

[0681] Output: Sending diagnostic data to healthcare provider

[0682] Step 12:

[0683] Healthcare providers review the submitted data and conduct consultations efficiently.

[0684] Specific operation: The medical provider checks the initial diagnosis results and image analysis results on the device before the consultation and begins the consultation.

[0685] Input: Diagnostic data sent from the server

[0686] Output: Efficient consultation

[0687] Step 13:

[0688] The server determines whether online consultation is applicable based on the initial diagnosis results.

[0689] Specific operation: The server analyzes the diagnosis results of the generative AI model, determines that the patient has a "mild cold," and concludes that an online consultation is possible.

[0690] Input: Initial diagnosis result

[0691] Output: Proposal for online consultation

[0692] Step 14:

[0693] The server sends the online consultation offer to the user.

[0694] Specific operation: The server sends a notification to the user's device asking, "Would you like to have an online consultation?"

[0695] Input: Online consultation suggestion

[0696] Output: Proposal notification to user

[0697] Step 15:

[0698] The user selects an online consultation.

[0699] Specific operation: The user clicks the "Request online consultation" button on the device.

[0700] Input: Select Online Consultation

[0701] Output: Update the server's online appointment schedule flag

[0702] Step 16:

[0703] The server determines the best time and date for the online consultation and notifies the user and the healthcare provider.

[0704] Specific operation: The server checks the reservation system to determine the available date and time for online consultation, and notifies the user and healthcare provider devices of the determined date and time.

[0705] Input: Online consultation selection and appointment status data from the booking system

[0706] Output: Deciding and notifying online consultation date and time

[0707] By going through the above steps, efficient and flexible medical services can be provided.

[0708] (Application example 1)

[0709] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0710] The food delivery industry lacks the means to recommend appropriate menu items that respond to individual customer preferences and circumstances. Furthermore, the system for determining and notifying optimal delivery times is not well developed, which can lead to lower customer satisfaction. Furthermore, the inability to smoothly handle questions or requests about dishes limits the customer experience.

[0711] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0712] In this invention, the server includes a means for receiving information about the user's preferences and situation and presenting recommended menus based on past data and health information, a means for determining and notifying the user of an optimal delivery time based on the user's desired delivery time, and a means for the user to ask questions or make requests about dishes online, thereby enabling food delivery services that meet the individual needs of the user.

[0713] A "user" is an individual who utilizes the system to input information and receive services.

[0714] A "generative AI model" is an artificial intelligence model that analyzes information based on past data and knowledge and generates appropriate results.

[0715] "Symptom input" refers to the act of a user inputting information about their own symptoms or condition into the system.

[0716] The "initial diagnosis result" is information such as the disease name and recommended medical department that is presented as a result of analysis by the generative AI model.

[0717] A "medical department" is a specialized department at a medical institution that provides diagnosis and treatment for specific types of illnesses or symptoms.

[0718] The "examination date and time" is the specific date and time when the user is scheduled to receive an examination.

[0719] "Notification" refers to the act of the system informing the user or information provider of determined information.

[0720] "Healthcare providers" are professionals such as doctors and nurses who provide health care services in hospitals and clinics.

[0721] "Preferences" refer to the types of food or cuisine that a user prefers.

[0722] "Past data" refers to user input information and behavioral history that the system has collected in the past.

[0723] "Health information" is information relating to the user's health condition and medical history.

[0724] A "recommended menu" is a list of dishes suggested by a generative AI model based on the user's preferences and health status.

[0725] "Desired delivery time" refers to the specific time at which a user would like to receive food delivery.

[0726] "Delivery time optimization" is the process of calculating the most appropriate delivery time based on the user's preferences and the restaurant's situation.

[0727] "Online consultation" is a system that allows users to communicate in real time with restaurant chefs or staff via the Internet.

[0728] Overall system configuration

[0729] This invention provides a system that provides customized support to both end users and restaurants in the food delivery industry. The system uses devices such as smartphones and tablets and operates in conjunction with a server. The server uses a generative AI model to analyze user input data and provide optimal menu recommendations and delivery times.

[0730] Hardware and software used

[0731] Hardware: Smartphones, servers

[0732] Software: Flask (Python web framework), TensorFlow (deep learning model), database (e.g., MySQL)

[0733] Specific operation flow of the system

[0734] 1. Enter symptoms and generate a recommendation menu

[0735] Users enter their preferences, allergy information, and current mood through a smartphone app. This information is sent from the device to a server. The server uses a generative AI model to analyze this information and provide the user with the optimal menu recommendations. This menu is generated based on past order data and the user's health information.

[0736] For example, if a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[0737] Example prompt sentence:

[0738] User Information:

[0739] Favourites: Chicken

[0740] Allergies: None

[0741] Mood: Tired

[0742] 2. Reservation optimization and notifications

[0743] After selecting from the recommended menu, the user inputs the desired delivery time. The server determines the optimal delivery time based on the restaurant's congestion status and the delivery staff's schedule, and notifies the user.

[0744] As a specific example, if the user requests "tomorrow at 2:00 p.m.", the server checks the reservation system, calculates the optimal delivery time, and notifies the user.

[0745] 3. Online consultation mode

[0746] If a user has any questions or requests regarding food, they can consult with restaurant staff online through a smartphone app. The server receives these requests and forwards them to the restaurant's chefs in real time.

[0747] Example prompt sentence:

[0748] User Request:

[0749] Dish name:Grilled chicken

[0750] Q: Can I make it less spicy?

[0751] Operational Scenario

[0752] The system begins when users use a smartphone app to enter their information. The information is sent to a server and analyzed by a generative AI model. An optimal menu recommendation is generated and presented to the user. The optimal delivery time is then determined and notified based on the user's desired delivery time. In addition, users can ask questions or make requests about dishes online.

[0753] In this way, the present invention significantly improves the efficiency and customer satisfaction of food delivery, and the customized service allows food delivery to be tailored to the individual needs of users.

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Step 1:

[0756] The user uses their smartphone to input their preferences, allergy information, current mood, etc. into the app. This inputs the user's individual information into the device, and the input data is sent to the server in JSON format.

[0757] input:

[0758] {

[0759] "preferences": "chicken",

[0760] "allergies": "none",

[0761] "mood": "tired"

[0762] }

[0763] output:

[0764] Send JSON data from the terminal to the server.

[0765] Step 2:

[0766] The server parses the received JSON data and passes the input data to the generative AI model, which then generates a recommended menu based on past order data and health information. The generated recommended menu is returned in JSON format and saved on the server.

[0767] input:

[0768] User data in JSON format

[0769] output:

[0770] JSON data of the recommended menu

[0771] Specific behavior:

[0772] Data is input into a generative AI model to generate recommended menus.

[0773] Step 3:

[0774] The server generates a recommended menu, which is sent to the smartphone app and displayed to the user. The user then selects an order and enters the desired delivery time. The entered delivery time is then sent back to the server.

[0775] input:

[0776] JSON data of the recommended menu

[0777] output:

[0778] Displaying a deserialized recommendation menu

[0779] Specific behavior:

[0780] Receive recommended menus from the server and display them to the user in the app.

[0781] Step 4:

[0782] The server calculates the optimal delivery time based on the received delivery time, the restaurant's congestion status, and the delivery person's schedule information. As a result, the optimal delivery time is obtained and notified to the user.

[0783] input:

[0784] User's desired delivery time, restaurant congestion information, delivery staff schedule data

[0785] output:

[0786] Notification of optimal delivery time

[0787] Specific behavior:

[0788] The server retrieves the necessary data from the reservation system and performs calculations using an optimization algorithm.

[0789] Step 5:

[0790] If a user has a question or request about a dish, they can enter it through the online consultation mode on their smartphone app, which then sends the request to the restaurant's chef via the server.

[0791] input:

[0792] Text data of cooking-related questions and requests

[0793] output:

[0794] Sending the request

[0795] Specific behavior:

[0796] The server receives the user's request and forwards it to the restaurant in real time.

[0797] Specific examples

[0798] Example 1:

[0799] If a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[0800] Example prompt sentence:

[0801] User Information:

[0802] Favourites: Chicken

[0803] Allergies: None

[0804] Mood: Tired

[0805] Example 2:

[0806] If the user enters "tomorrow 2:00 PM" as the "desired delivery time," the server will check the reservation system, calculate the optimal delivery time, and notify the user.

[0807] Example prompt sentence:

[0808] Desired delivery time: tomorrow at 2pm

[0809] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0810] The present invention relates to a medical support assistant system that shortens waiting times at hospitals and takes into account the emotions of users, and includes the following specific embodiments.

[0811] Symptom input and initial diagnosis

[0812] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the name of the diagnosed disease and the recommended medical department.

[0813] As a specific example, if a user inputs the symptom "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[0814] Utilizing the Emotion Engine

[0815] The server then analyzes the user's emotions using an emotion engine based on the user's input data. The emotion engine determines anxiety, stress, and urgency from the user's text and reflects this in the initial diagnosis results.

[0816] For example, if a user enters "I have a sore throat and can't sleep at night," the emotion engine will analyze that the user's anxiety is increasing and increase the priority of the consultation.

[0817] Reservation optimization and notifications

[0818] Based on the initial diagnosis and the user's emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user. The server determines the optimal consultation date and time based on the existing reservation status obtained from the hospital's reservation system. The determined consultation date and time is notified to the user.

[0819] As a specific example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and the emotion engine's analysis determines that the user is highly anxious, the server will prioritize reserving the earliest possible date and time (for example, 10:00 a.m. the following day).

[0820] Consultation scheduling and implementation

[0821] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model and their rationale, as well as the analysis results from the emotion engine, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[0822] As a specific example, a user visits a hospital at a specified date and time, and the medical provider confirms in advance the information that the user has a "sore throat" and that the user is "highly anxious," before beginning the examination.

[0823] Switching to Online Diagnostics

[0824] Based on the initial diagnosis and the emotion engine's analysis, the server determines whether an online consultation is appropriate. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[0825] For example, if a user inputs "I have a mild persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[0826] In this way, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[0827] The processing flow will be explained below.

[0828] Step 1:

[0829] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[0830] Step 2:

[0831] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[0832] Step 3:

[0833] The server uses an emotion engine to analyze emotions from the user's input data, which then performs text analysis to determine the user's anxiety and stress levels.

[0834] Step 4:

[0835] The server integrates the initial diagnosis results with the emotional state determined by the emotion engine to determine the priority of medical examinations and necessary measures. For example, if the user's anxiety is increasing, it will recommend an immediate medical examination.

[0836] Step 5:

[0837] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[0838] Step 6:

[0839] The server connects to the hospital's reservation system to obtain the current reservation status. It then analyzes the user's desired date and time and the existing reservation status using an optimization algorithm.

[0840] Step 7:

[0841] The server's optimization algorithm determines the best appointment time based on existing appointments, the user's emotional state, and their preferred date and time. For example, if the emotion engine detects high anxiety, an earlier date and time will be prioritized.

[0842] Step 8:

[0843] The server registers the determined consultation date and time in the appointment system as confirmed.

[0844] Step 9:

[0845] The server notifies the user's terminal of the confirmed consultation date and time.

[0846] Step 10:

[0847] The user visits the hospital at the scheduled time.

[0848] Step 11:

[0849] The server sends the initial diagnosis results of the generative AI model and their rationale, as well as the emotion analysis results of the emotion engine, to the healthcare provider's device in advance.

[0850] Step 12:

[0851] Before the consultation begins, the healthcare provider reviews information about the user's symptoms and emotional state and prepares for the consultation.

[0852] Step 13:

[0853] The healthcare provider initiates the consultation and uses the information provided in advance to provide efficient and appropriate care.

[0854] Step 14:

[0855] When a user uploads an image of a symptom (eg, an abnormal area of ​​skin) to the terminal, the terminal transmits the image data to the server.

[0856] Step 15:

[0857] The server runs an image analysis AI model and uses the information obtained from the images to improve the accuracy of initial diagnosis results.

[0858] Step 16:

[0859] The server determines whether online consultation is applicable based on the initial diagnosis results and the analysis results of the emotion engine.

[0860] Step 17:

[0861] If online consultation is available, the server notifies the user of the online consultation.

[0862] Step 18:

[0863] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[0864] Step 19:

[0865] An optimization algorithm on the server determines the best time and date for the online consultation.

[0866] Step 20:

[0867] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[0868] Step 21:

[0869] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and rationale, as well as the analysis results of the emotion engine, and issue any necessary instructions or prescriptions.

[0870] This detailed process flow allows users to receive efficient, flexible medical care that takes into consideration their emotions while minimizing waiting times, and also allows medical providers to receive information in advance, allowing for a smoother consultation.

[0871] Example 2

[0872] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0873] In conventional medical treatment systems, it often takes time for the system to determine the appropriate medical department and consultation date and time after the user inputs their symptoms, and the user's emotional state is rarely taken into consideration. As a result, users end up feeling anxious while waiting for their appointment, which reduces the efficiency of medical treatment. In addition, determining the appropriate consultation date and time and selecting online consultations are often done manually, which can disrupt the smooth flow of medical treatment.

[0874] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0875] In this invention, the server includes means for accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis, means for notifying the user of the determined consultation date and time, means for analyzing the emotional state using an emotion engine based on the user's symptom input, means for reflecting the analyzed emotional state in the initial diagnosis and setting the priority of the consultation, and means for transmitting the details of the consultation and the emotional state to a healthcare provider in advance. This makes it possible to efficiently perform the process from the user's symptom input to determining the consultation date and time, and improve the quality and efficiency of medical care by taking the user's emotional state into consideration.

[0876] "User" refers to an individual who uses the system to input their symptoms and receive medical treatment.

[0877] "Symptom input" refers to the act of a user inputting their own physical condition or state into a terminal.

[0878] "Terminal" refers to a computing device used by a user, such as a computer, smartphone, or tablet.

[0879] The term "server" refers to a computer system that receives information from users and uses generative AI models and emotion engines to analyze the data and determine appointment dates and times.

[0880] A "generative AI model" refers to an artificial intelligence system that generates initial diagnostic results from symptom information based on past data and medical knowledge.

[0881] "Initial diagnosis result" refers to the diagnosis obtained as a result of the generative AI model analyzing symptom information.

[0882] An "emotion engine" refers to a system that analyzes the user's emotional state from the text they input and determines their level of anxiety or stress.

[0883] "Appointment Date and Time" refers to the date and time designated for a user to meet with a healthcare provider.

[0884] A "department" refers to a hospital division that specializes in a particular area of ​​medicine.

[0885] "Notification" refers to the act of informing the user of the determined consultation date and time and details of the consultation.

[0886] "Examination details" refers to the specific details of medical treatment and examinations based on the user's symptoms.

[0887] "Healthcare provider" refers to a medical professional such as a doctor or nurse who provides medical services to a user.

[0888] "Online medical consultation" refers to a system in which a medical provider examines or consults with a user via the Internet.

[0889] "Emotional state" refers to psychological states such as anxiety, stress, and urgency that are determined from the text entered by the user.

[0890] "Consultation priority" refers to the criteria for determining the degree of priority for a user's consultation based on the analysis results of the emotion engine.

[0891] This invention relates to a medical support assistant system that shortens waiting times in hospitals and takes into account the user's emotions. The main components are a user terminal, a server, a generative AI model, and an emotion engine.

[0892] User terminal

[0893] Users input their symptoms using devices such as PCs, smartphones, and tablets. This symptom information is then sent from the device to a server. The device then sends the data to the server via the Internet using a secure communication protocol (e.g., HTTPS).

[0894] Specific examples

[0895] The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom entry field.

[0896] server

[0897] The server receives symptom information sent by the user and inputs it into the generative AI model. The generative AI model analyzes the symptom information based on past data and medical knowledge and generates an initial diagnosis. The server also analyzes the user's emotional state using an emotion engine. The analysis results are reflected in the initial diagnosis and are used to set examination priorities.

[0898] Software used

[0899] Generative AI model: A model that generates initial diagnosis results based on past data and medical knowledge

[0900] Emotion Engine: An engine that analyzes the emotional state of a user from their input text.

[0901] Specific examples

[0902] The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends a doctor visit. It also uses an emotion engine to analyze the user's anxieties and prioritizes the consultation.

[0903] Deciding and notifying the appointment date and time

[0904] The server determines the date and time of the consultation based on the initial diagnosis and emotion analysis results. It also works with the hospital's reservation system to determine the optimal consultation date and time, taking into account the user's preferred date and time. The server then notifies the user of the determined consultation date and time.

[0905] Specific examples

[0906] The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[0907] Providing information to healthcare providers

[0908] The server sends the initial diagnosis results from the generative AI model and the analysis results from the emotion engine to the healthcare provider's device in advance, allowing the healthcare provider to have prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[0909] Specific examples

[0910] The user visits the hospital at the specified date and time, and the medical provider confirms the information that the user has a sore throat and that the user is highly anxious beforehand and begins the examination.

[0911] Choosing an online consultation

[0912] The server determines whether an online consultation is appropriate based on the initial diagnosis and the analysis results of the emotion engine. If the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user.

[0913] Specific examples

[0914] If a user inputs "I have a mild, persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[0915] Prompt Sentence Examples

[0916] "Perform an initial diagnosis based on the symptoms entered by the user and recommend possible illnesses and medical specialties. Example: sore throat."

[0917] "Analyze user input text to determine anxiety or stress levels. Example: My throat hurts and I can't sleep at night."

[0918] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0919] Step 1:

[0920] The user enters the symptom information.

[0921] Input: The user inputs the symptoms on the device they use (PC, smartphone, tablet).

[0922] Data processing: Collect user input data in text format.

[0923] Output: Symptom information sent from the device to the server.

[0924] Specific operation: The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom input field.

[0925] Step 2:

[0926] The device sends the symptom information to the server.

[0927] Input: Symptom information entered by the user into the device.

[0928] Data Processing: Symptom information is encrypted using a secure communication protocol (e.g., HTTPS).

[0929] Output: Encrypted symptom information sent to the server.

[0930] Specific operation: The device sends input data such as "I've had a sore throat since last night and I also have a slight fever" to the server via HTTPS.

[0931] Step 3:

[0932] The server performs an initial diagnosis using the generated AI model.

[0933] Input: The symptom information sent to the server.

[0934] Data calculation: Symptom information is input into the generative AI model and analyzed based on past data and medical knowledge.

[0935] Output: Initial diagnosis (diagnosed disease name and recommended medical department).

[0936] Specific operation: The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends seeing an internal medicine doctor.

[0937] Step 4:

[0938] The server performs emotion analysis using an emotion engine.

[0939] Input: User symptom information and initial diagnosis results.

[0940] Data calculation: Symptom information is input into the emotion engine and the emotional state (anxiety, stress, urgency) is analyzed.

[0941] Output: Sentiment analysis results (user's emotional state).

[0942] Specific operation: The server uses an emotion engine to analyze the user's anxiety from symptom text such as "I've had a sore throat since last night and I also have a slight fever," and sets a high priority for medical treatment.

[0943] Step 5:

[0944] The server determines the appropriate appointment date and time and notifies the patient.

[0945] Input: Initial diagnosis results and sentiment analysis results, existing hospital reservations, and the user's desired date and time.

[0946] Data processing: In cooperation with the reservation system, the optimal appointment date and time is determined taking into account the user's wishes and emotional state.

[0947] Output: The determined appointment date and time, and notification of the same.

[0948] Specific operation: The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[0949] Step 6:

[0950] The server transmits the consultation details and emotional state to the healthcare provider.

[0951] Input: Initial diagnostic results of the generative AI model and analysis results of the emotion engine.

[0952] Data processing: Organize the medical examination details and emotional state and send them to the medical provider's terminal.

[0953] Output: Consultation details and emotional state sent to the healthcare provider.

[0954] Specific operation: The server sends the information "sore throat" and "user's anxiety is high" to the healthcare provider's terminal.

[0955] Step 7:

[0956] The user chooses to visit the clinic or have an online consultation.

[0957] Input: Confirmation of appointment or suggestion of online consultation.

[0958] Data calculation: Determines the optimal diagnostic method based on the user's selection.

[0959] Output: Notification of time and date for online consultation or to arrange a face-to-face consultation with a healthcare provider.

[0960] Specific operation: The user checks the notification on their smartphone and visits the hospital at the specified date and time. Alternatively, the user selects online consultation, and the server proposes 3:00 PM on the same day as the date and time for the online consultation and sends a notification to the user's smartphone.

[0961] (Application example 2)

[0962] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0963] Long waiting times and inefficient diagnoses are major problems in modern medical settings and pharmacies. Rapid and appropriate responses are required, especially when users complain of symptoms, but traditional approaches have difficulty meeting these requirements. Furthermore, because treatment and medication recommendations are made without taking the user's emotional state into consideration, user satisfaction and trust tend to decline. Furthermore, the difficulty of scheduling appointments with the appropriate department or pharmacist reduces medical efficiency and increases the workload of healthcare providers.

[0964] The identification processing 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 accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis result, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result, means for notifying the user of the determined consultation date and time, means for transmitting the details of the consultation to a healthcare provider in advance, means for analyzing the user's input data using emotion analysis means and determining the user's emotional state, and means for adjusting appointment priorities and determining the optimal consultation date and time taking the user's emotional state into consideration. This makes it possible to shorten waiting times and realize medical support that takes the user's emotional state into consideration, thereby improving medical efficiency and user satisfaction.

[0965] The "means for accepting symptom input from the user" is an interface that allows the user to input their own symptoms into the system.

[0966] "Means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis" refers to the algorithms and processes for using AI technology to analyze the symptoms entered by the user and obtain a provisional diagnosis.

[0967] The "means for determining an appropriate medical department and consultation date and time" is a system for optimally selecting the medical department and consultation date and time that the user should visit based on the results of the initial diagnosis.

[0968] The "means for notifying the user of the determined appointment date and time" refers to a mechanical or electronic means for communicating the determined appointment date and time and related information to the user.

[0969] The "means for proactively transmitting medical examination details to a healthcare provider" refers to the technology and process for proactively transmitting the user's symptom information and initial diagnosis results to a healthcare provider.

[0970] "Means for analyzing user input data using emotion analysis means and determining the user's emotional state" refers to emotion analysis technology and processes for evaluating the user's emotional state based on the user's input information.

[0971] The "means for adjusting appointment priorities and determining optimal consultation dates and times, taking into account the user's emotional state" is a system for adjusting the priority of appointment dates and times, taking into account the user's emotional state, based on the results of emotion analysis, and making optimal appointments.

[0972] The "means for accepting symptom images" is an interface for receiving image data relating to symptoms provided by the user.

[0973] "Means for improving the accuracy of initial diagnosis results by analyzing using an image analysis AI model" refers to the technology and process for improving the accuracy of initial diagnosis by using AI technology to analyze image data.

[0974] The "means for determining whether an online consultation is applicable" refers to the algorithms and processes for determining whether an online consultation is applicable based on the provided symptom information and diagnosis results.

[0975] The "means for determining and notifying the date and time of an appointment when an online consultation is selected" is a system for determining an appropriate date and time for the appointment and notifying the user and healthcare provider when an online consultation is selected.

[0976] The present invention is a system that consistently supports users from inputting their symptoms to making appointments and online consultations, and specific embodiments required to implement the present invention will be described below.

[0977] Hardware and Software Configuration

[0978] The system includes the following hardware and software:

[0979] Hardware: smartphones, robots, servers

[0980] Software: Python, generative AI model, sentiment analysis engine, reservation management system

[0981] Processing flow

[0982] Symptom input and initial diagnosis

[0983] Users input their symptoms via smartphone or robot. Once the symptoms are entered, the device sends this information to a server. The server then inputs the symptom information into a generative AI model, analyzes it, and generates an initial diagnosis. This diagnosis includes the diagnosed disease name and recommended medical department.

[0984] As a specific example, if a user inputs "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[0985] Sentiment analysis and prioritization

[0986] The server then uses a sentiment analysis engine to analyze the user's emotional state based on the user's input data. The analysis results, along with the diagnosis, are used to adjust the priority of appointments. For example, if a user inputs "I have a sore throat and can't sleep at night," the sentiment analysis engine will determine that the user's anxiety is increasing and raise the priority of the appointment.

[0987] Reservation optimization and notifications

[0988] Based on the initial diagnosis and emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user, and calculates the optimal consultation date and time. The determined consultation date and time is notified to the user.

[0989] For example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and emotion analysis indicates high anxiety, the server will prioritize reserving the earliest possible date and time, such as 10:00 a.m. the following day.

[0990] Consultation scheduling and implementation

[0991] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model, along with the rationale behind the diagnosis, as well as the emotional analysis results, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[0992] ●Example of prompt sentence:

[0993] Symptoms: Sore throat, sleepless nights

[0994] Desired appointment date and time: 2023-10-15 10:00:00, 2023-10-16 11:00:00

[0995] Initial diagnosis result: Common cold (cold)

[0996] Sentiment analysis results: High anxiety

[0997] Best time to see a doctor: 2023-10-15 14:00:00

[0998] Proposing and implementing online consultations

[0999] The server determines whether an online consultation is appropriate based on the initial diagnosis and sentiment analysis. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. The user can then consult with a healthcare provider via the Internet at the specified time.

[1000] As described above, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[1001] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1002] Step 1:

[1003] The user inputs symptoms into the terminal. The terminal receives the symptom data (in text format) entered by the user and sends the data to the server. At this point, the input is the user's symptom information, and the output is the symptom data sent to the server.

[1004] Step 2:

[1005] The server inputs the received symptom data into a generative AI model. The generative AI model analyzes the symptom data based on past case data and medical knowledge, and generates an initial diagnosis. The input at this point is the symptom data sent to the server, and the output is the initial diagnosis (diagnosed disease name and recommended medical department).

[1006] Step 3:

[1007] The server uses a sentiment analysis engine to analyze the user's emotional state from the symptom data. The sentiment analysis engine performs text analysis to determine the user's anxiety and stress levels. At this point, the input is the symptom data, and the output is the user's emotional state (e.g., high anxiety, normal, relaxed).

[1008] Step 4:

[1009] Based on the initial diagnosis and emotion analysis results, the server uses the appointment management system to determine the appropriate department and optimal consultation date and time. During this process, the desired consultation date and time entered by the user is also taken into consideration. The input at this point is the initial diagnosis result, emotion analysis result, and the user's desired consultation date and time, and the output is the determined optimal consultation date and time.

[1010] Step 5:

[1011] The server notifies the user of the determined appointment date and time. Notification can be done via smartphone, email, etc. The input at this point is the determined appointment date and time, and the output is a notification message sent to the user.

[1012] Step 6:

[1013] The server sends the initial diagnosis results and their rationale, as well as the emotion analysis results, generated by the generative AI model, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins. The input at this point is the initial diagnosis results, rationale, and emotion analysis results, and the output is this data sent to the healthcare provider.

[1014] Step 7:

[1015] The server determines whether an online consultation is applicable based on the initial diagnosis result and emotion analysis. If it is determined that an online consultation is applicable, it proposes an online consultation to the user. At this point, the input is the initial diagnosis result and emotion analysis result, and the output is a message proposing an online consultation.

[1016] Step 8:

[1017] If the user selects an online consultation, the server determines the optimal time and date for the online consultation and notifies the user and the healthcare provider. At this point, the input is the user's preference for an online consultation, and the output is a notification of the optimal time and date for the online consultation.

[1018] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1019] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1020] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1021] [Third embodiment]

[1022] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1023] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1025] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1026] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1027] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1029] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1030] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1032] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1033] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1034] The present invention relates to a medical support assistant system for shortening waiting times at hospitals, and is realized in the specific embodiments described below.

[1035] Symptom input and initial diagnosis

[1036] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the diagnosed disease name and recommended medical department. If necessary, the user can take an image related to the symptoms (for example, a photo of an abnormal area on the skin) and send this to the server via the device. The server then inputs this image data into an image analysis AI model, and the analysis results are reflected in the generative AI model's diagnosis.

[1037] As a specific example, if a user inputs the symptom "sore throat" and uploads an image, the server will use a generative AI model to make an initial diagnosis of "cold" and then use an image analysis AI model to confirm specific symptoms (e.g., redness or swelling).

[1038] Reservation optimization and notifications

[1039] Based on the initial diagnosis, the server determines the appropriate department. The user also inputs the desired consultation date and time, which is then sent to the server. The server then determines the optimal consultation date and time based on the desired date and time and existing appointments retrieved from the hospital's reservation system. The server's optimization algorithm efficiently performs this process and notifies the user of the optimal available consultation date and time.

[1040] For example, if a user enters "Tuesday or Wednesday morning next week would be convenient," the server will check the reservation system, find that there is availability at 11:00 a.m. on Tuesday, and notify the user.

[1041] Consultation scheduling and implementation

[1042] Once the reservation is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results obtained by the generative AI model and the basis for the diagnosis to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge about the user's symptoms before the consultation begins, improving the efficiency of the consultation.

[1043] As a concrete example, a user visits the hospital at 11:00 AM on a Tuesday, and the healthcare provider begins the consultation by confirming the initial diagnosis and imaging results for a "sore throat."

[1044] Switching to Online Diagnostics

[1045] The server determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the best time and date for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[1046] For example, if a user inputs "I have a persistent mild cough" and the server diagnoses it as a "mild cold" using a generative AI model, an online consultation will be suggested. If the user selects this option, a date and time for the online consultation will be scheduled and notified to the user and their healthcare provider.

[1047] In this way, the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[1048] The processing flow will be explained below.

[1049] Step 1:

[1050] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[1051] Step 2:

[1052] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[1053] Step 3:

[1054] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[1055] Step 4:

[1056] The server determines the appropriate medical department based on the symptom data and the diagnostic results of the generative AI model.

[1057] Step 5:

[1058] The server connects to the hospital's reservation system and obtains the current reservation status.

[1059] Step 6:

[1060] The server's optimization algorithm determines the optimal appointment date and time based on existing appointments and the user's desired date and time.

[1061] Step 7:

[1062] The server registers the determined consultation date and time in the appointment system as confirmed.

[1063] Step 8:

[1064] The server notifies the user's terminal of the confirmed reservation date and time.

[1065] Step 9:

[1066] The user visits the hospital at the scheduled time.

[1067] Step 10:

[1068] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device in advance.

[1069] Step 11:

[1070] The healthcare provider begins the consultation with prior knowledge of the user's symptoms before the consultation begins.

[1071] Step 12:

[1072] When a user uploads an image (eg, a photo of a symptom) to the terminal, the terminal transmits the image data to the server.

[1073] Step 13:

[1074] The server runs an image analysis AI model to improve the accuracy of initial diagnosis results based on information obtained from the images.

[1075] Step 14:

[1076] Based on the initial diagnosis, the server determines whether online consultation is possible.

[1077] Step 15:

[1078] If online consultation is available, the server notifies the user of the online consultation.

[1079] Step 16:

[1080] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[1081] Step 17:

[1082] An optimization algorithm on the server determines the best time and date for the online consultation.

[1083] Step 18:

[1084] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[1085] Step 19:

[1086] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and evidence, and issue any necessary instructions or prescriptions.

[1087] This detailed flow not only allows users to receive efficient medical care while minimizing waiting times, but also allows medical providers to conduct consultations smoothly.

[1088] Example 1

[1089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1090] In modern hospitals, long waiting times for consultations are a burden for patients. It is also difficult to efficiently guide patients to the appropriate department and arrange consultation dates and times. Furthermore, technology that improves patient convenience is needed to improve the accuracy of initial diagnoses and implement online consultations.

[1091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1092] In this invention, the server

[1093] a means for accepting symptom input;

[1094] means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis;

[1095] A means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result;

[1096] means for notifying the user of the determined consultation date and time;

[1097] means for proactively transmitting the consultation to a healthcare provider;

[1098] a means for receiving images relating to the symptom;

[1099] The system also includes a means for analyzing the images using an image analysis AI model to improve the accuracy of initial diagnosis results, which will shorten waiting times at hospitals, guide patients to the appropriate department, optimize appointments, improve the accuracy of initial diagnosis, and enable smooth online consultations.

[1100] A "user" is an individual who uses the system to input their symptoms and desired consultation date and time.

[1101] "Symptom input" refers to the act of a user inputting their own health condition and symptoms they are experiencing into a terminal.

[1102] A "generative AI model" is an artificial intelligence model that analyzes symptoms based on past data and medical knowledge and generates initial diagnosis results.

[1103] The "initial diagnosis result" is the disease name and recommended medical department information obtained as a result of analysis by the generative AI model.

[1104] The "appropriate department" is the medical specialty for which the user should be examined based on the initial diagnosis.

[1105] The "examination date and time" is the date and time designated for the user to receive an examination.

[1106] "Notification" refers to the act of informing the user of the consultation date and time and the results of the initial diagnosis.

[1107] The "image analysis AI model" is an artificial intelligence model that analyzes image data related to symptoms and improves the accuracy of initial diagnosis results.

[1108] An "online consultation" is a consultation conducted between a healthcare provider and a user over the Internet.

[1109] "Healthcare providers" are professionals such as doctors and nurses who provide medical examinations and treatment.

[1110] "Consultation details" refers to the user's symptoms, their analysis results, and detailed information about the consultation.

[1111] The "server" is the central computer in the system that receives input from the user, generates diagnostic results using generative AI models and image analysis AI models, and determines and notifies the patient of the appropriate medical department and consultation date and time.

[1112] A "terminal" is a device through which a user inputs symptoms and desired date and time and communicates with a server.

[1113] The present invention provides a medical support assistant system that shortens waiting times at hospitals and provides efficient medical services. The system accepts symptom input from users, analyzes the input using a generative AI model and an image analysis AI model, and generates an initial diagnosis. It then determines the appropriate department and optimal consultation date and time and notifies the user and healthcare provider.

[1114] First, the user inputs their symptoms using their own device (smartphone, PC, etc.). The device then sends this information to a server. The server then inputs the received symptom information into a generative AI model (such as TensorFlow or PyTorch) and generates an initial diagnosis based on past data and medical knowledge. Specifically, if the symptom input is "sore throat," the server will use the generative AI model to make an initial diagnosis of "cold."

[1115] Additionally, users can take images of their symptoms (e.g., a photo of their throat) and send them to a server via their device. The server inputs this image data into an image analysis AI model (e.g., OpenCV or Keras), and the analysis results are reflected in the generative AI model's diagnostic results. This improves the accuracy of the diagnosis. For example, by uploading a photo of the throat, the image analysis AI model can detect redness and swelling, and these results are added to the diagnostic results.

[1116] Once the diagnosis is complete, the server determines the appropriate medical department (e.g., "Internal Medicine"). Next, the user inputs the desired consultation date and time (e.g., "Tuesday or Wednesday morning next week") and sends it to the server. The server retrieves existing reservations from the hospital's reservation system and determines the optimal consultation date and time by comparing it with the desired date and time. The server notifies the user of the determined date and time (e.g., "Appointment for 11:00 AM on Tuesday").

[1117] Once the appointment is confirmed, the user visits the hospital at the specified date and time for a consultation. The server sends the initial diagnosis and its basis to the medical provider's terminal in advance, allowing the medical provider to obtain prior knowledge of the user's symptoms before the consultation, thereby improving the efficiency of the consultation.

[1118] The server also determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the most appropriate time and date for the online consultation, which will also be notified to the user and the healthcare provider.

[1119] As a concrete example, the following prompt sentence could be input into a generative AI model:

[1120] Prompt: Implement a flow for initial diagnosis and appointment optimization for patients with the symptom "sore throat."

[1121] Prompt: Create a code that optimizes appointments based on the patient's preferred time and the clinic's available time for appointments next week and notifies them.

[1122] Prompt: Develop a system to suggest an online consultation for a patient with mild cold symptoms, determine the best time to schedule the appointment, and notify the user and their healthcare provider.

[1123] In this way, the system of the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[1124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1125] Step 1:

[1126] The user enters the symptoms.

[1127] Specific actions: The user opens the system's input screen on their smartphone or computer and enters "I have a sore throat."

[1128] Input: Symptoms entered by the user (e.g., "I have a sore throat")

[1129] Output: Data that the device uses to send user symptom input to the server

[1130] Step 2:

[1131] The device sends the symptom information to the server.

[1132] Specific operation: The device sends the entered symptom data to the server via an HTTP request.

[1133] Input: User-entered symptom data

[1134] Output: Symptom data received by the server

[1135] Step 3:

[1136] The symptom information received by the server is input into a generative AI model to generate an initial diagnosis result.

[1137] Specific operation: The server passes the received symptom data to the generative AI model, which then initiates the diagnostic process. The generative AI model performs an initial diagnosis based on past data and medical knowledge, and diagnoses the illness as a "cold."

[1138] Input: Received symptom data

[1139] Output: Initial diagnosis result from the generative AI model (e.g., "cold").

[1140] Step 4:

[1141] The user takes an image of the symptoms and sends it to the server via the terminal.

[1142] Specific operation: The user takes a photo of their throat with their smartphone and clicks the system's upload button to send the image to the server.

[1143] Input: User-taken symptom image

[1144] Output: Image data received by the server

[1145] Step 5:

[1146] The server inputs the image data into an image analysis AI model and reflects the analysis results in the initial diagnosis.

[1147] How it works: The server passes the image data to the image analysis AI model, which then performs image analysis. The image analysis AI model detects redness and swelling and adds the results to the generative AI model's diagnosis.

[1148] Input: Received image data

[1149] Output: Final diagnosis result reflecting the image analysis results

[1150] Step 6:

[1151] The server determines the appropriate medical department based on the initial diagnosis results.

[1152] Specific operation: The server analyzes the initial diagnosis results and determines "internal medicine" as the recommended medical specialty.

[1153] Input: Initial diagnosis result

[1154] Output: The appropriate medical specialty (e.g., "Internal Medicine")

[1155] Step 7:

[1156] The user inputs the desired consultation date and time into the terminal and transmits it to the server.

[1157] Specific operation: The user enters "Tuesday or Wednesday morning next week" as the desired date and time into the system and submits it.

[1158] Input: User's desired appointment date and time

[1159] Output: Desired appointment date and time data received by the server

[1160] Step 8:

[1161] The server compares the desired date and time with the existing reservation status obtained from the hospital's reservation system and determines the optimal date and time for the consultation.

[1162] Specific behavior: The server uses the hospital's reservation system API to check the current availability and finds that 11:00 AM on Tuesday is available.

[1163] Input: User's desired consultation date and time data, and reservation status data from the reservation system

[1164] Output: Best appointment time (e.g. "Tuesday at 11 AM")

[1165] Step 9:

[1166] The server notifies the user of the best time and date for an appointment.

[1167] Specific operation: The server sends a reservation confirmation notification to the user's device, displaying "Reservation confirmed for 11:00 AM on Tuesday."

[1168] Input: Best appointment time

[1169] Output: Confirmation of reservation sent to user

[1170] Step 10:

[1171] The user visits the hospital at the designated date and time and receives a medical examination.

[1172] What happens: A user arrives at the hospital at 11:00 AM on a Tuesday and confirms their appointment with the receptionist.

[1173] Input: Reservation date and time

[1174] Output: Start of hospital consultation

[1175] Step 11:

[1176] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device.

[1177] Specific operation: The server sends a report containing the initial diagnosis and image analysis results to the healthcare provider's device.

[1178] Input: Initial diagnosis results, image analysis results

[1179] Output: Sending diagnostic data to healthcare provider

[1180] Step 12:

[1181] Healthcare providers review the submitted data and conduct consultations efficiently.

[1182] Specific operation: The medical provider checks the initial diagnosis results and image analysis results on the device before the consultation and begins the consultation.

[1183] Input: Diagnostic data sent from the server

[1184] Output: Efficient consultation

[1185] Step 13:

[1186] The server determines whether online consultation is applicable based on the initial diagnosis results.

[1187] Specific operation: The server analyzes the diagnosis results of the generative AI model, determines that the patient has a "mild cold," and concludes that an online consultation is possible.

[1188] Input: Initial diagnosis result

[1189] Output: Proposal for online consultation

[1190] Step 14:

[1191] The server sends the online consultation offer to the user.

[1192] Specific operation: The server sends a notification to the user's device asking, "Would you like to have an online consultation?"

[1193] Input: Online consultation suggestion

[1194] Output: Proposal notification to user

[1195] Step 15:

[1196] The user selects an online consultation.

[1197] Specific operation: The user clicks the "Request online consultation" button on the device.

[1198] Input: Select Online Consultation

[1199] Output: Update the server's online appointment schedule flag

[1200] Step 16:

[1201] The server determines the best time and date for the online consultation and notifies the user and the healthcare provider.

[1202] Specific operation: The server checks the reservation system to determine the available date and time for online consultation, and notifies the user and healthcare provider devices of the determined date and time.

[1203] Input: Online consultation selection and appointment status data from the booking system

[1204] Output: Deciding and notifying online consultation date and time

[1205] By going through the above steps, efficient and flexible medical services can be provided.

[1206] (Application example 1)

[1207] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1208] The food delivery industry lacks the means to recommend appropriate menu items that respond to individual customer preferences and circumstances. Furthermore, the system for determining and notifying optimal delivery times is not well developed, which can lead to lower customer satisfaction. Furthermore, the inability to smoothly handle questions or requests about dishes limits the customer experience.

[1209] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1210] In this invention, the server includes a means for receiving information about the user's preferences and situation and presenting recommended menus based on past data and health information, a means for determining and notifying the user of an optimal delivery time based on the user's desired delivery time, and a means for the user to ask questions or make requests about dishes online, thereby enabling food delivery services that meet the individual needs of the user.

[1211] A "user" is an individual who utilizes the system to input information and receive services.

[1212] A "generative AI model" is an artificial intelligence model that analyzes information based on past data and knowledge and generates appropriate results.

[1213] "Symptom input" refers to the act of a user inputting information about their own symptoms or condition into the system.

[1214] The "initial diagnosis result" is information such as the disease name and recommended medical department that is presented as a result of analysis by the generative AI model.

[1215] A "medical department" is a specialized department at a medical institution that provides diagnosis and treatment for specific types of illnesses or symptoms.

[1216] The "examination date and time" is the specific date and time when the user is scheduled to receive an examination.

[1217] "Notification" refers to the act of the system informing the user or information provider of determined information.

[1218] "Healthcare providers" are professionals such as doctors and nurses who provide health care services in hospitals and clinics.

[1219] "Preferences" refer to the types of food or cuisine that a user prefers.

[1220] "Past data" refers to user input information and behavioral history that the system has collected in the past.

[1221] "Health information" is information relating to the user's health condition and medical history.

[1222] A "recommended menu" is a list of dishes suggested by a generative AI model based on the user's preferences and health status.

[1223] "Desired delivery time" refers to the specific time at which a user would like to receive food delivery.

[1224] "Delivery time optimization" is the process of calculating the most appropriate delivery time based on the user's preferences and the restaurant's situation.

[1225] "Online consultation" is a system that allows users to communicate in real time with restaurant chefs or staff via the Internet.

[1226] Overall system configuration

[1227] This invention provides a system that provides customized support to both end users and restaurants in the food delivery industry. The system uses devices such as smartphones and tablets and operates in conjunction with a server. The server uses a generative AI model to analyze user input data and provide optimal menu recommendations and delivery times.

[1228] Hardware and software used

[1229] Hardware: Smartphones, servers

[1230] Software: Flask (Python web framework), TensorFlow (deep learning model), database (e.g., MySQL)

[1231] Specific operation flow of the system

[1232] 1. Enter symptoms and generate a recommendation menu

[1233] Users enter their preferences, allergy information, and current mood through a smartphone app. This information is sent from the device to a server. The server uses a generative AI model to analyze this information and provide the user with the optimal menu recommendations. This menu is generated based on past order data and the user's health information.

[1234] For example, if a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[1235] Example prompt sentence:

[1236] User Information:

[1237] Favourites: Chicken

[1238] Allergies: None

[1239] Mood: Tired

[1240] 2. Reservation optimization and notifications

[1241] After selecting from the recommended menu, the user inputs the desired delivery time. The server determines the optimal delivery time based on the restaurant's congestion status and the delivery staff's schedule, and notifies the user.

[1242] As a specific example, if the user requests "tomorrow at 2:00 p.m.", the server checks the reservation system, calculates the optimal delivery time, and notifies the user.

[1243] 3. Online consultation mode

[1244] If a user has any questions or requests regarding food, they can consult with restaurant staff online through a smartphone app. The server receives these requests and forwards them to the restaurant's chefs in real time.

[1245] Example prompt sentence:

[1246] User Request:

[1247] Dish name:Grilled chicken

[1248] Q: Can I make it less spicy?

[1249] Operational Scenario

[1250] The system begins when users use a smartphone app to enter their information. The information is sent to a server and analyzed by a generative AI model. An optimal menu recommendation is generated and presented to the user. The optimal delivery time is then determined and notified based on the user's desired delivery time. In addition, users can ask questions or make requests about dishes online.

[1251] In this way, the present invention significantly improves the efficiency and customer satisfaction of food delivery, and the customized service allows food delivery to be tailored to the individual needs of users.

[1252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1253] Step 1:

[1254] The user uses their smartphone to input their preferences, allergy information, current mood, etc. into the app. This inputs the user's individual information into the device, and the input data is sent to the server in JSON format.

[1255] input:

[1256] {

[1257] "preferences": "chicken",

[1258] "allergies": "none",

[1259] "mood": "tired"

[1260] }

[1261] output:

[1262] Send JSON data from the terminal to the server.

[1263] Step 2:

[1264] The server parses the received JSON data and passes the input data to the generative AI model, which then generates a recommended menu based on past order data and health information. The generated recommended menu is returned in JSON format and saved on the server.

[1265] input:

[1266] User data in JSON format

[1267] output:

[1268] JSON data of the recommended menu

[1269] Specific behavior:

[1270] Data is input into a generative AI model to generate recommended menus.

[1271] Step 3:

[1272] The server generates a recommended menu, which is sent to the smartphone app and displayed to the user. The user then selects an order and enters the desired delivery time. The entered delivery time is then sent back to the server.

[1273] input:

[1274] JSON data of the recommended menu

[1275] output:

[1276] Displaying a deserialized recommendation menu

[1277] Specific behavior:

[1278] Receive recommended menus from the server and display them to the user in the app.

[1279] Step 4:

[1280] The server calculates the optimal delivery time based on the received delivery time, the restaurant's congestion status, and the delivery person's schedule information. As a result, the optimal delivery time is obtained and notified to the user.

[1281] input:

[1282] User's desired delivery time, restaurant congestion information, delivery staff schedule data

[1283] output:

[1284] Notification of optimal delivery time

[1285] Specific behavior:

[1286] The server retrieves the necessary data from the reservation system and performs calculations using an optimization algorithm.

[1287] Step 5:

[1288] If a user has a question or request about a dish, they can enter it through the online consultation mode on their smartphone app, which then sends the request to the restaurant's chef via the server.

[1289] input:

[1290] Text data of cooking-related questions and requests

[1291] output:

[1292] Sending the request

[1293] Specific behavior:

[1294] The server receives the user's request and forwards it to the restaurant in real time.

[1295] Specific examples

[1296] Example 1:

[1297] If a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[1298] Example prompt sentence:

[1299] User Information:

[1300] Favourites: Chicken

[1301] Allergies: None

[1302] Mood: Tired

[1303] Example 2:

[1304] If the user enters "tomorrow 2:00 PM" as the "desired delivery time," the server will check the reservation system, calculate the optimal delivery time, and notify the user.

[1305] Example prompt sentence:

[1306] Desired delivery time: tomorrow at 2pm

[1307] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1308] The present invention relates to a medical support assistant system that shortens waiting times at hospitals and takes into account the emotions of users, and includes the following specific embodiments.

[1309] Symptom input and initial diagnosis

[1310] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the name of the diagnosed disease and the recommended medical department.

[1311] As a specific example, if a user inputs the symptom "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[1312] Utilizing the Emotion Engine

[1313] The server then analyzes the user's emotions using an emotion engine based on the user's input data. The emotion engine determines anxiety, stress, and urgency from the user's text and reflects this in the initial diagnosis results.

[1314] For example, if a user enters "I have a sore throat and can't sleep at night," the emotion engine will analyze that the user's anxiety is increasing and increase the priority of the consultation.

[1315] Reservation optimization and notifications

[1316] Based on the initial diagnosis and the user's emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user. The server determines the optimal consultation date and time based on the existing reservation status obtained from the hospital's reservation system. The determined consultation date and time is notified to the user.

[1317] As a specific example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and the emotion engine's analysis determines that the user is highly anxious, the server will prioritize reserving the earliest possible date and time (for example, 10:00 a.m. the following day).

[1318] Consultation scheduling and implementation

[1319] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model and their rationale, as well as the analysis results from the emotion engine, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[1320] As a specific example, a user visits a hospital at a specified date and time, and the medical provider confirms in advance the information that the user has a "sore throat" and that the user is "highly anxious," before beginning the examination.

[1321] Switching to Online Diagnostics

[1322] Based on the initial diagnosis and the emotion engine's analysis, the server determines whether an online consultation is appropriate. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[1323] For example, if a user inputs "I have a mild persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[1324] In this way, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[1325] The processing flow will be explained below.

[1326] Step 1:

[1327] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[1328] Step 2:

[1329] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[1330] Step 3:

[1331] The server uses an emotion engine to analyze emotions from the user's input data, which then performs text analysis to determine the user's anxiety and stress levels.

[1332] Step 4:

[1333] The server integrates the initial diagnosis results with the emotional state determined by the emotion engine to determine the priority of medical examinations and necessary measures. For example, if the user's anxiety is increasing, it will recommend an immediate medical examination.

[1334] Step 5:

[1335] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[1336] Step 6:

[1337] The server connects to the hospital's reservation system to obtain the current reservation status. It then analyzes the user's desired date and time and the existing reservation status using an optimization algorithm.

[1338] Step 7:

[1339] The server's optimization algorithm determines the best appointment time based on existing appointments, the user's emotional state, and their preferred date and time. For example, if the emotion engine detects high anxiety, an earlier date and time will be prioritized.

[1340] Step 8:

[1341] The server registers the determined consultation date and time in the appointment system as confirmed.

[1342] Step 9:

[1343] The server notifies the user's terminal of the confirmed consultation date and time.

[1344] Step 10:

[1345] The user visits the hospital at the scheduled time.

[1346] Step 11:

[1347] The server sends the initial diagnosis results of the generative AI model and their rationale, as well as the emotion analysis results of the emotion engine, to the healthcare provider's device in advance.

[1348] Step 12:

[1349] Before the consultation begins, the healthcare provider reviews information about the user's symptoms and emotional state and prepares for the consultation.

[1350] Step 13:

[1351] The healthcare provider initiates the consultation and uses the information provided in advance to provide efficient and appropriate care.

[1352] Step 14:

[1353] When a user uploads an image of a symptom (eg, an abnormal area of ​​skin) to the terminal, the terminal transmits the image data to the server.

[1354] Step 15:

[1355] The server runs an image analysis AI model and uses the information obtained from the images to improve the accuracy of initial diagnosis results.

[1356] Step 16:

[1357] The server determines whether online consultation is applicable based on the initial diagnosis results and the analysis results of the emotion engine.

[1358] Step 17:

[1359] If online consultation is available, the server notifies the user of the online consultation.

[1360] Step 18:

[1361] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[1362] Step 19:

[1363] An optimization algorithm on the server determines the best time and date for the online consultation.

[1364] Step 20:

[1365] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[1366] Step 21:

[1367] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and rationale, as well as the analysis results of the emotion engine, and issue any necessary instructions or prescriptions.

[1368] This detailed process flow allows users to receive efficient, flexible medical care that takes into consideration their emotions while minimizing waiting times, and also allows medical providers to receive information in advance, allowing for a smoother consultation.

[1369] Example 2

[1370] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1371] In conventional medical treatment systems, it often takes time for the system to determine the appropriate medical department and consultation date and time after the user inputs their symptoms, and the user's emotional state is rarely taken into consideration. As a result, users end up feeling anxious while waiting for their appointment, which reduces the efficiency of medical treatment. In addition, determining the appropriate consultation date and time and selecting online consultations are often done manually, which can disrupt the smooth flow of medical treatment.

[1372] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1373] In this invention, the server includes means for accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis, means for notifying the user of the determined consultation date and time, means for analyzing the emotional state using an emotion engine based on the user's symptom input, means for reflecting the analyzed emotional state in the initial diagnosis and setting the priority of the consultation, and means for transmitting the details of the consultation and the emotional state to a healthcare provider in advance. This makes it possible to efficiently perform the process from the user's symptom input to determining the consultation date and time, and improve the quality and efficiency of medical care by taking the user's emotional state into consideration.

[1374] "User" refers to an individual who uses the system to input their symptoms and receive medical treatment.

[1375] "Symptom input" refers to the act of a user inputting their own physical condition or state into a terminal.

[1376] "Terminal" refers to a computing device used by a user, such as a computer, smartphone, or tablet.

[1377] The term "server" refers to a computer system that receives information from users and uses generative AI models and emotion engines to analyze the data and determine appointment dates and times.

[1378] A "generative AI model" refers to an artificial intelligence system that generates initial diagnostic results from symptom information based on past data and medical knowledge.

[1379] "Initial diagnosis result" refers to the diagnosis obtained as a result of the generative AI model analyzing symptom information.

[1380] An "emotion engine" refers to a system that analyzes the user's emotional state from the text they input and determines their level of anxiety or stress.

[1381] "Appointment Date and Time" refers to the date and time designated for a user to meet with a healthcare provider.

[1382] A "department" refers to a hospital division that specializes in a particular area of ​​medicine.

[1383] "Notification" refers to the act of informing the user of the determined consultation date and time and details of the consultation.

[1384] "Examination details" refers to the specific details of medical treatment and examinations based on the user's symptoms.

[1385] "Healthcare provider" refers to a medical professional such as a doctor or nurse who provides medical services to a user.

[1386] "Online medical consultation" refers to a system in which a medical provider examines or consults with a user via the Internet.

[1387] "Emotional state" refers to psychological states such as anxiety, stress, and urgency that are determined from the text entered by the user.

[1388] "Consultation priority" refers to the criteria for determining the degree of priority for a user's consultation based on the analysis results of the emotion engine.

[1389] This invention relates to a medical support assistant system that shortens waiting times in hospitals and takes into account the user's emotions. The main components are a user terminal, a server, a generative AI model, and an emotion engine.

[1390] User terminal

[1391] Users input their symptoms using devices such as PCs, smartphones, and tablets. This symptom information is then sent from the device to a server. The device then sends the data to the server via the Internet using a secure communication protocol (e.g., HTTPS).

[1392] Specific examples

[1393] The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom entry field.

[1394] server

[1395] The server receives symptom information sent by the user and inputs it into the generative AI model. The generative AI model analyzes the symptom information based on past data and medical knowledge and generates an initial diagnosis. The server also analyzes the user's emotional state using an emotion engine. The analysis results are reflected in the initial diagnosis and are used to set examination priorities.

[1396] Software used

[1397] Generative AI model: A model that generates initial diagnosis results based on past data and medical knowledge

[1398] Emotion Engine: An engine that analyzes the emotional state of a user from their input text.

[1399] Specific examples

[1400] The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends a doctor visit. It also uses an emotion engine to analyze the user's anxieties and prioritizes the consultation.

[1401] Deciding and notifying the appointment date and time

[1402] The server determines the date and time of the consultation based on the initial diagnosis and emotion analysis results. It also works with the hospital's reservation system to determine the optimal consultation date and time, taking into account the user's preferred date and time. The server then notifies the user of the determined consultation date and time.

[1403] Specific examples

[1404] The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[1405] Providing information to healthcare providers

[1406] The server sends the initial diagnosis results from the generative AI model and the analysis results from the emotion engine to the healthcare provider's device in advance, allowing the healthcare provider to have prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[1407] Specific examples

[1408] The user visits the hospital at the specified date and time, and the medical provider confirms the information that the user has a sore throat and that the user is highly anxious beforehand and begins the examination.

[1409] Choosing an online consultation

[1410] The server determines whether an online consultation is appropriate based on the initial diagnosis and the analysis results of the emotion engine. If the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user.

[1411] Specific examples

[1412] If a user inputs "I have a mild, persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[1413] Prompt Sentence Examples

[1414] "Perform an initial diagnosis based on the symptoms entered by the user and recommend possible illnesses and medical specialties. Example: sore throat."

[1415] "Analyze user input text to determine anxiety or stress levels. Example: My throat hurts and I can't sleep at night."

[1416] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1417] Step 1:

[1418] The user enters the symptom information.

[1419] Input: The user inputs the symptoms on the device they use (PC, smartphone, tablet).

[1420] Data processing: Collect user input data in text format.

[1421] Output: Symptom information sent from the device to the server.

[1422] Specific operation: The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom input field.

[1423] Step 2:

[1424] The device sends the symptom information to the server.

[1425] Input: Symptom information entered by the user into the device.

[1426] Data Processing: Symptom information is encrypted using a secure communication protocol (e.g., HTTPS).

[1427] Output: Encrypted symptom information sent to the server.

[1428] Specific operation: The device sends input data such as "I've had a sore throat since last night and I also have a slight fever" to the server via HTTPS.

[1429] Step 3:

[1430] The server performs an initial diagnosis using the generated AI model.

[1431] Input: The symptom information sent to the server.

[1432] Data calculation: Symptom information is input into the generative AI model and analyzed based on past data and medical knowledge.

[1433] Output: Initial diagnosis (diagnosed disease name and recommended medical department).

[1434] Specific operation: The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends seeing an internal medicine doctor.

[1435] Step 4:

[1436] The server performs emotion analysis using an emotion engine.

[1437] Input: User symptom information and initial diagnosis results.

[1438] Data calculation: Symptom information is input into the emotion engine and the emotional state (anxiety, stress, urgency) is analyzed.

[1439] Output: Sentiment analysis results (user's emotional state).

[1440] Specific operation: The server uses an emotion engine to analyze the user's anxiety from symptom text such as "I've had a sore throat since last night and I also have a slight fever," and sets a high priority for medical treatment.

[1441] Step 5:

[1442] The server determines the appropriate appointment date and time and notifies the patient.

[1443] Input: Initial diagnosis results and sentiment analysis results, existing hospital reservations, and the user's desired date and time.

[1444] Data processing: In cooperation with the reservation system, the optimal appointment date and time is determined taking into account the user's wishes and emotional state.

[1445] Output: The determined appointment date and time, and notification of the same.

[1446] Specific operation: The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[1447] Step 6:

[1448] The server transmits the consultation details and emotional state to the healthcare provider.

[1449] Input: Initial diagnostic results of the generative AI model and analysis results of the emotion engine.

[1450] Data processing: Organize the medical examination details and emotional state and send them to the medical provider's terminal.

[1451] Output: Consultation details and emotional state sent to the healthcare provider.

[1452] Specific operation: The server sends the information "sore throat" and "user's anxiety is high" to the healthcare provider's terminal.

[1453] Step 7:

[1454] The user chooses to visit the clinic or have an online consultation.

[1455] Input: Confirmation of appointment or suggestion of online consultation.

[1456] Data calculation: Determines the optimal diagnostic method based on the user's selection.

[1457] Output: Notification of time and date for online consultation or to arrange a face-to-face consultation with a healthcare provider.

[1458] Specific operation: The user checks the notification on their smartphone and visits the hospital at the specified date and time. Alternatively, the user selects online consultation, and the server proposes 3:00 PM on the same day as the date and time for the online consultation and sends a notification to the user's smartphone.

[1459] (Application example 2)

[1460] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1461] Long waiting times and inefficient diagnoses are major problems in modern medical settings and pharmacies. Rapid and appropriate responses are required, especially when users complain of symptoms, but traditional approaches have difficulty meeting these requirements. Furthermore, because treatment and medication recommendations are made without taking the user's emotional state into consideration, user satisfaction and trust tend to decline. Furthermore, the difficulty of scheduling appointments with the appropriate department or pharmacist reduces medical efficiency and increases the workload of healthcare providers.

[1462] The identification processing 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 accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis result, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result, means for notifying the user of the determined consultation date and time, means for transmitting the details of the consultation to a healthcare provider in advance, means for analyzing the user's input data using emotion analysis means and determining the user's emotional state, and means for adjusting appointment priorities and determining the optimal consultation date and time taking the user's emotional state into consideration. This makes it possible to shorten waiting times and realize medical support that takes the user's emotional state into consideration, thereby improving medical efficiency and user satisfaction.

[1463] The "means for accepting symptom input from the user" is an interface that allows the user to input their own symptoms into the system.

[1464] "Means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis" refers to the algorithms and processes for using AI technology to analyze the symptoms entered by the user and obtain a provisional diagnosis.

[1465] The "means for determining an appropriate medical department and consultation date and time" is a system for optimally selecting the medical department and consultation date and time that the user should visit based on the results of the initial diagnosis.

[1466] The "means for notifying the user of the determined appointment date and time" refers to a mechanical or electronic means for communicating the determined appointment date and time and related information to the user.

[1467] The "means for proactively transmitting medical examination details to a healthcare provider" refers to the technology and process for proactively transmitting the user's symptom information and initial diagnosis results to a healthcare provider.

[1468] "Means for analyzing user input data using emotion analysis means and determining the user's emotional state" refers to emotion analysis technology and processes for evaluating the user's emotional state based on the user's input information.

[1469] The "means for adjusting appointment priorities and determining optimal consultation dates and times, taking into account the user's emotional state" is a system for adjusting the priority of appointment dates and times, taking into account the user's emotional state, based on the results of emotion analysis, and making optimal appointments.

[1470] The "means for accepting symptom images" is an interface for receiving image data relating to symptoms provided by the user.

[1471] "Means for improving the accuracy of initial diagnosis results by analyzing using an image analysis AI model" refers to the technology and process for improving the accuracy of initial diagnosis by using AI technology to analyze image data.

[1472] The "means for determining whether an online consultation is applicable" refers to the algorithms and processes for determining whether an online consultation is applicable based on the provided symptom information and diagnosis results.

[1473] The "means for determining and notifying the date and time of an appointment when an online consultation is selected" is a system for determining an appropriate date and time for the appointment and notifying the user and healthcare provider when an online consultation is selected.

[1474] The present invention is a system that consistently supports users from inputting their symptoms to making appointments and online consultations, and specific embodiments required to implement the present invention will be described below.

[1475] Hardware and Software Configuration

[1476] The system includes the following hardware and software:

[1477] Hardware: smartphones, robots, servers

[1478] Software: Python, generative AI model, sentiment analysis engine, reservation management system

[1479] Processing flow

[1480] Symptom input and initial diagnosis

[1481] Users input their symptoms via smartphone or robot. Once the symptoms are entered, the device sends this information to a server. The server then inputs the symptom information into a generative AI model, analyzes it, and generates an initial diagnosis. This diagnosis includes the diagnosed disease name and recommended medical department.

[1482] As a specific example, if a user inputs "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[1483] Sentiment analysis and prioritization

[1484] The server then uses a sentiment analysis engine to analyze the user's emotional state based on the user's input data. The analysis results, along with the diagnosis, are used to adjust the priority of appointments. For example, if a user inputs "I have a sore throat and can't sleep at night," the sentiment analysis engine will determine that the user's anxiety is increasing and raise the priority of the appointment.

[1485] Reservation optimization and notifications

[1486] Based on the initial diagnosis and emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user, and calculates the optimal consultation date and time. The determined consultation date and time is notified to the user.

[1487] For example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and emotion analysis indicates high anxiety, the server will prioritize reserving the earliest possible date and time, such as 10:00 a.m. the following day.

[1488] Consultation scheduling and implementation

[1489] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model, along with the rationale behind the diagnosis, as well as the emotional analysis results, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[1490] ●Example of prompt sentence:

[1491] Symptoms: Sore throat, sleepless nights

[1492] Desired appointment date and time: 2023-10-15 10:00:00, 2023-10-16 11:00:00

[1493] Initial diagnosis result: Common cold (cold)

[1494] Sentiment analysis results: High anxiety

[1495] Best time to see a doctor: 2023-10-15 14:00:00

[1496] Proposing and implementing online consultations

[1497] The server determines whether an online consultation is appropriate based on the initial diagnosis and sentiment analysis. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. The user can then consult with a healthcare provider via the Internet at the specified time.

[1498] As described above, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[1499] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1500] Step 1:

[1501] The user inputs symptoms into the terminal. The terminal receives the symptom data (in text format) entered by the user and sends the data to the server. At this point, the input is the user's symptom information, and the output is the symptom data sent to the server.

[1502] Step 2:

[1503] The server inputs the received symptom data into a generative AI model. The generative AI model analyzes the symptom data based on past case data and medical knowledge, and generates an initial diagnosis. The input at this point is the symptom data sent to the server, and the output is the initial diagnosis (diagnosed disease name and recommended medical department).

[1504] Step 3:

[1505] The server uses a sentiment analysis engine to analyze the user's emotional state from the symptom data. The sentiment analysis engine performs text analysis to determine the user's anxiety and stress levels. At this point, the input is the symptom data, and the output is the user's emotional state (e.g., high anxiety, normal, relaxed).

[1506] Step 4:

[1507] Based on the initial diagnosis and emotion analysis results, the server uses the appointment management system to determine the appropriate department and optimal consultation date and time. During this process, the desired consultation date and time entered by the user is also taken into consideration. The input at this point is the initial diagnosis result, emotion analysis result, and the user's desired consultation date and time, and the output is the determined optimal consultation date and time.

[1508] Step 5:

[1509] The server notifies the user of the determined appointment date and time. Notification can be done via smartphone, email, etc. The input at this point is the determined appointment date and time, and the output is a notification message sent to the user.

[1510] Step 6:

[1511] The server sends the initial diagnosis results and their rationale, as well as the emotion analysis results, generated by the generative AI model, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins. The input at this point is the initial diagnosis results, rationale, and emotion analysis results, and the output is this data sent to the healthcare provider.

[1512] Step 7:

[1513] The server determines whether an online consultation is applicable based on the initial diagnosis result and emotion analysis. If it is determined that an online consultation is applicable, it proposes an online consultation to the user. At this point, the input is the initial diagnosis result and emotion analysis result, and the output is a message proposing an online consultation.

[1514] Step 8:

[1515] If the user selects an online consultation, the server determines the optimal time and date for the online consultation and notifies the user and the healthcare provider. At this point, the input is the user's preference for an online consultation, and the output is a notification of the optimal time and date for the online consultation.

[1516] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1517] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1518] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1519] [Fourth embodiment]

[1520] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1521] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1522] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1523] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1524] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1525] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1526] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1527] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1528] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1529] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1530] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1531] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1532] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1533] The present invention relates to a medical support assistant system for shortening waiting times at hospitals, and is realized in the specific embodiments described below.

[1534] Symptom input and initial diagnosis

[1535] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the diagnosed disease name and recommended medical department. If necessary, the user can take an image related to the symptoms (for example, a photo of an abnormal area on the skin) and send this to the server via the device. The server then inputs this image data into an image analysis AI model, and the analysis results are reflected in the generative AI model's diagnosis.

[1536] As a specific example, if a user inputs the symptom "sore throat" and uploads an image, the server will use a generative AI model to make an initial diagnosis of "cold" and then use an image analysis AI model to confirm specific symptoms (e.g., redness or swelling).

[1537] Reservation optimization and notifications

[1538] Based on the initial diagnosis, the server determines the appropriate department. The user also inputs the desired consultation date and time, which is then sent to the server. The server then determines the optimal consultation date and time based on the desired date and time and existing appointments retrieved from the hospital's reservation system. The server's optimization algorithm efficiently performs this process and notifies the user of the optimal available consultation date and time.

[1539] For example, if a user enters "Tuesday or Wednesday morning next week would be convenient," the server will check the reservation system, find that there is availability at 11:00 a.m. on Tuesday, and notify the user.

[1540] Consultation scheduling and implementation

[1541] Once the reservation is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results obtained by the generative AI model and the basis for the diagnosis to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge about the user's symptoms before the consultation begins, improving the efficiency of the consultation.

[1542] As a concrete example, a user visits the hospital at 11:00 AM on a Tuesday, and the healthcare provider begins the consultation by confirming the initial diagnosis and imaging results for a "sore throat."

[1543] Switching to Online Diagnostics

[1544] The server determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the best time and date for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[1545] For example, if a user inputs "I have a persistent mild cough" and the server diagnoses it as a "mild cold" using a generative AI model, an online consultation will be suggested. If the user selects this option, a date and time for the online consultation will be scheduled and notified to the user and their healthcare provider.

[1546] In this way, the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[1547] The processing flow will be explained below.

[1548] Step 1:

[1549] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[1550] Step 2:

[1551] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[1552] Step 3:

[1553] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[1554] Step 4:

[1555] The server determines the appropriate medical department based on the symptom data and the diagnostic results of the generative AI model.

[1556] Step 5:

[1557] The server connects to the hospital's reservation system and obtains the current reservation status.

[1558] Step 6:

[1559] The server's optimization algorithm determines the optimal appointment date and time based on existing appointments and the user's desired date and time.

[1560] Step 7:

[1561] The server registers the determined consultation date and time in the appointment system as confirmed.

[1562] Step 8:

[1563] The server notifies the user's terminal of the confirmed reservation date and time.

[1564] Step 9:

[1565] The user visits the hospital at the scheduled time.

[1566] Step 10:

[1567] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device in advance.

[1568] Step 11:

[1569] The healthcare provider begins the consultation with prior knowledge of the user's symptoms before the consultation begins.

[1570] Step 12:

[1571] When a user uploads an image (eg, a photo of a symptom) to the terminal, the terminal transmits the image data to the server.

[1572] Step 13:

[1573] The server runs an image analysis AI model to improve the accuracy of initial diagnosis results based on information obtained from the images.

[1574] Step 14:

[1575] Based on the initial diagnosis, the server determines whether online consultation is possible.

[1576] Step 15:

[1577] If online consultation is available, the server notifies the user of the online consultation.

[1578] Step 16:

[1579] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[1580] Step 17:

[1581] An optimization algorithm on the server determines the best time and date for the online consultation.

[1582] Step 18:

[1583] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[1584] Step 19:

[1585] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and evidence, and issue any necessary instructions or prescriptions.

[1586] This detailed flow not only allows users to receive efficient medical care while minimizing waiting times, but also allows medical providers to conduct consultations smoothly.

[1587] Example 1

[1588] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1589] In modern hospitals, long waiting times for consultations are a burden for patients. It is also difficult to efficiently guide patients to the appropriate department and arrange consultation dates and times. Furthermore, technology that improves patient convenience is needed to improve the accuracy of initial diagnoses and implement online consultations.

[1590] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1591] In this invention, the server

[1592] a means for accepting symptom input;

[1593] means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis;

[1594] A means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result;

[1595] means for notifying the user of the determined consultation date and time;

[1596] means for proactively transmitting the consultation to a healthcare provider;

[1597] a means for receiving images relating to the symptom;

[1598] The system also includes a means for analyzing the images using an image analysis AI model to improve the accuracy of initial diagnosis results, which will shorten waiting times at hospitals, guide patients to the appropriate department, optimize appointments, improve the accuracy of initial diagnosis, and enable smooth online consultations.

[1599] A "user" is an individual who uses the system to input their symptoms and desired consultation date and time.

[1600] "Symptom input" refers to the act of a user inputting their own health condition and symptoms they are experiencing into a terminal.

[1601] A "generative AI model" is an artificial intelligence model that analyzes symptoms based on past data and medical knowledge and generates initial diagnosis results.

[1602] The "initial diagnosis result" is the disease name and recommended medical department information obtained as a result of analysis by the generative AI model.

[1603] The "appropriate department" is the medical specialty for which the user should be examined based on the initial diagnosis.

[1604] The "examination date and time" is the date and time designated for the user to receive an examination.

[1605] "Notification" refers to the act of informing the user of the consultation date and time and the results of the initial diagnosis.

[1606] The "image analysis AI model" is an artificial intelligence model that analyzes image data related to symptoms and improves the accuracy of initial diagnosis results.

[1607] An "online consultation" is a consultation conducted between a healthcare provider and a user over the Internet.

[1608] "Healthcare providers" are professionals such as doctors and nurses who provide medical examinations and treatment.

[1609] "Consultation details" refers to the user's symptoms, their analysis results, and detailed information about the consultation.

[1610] The "server" is the central computer in the system that receives input from the user, generates diagnostic results using generative AI models and image analysis AI models, and determines and notifies the patient of the appropriate medical department and consultation date and time.

[1611] A "terminal" is a device through which a user inputs symptoms and desired date and time and communicates with a server.

[1612] The present invention provides a medical support assistant system that shortens waiting times at hospitals and provides efficient medical services. The system accepts symptom input from users, analyzes the input using a generative AI model and an image analysis AI model, and generates an initial diagnosis. It then determines the appropriate department and optimal consultation date and time and notifies the user and healthcare provider.

[1613] First, the user inputs their symptoms using their own device (smartphone, PC, etc.). The device then sends this information to a server. The server then inputs the received symptom information into a generative AI model (such as TensorFlow or PyTorch) and generates an initial diagnosis based on past data and medical knowledge. Specifically, if the symptom input is "sore throat," the server will use the generative AI model to make an initial diagnosis of "cold."

[1614] Additionally, users can take images of their symptoms (e.g., a photo of their throat) and send them to a server via their device. The server inputs this image data into an image analysis AI model (e.g., OpenCV or Keras), and the analysis results are reflected in the generative AI model's diagnostic results. This improves the accuracy of the diagnosis. For example, by uploading a photo of the throat, the image analysis AI model can detect redness and swelling, and these results are added to the diagnostic results.

[1615] Once the diagnosis is complete, the server determines the appropriate medical department (e.g., "Internal Medicine"). Next, the user inputs the desired consultation date and time (e.g., "Tuesday or Wednesday morning next week") and sends it to the server. The server retrieves existing reservations from the hospital's reservation system and determines the optimal consultation date and time by comparing it with the desired date and time. The server notifies the user of the determined date and time (e.g., "Appointment for 11:00 AM on Tuesday").

[1616] Once the appointment is confirmed, the user visits the hospital at the specified date and time for a consultation. The server sends the initial diagnosis and its basis to the medical provider's terminal in advance, allowing the medical provider to obtain prior knowledge of the user's symptoms before the consultation, thereby improving the efficiency of the consultation.

[1617] The server also determines whether an online consultation is appropriate based on the initial diagnosis. For example, if the symptoms are mild, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the most appropriate time and date for the online consultation, which will also be notified to the user and the healthcare provider.

[1618] As a concrete example, the following prompt sentence could be input into a generative AI model:

[1619] Prompt: Implement a flow for initial diagnosis and appointment optimization for patients with the symptom "sore throat."

[1620] Prompt: Create a code that optimizes appointments based on the patient's preferred time and the clinic's available time for appointments next week and notifies them.

[1621] Prompt: Develop a system to suggest an online consultation for a patient with mild cold symptoms, determine the best time to schedule the appointment, and notify the user and their healthcare provider.

[1622] In this way, the system of the present invention makes it possible to significantly reduce waiting times at hospitals and provide efficient and flexible medical services.

[1623] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1624] Step 1:

[1625] The user enters the symptoms.

[1626] Specific actions: The user opens the system's input screen on their smartphone or computer and enters "I have a sore throat."

[1627] Input: Symptoms entered by the user (e.g., "I have a sore throat")

[1628] Output: Data that the device uses to send user symptom input to the server

[1629] Step 2:

[1630] The device sends the symptom information to the server.

[1631] Specific operation: The device sends the entered symptom data to the server via an HTTP request.

[1632] Input: User-entered symptom data

[1633] Output: Symptom data received by the server

[1634] Step 3:

[1635] The symptom information received by the server is input into a generative AI model to generate an initial diagnosis result.

[1636] Specific operation: The server passes the received symptom data to the generative AI model, which then initiates the diagnostic process. The generative AI model performs an initial diagnosis based on past data and medical knowledge, and diagnoses the illness as a "cold."

[1637] Input: Received symptom data

[1638] Output: Initial diagnosis result from the generative AI model (e.g., "cold").

[1639] Step 4:

[1640] The user takes an image of the symptoms and sends it to the server via the terminal.

[1641] Specific operation: The user takes a photo of their throat with their smartphone and clicks the system's upload button to send the image to the server.

[1642] Input: User-taken symptom image

[1643] Output: Image data received by the server

[1644] Step 5:

[1645] The server inputs the image data into an image analysis AI model and reflects the analysis results in the initial diagnosis.

[1646] How it works: The server passes the image data to the image analysis AI model, which then performs image analysis. The image analysis AI model detects redness and swelling and adds the results to the generative AI model's diagnosis.

[1647] Input: Received image data

[1648] Output: Final diagnosis result reflecting the image analysis results

[1649] Step 6:

[1650] The server determines the appropriate medical department based on the initial diagnosis results.

[1651] Specific operation: The server analyzes the initial diagnosis results and determines "internal medicine" as the recommended medical specialty.

[1652] Input: Initial diagnosis result

[1653] Output: The appropriate medical specialty (e.g., "Internal Medicine")

[1654] Step 7:

[1655] The user inputs the desired consultation date and time into the terminal and transmits it to the server.

[1656] Specific operation: The user enters "Tuesday or Wednesday morning next week" as the desired date and time into the system and submits it.

[1657] Input: User's desired appointment date and time

[1658] Output: Desired appointment date and time data received by the server

[1659] Step 8:

[1660] The server compares the desired date and time with the existing reservation status obtained from the hospital's reservation system and determines the optimal date and time for the consultation.

[1661] Specific behavior: The server uses the hospital's reservation system API to check the current availability and finds that 11:00 AM on Tuesday is available.

[1662] Input: User's desired consultation date and time data, and reservation status data from the reservation system

[1663] Output: Best appointment time (e.g. "Tuesday at 11 AM")

[1664] Step 9:

[1665] The server notifies the user of the best time and date for an appointment.

[1666] Specific operation: The server sends a reservation confirmation notification to the user's device, displaying "Reservation confirmed for 11:00 AM on Tuesday."

[1667] Input: Best appointment time

[1668] Output: Confirmation of reservation sent to user

[1669] Step 10:

[1670] The user visits the hospital at the designated date and time and receives a medical examination.

[1671] What happens: A user arrives at the hospital at 11:00 AM on a Tuesday and confirms their appointment with the receptionist.

[1672] Input: Reservation date and time

[1673] Output: Start of hospital consultation

[1674] Step 11:

[1675] The server sends the generative AI model's initial diagnosis results and their rationale to the healthcare provider's device.

[1676] Specific operation: The server sends a report containing the initial diagnosis and image analysis results to the healthcare provider's device.

[1677] Input: Initial diagnosis results, image analysis results

[1678] Output: Sending diagnostic data to healthcare provider

[1679] Step 12:

[1680] Healthcare providers review the submitted data and conduct consultations efficiently.

[1681] Specific operation: The medical provider checks the initial diagnosis results and image analysis results on the device before the consultation and begins the consultation.

[1682] Input: Diagnostic data sent from the server

[1683] Output: Efficient consultation

[1684] Step 13:

[1685] The server determines whether online consultation is applicable based on the initial diagnosis results.

[1686] Specific operation: The server analyzes the diagnosis results of the generative AI model, determines that the patient has a "mild cold," and concludes that an online consultation is possible.

[1687] Input: Initial diagnosis result

[1688] Output: Proposal for online consultation

[1689] Step 14:

[1690] The server sends the online consultation offer to the user.

[1691] Specific operation: The server sends a notification to the user's device asking, "Would you like to have an online consultation?"

[1692] Input: Online consultation suggestion

[1693] Output: Proposal notification to user

[1694] Step 15:

[1695] The user selects an online consultation.

[1696] Specific operation: The user clicks the "Request online consultation" button on the device.

[1697] Input: Select Online Consultation

[1698] Output: Update the server's online appointment schedule flag

[1699] Step 16:

[1700] The server determines the best time and date for the online consultation and notifies the user and the healthcare provider.

[1701] Specific operation: The server checks the reservation system to determine the available date and time for online consultation, and notifies the user and healthcare provider devices of the determined date and time.

[1702] Input: Online consultation selection and appointment status data from the booking system

[1703] Output: Deciding and notifying online consultation date and time

[1704] By going through the above steps, efficient and flexible medical services can be provided.

[1705] (Application example 1)

[1706] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1707] The food delivery industry lacks the means to recommend appropriate menu items that respond to individual customer preferences and circumstances. Furthermore, the system for determining and notifying optimal delivery times is not well developed, which can lead to lower customer satisfaction. Furthermore, the inability to smoothly handle questions or requests about dishes limits the customer experience.

[1708] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1709] In this invention, the server includes a means for receiving information about the user's preferences and situation and presenting recommended menus based on past data and health information, a means for determining and notifying the user of an optimal delivery time based on the user's desired delivery time, and a means for the user to ask questions or make requests about dishes online, thereby enabling food delivery services that meet the individual needs of the user.

[1710] A "user" is an individual who utilizes the system to input information and receive services.

[1711] A "generative AI model" is an artificial intelligence model that analyzes information based on past data and knowledge and generates appropriate results.

[1712] "Symptom input" refers to the act of a user inputting information about their own symptoms or condition into the system.

[1713] The "initial diagnosis result" is information such as the disease name and recommended medical department that is presented as a result of analysis by the generative AI model.

[1714] A "medical department" is a specialized department at a medical institution that provides diagnosis and treatment for specific types of illnesses or symptoms.

[1715] The "examination date and time" is the specific date and time when the user is scheduled to receive an examination.

[1716] "Notification" refers to the act of the system informing the user or information provider of determined information.

[1717] "Healthcare providers" are professionals such as doctors and nurses who provide health care services in hospitals and clinics.

[1718] "Preferences" refer to the types of food or cuisine that a user prefers.

[1719] "Past data" refers to user input information and behavioral history that the system has collected in the past.

[1720] "Health information" is information relating to the user's health condition and medical history.

[1721] A "recommended menu" is a list of dishes suggested by a generative AI model based on the user's preferences and health status.

[1722] "Desired delivery time" refers to the specific time at which a user would like to receive food delivery.

[1723] "Delivery time optimization" is the process of calculating the most appropriate delivery time based on the user's preferences and the restaurant's situation.

[1724] "Online consultation" is a system that allows users to communicate in real time with restaurant chefs or staff via the Internet.

[1725] Overall system configuration

[1726] This invention provides a system that provides customized support to both end users and restaurants in the food delivery industry. The system uses devices such as smartphones and tablets and operates in conjunction with a server. The server uses a generative AI model to analyze user input data and provide optimal menu recommendations and delivery times.

[1727] Hardware and software used

[1728] Hardware: Smartphones, servers

[1729] Software: Flask (Python web framework), TensorFlow (deep learning model), database (e.g., MySQL)

[1730] Specific operation flow of the system

[1731] 1. Enter symptoms and generate a recommendation menu

[1732] Users enter their preferences, allergy information, and current mood through a smartphone app. This information is sent from the device to a server. The server uses a generative AI model to analyze this information and provide the user with the optimal menu recommendations. This menu is generated based on past order data and the user's health information.

[1733] For example, if a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[1734] Example prompt sentence:

[1735] User Information:

[1736] Favourites: Chicken

[1737] Allergies: None

[1738] Mood: Tired

[1739] 2. Reservation optimization and notifications

[1740] After selecting from the recommended menu, the user inputs the desired delivery time. The server determines the optimal delivery time based on the restaurant's congestion status and the delivery staff's schedule, and notifies the user.

[1741] As a specific example, if the user requests "tomorrow at 2:00 p.m.", the server checks the reservation system, calculates the optimal delivery time, and notifies the user.

[1742] 3. Online consultation mode

[1743] If a user has any questions or requests regarding food, they can consult with restaurant staff online through a smartphone app. The server receives these requests and forwards them to the restaurant's chefs in real time.

[1744] Example prompt sentence:

[1745] User Request:

[1746] Dish name:Grilled chicken

[1747] Q: Can I make it less spicy?

[1748] Operational Scenario

[1749] The system begins when users use a smartphone app to enter their information. The information is sent to a server and analyzed by a generative AI model. An optimal menu recommendation is generated and presented to the user. The optimal delivery time is then determined and notified based on the user's desired delivery time. In addition, users can ask questions or make requests about dishes online.

[1750] In this way, the present invention significantly improves the efficiency and customer satisfaction of food delivery, and the customized service allows food delivery to be tailored to the individual needs of users.

[1751] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1752] Step 1:

[1753] The user uses their smartphone to input their preferences, allergy information, current mood, etc. into the app. This inputs the user's individual information into the device, and the input data is sent to the server in JSON format.

[1754] input:

[1755] {

[1756] "preferences": "chicken",

[1757] "allergies": "none",

[1758] "mood": "tired"

[1759] }

[1760] output:

[1761] Send JSON data from the terminal to the server.

[1762] Step 2:

[1763] The server parses the received JSON data and passes the input data to the generative AI model, which then generates a recommended menu based on past order data and health information. The generated recommended menu is returned in JSON format and saved on the server.

[1764] input:

[1765] User data in JSON format

[1766] output:

[1767] JSON data of the recommended menu

[1768] Specific behavior:

[1769] Data is input into a generative AI model to generate recommended menus.

[1770] Step 3:

[1771] The server generates a recommended menu, which is sent to the smartphone app and displayed to the user. The user then decides what to order and enters the desired delivery time. The entered delivery time is then sent back to the server.

[1772] input:

[1773] JSON data of the recommended menu

[1774] output:

[1775] Displaying a deserialized recommendation menu

[1776] Specific behavior:

[1777] Receive recommended menus from the server and display them to the user in the app.

[1778] Step 4:

[1779] The server calculates the optimal delivery time based on the received delivery time, the restaurant's congestion status, and the delivery person's schedule information. As a result, the optimal delivery time is obtained and notified to the user.

[1780] input:

[1781] User's desired delivery time, restaurant congestion information, delivery staff schedule data

[1782] output:

[1783] Notification of optimal delivery time

[1784] Specific behavior:

[1785] The server retrieves the necessary data from the reservation system and performs calculations using an optimization algorithm.

[1786] Step 5:

[1787] If a user has a question or request about a dish, they can enter it through the online consultation mode on their smartphone app, which then sends the request to the restaurant's chef via the server.

[1788] input:

[1789] Text data of cooking-related questions and requests

[1790] output:

[1791] Sending the request

[1792] Specific behavior:

[1793] The server receives the user's request and forwards it to the restaurant in real time.

[1794] Specific examples

[1795] Example 1:

[1796] If a user inputs that they are "tired" and prefers "chicken dishes," the server will recommend "chicken breast salad" or "grilled chicken" as "high-protein, low-fat dishes that are good for recovering from fatigue."

[1797] Example prompt sentence:

[1798] User Information:

[1799] Favourites: Chicken

[1800] Allergies: None

[1801] Mood: Tired

[1802] Example 2:

[1803] If the user enters "tomorrow 2:00 PM" as the "desired delivery time," the server will check the reservation system, calculate the optimal delivery time, and notify the user.

[1804] Example prompt sentence:

[1805] Desired delivery time: tomorrow at 2pm

[1806] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1807] The present invention relates to a medical support assistant system that shortens waiting times at hospitals and takes into account the emotions of users, and includes the following specific embodiments.

[1808] Symptom input and initial diagnosis

[1809] First, the user enters their symptoms into the device. The device then sends this symptom information to the server. The server then inputs the received symptom information into a generative AI model for analysis. The generative AI model generates an initial diagnosis based on multiple historical data and medical knowledge. This diagnosis includes the name of the diagnosed disease and the recommended medical department.

[1810] As a specific example, if a user inputs the symptom "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[1811] Utilizing the Emotion Engine

[1812] The server then analyzes the user's emotions using an emotion engine based on the user's input data. The emotion engine determines anxiety, stress, and urgency from the user's text and reflects this in the initial diagnosis results.

[1813] For example, if a user inputs "I have a sore throat and can't sleep at night," the emotion engine will analyze that the user's anxiety is increasing and increase the priority of the consultation.

[1814] Reservation optimization and notifications

[1815] Based on the initial diagnosis and the user's emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user. The server determines the optimal consultation date and time based on the existing reservation status obtained from the hospital's reservation system. The determined consultation date and time is notified to the user.

[1816] As a specific example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and the emotion engine's analysis determines that the user is highly anxious, the server will prioritize reserving the earliest possible date and time (for example, 10:00 a.m. the following day).

[1817] Consultation scheduling and implementation

[1818] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model and their rationale, as well as the analysis results from the emotion engine, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[1819] As a specific example, a user visits a hospital at a specified date and time, and the medical provider confirms in advance the information that the user has a "sore throat" and that the user is "highly anxious," before beginning the examination.

[1820] Switching to Online Diagnostics

[1821] Based on the initial diagnosis and the emotion engine's analysis, the server determines whether an online consultation is appropriate. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. Once the online consultation is scheduled, the user can meet with the healthcare provider via the Internet at the specified time.

[1822] For example, if a user inputs "I have a mild persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[1823] In this way, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[1824] The processing flow will be explained below.

[1825] Step 1:

[1826] The user inputs their symptoms into the terminal, which then transmits the input symptom data to the server.

[1827] Step 2:

[1828] The server inputs the received symptom data into a generative AI model, which analyzes the data and generates an initial diagnosis, including the diagnosed disease and recommended medical specialty.

[1829] Step 3:

[1830] The server uses an emotion engine to analyze emotions from the user's input data, which then performs text analysis to determine the user's anxiety and stress levels.

[1831] Step 4:

[1832] The server integrates the initial diagnosis results with the emotional state determined by the emotion engine to determine the priority of medical examinations and necessary measures. For example, if the user's anxiety is increasing, it will recommend an immediate medical examination.

[1833] Step 5:

[1834] The user inputs the desired consultation date and time into the terminal, which then transmits the desired date and time data to the server.

[1835] Step 6:

[1836] The server connects to the hospital's reservation system to obtain the current reservation status. It then analyzes the user's desired date and time and the existing reservation status using an optimization algorithm.

[1837] Step 7:

[1838] The server's optimization algorithm determines the best appointment time based on existing appointments, the user's emotional state, and their preferred date and time. For example, if the emotion engine detects high anxiety, an earlier date and time will be prioritized.

[1839] Step 8:

[1840] The server registers the determined consultation date and time in the appointment system as confirmed.

[1841] Step 9:

[1842] The server notifies the user's terminal of the confirmed consultation date and time.

[1843] Step 10:

[1844] The user visits the hospital at the scheduled time.

[1845] Step 11:

[1846] The server sends the initial diagnosis results of the generative AI model and their rationale, as well as the emotion analysis results of the emotion engine, to the healthcare provider's device in advance.

[1847] Step 12:

[1848] Before the consultation begins, the healthcare provider reviews information about the user's symptoms and emotional state and prepares for the consultation.

[1849] Step 13:

[1850] The healthcare provider initiates the consultation and uses the information provided in advance to provide efficient and appropriate care.

[1851] Step 14:

[1852] When a user uploads an image of a symptom (eg, an abnormal area of ​​skin) to the terminal, the terminal transmits the image data to the server.

[1853] Step 15:

[1854] The server runs an image analysis AI model and uses the information obtained from the images to improve the accuracy of initial diagnosis results.

[1855] Step 16:

[1856] The server determines whether online consultation is applicable based on the initial diagnosis results and the analysis results of the emotion engine.

[1857] Step 17:

[1858] If online consultation is available, the server notifies the user of the online consultation.

[1859] Step 18:

[1860] If the user selects online consultation, they input their desired date and time into the terminal, which then sends this information to the server.

[1861] Step 19:

[1862] An optimization algorithm on the server determines the best time and date for the online consultation.

[1863] Step 20:

[1864] The server notifies the user and the healthcare provider of the date and time of the online consultation.

[1865] Step 21:

[1866] The user and healthcare provider will conduct an online consultation at the specified date and time. The healthcare provider will conduct a detailed examination based on the generative AI's diagnosis and rationale, as well as the analysis results of the emotion engine, and issue any necessary instructions or prescriptions.

[1867] This detailed process flow allows users to receive efficient, flexible medical care that takes into consideration their emotions while minimizing waiting times, and also allows medical providers to receive information in advance, allowing for a smoother consultation.

[1868] Example 2

[1869] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1870] In conventional medical treatment systems, it often takes time for the system to determine the appropriate medical department and consultation date and time after the user inputs their symptoms, and the user's emotional state is rarely taken into consideration. As a result, users end up feeling anxious while waiting for their appointment, which reduces the efficiency of medical treatment. In addition, determining the appropriate consultation date and time and selecting online consultations are often done manually, which can disrupt the smooth flow of medical treatment.

[1871] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1872] In this invention, the server includes means for accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis, means for notifying the user of the determined consultation date and time, means for analyzing the emotional state using an emotion engine based on the user's symptom input, means for reflecting the analyzed emotional state in the initial diagnosis and setting the priority of the consultation, and means for transmitting the details of the consultation and the emotional state to a healthcare provider in advance. This makes it possible to efficiently perform the process from the user's symptom input to determining the consultation date and time, and improve the quality and efficiency of medical care by taking the user's emotional state into consideration.

[1873] "User" refers to an individual who uses the system to input their symptoms and receive medical treatment.

[1874] "Symptom input" refers to the act of a user inputting their own physical condition or state into a terminal.

[1875] "Terminal" refers to a computing device used by a user, such as a computer, smartphone, or tablet.

[1876] The term "server" refers to a computer system that receives information from users and uses generative AI models and emotion engines to analyze the data and determine appointment dates and times.

[1877] A "generative AI model" refers to an artificial intelligence system that generates initial diagnostic results from symptom information based on past data and medical knowledge.

[1878] "Initial diagnosis result" refers to the diagnosis obtained as a result of the generative AI model analyzing symptom information.

[1879] An "emotion engine" refers to a system that analyzes the user's emotional state from the text they input and determines their level of anxiety or stress.

[1880] "Appointment Date and Time" refers to the date and time designated for a user to meet with a healthcare provider.

[1881] A "department" refers to a hospital division that specializes in a particular area of ​​medicine.

[1882] "Notification" refers to the act of informing the user of the determined consultation date and time and details of the consultation.

[1883] "Examination details" refers to the specific details of medical treatment and examinations based on the user's symptoms.

[1884] "Healthcare provider" refers to a medical professional such as a doctor or nurse who provides medical services to a user.

[1885] "Online medical consultation" refers to a system in which a medical provider examines or consults with a user via the Internet.

[1886] "Emotional state" refers to psychological states such as anxiety, stress, and urgency that are determined from the text entered by the user.

[1887] "Consultation priority" refers to the criteria for determining the degree of priority for a user's consultation based on the analysis results of the emotion engine.

[1888] This invention relates to a medical support assistant system that shortens waiting times in hospitals and takes into account the user's emotions. The main components are a user terminal, a server, a generative AI model, and an emotion engine.

[1889] User terminal

[1890] Users input their symptoms using devices such as PCs, smartphones, and tablets. This symptom information is then sent from the device to a server. The device then sends the data to the server via the Internet using a secure communication protocol (e.g., HTTPS).

[1891] Specific examples

[1892] The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom entry field.

[1893] server

[1894] The server receives symptom information sent by the user and inputs it into the generative AI model. The generative AI model analyzes the symptom information based on past data and medical knowledge and generates an initial diagnosis. The server also analyzes the user's emotional state using an emotion engine. The analysis results are reflected in the initial diagnosis and are used to set examination priorities.

[1895] Software used

[1896] Generative AI model: A model that generates initial diagnosis results based on past data and medical knowledge

[1897] Emotion Engine: An engine that analyzes the emotional state of a user from their input text.

[1898] Specific examples

[1899] The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends a doctor visit. It also uses an emotion engine to analyze the user's anxieties and prioritizes the consultation.

[1900] Deciding and notifying the appointment date and time

[1901] The server determines the date and time of the consultation based on the initial diagnosis and emotion analysis results. It also works with the hospital's reservation system to determine the optimal consultation date and time, taking into account the user's preferred date and time. The server then notifies the user of the determined consultation date and time.

[1902] Specific examples

[1903] The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[1904] Providing information to healthcare providers

[1905] The server sends the initial diagnosis results from the generative AI model and the analysis results from the emotion engine to the healthcare provider's device in advance, allowing the healthcare provider to have prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[1906] Specific examples

[1907] The user visits the hospital at the specified date and time, and the medical provider confirms the information that the user has a sore throat and that the user is highly anxious beforehand and begins the examination.

[1908] Choosing an online consultation

[1909] The server determines whether an online consultation is appropriate based on the initial diagnosis and the analysis results of the emotion engine. If the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user.

[1910] Specific examples

[1911] If a user inputs "I have a mild, persistent cough" and the emotion engine determines that this is particularly worrying, the server will suggest an immediate online consultation. If the user selects this option, the server will determine the best time and date for the consultation (e.g., 3:00 p.m. that day) and notify the user and their healthcare provider.

[1912] Prompt Sentence Examples

[1913] "Perform an initial diagnosis based on the symptoms entered by the user and recommend possible illnesses and medical specialties. Example: sore throat."

[1914] "Analyze user input text to determine anxiety or stress levels. Example: My throat hurts and I can't sleep at night."

[1915] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1916] Step 1:

[1917] The user enters the symptom information.

[1918] Input: The user inputs the symptoms on the device they use (PC, smartphone, tablet).

[1919] Data processing: Collect user input data in text format.

[1920] Output: Symptom information sent from the device to the server.

[1921] Specific operation: The user launches the smartphone application and enters "I've had a sore throat since last night and I also have a slight fever" in the symptom input field.

[1922] Step 2:

[1923] The device sends the symptom information to the server.

[1924] Input: Symptom information entered by the user into the device.

[1925] Data Processing: Symptom information is encrypted using a secure communication protocol (e.g., HTTPS).

[1926] Output: Encrypted symptom information sent to the server.

[1927] Specific operation: The device sends input data such as "I've had a sore throat since last night and I also have a slight fever" to the server via HTTPS.

[1928] Step 3:

[1929] The server performs an initial diagnosis using the generated AI model.

[1930] Input: The symptom information sent to the server.

[1931] Data calculation: Symptom information is input into the generative AI model and analyzed based on past data and medical knowledge.

[1932] Output: Initial diagnosis (diagnosed disease name and recommended medical department).

[1933] Specific operation: The server inputs data such as "I've had a sore throat since last night and I also have a slight fever" into the generated AI model, which makes an initial diagnosis of "cold" and recommends seeing an internal medicine doctor.

[1934] Step 4:

[1935] The server performs emotion analysis using an emotion engine.

[1936] Input: User symptom information and initial diagnosis results.

[1937] Data calculation: Symptom information is input into the emotion engine and the emotional state (anxiety, stress, urgency) is analyzed.

[1938] Output: Sentiment analysis results (user's emotional state).

[1939] Specific operation: The server uses an emotion engine to analyze the user's anxiety from symptom text such as "I've had a sore throat since last night and I also have a slight fever," and sets a high priority for medical treatment.

[1940] Step 5:

[1941] The server determines the appropriate appointment date and time and notifies the patient.

[1942] Input: Initial diagnosis results and sentiment analysis results, existing hospital reservations, and the user's desired date and time.

[1943] Data processing: In cooperation with the reservation system, the optimal appointment date and time is determined taking into account the user's wishes and emotional state.

[1944] Output: The determined appointment date and time, and notification of the same.

[1945] Specific operation: The server checks the reservation system, confirms that "10:00 AM the next day" is available, and sends a notification to the user's smartphone saying, "Your appointment with an internal medicine doctor has been confirmed for 10:00 AM the next day."

[1946] Step 6:

[1947] The server transmits the consultation details and emotional state to the healthcare provider.

[1948] Input: Initial diagnostic results of the generative AI model and analysis results of the emotion engine.

[1949] Data processing: Organize the medical examination details and emotional state and send them to the medical provider's terminal.

[1950] Output: Consultation details and emotional state sent to the healthcare provider.

[1951] Specific operation: The server sends the information "sore throat" and "user's anxiety is high" to the healthcare provider's terminal.

[1952] Step 7:

[1953] The user chooses to visit the clinic or have an online consultation.

[1954] Input: Confirmation of appointment or suggestion of online consultation.

[1955] Data calculation: Determines the optimal diagnostic method based on the user's selection.

[1956] Output: Notification of time and date for online consultation or to arrange a face-to-face consultation with a healthcare provider.

[1957] Specific operation: The user checks the notification on their smartphone and visits the hospital at the specified date and time. Alternatively, the user selects online consultation, and the server proposes 3:00 PM on the same day as the date and time for the online consultation and sends a notification to the user's smartphone.

[1958] (Application example 2)

[1959] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1960] Long waiting times and inefficient diagnoses are major problems in modern medical settings and pharmacies. Rapid and appropriate responses are required, especially when users complain of symptoms, but traditional approaches have difficulty meeting these requirements. Furthermore, because treatment and medication recommendations are made without taking the user's emotional state into consideration, user satisfaction and trust tend to decline. Furthermore, the difficulty of scheduling appointments with the appropriate department or pharmacist reduces medical efficiency and increases the workload of healthcare providers.

[1961] The identification processing 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 accepting symptom input from a user, means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis result, means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result, means for notifying the user of the determined consultation date and time, means for transmitting the details of the consultation to a healthcare provider in advance, means for analyzing the user's input data using emotion analysis means and determining the user's emotional state, and means for adjusting appointment priorities and determining the optimal consultation date and time taking the user's emotional state into consideration. This makes it possible to shorten waiting times and realize medical support that takes the user's emotional state into consideration, thereby improving medical efficiency and user satisfaction.

[1962] The "means for accepting symptom input from the user" is an interface that allows the user to input their own symptoms into the system.

[1963] "Means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis" refers to the algorithms and processes for using AI technology to analyze the symptoms entered by the user and obtain a provisional diagnosis.

[1964] The "means for determining an appropriate medical department and consultation date and time" is a system for optimally selecting the medical department and consultation date and time that the user should visit based on the results of the initial diagnosis.

[1965] The "means for notifying the user of the determined appointment date and time" refers to a mechanical or electronic means for communicating the determined appointment date and time and related information to the user.

[1966] The "means for proactively transmitting medical examination details to a healthcare provider" refers to the technology and process for proactively transmitting the user's symptom information and initial diagnosis results to a healthcare provider.

[1967] "Means for analyzing user input data using emotion analysis means and determining the user's emotional state" refers to emotion analysis technology and processes for evaluating the user's emotional state based on the user's input information.

[1968] The "means for adjusting appointment priorities and determining optimal consultation dates and times, taking into account the user's emotional state" is a system for adjusting the priority of appointment dates and times, taking into account the user's emotional state, based on the results of emotion analysis, and making optimal appointments.

[1969] The "means for accepting symptom images" is an interface for receiving image data relating to symptoms provided by the user.

[1970] "Means for improving the accuracy of initial diagnosis results by analyzing using an image analysis AI model" refers to the technology and process for improving the accuracy of initial diagnosis by using AI technology to analyze image data.

[1971] The "means for determining whether an online consultation is applicable" refers to the algorithms and processes for determining whether an online consultation is applicable based on the provided symptom information and diagnosis results.

[1972] The "means for determining and notifying the date and time of an appointment when an online consultation is selected" is a system for determining an appropriate date and time for the appointment and notifying the user and healthcare provider when an online consultation is selected.

[1973] The present invention is a system that consistently supports users from inputting their symptoms to making appointments and online consultations, and specific embodiments required to implement the present invention will be described below.

[1974] Hardware and Software Configuration

[1975] The system includes the following hardware and software:

[1976] Hardware: smartphones, robots, servers

[1977] Software: Python, generative AI model, sentiment analysis engine, reservation management system

[1978] Processing flow

[1979] Symptom input and initial diagnosis

[1980] Users input their symptoms via smartphone or robot. Once the symptoms are entered, the device sends this information to a server. The server then inputs the symptom information into a generative AI model, analyzes it, and generates an initial diagnosis. This diagnosis includes the diagnosed disease name and recommended medical department.

[1981] As a specific example, if a user inputs "sore throat," the server will use a generative AI model to make an initial diagnosis of "cold" and recommend an appropriate medical department.

[1982] Sentiment analysis and prioritization

[1983] The server then uses a sentiment analysis engine to analyze the user's emotional state based on the user's input data. The analysis results, along with the diagnosis, are used to adjust the priority of appointments. For example, if a user inputs "I have a sore throat and can't sleep at night," the sentiment analysis engine will determine that the user's anxiety is increasing and raise the priority of the appointment.

[1984] Reservation optimization and notifications

[1985] Based on the initial diagnosis and emotional state, the server determines the appropriate department and consultation date and time. It also takes into account the desired consultation date and time entered by the user, and calculates the optimal consultation date and time. The determined consultation date and time is notified to the user.

[1986] For example, if a user inputs "Tuesday or Wednesday morning next week would be convenient," and emotion analysis indicates high anxiety, the server will prioritize reserving the earliest possible date and time, such as 10:00 a.m. the following day.

[1987] Consultation scheduling and implementation

[1988] Once the appointment is confirmed, the user visits the hospital at the specified date and time. The server sends the initial diagnosis results from the generative AI model, along with the rationale behind the diagnosis, as well as the emotional analysis results, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins, improving the efficiency of the consultation.

[1989] ●Example of prompt sentence:

[1990] Symptoms: Sore throat, sleepless nights

[1991] Desired appointment date and time: 2023-10-15 10:00:00, 2023-10-16 11:00:00

[1992] Initial diagnosis result: Common cold (cold)

[1993] Sentiment analysis results: High anxiety

[1994] Best time to see a doctor: 2023-10-15 14:00:00

[1995] Proposing and implementing online consultations

[1996] The server determines whether an online consultation is appropriate based on the initial diagnosis and sentiment analysis. For example, if the symptoms are mild or the user shows high anxiety, the server will suggest an online consultation to the user. If the user selects an online consultation, the server will determine the optimal date and time for the online consultation and notify the user. The user can then consult with a healthcare provider via the Internet at the specified time.

[1997] As described above, the present invention not only reduces waiting times but also provides flexible and efficient medical support that takes into account the user's emotions.

[1998] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1999] Step 1:

[2000] The user inputs symptoms into the terminal. The terminal receives the symptom data (in text format) entered by the user and sends the data to the server. At this point, the input is the user's symptom information, and the output is the symptom data sent to the server.

[2001] Step 2:

[2002] The server inputs the received symptom data into a generative AI model. The generative AI model analyzes the symptom data based on past case data and medical knowledge, and generates an initial diagnosis. The input at this point is the symptom data sent to the server, and the output is the initial diagnosis (diagnosed disease name and recommended medical department).

[2003] Step 3:

[2004] The server uses a sentiment analysis engine to analyze the user's emotional state from the symptom data. The sentiment analysis engine performs text analysis to determine the user's anxiety and stress levels. At this point, the input is the symptom data, and the output is the user's emotional state (e.g., high anxiety, normal, relaxed).

[2005] Step 4:

[2006] Based on the initial diagnosis and emotion analysis results, the server uses the appointment management system to determine the appropriate department and optimal consultation date and time. During this process, the desired consultation date and time entered by the user is also taken into consideration. The input at this point is the initial diagnosis result, emotion analysis result, and the user's desired consultation date and time, and the output is the determined optimal consultation date and time.

[2007] Step 5:

[2008] The server notifies the user of the determined appointment date and time. Notification can be done via smartphone, email, etc. The input at this point is the determined appointment date and time, and the output is a notification message sent to the user.

[2009] Step 6:

[2010] The server sends the initial diagnosis results and their rationale, as well as the emotion analysis results, generated by the generative AI model, to the healthcare provider's device in advance. This allows the healthcare provider to obtain prior knowledge of the user's symptoms and emotional state before the consultation begins. The input at this point is the initial diagnosis results, rationale, and emotion analysis results, and the output is this data sent to the healthcare provider.

[2011] Step 7:

[2012] The server determines whether an online consultation is applicable based on the initial diagnosis result and emotion analysis. If it is determined that an online consultation is applicable, it proposes an online consultation to the user. At this point, the input is the initial diagnosis result and emotion analysis result, and the output is a message proposing an online consultation.

[2013] Step 8:

[2014] If the user selects an online consultation, the server determines the optimal time and date for the online consultation and notifies the user and the healthcare provider. At this point, the input is the user's preference for an online consultation, and the output is a notification of the optimal time and date for the online consultation.

[2015] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2016] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2017] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2018] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2019] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric cir...

Claims

1. means for accepting symptom input from a user; means for analyzing the symptoms using a generative AI model and obtaining an initial diagnosis; A means for determining an appropriate medical department and consultation date and time based on the initial diagnosis result; means for notifying the user of the determined consultation date and time; means for proactively transmitting the consultation to a healthcare provider; A system including:

2. means for accepting a symptom image; A means for analyzing the image using an image analysis AI model to improve the accuracy of the initial diagnosis result; A means of determining whether online consultation is applicable; and A means of determining and notifying the date and time of an appointment if online consultation is selected; The system of claim 1 , comprising:

3. A means to notify healthcare providers of initial diagnostic results and evidence to improve the efficiency of medical care; The system of claim 1 , comprising:

Images